51 files changed, 4172 insertions, 3389 deletions

diff --git a/src/common/assert.h b/src/common/assert.h
index cd9b819a9..70214efae 100644
--- a/src/common/assert.h
+++ b/src/common/assert.h
@@ -18,25 +18,29 @@
 // enough for our purposes.
 template <typename Fn>
 #if defined(_MSC_VER)
-    __declspec(noinline, noreturn)
+__declspec(noinline, noreturn)
 #elif defined(__GNUC__)
     __attribute__((noinline, noreturn, cold))
 #endif
-static void assert_noinline_call(const Fn& fn) {
+    static void assert_noinline_call(const Fn& fn) {
     fn();
     Crash();
     exit(1); // Keeps GCC's mouth shut about this actually returning
 }
 
-#define ASSERT(_a_) \
-    do if (!(_a_)) { assert_noinline_call([] { \
-        LOG_CRITICAL(Debug, "Assertion Failed!"); \
-    }); } while (0)
-
-#define ASSERT_MSG(_a_, ...) \
-    do if (!(_a_)) { assert_noinline_call([&] { \
-        LOG_CRITICAL(Debug, "Assertion Failed!\n" __VA_ARGS__); \
-    }); } while (0)
+#define ASSERT(_a_)                                                                                \
+    do                                                                                             \
+        if (!(_a_)) {                                                                              \
+            assert_noinline_call([] { LOG_CRITICAL(Debug, "Assertion Failed!"); });                \
+        }                                                                                          \
+    while (0)
+
+#define ASSERT_MSG(_a_, ...)                                                                       \
+    do                                                                                             \
+        if (!(_a_)) {                                                                              \
+            assert_noinline_call([&] { LOG_CRITICAL(Debug, "Assertion Failed!\n" __VA_ARGS__); }); \
+        }                                                                                          \
+    while (0)
 
 #define UNREACHABLE() ASSERT_MSG(false, "Unreachable code!")
 #define UNREACHABLE_MSG(...) ASSERT_MSG(false, __VA_ARGS__)
diff --git a/src/common/bit_field.h b/src/common/bit_field.h
index 4748999ed..8d45743e2 100644
--- a/src/common/bit_field.h
+++ b/src/common/bit_field.h
@@ -1,7 +1,6 @@
 // Licensed under GPLv2 or any later version
 // Refer to the license.txt file included.
 
-
 // Copyright 2014 Tony Wasserka
 // All rights reserved.
 //
@@ -29,7 +28,6 @@
 // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
-
 #pragma once
 
 #include <cstddef>
@@ -111,9 +109,8 @@
  * symptoms.
  */
 #pragma pack(1)
-template<std::size_t position, std::size_t bits, typename T>
-struct BitField
-{
+template <std::size_t position, std::size_t bits, typename T>
+struct BitField {
 private:
     // We hide the copy assigment operator here, because the default copy
     // assignment would copy the full storage value, rather than just the bits
@@ -141,13 +138,10 @@ public:
     }
 
     FORCE_INLINE T Value() const {
-        if (std::numeric_limits<T>::is_signed)
-        {
-            std::size_t shift = 8 * sizeof(T)-bits;
+        if (std::numeric_limits<T>::is_signed) {
+            std::size_t shift = 8 * sizeof(T) - bits;
             return (T)((storage << (shift - position)) >> shift);
-        }
-        else
-        {
+        } else {
             return (T)((storage & GetMask()) >> position);
         }
     }
@@ -162,15 +156,14 @@ private:
     // T is an enumeration. Note that T is wrapped within an enable_if in the
     // former case to workaround compile errors which arise when using
     // std::underlying_type<T>::type directly.
-    typedef typename std::conditional < std::is_enum<T>::value,
-        std::underlying_type<T>,
-        std::enable_if < true, T >> ::type::type StorageType;
+    typedef typename std::conditional<std::is_enum<T>::value, std::underlying_type<T>,
+                                      std::enable_if<true, T>>::type::type StorageType;
 
     // Unsigned version of StorageType
     typedef typename std::make_unsigned<StorageType>::type StorageTypeU;
 
     FORCE_INLINE StorageType GetMask() const {
-        return (((StorageTypeU)~0) >> (8 * sizeof(T)-bits)) << position;
+        return (((StorageTypeU)~0) >> (8 * sizeof(T) - bits)) << position;
     }
 
     StorageType storage;
@@ -186,5 +179,6 @@ private:
 #pragma pack()
 
 #if (__GNUC__ >= 5) || defined(__clang__) || defined(_MSC_VER)
-static_assert(std::is_trivially_copyable<BitField<0, 1, unsigned>>::value, "BitField must be trivially copyable");
+static_assert(std::is_trivially_copyable<BitField<0, 1, unsigned>>::value,
+              "BitField must be trivially copyable");
 #endif
diff --git a/src/common/bit_set.h b/src/common/bit_set.h
index 7f5de8df2..b83cbbb36 100644
--- a/src/common/bit_set.h
+++ b/src/common/bit_set.h
@@ -18,49 +18,60 @@ namespace Common {
 
 #ifdef _WIN32
 template <typename T>
-static inline int CountSetBits(T v)
-{
+static inline int CountSetBits(T v) {
     // from https://graphics.stanford.edu/~seander/bithacks.html
     // GCC has this built in, but MSVC's intrinsic will only emit the actual
     // POPCNT instruction, which we're not depending on
-    v = v - ((v >> 1) & (T)~(T)0/3);
-    v = (v & (T)~(T)0/15*3) + ((v >> 2) & (T)~(T)0/15*3);
-    v = (v + (v >> 4)) & (T)~(T)0/255*15;
-    return (T)(v * ((T)~(T)0/255)) >> (sizeof(T) - 1) * 8;
+    v = v - ((v >> 1) & (T) ~(T)0 / 3);
+    v = (v & (T) ~(T)0 / 15 * 3) + ((v >> 2) & (T) ~(T)0 / 15 * 3);
+    v = (v + (v >> 4)) & (T) ~(T)0 / 255 * 15;
+    return (T)(v * ((T) ~(T)0 / 255)) >> (sizeof(T) - 1) * 8;
 }
-static inline int LeastSignificantSetBit(u8 val)
-{
+static inline int LeastSignificantSetBit(u8 val) {
     unsigned long index;
     _BitScanForward(&index, val);
     return (int)index;
 }
-static inline int LeastSignificantSetBit(u16 val)
-{
+static inline int LeastSignificantSetBit(u16 val) {
     unsigned long index;
     _BitScanForward(&index, val);
     return (int)index;
 }
-static inline int LeastSignificantSetBit(u32 val)
-{
+static inline int LeastSignificantSetBit(u32 val) {
     unsigned long index;
     _BitScanForward(&index, val);
     return (int)index;
 }
-static inline int LeastSignificantSetBit(u64 val)
-{
+static inline int LeastSignificantSetBit(u64 val) {
     unsigned long index;
     _BitScanForward64(&index, val);
     return (int)index;
 }
 #else
-static inline int CountSetBits(u8 val) { return __builtin_popcount(val); }
-static inline int CountSetBits(u16 val) { return __builtin_popcount(val); }
-static inline int CountSetBits(u32 val) { return __builtin_popcount(val); }
-static inline int CountSetBits(u64 val) { return __builtin_popcountll(val); }
-static inline int LeastSignificantSetBit(u8 val) { return __builtin_ctz(val); }
-static inline int LeastSignificantSetBit(u16 val) { return __builtin_ctz(val); }
-static inline int LeastSignificantSetBit(u32 val) { return __builtin_ctz(val); }
-static inline int LeastSignificantSetBit(u64 val) { return __builtin_ctzll(val); }
+static inline int CountSetBits(u8 val) {
+    return __builtin_popcount(val);
+}
+static inline int CountSetBits(u16 val) {
+    return __builtin_popcount(val);
+}
+static inline int CountSetBits(u32 val) {
+    return __builtin_popcount(val);
+}
+static inline int CountSetBits(u64 val) {
+    return __builtin_popcountll(val);
+}
+static inline int LeastSignificantSetBit(u8 val) {
+    return __builtin_ctz(val);
+}
+static inline int LeastSignificantSetBit(u16 val) {
+    return __builtin_ctz(val);
+}
+static inline int LeastSignificantSetBit(u32 val) {
+    return __builtin_ctz(val);
+}
+static inline int LeastSignificantSetBit(u64 val) {
+    return __builtin_ctzll(val);
+}
 #endif
 
 // Similar to std::bitset, this is a class which encapsulates a bitset, i.e.
@@ -84,100 +95,144 @@ static inline int LeastSignificantSetBit(u64 val) { return __builtin_ctzll(val);
 // TODO: use constexpr when MSVC gets out of the Dark Ages
 
 template <typename IntTy>
-class BitSet
-{
+class BitSet {
     static_assert(!std::is_signed<IntTy>::value, "BitSet should not be used with signed types");
+
 public:
     // A reference to a particular bit, returned from operator[].
-    class Ref
-    {
+    class Ref {
     public:
-        Ref(Ref&& other) : m_bs(other.m_bs), m_mask(other.m_mask) {}
-        Ref(BitSet* bs, IntTy mask) : m_bs(bs), m_mask(mask) {}
-        operator bool() const { return (m_bs->m_val & m_mask) != 0; }
-        bool operator=(bool set)
-        {
+        Ref(Ref&& other) : m_bs(other.m_bs), m_mask(other.m_mask) {
+        }
+        Ref(BitSet* bs, IntTy mask) : m_bs(bs), m_mask(mask) {
+        }
+        operator bool() const {
+            return (m_bs->m_val & m_mask) != 0;
+        }
+        bool operator=(bool set) {
             m_bs->m_val = (m_bs->m_val & ~m_mask) | (set ? m_mask : 0);
             return set;
         }
+
     private:
         BitSet* m_bs;
         IntTy m_mask;
     };
 
     // A STL-like iterator is required to be able to use range-based for loops.
-    class Iterator
-    {
+    class Iterator {
     public:
-        Iterator(const Iterator& other) : m_val(other.m_val), m_bit(other.m_bit) {}
-        Iterator(IntTy val, int bit) : m_val(val), m_bit(bit) {}
-        Iterator& operator=(Iterator other) { new (this) Iterator(other); return *this; }
-        int operator*() { return m_bit; }
-        Iterator& operator++()
-        {
-            if (m_val == 0)
-            {
+        Iterator(const Iterator& other) : m_val(other.m_val), m_bit(other.m_bit) {
+        }
+        Iterator(IntTy val, int bit) : m_val(val), m_bit(bit) {
+        }
+        Iterator& operator=(Iterator other) {
+            new (this) Iterator(other);
+            return *this;
+        }
+        int operator*() {
+            return m_bit;
+        }
+        Iterator& operator++() {
+            if (m_val == 0) {
                 m_bit = -1;
-            }
-            else
-            {
+            } else {
                 int bit = LeastSignificantSetBit(m_val);
                 m_val &= ~(1 << bit);
                 m_bit = bit;
             }
             return *this;
         }
-        Iterator operator++(int _)
-        {
+        Iterator operator++(int _) {
             Iterator other(*this);
             ++*this;
             return other;
         }
-        bool operator==(Iterator other) const { return m_bit == other.m_bit; }
-        bool operator!=(Iterator other) const { return m_bit != other.m_bit; }
+        bool operator==(Iterator other) const {
+            return m_bit == other.m_bit;
+        }
+        bool operator!=(Iterator other) const {
+            return m_bit != other.m_bit;
+        }
+
     private:
         IntTy m_val;
         int m_bit;
     };
 
-    BitSet() : m_val(0) {}
-    explicit BitSet(IntTy val) : m_val(val) {}
-    BitSet(std::initializer_list<int> init)
-    {
+    BitSet() : m_val(0) {
+    }
+    explicit BitSet(IntTy val) : m_val(val) {
+    }
+    BitSet(std::initializer_list<int> init) {
         m_val = 0;
         for (int bit : init)
             m_val |= (IntTy)1 << bit;
     }
 
-    static BitSet AllTrue(size_t count)
-    {
-        return BitSet(count == sizeof(IntTy)*8 ? ~(IntTy)0 : (((IntTy)1 << count) - 1));
-    }
-
-    Ref operator[](size_t bit) { return Ref(this, (IntTy)1 << bit); }
-    const Ref operator[](size_t bit) const { return (*const_cast<BitSet*>(this))[bit]; }
-    bool operator==(BitSet other) const { return m_val == other.m_val; }
-    bool operator!=(BitSet other) const { return m_val != other.m_val; }
-    bool operator<(BitSet other) const { return m_val < other.m_val; }
-    bool operator>(BitSet other) const { return m_val > other.m_val; }
-    BitSet operator|(BitSet other) const { return BitSet(m_val | other.m_val); }
-    BitSet operator&(BitSet other) const { return BitSet(m_val & other.m_val); }
-    BitSet operator^(BitSet other) const { return BitSet(m_val ^ other.m_val); }
-    BitSet operator~() const { return BitSet(~m_val); }
-    BitSet& operator|=(BitSet other) { return *this = *this | other; }
-    BitSet& operator&=(BitSet other) { return *this = *this & other; }
-    BitSet& operator^=(BitSet other) { return *this = *this ^ other; }
+    static BitSet AllTrue(size_t count) {
+        return BitSet(count == sizeof(IntTy) * 8 ? ~(IntTy)0 : (((IntTy)1 << count) - 1));
+    }
+
+    Ref operator[](size_t bit) {
+        return Ref(this, (IntTy)1 << bit);
+    }
+    const Ref operator[](size_t bit) const {
+        return (*const_cast<BitSet*>(this))[bit];
+    }
+    bool operator==(BitSet other) const {
+        return m_val == other.m_val;
+    }
+    bool operator!=(BitSet other) const {
+        return m_val != other.m_val;
+    }
+    bool operator<(BitSet other) const {
+        return m_val < other.m_val;
+    }
+    bool operator>(BitSet other) const {
+        return m_val > other.m_val;
+    }
+    BitSet operator|(BitSet other) const {
+        return BitSet(m_val | other.m_val);
+    }
+    BitSet operator&(BitSet other) const {
+        return BitSet(m_val & other.m_val);
+    }
+    BitSet operator^(BitSet other) const {
+        return BitSet(m_val ^ other.m_val);
+    }
+    BitSet operator~() const {
+        return BitSet(~m_val);
+    }
+    BitSet& operator|=(BitSet other) {
+        return *this = *this | other;
+    }
+    BitSet& operator&=(BitSet other) {
+        return *this = *this & other;
+    }
+    BitSet& operator^=(BitSet other) {
+        return *this = *this ^ other;
+    }
     operator u32() = delete;
-    operator bool() { return m_val != 0; }
+    operator bool() {
+        return m_val != 0;
+    }
 
     // Warning: Even though on modern CPUs this is a single fast instruction,
     // Dolphin's official builds do not currently assume POPCNT support on x86,
     // so slower explicit bit twiddling is generated.  Still should generally
     // be faster than a loop.
-    unsigned int Count() const { return CountSetBits(m_val); }
+    unsigned int Count() const {
+        return CountSetBits(m_val);
+    }
 
-    Iterator begin() const { Iterator it(m_val, 0); return ++it; }
-    Iterator end() const { return Iterator(m_val, -1); }
+    Iterator begin() const {
+        Iterator it(m_val, 0);
+        return ++it;
+    }
+    Iterator end() const {
+        return Iterator(m_val, -1);
+    }
 
     IntTy m_val;
 };
diff --git a/src/common/break_points.cpp b/src/common/break_points.cpp
index e7d0d3e43..3218db314 100644
--- a/src/common/break_points.cpp
+++ b/src/common/break_points.cpp
@@ -5,30 +5,27 @@
 #include "common/break_points.h"
 #include "common/logging/log.h"
 
-#include <sstream>
 #include <algorithm>
+#include <sstream>
 
-bool BreakPoints::IsAddressBreakPoint(u32 iAddress) const
-{
+bool BreakPoints::IsAddressBreakPoint(u32 iAddress) const {
     auto cond = [&iAddress](const TBreakPoint& bp) { return bp.iAddress == iAddress; };
-    auto it   = std::find_if(m_BreakPoints.begin(), m_BreakPoints.end(), cond);
+    auto it = std::find_if(m_BreakPoints.begin(), m_BreakPoints.end(), cond);
     return it != m_BreakPoints.end();
 }
 
-bool BreakPoints::IsTempBreakPoint(u32 iAddress) const
-{
-    auto cond = [&iAddress](const TBreakPoint& bp) { return bp.iAddress == iAddress && bp.bTemporary; };
-    auto it   = std::find_if(m_BreakPoints.begin(), m_BreakPoints.end(), cond);
+bool BreakPoints::IsTempBreakPoint(u32 iAddress) const {
+    auto cond = [&iAddress](const TBreakPoint& bp) {
+        return bp.iAddress == iAddress && bp.bTemporary;
+    };
+    auto it = std::find_if(m_BreakPoints.begin(), m_BreakPoints.end(), cond);
     return it != m_BreakPoints.end();
 }
 
-BreakPoints::TBreakPointsStr BreakPoints::GetStrings() const
-{
+BreakPoints::TBreakPointsStr BreakPoints::GetStrings() const {
     TBreakPointsStr bps;
-    for (auto breakpoint : m_BreakPoints)
-    {
-        if (!breakpoint.bTemporary)
-        {
+    for (auto breakpoint : m_BreakPoints) {
+        if (!breakpoint.bTemporary) {
             std::stringstream bp;
             bp << std::hex << breakpoint.iAddress << " " << (breakpoint.bOn ? "n" : "");
             bps.push_back(bp.str());
@@ -38,10 +35,8 @@ BreakPoints::TBreakPointsStr BreakPoints::GetStrings() const
     return bps;
 }
 
-void BreakPoints::AddFromStrings(const TBreakPointsStr& bps)
-{
-    for (auto bps_item : bps)
-    {
+void BreakPoints::AddFromStrings(const TBreakPointsStr& bps) {
+    for (auto bps_item : bps) {
         TBreakPoint bp;
         std::stringstream bpstr;
         bpstr << std::hex << bps_item;
@@ -52,18 +47,15 @@ void BreakPoints::AddFromStrings(const TBreakPointsStr& bps)
     }
 }
 
-void BreakPoints::Add(const TBreakPoint& bp)
-{
-    if (!IsAddressBreakPoint(bp.iAddress))
-    {
+void BreakPoints::Add(const TBreakPoint& bp) {
+    if (!IsAddressBreakPoint(bp.iAddress)) {
         m_BreakPoints.push_back(bp);
-        //if (jit)
+        // if (jit)
         //    jit->GetBlockCache()->InvalidateICache(bp.iAddress, 4);
     }
 }
 
-void BreakPoints::Add(u32 em_address, bool temp)
-{
+void BreakPoints::Add(u32 em_address, bool temp) {
     if (!IsAddressBreakPoint(em_address)) // only add new addresses
     {
         TBreakPoint pt; // breakpoint settings
@@ -73,22 +65,20 @@ void BreakPoints::Add(u32 em_address, bool temp)
 
         m_BreakPoints.push_back(pt);
 
-        //if (jit)
+        // if (jit)
         //    jit->GetBlockCache()->InvalidateICache(em_address, 4);
     }
 }
 
-void BreakPoints::Remove(u32 em_address)
-{
+void BreakPoints::Remove(u32 em_address) {
     auto cond = [&em_address](const TBreakPoint& bp) { return bp.iAddress == em_address; };
-    auto it   = std::find_if(m_BreakPoints.begin(), m_BreakPoints.end(), cond);
+    auto it = std::find_if(m_BreakPoints.begin(), m_BreakPoints.end(), cond);
     if (it != m_BreakPoints.end())
         m_BreakPoints.erase(it);
 }
 
-void BreakPoints::Clear()
-{
-    //if (jit)
+void BreakPoints::Clear() {
+    // if (jit)
     //{
     //    std::for_each(m_BreakPoints.begin(), m_BreakPoints.end(),
     //        [](const TBreakPoint& bp)
diff --git a/src/common/break_points.h b/src/common/break_points.h
index b0629df37..1a5b7d296 100644
--- a/src/common/break_points.h
+++ b/src/common/break_points.h
@@ -4,28 +4,28 @@
 
 #pragma once
 
-#include <vector>
 #include <string>
+#include <vector>
 
 #include "common/common_types.h"
 
 class DebugInterface;
 
-struct TBreakPoint
-{
-    u32  iAddress;
+struct TBreakPoint {
+    u32 iAddress;
     bool bOn;
     bool bTemporary;
 };
 
 // Code breakpoints.
-class BreakPoints
-{
+class BreakPoints {
 public:
     typedef std::vector<TBreakPoint> TBreakPoints;
     typedef std::vector<std::string> TBreakPointsStr;
 
-    const TBreakPoints& GetBreakPoints() { return m_BreakPoints; }
+    const TBreakPoints& GetBreakPoints() {
+        return m_BreakPoints;
+    }
 
     TBreakPointsStr GetStrings() const;
     void AddFromStrings(const TBreakPointsStr& bps);
@@ -35,7 +35,7 @@ public:
     bool IsTempBreakPoint(u32 iAddress) const;
 
     // Add BreakPoint
-    void Add(u32 em_address, bool temp=false);
+    void Add(u32 em_address, bool temp = false);
     void Add(const TBreakPoint& bp);
 
     // Remove Breakpoint
@@ -46,5 +46,5 @@ public:
 
 private:
     TBreakPoints m_BreakPoints;
-    u32          m_iBreakOnCount;
+    u32 m_iBreakOnCount;
 };
diff --git a/src/common/chunk_file.h b/src/common/chunk_file.h
index 1e1bcff31..3b36c0a9e 100644
--- a/src/common/chunk_file.h
+++ b/src/common/chunk_file.h
@@ -41,81 +41,86 @@
 #include "common/logging/log.h"
 
 template <class T>
-struct LinkedListItem : public T
-{
-    LinkedListItem<T> *next;
+struct LinkedListItem : public T {
+    LinkedListItem<T>* next;
 };
 
 class PointerWrap;
 
-class PointerWrapSection
-{
+class PointerWrapSection {
 public:
-    PointerWrapSection(PointerWrap &p, int ver, const char *title) : p_(p), ver_(ver), title_(title) {
+    PointerWrapSection(PointerWrap& p, int ver, const char* title)
+        : p_(p), ver_(ver), title_(title) {
     }
     ~PointerWrapSection();
 
-    bool operator == (const int &v) const { return ver_ == v; }
-    bool operator != (const int &v) const { return ver_ != v; }
-    bool operator <= (const int &v) const { return ver_ <= v; }
-    bool operator >= (const int &v) const { return ver_ >= v; }
-    bool operator <  (const int &v) const { return ver_ < v; }
-    bool operator >  (const int &v) const { return ver_ > v; }
+    bool operator==(const int& v) const {
+        return ver_ == v;
+    }
+    bool operator!=(const int& v) const {
+        return ver_ != v;
+    }
+    bool operator<=(const int& v) const {
+        return ver_ <= v;
+    }
+    bool operator>=(const int& v) const {
+        return ver_ >= v;
+    }
+    bool operator<(const int& v) const {
+        return ver_ < v;
+    }
+    bool operator>(const int& v) const {
+        return ver_ > v;
+    }
 
-    operator bool() const  {
+    operator bool() const {
         return ver_ > 0;
     }
 
 private:
-    PointerWrap &p_;
+    PointerWrap& p_;
     int ver_;
-    const char *title_;
+    const char* title_;
 };
 
 // Wrapper class
-class PointerWrap
-{
-    // This makes it a compile error if you forget to define DoState() on non-POD.
-    // Which also can be a problem, for example struct tm is non-POD on linux, for whatever reason...
+class PointerWrap {
+// This makes it a compile error if you forget to define DoState() on non-POD.
+// Which also can be a problem, for example struct tm is non-POD on linux, for whatever reason...
 #ifdef _MSC_VER
-    template<typename T, bool isPOD = std::is_pod<T>::value, bool isPointer = std::is_pointer<T>::value>
+    template <typename T, bool isPOD = std::is_pod<T>::value,
+              bool isPointer = std::is_pointer<T>::value>
 #else
-    template<typename T, bool isPOD = __is_pod(T), bool isPointer = std::is_pointer<T>::value>
+    template <typename T, bool isPOD = __is_pod(T), bool isPointer = std::is_pointer<T>::value>
 #endif
-    struct DoHelper
-    {
-        static void DoArray(PointerWrap *p, T *x, int count)
-        {
+    struct DoHelper {
+        static void DoArray(PointerWrap* p, T* x, int count) {
             for (int i = 0; i < count; ++i)
                 p->Do(x[i]);
         }
 
-        static void Do(PointerWrap *p, T &x)
-        {
+        static void Do(PointerWrap* p, T& x) {
             p->DoClass(x);
         }
     };
 
-    template<typename T>
-    struct DoHelper<T, true, false>
-    {
-        static void DoArray(PointerWrap *p, T *x, int count)
-        {
-            p->DoVoid((void *)x, sizeof(T) * count);
+    template <typename T>
+    struct DoHelper<T, true, false> {
+        static void DoArray(PointerWrap* p, T* x, int count) {
+            p->DoVoid((void*)x, sizeof(T) * count);
         }
 
-        static void Do(PointerWrap *p, T &x)
-        {
-            p->DoVoid((void *)&x, sizeof(x));
+        static void Do(PointerWrap* p, T& x) {
+            p->DoVoid((void*)&x, sizeof(x));
         }
     };
 
 public:
     enum Mode {
         MODE_READ = 1, // load
-        MODE_WRITE, // save
-        MODE_MEASURE, // calculate size
-        MODE_VERIFY, // compare
+        MODE_WRITE,    // save
+        MODE_MEASURE,  // calculate size
+        MODE_VERIFY,   // compare
     };
 
     enum Error {
@@ -124,247 +129,239 @@ public:
         ERROR_FAILURE = 2,
     };
 
-    u8 **ptr;
+    u8** ptr;
     Mode mode;
     Error error;
 
 public:
-    PointerWrap(u8 **ptr_, Mode mode_) : ptr(ptr_), mode(mode_), error(ERROR_NONE) {}
-    PointerWrap(unsigned char **ptr_, int mode_) : ptr((u8**)ptr_), mode((Mode)mode_), error(ERROR_NONE) {}
+    PointerWrap(u8** ptr_, Mode mode_) : ptr(ptr_), mode(mode_), error(ERROR_NONE) {
+    }
+    PointerWrap(unsigned char** ptr_, int mode_)
+        : ptr((u8**)ptr_), mode((Mode)mode_), error(ERROR_NONE) {
+    }
 
-    PointerWrapSection Section(const char *title, int ver) {
+    PointerWrapSection Section(const char* title, int ver) {
         return Section(title, ver, ver);
     }
 
     // The returned object can be compared against the version that was loaded.
     // This can be used to support versions as old as minVer.
     // Version = 0 means the section was not found.
-    PointerWrapSection Section(const char *title, int minVer, int ver) {
+    PointerWrapSection Section(const char* title, int minVer, int ver) {
         char marker[16] = {0};
         int foundVersion = ver;
 
         strncpy(marker, title, sizeof(marker));
-        if (!ExpectVoid(marker, sizeof(marker)))
-        {
+        if (!ExpectVoid(marker, sizeof(marker))) {
             // Might be before we added name markers for safety.
             if (foundVersion == 1 && ExpectVoid(&foundVersion, sizeof(foundVersion)))
                 DoMarker(title);
             // Wasn't found, but maybe we can still load the state.
             else
                 foundVersion = 0;
-        }
-        else
+        } else
             Do(foundVersion);
 
         if (error == ERROR_FAILURE || foundVersion < minVer || foundVersion > ver) {
-            LOG_ERROR(Common, "Savestate failure: wrong version %d found for %s", foundVersion, title);
+            LOG_ERROR(Common, "Savestate failure: wrong version %d found for %s", foundVersion,
+                      title);
             SetError(ERROR_FAILURE);
             return PointerWrapSection(*this, -1, title);
         }
         return PointerWrapSection(*this, foundVersion, title);
     }
 
-    void SetMode(Mode mode_) {mode = mode_;}
-    Mode GetMode() const {return mode;}
-    u8 **GetPPtr() {return ptr;}
-    void SetError(Error error_)
-    {
+    void SetMode(Mode mode_) {
+        mode = mode_;
+    }
+    Mode GetMode() const {
+        return mode;
+    }
+    u8** GetPPtr() {
+        return ptr;
+    }
+    void SetError(Error error_) {
         if (error < error_)
             error = error_;
         if (error > ERROR_WARNING)
             mode = PointerWrap::MODE_MEASURE;
     }
 
-    bool ExpectVoid(void *data, int size)
-    {
+    bool ExpectVoid(void* data, int size) {
         switch (mode) {
-        case MODE_READ:    if (memcmp(data, *ptr, size) != 0) return false; break;
-        case MODE_WRITE: memcpy(*ptr, data, size); break;
-        case MODE_MEASURE: break;  // MODE_MEASURE - don't need to do anything
+        case MODE_READ:
+            if (memcmp(data, *ptr, size) != 0)
+                return false;
+            break;
+        case MODE_WRITE:
+            memcpy(*ptr, data, size);
+            break;
+        case MODE_MEASURE:
+            break; // MODE_MEASURE - don't need to do anything
         case MODE_VERIFY:
             for (int i = 0; i < size; i++) {
-                DEBUG_ASSERT_MSG(((u8*)data)[i] == (*ptr)[i],
+                DEBUG_ASSERT_MSG(
+                    ((u8*)data)[i] == (*ptr)[i],
                     "Savestate verification failure: %d (0x%X) (at %p) != %d (0x%X) (at %p).\n",
-                    ((u8*)data)[i], ((u8*)data)[i], &((u8*)data)[i],
-                    (*ptr)[i], (*ptr)[i], &(*ptr)[i]);
+                    ((u8*)data)[i], ((u8*)data)[i], &((u8*)data)[i], (*ptr)[i], (*ptr)[i],
+                    &(*ptr)[i]);
             }
             break;
-        default: break;  // throw an error?
+        default:
+            break; // throw an error?
         }
         (*ptr) += size;
         return true;
     }
 
-    void DoVoid(void *data, int size)
-    {
+    void DoVoid(void* data, int size) {
         switch (mode) {
-        case MODE_READ:    memcpy(data, *ptr, size); break;
-        case MODE_WRITE: memcpy(*ptr, data, size); break;
-        case MODE_MEASURE: break;  // MODE_MEASURE - don't need to do anything
+        case MODE_READ:
+            memcpy(data, *ptr, size);
+            break;
+        case MODE_WRITE:
+            memcpy(*ptr, data, size);
+            break;
+        case MODE_MEASURE:
+            break; // MODE_MEASURE - don't need to do anything
         case MODE_VERIFY:
             for (int i = 0; i < size; i++) {
-                DEBUG_ASSERT_MSG(((u8*)data)[i] == (*ptr)[i],
+                DEBUG_ASSERT_MSG(
+                    ((u8*)data)[i] == (*ptr)[i],
                     "Savestate verification failure: %d (0x%X) (at %p) != %d (0x%X) (at %p).\n",
-                    ((u8*)data)[i], ((u8*)data)[i], &((u8*)data)[i],
-                    (*ptr)[i], (*ptr)[i], &(*ptr)[i]);
+                    ((u8*)data)[i], ((u8*)data)[i], &((u8*)data)[i], (*ptr)[i], (*ptr)[i],
+                    &(*ptr)[i]);
             }
             break;
-        default: break;  // throw an error?
+        default:
+            break; // throw an error?
         }
         (*ptr) += size;
     }
 
-    template<class K, class T>
-    void Do(std::map<K, T *> &x)
-    {
-        if (mode == MODE_READ)
-        {
-            for (auto it = x.begin(), end = x.end(); it != end; ++it)
-            {
+    template <class K, class T>
+    void Do(std::map<K, T*>& x) {
+        if (mode == MODE_READ) {
+            for (auto it = x.begin(), end = x.end(); it != end; ++it) {
                 if (it->second != nullptr)
                     delete it->second;
             }
         }
-        T *dv = nullptr;
+        T* dv = nullptr;
         DoMap(x, dv);
     }
 
-    template<class K, class T>
-    void Do(std::map<K, T> &x)
-    {
+    template <class K, class T>
+    void Do(std::map<K, T>& x) {
         T dv = T();
         DoMap(x, dv);
     }
 
-    template<class K, class T>
-    void DoMap(std::map<K, T> &x, T &default_val)
-    {
+    template <class K, class T>
+    void DoMap(std::map<K, T>& x, T& default_val) {
         unsigned int number = (unsigned int)x.size();
         Do(number);
         switch (mode) {
-        case MODE_READ:
-            {
-                x.clear();
-                while (number > 0)
-                {
-                    K first = K();
-                    Do(first);
-                    T second = default_val;
-                    Do(second);
-                    x[first] = second;
-                    --number;
-                }
+        case MODE_READ: {
+            x.clear();
+            while (number > 0) {
+                K first = K();
+                Do(first);
+                T second = default_val;
+                Do(second);
+                x[first] = second;
+                --number;
             }
-            break;
+        } break;
         case MODE_WRITE:
         case MODE_MEASURE:
-        case MODE_VERIFY:
-            {
-                typename std::map<K, T>::iterator itr = x.begin();
-                while (number > 0)
-                {
-                    K first = itr->first;
-                    Do(first);
-                    Do(itr->second);
-                    --number;
-                    ++itr;
-                }
+        case MODE_VERIFY: {
+            typename std::map<K, T>::iterator itr = x.begin();
+            while (number > 0) {
+                K first = itr->first;
+                Do(first);
+                Do(itr->second);
+                --number;
+                ++itr;
             }
-            break;
+        } break;
         }
     }
 
-    template<class K, class T>
-    void Do(std::multimap<K, T *> &x)
-    {
-        if (mode == MODE_READ)
-        {
-            for (auto it = x.begin(), end = x.end(); it != end; ++it)
-            {
+    template <class K, class T>
+    void Do(std::multimap<K, T*>& x) {
+        if (mode == MODE_READ) {
+            for (auto it = x.begin(), end = x.end(); it != end; ++it) {
                 if (it->second != nullptr)
                     delete it->second;
             }
         }
-        T *dv = nullptr;
+        T* dv = nullptr;
         DoMultimap(x, dv);
     }
 
-    template<class K, class T>
-    void Do(std::multimap<K, T> &x)
-    {
+    template <class K, class T>
+    void Do(std::multimap<K, T>& x) {
         T dv = T();
         DoMultimap(x, dv);
     }
 
-    template<class K, class T>
-    void DoMultimap(std::multimap<K, T> &x, T &default_val)
-    {
+    template <class K, class T>
+    void DoMultimap(std::multimap<K, T>& x, T& default_val) {
         unsigned int number = (unsigned int)x.size();
         Do(number);
         switch (mode) {
-        case MODE_READ:
-            {
-                x.clear();
-                while (number > 0)
-                {
-                    K first = K();
-                    Do(first);
-                    T second = default_val;
-                    Do(second);
-                    x.insert(std::make_pair(first, second));
-                    --number;
-                }
+        case MODE_READ: {
+            x.clear();
+            while (number > 0) {
+                K first = K();
+                Do(first);
+                T second = default_val;
+                Do(second);
+                x.insert(std::make_pair(first, second));
+                --number;
             }
-            break;
+        } break;
         case MODE_WRITE:
         case MODE_MEASURE:
-        case MODE_VERIFY:
-            {
-                typename std::multimap<K, T>::iterator itr = x.begin();
-                while (number > 0)
-                {
-                    Do(itr->first);
-                    Do(itr->second);
-                    --number;
-                    ++itr;
-                }
+        case MODE_VERIFY: {
+            typename std::multimap<K, T>::iterator itr = x.begin();
+            while (number > 0) {
+                Do(itr->first);
+                Do(itr->second);
+                --number;
+                ++itr;
             }
-            break;
+        } break;
         }
     }
 
     // Store vectors.
-    template<class T>
-    void Do(std::vector<T *> &x)
-    {
-        T *dv = nullptr;
+    template <class T>
+    void Do(std::vector<T*>& x) {
+        T* dv = nullptr;
         DoVector(x, dv);
     }
 
-    template<class T>
-    void Do(std::vector<T> &x)
-    {
+    template <class T>
+    void Do(std::vector<T>& x) {
         T dv = T();
         DoVector(x, dv);
     }
 
-
-    template<class T>
-    void DoPOD(std::vector<T> &x)
-    {
+    template <class T>
+    void DoPOD(std::vector<T>& x) {
         T dv = T();
         DoVectorPOD(x, dv);
     }
 
-    template<class T>
-    void Do(std::vector<T> &x, T &default_val)
-    {
+    template <class T>
+    void Do(std::vector<T>& x, T& default_val) {
         DoVector(x, default_val);
     }
 
-    template<class T>
-    void DoVector(std::vector<T> &x, T &default_val)
-    {
+    template <class T>
+    void DoVector(std::vector<T>& x, T& default_val) {
         u32 vec_size = (u32)x.size();
         Do(vec_size);
         x.resize(vec_size, default_val);
@@ -372,9 +369,8 @@ public:
             DoArray(&x[0], vec_size);
     }
 
-    template<class T>
-    void DoVectorPOD(std::vector<T> &x, T &default_val)
-    {
+    template <class T>
+    void DoVectorPOD(std::vector<T>& x, T& default_val) {
         u32 vec_size = (u32)x.size();
         Do(vec_size);
         x.resize(vec_size, default_val);
@@ -383,55 +379,48 @@ public:
     }
 
     // Store deques.
-    template<class T>
-    void Do(std::deque<T *> &x)
-    {
-        T *dv = nullptr;
+    template <class T>
+    void Do(std::deque<T*>& x) {
+        T* dv = nullptr;
         DoDeque(x, dv);
     }
 
-    template<class T>
-    void Do(std::deque<T> &x)
-    {
+    template <class T>
+    void Do(std::deque<T>& x) {
         T dv = T();
         DoDeque(x, dv);
     }
 
-    template<class T>
-    void DoDeque(std::deque<T> &x, T &default_val)
-    {
+    template <class T>
+    void DoDeque(std::deque<T>& x, T& default_val) {
         u32 deq_size = (u32)x.size();
         Do(deq_size);
         x.resize(deq_size, default_val);
         u32 i;
-        for(i = 0; i < deq_size; i++)
+        for (i = 0; i < deq_size; i++)
             Do(x[i]);
     }
 
     // Store STL lists.
-    template<class T>
-    void Do(std::list<T *> &x)
-    {
-        T *dv = nullptr;
+    template <class T>
+    void Do(std::list<T*>& x) {
+        T* dv = nullptr;
         Do(x, dv);
     }
 
-    template<class T>
-    void Do(std::list<T> &x)
-    {
+    template <class T>
+    void Do(std::list<T>& x) {
         T dv = T();
         DoList(x, dv);
     }
 
-    template<class T>
-    void Do(std::list<T> &x, T &default_val)
-    {
+    template <class T>
+    void Do(std::list<T>& x, T& default_val) {
         DoList(x, default_val);
     }
 
-    template<class T>
-    void DoList(std::list<T> &x, T &default_val)
-    {
+    template <class T>
+    void DoList(std::list<T>& x, T& default_val) {
         u32 list_size = (u32)x.size();
         Do(list_size);
         x.resize(list_size, default_val);
@@ -441,15 +430,11 @@ public:
             Do(*itr);
     }
 
-
     // Store STL sets.
     template <class T>
-    void Do(std::set<T *> &x)
-    {
-        if (mode == MODE_READ)
-        {
-            for (auto it = x.begin(), end = x.end(); it != end; ++it)
-            {
+    void Do(std::set<T*>& x) {
+        if (mode == MODE_READ) {
+            for (auto it = x.begin(), end = x.end(); it != end; ++it) {
                 if (*it != nullptr)
                     delete *it;
             }
@@ -458,39 +443,31 @@ public:
     }
 
     template <class T>
-    void Do(std::set<T> &x)
-    {
+    void Do(std::set<T>& x) {
         DoSet(x);
     }
 
     template <class T>
-    void DoSet(std::set<T> &x)
-    {
+    void DoSet(std::set<T>& x) {
         unsigned int number = (unsigned int)x.size();
         Do(number);
 
-        switch (mode)
-        {
-        case MODE_READ:
-            {
-                x.clear();
-                while (number-- > 0)
-                {
-                    T it = T();
-                    Do(it);
-                    x.insert(it);
-                }
+        switch (mode) {
+        case MODE_READ: {
+            x.clear();
+            while (number-- > 0) {
+                T it = T();
+                Do(it);
+                x.insert(it);
             }
-            break;
+        } break;
         case MODE_WRITE:
         case MODE_MEASURE:
-        case MODE_VERIFY:
-            {
-                typename std::set<T>::iterator itr = x.begin();
-                while (number-- > 0)
-                    Do(*itr++);
-            }
-            break;
+        case MODE_VERIFY: {
+            typename std::set<T>::iterator itr = x.begin();
+            while (number-- > 0)
+                Do(*itr++);
+        } break;
 
         default:
             LOG_ERROR(Common, "Savestate error: invalid mode %d.", mode);
@@ -498,51 +475,58 @@ public:
     }
 
     // Store strings.
-    void Do(std::string &x)
-    {
+    void Do(std::string& x) {
         int stringLen = (int)x.length() + 1;
         Do(stringLen);
 
         switch (mode) {
-        case MODE_READ:        x = (char*)*ptr; break;
-        case MODE_WRITE:    memcpy(*ptr, x.c_str(), stringLen); break;
-        case MODE_MEASURE: break;
+        case MODE_READ:
+            x = (char*)*ptr;
+            break;
+        case MODE_WRITE:
+            memcpy(*ptr, x.c_str(), stringLen);
+            break;
+        case MODE_MEASURE:
+            break;
         case MODE_VERIFY:
             DEBUG_ASSERT_MSG((x == (char*)*ptr),
-                "Savestate verification failure: \"%s\" != \"%s\" (at %p).\n",
-                x.c_str(), (char*)*ptr, ptr);
+                             "Savestate verification failure: \"%s\" != \"%s\" (at %p).\n",
+                             x.c_str(), (char*)*ptr, ptr);
             break;
         }
         (*ptr) += stringLen;
     }
 
-    void Do(std::wstring &x)
-    {
-        int stringLen = sizeof(wchar_t)*((int)x.length() + 1);
+    void Do(std::wstring& x) {
+        int stringLen = sizeof(wchar_t) * ((int)x.length() + 1);
         Do(stringLen);
 
         switch (mode) {
-        case MODE_READ:        x = (wchar_t*)*ptr; break;
-        case MODE_WRITE:    memcpy(*ptr, x.c_str(), stringLen); break;
-        case MODE_MEASURE: break;
+        case MODE_READ:
+            x = (wchar_t*)*ptr;
+            break;
+        case MODE_WRITE:
+            memcpy(*ptr, x.c_str(), stringLen);
+            break;
+        case MODE_MEASURE:
+            break;
         case MODE_VERIFY:
             DEBUG_ASSERT_MSG((x == (wchar_t*)*ptr),
-                "Savestate verification failure: \"%ls\" != \"%ls\" (at %p).\n",
-                x.c_str(), (wchar_t*)*ptr, ptr);
+                             "Savestate verification failure: \"%ls\" != \"%ls\" (at %p).\n",
+                             x.c_str(), (wchar_t*)*ptr, ptr);
             break;
         }
         (*ptr) += stringLen;
     }
 
-    template<class T>
-    void DoClass(T &x) {
+    template <class T>
+    void DoClass(T& x) {
         x.DoState(*this);
     }
 
-    template<class T>
-    void DoClass(T *&x) {
-        if (mode == MODE_READ)
-        {
+    template <class T>
+    void DoClass(T*& x) {
+        if (mode == MODE_READ) {
             if (x != nullptr)
                 delete x;
             x = new T();
@@ -550,81 +534,70 @@ public:
         x->DoState(*this);
     }
 
-    template<class T>
-    void DoArray(T *x, int count) {
+    template <class T>
+    void DoArray(T* x, int count) {
         DoHelper<T>::DoArray(this, x, count);
     }
 
-    template<class T>
-    void Do(T &x) {
+    template <class T>
+    void Do(T& x) {
         DoHelper<T>::Do(this, x);
     }
 
-    template<class T>
-    void DoPOD(T &x) {
+    template <class T>
+    void DoPOD(T& x) {
         DoHelper<T>::Do(this, x);
     }
 
-    template<class T>
-    void DoPointer(T* &x, T*const base) {
-        // pointers can be more than 2^31 apart, but you're using this function wrong if you need that much range
+    template <class T>
+    void DoPointer(T*& x, T* const base) {
+        // pointers can be more than 2^31 apart, but you're using this function wrong if you need
+        // that much range
         s32 offset = x - base;
         Do(offset);
         if (mode == MODE_READ)
             x = base + offset;
     }
 
-    template<class T, LinkedListItem<T>* (*TNew)(), void (*TFree)(LinkedListItem<T>*), void (*TDo)(PointerWrap&, T*)>
-    void DoLinkedList(LinkedListItem<T>*& list_start, LinkedListItem<T>** list_end = nullptr)
-    {
+    template <class T, LinkedListItem<T>* (*TNew)(), void (*TFree)(LinkedListItem<T>*),
+              void (*TDo)(PointerWrap&, T*)>
+    void DoLinkedList(LinkedListItem<T>*& list_start, LinkedListItem<T>** list_end = nullptr) {
         LinkedListItem<T>* list_cur = list_start;
         LinkedListItem<T>* prev = nullptr;
 
-        while (true)
-        {
+        while (true) {
             u8 shouldExist = (list_cur ? 1 : 0);
             Do(shouldExist);
-            if (shouldExist == 1)
-            {
+            if (shouldExist == 1) {
                 LinkedListItem<T>* cur = list_cur ? list_cur : TNew();
                 TDo(*this, (T*)cur);
-                if (!list_cur)
-                {
-                    if (mode == MODE_READ)
-                    {
+                if (!list_cur) {
+                    if (mode == MODE_READ) {
                         cur->next = nullptr;
                         list_cur = cur;
                         if (prev)
                             prev->next = cur;
                         else
                             list_start = cur;
-                    }
-                    else
-                    {
+                    } else {
                         TFree(cur);
                         continue;
                     }
                 }
-            }
-            else
-            {
-                if (mode == MODE_READ)
-                {
+            } else {
+                if (mode == MODE_READ) {
                     if (prev)
                         prev->next = nullptr;
                     if (list_end)
                         *list_end = prev;
-                    if (list_cur)
-                    {
+                    if (list_cur) {
                         if (list_start == list_cur)
                             list_start = nullptr;
-                        do
-                        {
+                        do {
                             LinkedListItem<T>* next = list_cur->next;
                             TFree(list_cur);
                             list_cur = next;
-                        }
-                        while (list_cur);
+                        } while (list_cur);
                     }
                 }
                 break;
@@ -634,13 +607,13 @@ public:
         }
     }
 
-    void DoMarker(const char* prevName, u32 arbitraryNumber=0x42)
-    {
+    void DoMarker(const char* prevName, u32 arbitraryNumber = 0x42) {
         u32 cookie = arbitraryNumber;
         Do(cookie);
-        if(mode == PointerWrap::MODE_READ && cookie != arbitraryNumber)
-        {
-            LOG_ERROR(Common, "After \"%s\", found %d (0x%X) instead of save marker %d (0x%X). Aborting savestate load...", prevName, cookie, cookie, arbitraryNumber, arbitraryNumber);
+        if (mode == PointerWrap::MODE_READ && cookie != arbitraryNumber) {
+            LOG_ERROR(Common, "After \"%s\", found %d (0x%X) instead of save marker %d (0x%X). "
+                              "Aborting savestate load...",
+                      prevName, cookie, cookie, arbitraryNumber, arbitraryNumber);
             SetError(ERROR_FAILURE);
         }
     }
diff --git a/src/common/code_block.h b/src/common/code_block.h
index 2fa4a0090..58696737e 100644
--- a/src/common/code_block.h
+++ b/src/common/code_block.h
@@ -14,24 +14,28 @@
 // having to prefix them with gen-> or something similar.
 // Example implementation:
 // class JIT : public CodeBlock<ARMXEmitter> {}
-template<class T> class CodeBlock : public T, NonCopyable
-{
+template <class T>
+class CodeBlock : public T, NonCopyable {
 private:
     // A privately used function to set the executable RAM space to something invalid.
-    // For debugging usefulness it should be used to set the RAM to a host specific breakpoint instruction
+    // For debugging usefulness it should be used to set the RAM to a host specific breakpoint
+    // instruction
     virtual void PoisonMemory() = 0;
 
 protected:
-    u8 *region;
+    u8* region;
     size_t region_size;
 
 public:
-    CodeBlock() : region(nullptr), region_size(0) {}
-    virtual ~CodeBlock() { if (region) FreeCodeSpace(); }
+    CodeBlock() : region(nullptr), region_size(0) {
+    }
+    virtual ~CodeBlock() {
+        if (region)
+            FreeCodeSpace();
+    }
 
     // Call this before you generate any code.
-    void AllocCodeSpace(int size)
-    {
+    void AllocCodeSpace(int size) {
         region_size = size;
         region = (u8*)AllocateExecutableMemory(region_size);
         T::SetCodePtr(region);
@@ -39,15 +43,13 @@ public:
 
     // Always clear code space with breakpoints, so that if someone accidentally executes
     // uninitialized, it just breaks into the debugger.
-    void ClearCodeSpace()
-    {
+    void ClearCodeSpace() {
         PoisonMemory();
         ResetCodePtr();
     }
 
     // Call this when shutting down. Don't rely on the destructor, even though it'll do the job.
-    void FreeCodeSpace()
-    {
+    void FreeCodeSpace() {
 #ifdef __SYMBIAN32__
         ResetExecutableMemory(region);
 #else
@@ -57,33 +59,29 @@ public:
         region_size = 0;
     }
 
-    bool IsInSpace(const u8 *ptr)
-    {
+    bool IsInSpace(const u8* ptr) {
         return (ptr >= region) && (ptr < (region + region_size));
     }
 
     // Cannot currently be undone. Will write protect the entire code region.
     // Start over if you need to change the code (call FreeCodeSpace(), AllocCodeSpace()).
-    void WriteProtect()
-    {
+    void WriteProtect() {
         WriteProtectMemory(region, region_size, true);
     }
 
-    void ResetCodePtr()
-    {
+    void ResetCodePtr() {
         T::SetCodePtr(region);
     }
 
-    size_t GetSpaceLeft() const
-    {
+    size_t GetSpaceLeft() const {
         return region_size - (T::GetCodePtr() - region);
     }
 
-    u8 *GetBasePtr() {
+    u8* GetBasePtr() {
         return region;
     }
 
-    size_t GetOffset(const u8 *ptr) const {
+    size_t GetOffset(const u8* ptr) const {
         return ptr - region;
     }
 };
diff --git a/src/common/color.h b/src/common/color.h
index 908879ea6..4ebd4f3d0 100644
--- a/src/common/color.h
+++ b/src/common/color.h
@@ -56,7 +56,7 @@ constexpr u8 Convert8To6(u8 value) {
  * @return Result color decoded as Math::Vec4<u8>
  */
 inline const Math::Vec4<u8> DecodeRGBA8(const u8* bytes) {
-    return { bytes[3], bytes[2], bytes[1], bytes[0] };
+    return {bytes[3], bytes[2], bytes[1], bytes[0]};
 }
 
 /**
@@ -65,7 +65,7 @@ inline const Math::Vec4<u8> DecodeRGBA8(const u8* bytes) {
  * @return Result color decoded as Math::Vec4<u8>
  */
 inline const Math::Vec4<u8> DecodeRGB8(const u8* bytes) {
-    return { bytes[2], bytes[1], bytes[0], 255 };
+    return {bytes[2], bytes[1], bytes[0], 255};
 }
 
 /**
@@ -74,7 +74,7 @@ inline const Math::Vec4<u8> DecodeRGB8(const u8* bytes) {
  * @return Result color decoded as Math::Vec4<u8>
  */
 inline const Math::Vec4<u8> DecodeRG8(const u8* bytes) {
-    return { bytes[1], bytes[0], 0, 255 };
+    return {bytes[1], bytes[0], 0, 255};
 }
 
 /**
@@ -84,8 +84,8 @@ inline const Math::Vec4<u8> DecodeRG8(const u8* bytes) {
  */
 inline const Math::Vec4<u8> DecodeRGB565(const u8* bytes) {
     const u16_le pixel = *reinterpret_cast<const u16_le*>(bytes);
-    return { Convert5To8((pixel >> 11) & 0x1F), Convert6To8((pixel >> 5) & 0x3F),
-        Convert5To8(pixel & 0x1F), 255 };
+    return {Convert5To8((pixel >> 11) & 0x1F), Convert6To8((pixel >> 5) & 0x3F),
+            Convert5To8(pixel & 0x1F), 255};
 }
 
 /**
@@ -95,8 +95,8 @@ inline const Math::Vec4<u8> DecodeRGB565(const u8* bytes) {
  */
 inline const Math::Vec4<u8> DecodeRGB5A1(const u8* bytes) {
     const u16_le pixel = *reinterpret_cast<const u16_le*>(bytes);
-    return { Convert5To8((pixel >> 11) & 0x1F), Convert5To8((pixel >> 6) & 0x1F),
-        Convert5To8((pixel >> 1) & 0x1F), Convert1To8(pixel & 0x1) };
+    return {Convert5To8((pixel >> 11) & 0x1F), Convert5To8((pixel >> 6) & 0x1F),
+            Convert5To8((pixel >> 1) & 0x1F), Convert1To8(pixel & 0x1)};
 }
 
 /**
@@ -106,8 +106,8 @@ inline const Math::Vec4<u8> DecodeRGB5A1(const u8* bytes) {
  */
 inline const Math::Vec4<u8> DecodeRGBA4(const u8* bytes) {
     const u16_le pixel = *reinterpret_cast<const u16_le*>(bytes);
-    return { Convert4To8((pixel >> 12) & 0xF), Convert4To8((pixel >> 8) & 0xF),
-        Convert4To8((pixel >> 4) & 0xF), Convert4To8(pixel & 0xF) };
+    return {Convert4To8((pixel >> 12) & 0xF), Convert4To8((pixel >> 8) & 0xF),
+            Convert4To8((pixel >> 4) & 0xF), Convert4To8(pixel & 0xF)};
 }
 
 /**
@@ -134,7 +134,7 @@ inline u32 DecodeD24(const u8* bytes) {
  * @return Resulting values stored as a Math::Vec2
  */
 inline const Math::Vec2<u32> DecodeD24S8(const u8* bytes) {
-    return { static_cast<u32>((bytes[2] << 16) | (bytes[1] << 8) | bytes[0]), bytes[3] };
+    return {static_cast<u32>((bytes[2] << 16) | (bytes[1] << 8) | bytes[0]), bytes[3]};
 }
 
 /**
@@ -175,8 +175,8 @@ inline void EncodeRG8(const Math::Vec4<u8>& color, u8* bytes) {
  * @param bytes Destination pointer to store encoded color
  */
 inline void EncodeRGB565(const Math::Vec4<u8>& color, u8* bytes) {
-    *reinterpret_cast<u16_le*>(bytes) = (Convert8To5(color.r()) << 11) |
-        (Convert8To6(color.g()) << 5) | Convert8To5(color.b());
+    *reinterpret_cast<u16_le*>(bytes) =
+        (Convert8To5(color.r()) << 11) | (Convert8To6(color.g()) << 5) | Convert8To5(color.b());
 }
 
 /**
@@ -186,7 +186,8 @@ inline void EncodeRGB565(const Math::Vec4<u8>& color, u8* bytes) {
  */
 inline void EncodeRGB5A1(const Math::Vec4<u8>& color, u8* bytes) {
     *reinterpret_cast<u16_le*>(bytes) = (Convert8To5(color.r()) << 11) |
-        (Convert8To5(color.g()) << 6) | (Convert8To5(color.b()) << 1) | Convert8To1(color.a());
+                                        (Convert8To5(color.g()) << 6) |
+                                        (Convert8To5(color.b()) << 1) | Convert8To1(color.a());
 }
 
 /**
@@ -196,7 +197,8 @@ inline void EncodeRGB5A1(const Math::Vec4<u8>& color, u8* bytes) {
  */
 inline void EncodeRGBA4(const Math::Vec4<u8>& color, u8* bytes) {
     *reinterpret_cast<u16_le*>(bytes) = (Convert8To4(color.r()) << 12) |
-        (Convert8To4(color.g()) << 8) | (Convert8To4(color.b()) << 4) | Convert8To4(color.a());
+                                        (Convert8To4(color.g()) << 8) |
+                                        (Convert8To4(color.b()) << 4) | Convert8To4(color.a());
 }
 
 /**
diff --git a/src/common/common_funcs.h b/src/common/common_funcs.h
index 4633897ce..ad5bdbc08 100644
--- a/src/common/common_funcs.h
+++ b/src/common/common_funcs.h
@@ -14,7 +14,7 @@
 
 /// Textually concatenates two tokens. The double-expansion is required by the C preprocessor.
 #define CONCAT2(x, y) DO_CONCAT2(x, y)
-#define DO_CONCAT2(x, y) x ## y
+#define DO_CONCAT2(x, y) x##y
 
 // helper macro to properly align structure members.
 // Calling INSERT_PADDING_BYTES will add a new member variable with a name like "pad121",
@@ -24,9 +24,9 @@
 
 // Inlining
 #ifdef _WIN32
-    #define FORCE_INLINE __forceinline
+#define FORCE_INLINE __forceinline
 #else
-    #define FORCE_INLINE inline __attribute__((always_inline))
+#define FORCE_INLINE inline __attribute__((always_inline))
 #endif
 
 #ifndef _MSC_VER
@@ -46,7 +46,8 @@
 #else
 inline u32 rotl(u32 x, int shift) {
     shift &= 31;
-    if (!shift) return x;
+    if (!shift)
+        return x;
     return (x << shift) | (x >> (32 - shift));
 }
 #endif
@@ -56,17 +57,18 @@ inline u32 rotl(u32 x, int shift) {
 #else
 inline u32 rotr(u32 x, int shift) {
     shift &= 31;
-    if (!shift) return x;
+    if (!shift)
+        return x;
     return (x >> shift) | (x << (32 - shift));
 }
 #endif
 
-inline u64 _rotl64(u64 x, unsigned int shift){
+inline u64 _rotl64(u64 x, unsigned int shift) {
     unsigned int n = shift % 64;
     return (x << n) | (x >> (64 - n));
 }
 
-inline u64 _rotr64(u64 x, unsigned int shift){
+inline u64 _rotr64(u64 x, unsigned int shift) {
     unsigned int n = shift % 64;
     return (x >> n) | (x << (64 - n));
 }
@@ -74,17 +76,18 @@ inline u64 _rotr64(u64 x, unsigned int shift){
 #else // _MSC_VER
 
 #if (_MSC_VER < 1900)
-    // Function Cross-Compatibility
-    #define snprintf _snprintf
+// Function Cross-Compatibility
+#define snprintf _snprintf
 #endif
 
 // Locale Cross-Compatibility
 #define locale_t _locale_t
 
 extern "C" {
-    __declspec(dllimport) void __stdcall DebugBreak(void);
+__declspec(dllimport) void __stdcall DebugBreak(void);
 }
-#define Crash() {DebugBreak();}
+#define Crash()                                                                                    \
+    { DebugBreak(); }
 
 // cstdlib provides these on MSVC
 #define rotr _rotr
diff --git a/src/common/common_paths.h b/src/common/common_paths.h
index 2903f2cf2..a5342a610 100644
--- a/src/common/common_paths.h
+++ b/src/common/common_paths.h
@@ -16,13 +16,13 @@
 #define ROOT_DIR "."
 #define USERDATA_DIR "user"
 #ifdef USER_DIR
-    #define EMU_DATA_DIR USER_DIR
+#define EMU_DATA_DIR USER_DIR
 #else
-    #ifdef _WIN32
-        #define EMU_DATA_DIR "Citra Emulator"
-    #else
-        #define EMU_DATA_DIR "citra-emu"
-    #endif
+#ifdef _WIN32
+#define EMU_DATA_DIR "Citra Emulator"
+#else
+#define EMU_DATA_DIR "citra-emu"
+#endif
 #endif
 
 // Dirs in both User and Sys
@@ -31,32 +31,32 @@
 #define JAP_DIR "JAP"
 
 // Subdirs in the User dir returned by GetUserPath(D_USER_IDX)
-#define CONFIG_DIR               "config"
-#define GAMECONFIG_DIR           "game_config"
-#define MAPS_DIR                 "maps"
-#define CACHE_DIR                "cache"
-#define SDMC_DIR                 "sdmc"
-#define NAND_DIR                 "nand"
-#define SYSDATA_DIR              "sysdata"
-#define SHADERCACHE_DIR          "shader_cache"
-#define STATESAVES_DIR           "state_saves"
-#define SCREENSHOTS_DIR          "screenShots"
-#define DUMP_DIR                 "dump"
-#define DUMP_TEXTURES_DIR        "textures"
-#define DUMP_FRAMES_DIR          "frames"
-#define DUMP_AUDIO_DIR           "audio"
-#define LOGS_DIR                 "logs"
-#define SHADERS_DIR              "shaders"
-#define SYSCONF_DIR              "sysconf"
+#define CONFIG_DIR "config"
+#define GAMECONFIG_DIR "game_config"
+#define MAPS_DIR "maps"
+#define CACHE_DIR "cache"
+#define SDMC_DIR "sdmc"
+#define NAND_DIR "nand"
+#define SYSDATA_DIR "sysdata"
+#define SHADERCACHE_DIR "shader_cache"
+#define STATESAVES_DIR "state_saves"
+#define SCREENSHOTS_DIR "screenShots"
+#define DUMP_DIR "dump"
+#define DUMP_TEXTURES_DIR "textures"
+#define DUMP_FRAMES_DIR "frames"
+#define DUMP_AUDIO_DIR "audio"
+#define LOGS_DIR "logs"
+#define SHADERS_DIR "shaders"
+#define SYSCONF_DIR "sysconf"
 
 // Filenames
 // Files in the directory returned by GetUserPath(D_CONFIG_IDX)
-#define EMU_CONFIG        "emu.ini"
-#define DEBUGGER_CONFIG   "debugger.ini"
-#define LOGGER_CONFIG     "logger.ini"
+#define EMU_CONFIG "emu.ini"
+#define DEBUGGER_CONFIG "debugger.ini"
+#define LOGGER_CONFIG "logger.ini"
 
 // Sys files
-#define SHARED_FONT       "shared_font.bin"
+#define SHARED_FONT "shared_font.bin"
 
 // Files in the directory returned by GetUserPath(D_LOGS_IDX)
 #define MAIN_LOG "emu.log"
diff --git a/src/common/common_types.h b/src/common/common_types.h
index 9f51dff18..ee18eac81 100644
--- a/src/common/common_types.h
+++ b/src/common/common_types.h
@@ -32,18 +32,18 @@
 #endif
 #endif
 
-typedef std::uint8_t  u8;  ///< 8-bit unsigned byte
+typedef std::uint8_t u8;   ///< 8-bit unsigned byte
 typedef std::uint16_t u16; ///< 16-bit unsigned short
 typedef std::uint32_t u32; ///< 32-bit unsigned word
 typedef std::uint64_t u64; ///< 64-bit unsigned int
 
-typedef std::int8_t  s8;  ///< 8-bit signed byte
+typedef std::int8_t s8;   ///< 8-bit signed byte
 typedef std::int16_t s16; ///< 16-bit signed short
 typedef std::int32_t s32; ///< 32-bit signed word
 typedef std::int64_t s64; ///< 64-bit signed int
 
-typedef float   f32; ///< 32-bit floating point
-typedef double  f64; ///< 64-bit floating point
+typedef float f32;  ///< 32-bit floating point
+typedef double f64; ///< 64-bit floating point
 
 // TODO: It would be nice to eventually replace these with strong types that prevent accidental
 // conversion between each other.
diff --git a/src/common/emu_window.cpp b/src/common/emu_window.cpp
index fd728c109..c86f663a8 100644
--- a/src/common/emu_window.cpp
+++ b/src/common/emu_window.cpp
@@ -44,18 +44,17 @@ void EmuWindow::CirclePadUpdated(float x, float y) {
  */
 static bool IsWithinTouchscreen(const EmuWindow::FramebufferLayout& layout, unsigned framebuffer_x,
                                 unsigned framebuffer_y) {
-    return (framebuffer_y >= layout.bottom_screen.top    &&
-            framebuffer_y <  layout.bottom_screen.bottom &&
-            framebuffer_x >= layout.bottom_screen.left   &&
-            framebuffer_x <  layout.bottom_screen.right);
+    return (
+        framebuffer_y >= layout.bottom_screen.top && framebuffer_y < layout.bottom_screen.bottom &&
+        framebuffer_x >= layout.bottom_screen.left && framebuffer_x < layout.bottom_screen.right);
 }
 
-std::tuple<unsigned,unsigned> EmuWindow::ClipToTouchScreen(unsigned new_x, unsigned new_y) {
+std::tuple<unsigned, unsigned> EmuWindow::ClipToTouchScreen(unsigned new_x, unsigned new_y) {
     new_x = std::max(new_x, framebuffer_layout.bottom_screen.left);
-    new_x = std::min(new_x, framebuffer_layout.bottom_screen.right-1);
+    new_x = std::min(new_x, framebuffer_layout.bottom_screen.right - 1);
 
     new_y = std::max(new_y, framebuffer_layout.bottom_screen.top);
-    new_y = std::min(new_y, framebuffer_layout.bottom_screen.bottom-1);
+    new_y = std::min(new_y, framebuffer_layout.bottom_screen.bottom - 1);
 
     return std::make_tuple(new_x, new_y);
 }
@@ -64,10 +63,12 @@ void EmuWindow::TouchPressed(unsigned framebuffer_x, unsigned framebuffer_y) {
     if (!IsWithinTouchscreen(framebuffer_layout, framebuffer_x, framebuffer_y))
         return;
 
-    touch_x = VideoCore::kScreenBottomWidth * (framebuffer_x - framebuffer_layout.bottom_screen.left) /
-        (framebuffer_layout.bottom_screen.right - framebuffer_layout.bottom_screen.left);
-    touch_y = VideoCore::kScreenBottomHeight * (framebuffer_y - framebuffer_layout.bottom_screen.top) /
-        (framebuffer_layout.bottom_screen.bottom - framebuffer_layout.bottom_screen.top);
+    touch_x = VideoCore::kScreenBottomWidth *
+              (framebuffer_x - framebuffer_layout.bottom_screen.left) /
+              (framebuffer_layout.bottom_screen.right - framebuffer_layout.bottom_screen.left);
+    touch_y = VideoCore::kScreenBottomHeight *
+              (framebuffer_y - framebuffer_layout.bottom_screen.top) /
+              (framebuffer_layout.bottom_screen.bottom - framebuffer_layout.bottom_screen.top);
 
     touch_pressed = true;
     pad_state.touch.Assign(1);
@@ -90,16 +91,19 @@ void EmuWindow::TouchMoved(unsigned framebuffer_x, unsigned framebuffer_y) {
     TouchPressed(framebuffer_x, framebuffer_y);
 }
 
-EmuWindow::FramebufferLayout EmuWindow::FramebufferLayout::DefaultScreenLayout(unsigned width, unsigned height) {
+EmuWindow::FramebufferLayout EmuWindow::FramebufferLayout::DefaultScreenLayout(unsigned width,
+                                                                               unsigned height) {
     // When hiding the widget, the function receives a size of 0
-    if (width == 0) width = 1;
-    if (height == 0) height = 1;
+    if (width == 0)
+        width = 1;
+    if (height == 0)
+        height = 1;
 
-    EmuWindow::FramebufferLayout res = { width, height, {}, {} };
+    EmuWindow::FramebufferLayout res = {width, height, {}, {}};
 
     float window_aspect_ratio = static_cast<float>(height) / width;
-    float emulation_aspect_ratio = static_cast<float>(VideoCore::kScreenTopHeight * 2) /
-        VideoCore::kScreenTopWidth;
+    float emulation_aspect_ratio =
+        static_cast<float>(VideoCore::kScreenTopHeight * 2) / VideoCore::kScreenTopWidth;
 
     if (window_aspect_ratio > emulation_aspect_ratio) {
         // Window is narrower than the emulation content => apply borders to the top and bottom
@@ -110,8 +114,9 @@ EmuWindow::FramebufferLayout EmuWindow::FramebufferLayout::DefaultScreenLayout(u
         res.top_screen.top = (height - viewport_height) / 2;
         res.top_screen.bottom = res.top_screen.top + viewport_height / 2;
 
-        int bottom_width = static_cast<int>((static_cast<float>(VideoCore::kScreenBottomWidth) /
-            VideoCore::kScreenTopWidth) * (res.top_screen.right - res.top_screen.left));
+        int bottom_width = static_cast<int>(
+            (static_cast<float>(VideoCore::kScreenBottomWidth) / VideoCore::kScreenTopWidth) *
+            (res.top_screen.right - res.top_screen.left));
         int bottom_border = ((res.top_screen.right - res.top_screen.left) - bottom_width) / 2;
 
         res.bottom_screen.left = bottom_border;
@@ -127,8 +132,9 @@ EmuWindow::FramebufferLayout EmuWindow::FramebufferLayout::DefaultScreenLayout(u
         res.top_screen.top = 0;
         res.top_screen.bottom = res.top_screen.top + height / 2;
 
-        int bottom_width = static_cast<int>((static_cast<float>(VideoCore::kScreenBottomWidth) /
-            VideoCore::kScreenTopWidth) * (res.top_screen.right - res.top_screen.left));
+        int bottom_width = static_cast<int>(
+            (static_cast<float>(VideoCore::kScreenBottomWidth) / VideoCore::kScreenTopWidth) *
+            (res.top_screen.right - res.top_screen.left));
         int bottom_border = ((res.top_screen.right - res.top_screen.left) - bottom_width) / 2;
 
         res.bottom_screen.left = res.top_screen.left + bottom_border;
diff --git a/src/common/emu_window.h b/src/common/emu_window.h
index 57e303b6d..de8badd4f 100644
--- a/src/common/emu_window.h
+++ b/src/common/emu_window.h
@@ -30,15 +30,14 @@
  * - DO NOT TREAT THIS CLASS AS A GUI TOOLKIT ABSTRACTION LAYER. That's not what it is. Please
  *   re-read the upper points again and think about it if you don't see this.
  */
-class EmuWindow
-{
+class EmuWindow {
 public:
     /// Data structure to store emuwindow configuration
     struct WindowConfig {
-        bool    fullscreen;
-        int     res_width;
-        int     res_height;
-        std::pair<unsigned,unsigned> min_client_area_size;
+        bool fullscreen;
+        int res_width;
+        int res_height;
+        std::pair<unsigned, unsigned> min_client_area_size;
     };
 
     /// Describes the layout of the window framebuffer (size and top/bottom screen positions)
@@ -193,15 +192,18 @@ public:
 
     /**
      * Returns currently active configuration.
-     * @note Accesses to the returned object need not be consistent because it may be modified in another thread
+     * @note Accesses to the returned object need not be consistent because it may be modified in
+     * another thread
      */
     const WindowConfig& GetActiveConfig() const {
         return active_config;
     }
 
     /**
-     * Requests the internal configuration to be replaced by the specified argument at some point in the future.
-     * @note This method is thread-safe, because it delays configuration changes to the GUI event loop. Hence there is no guarantee on when the requested configuration will be active.
+     * Requests the internal configuration to be replaced by the specified argument at some point in
+     * the future.
+     * @note This method is thread-safe, because it delays configuration changes to the GUI event
+     * loop. Hence there is no guarantee on when the requested configuration will be active.
      */
     void SetConfig(const WindowConfig& val) {
         config = val;
@@ -227,7 +229,8 @@ protected:
         circle_pad_y = 0;
         touch_pressed = false;
     }
-    virtual ~EmuWindow() {}
+    virtual ~EmuWindow() {
+    }
 
     /**
      * Processes any pending configuration changes from the last SetConfig call.
@@ -258,7 +261,7 @@ protected:
      * Update internal client area size with the given parameter.
      * @note EmuWindow implementations will usually use this in window resize event handlers.
      */
-    void NotifyClientAreaSizeChanged(const std::pair<unsigned,unsigned>& size) {
+    void NotifyClientAreaSizeChanged(const std::pair<unsigned, unsigned>& size) {
         client_area_width = size.first;
         client_area_height = size.second;
     }
@@ -266,32 +269,35 @@ protected:
 private:
     /**
      * Handler called when the minimal client area was requested to be changed via SetConfig.
-     * For the request to be honored, EmuWindow implementations will usually reimplement this function.
+     * For the request to be honored, EmuWindow implementations will usually reimplement this
+     * function.
      */
-    virtual void OnMinimalClientAreaChangeRequest(const std::pair<unsigned,unsigned>& minimal_size) {
+    virtual void
+    OnMinimalClientAreaChangeRequest(const std::pair<unsigned, unsigned>& minimal_size) {
         // By default, ignore this request and do nothing.
     }
 
     FramebufferLayout framebuffer_layout; ///< Current framebuffer layout
 
-    unsigned client_area_width;    ///< Current client width, should be set by window impl.
-    unsigned client_area_height;   ///< Current client height, should be set by window impl.
+    unsigned client_area_width;  ///< Current client width, should be set by window impl.
+    unsigned client_area_height; ///< Current client height, should be set by window impl.
 
-    WindowConfig config;         ///< Internal configuration (changes pending for being applied in ProcessConfigurationChanges)
-    WindowConfig active_config;  ///< Internal active configuration
+    WindowConfig config;        ///< Internal configuration (changes pending for being applied in
+                                /// ProcessConfigurationChanges)
+    WindowConfig active_config; ///< Internal active configuration
 
-    bool touch_pressed;          ///< True if touchpad area is currently pressed, otherwise false
+    bool touch_pressed; ///< True if touchpad area is currently pressed, otherwise false
 
-    u16 touch_x;    ///< Touchpad X-position in native 3DS pixel coordinates (0-320)
-    u16 touch_y;    ///< Touchpad Y-position in native 3DS pixel coordinates (0-240)
+    u16 touch_x; ///< Touchpad X-position in native 3DS pixel coordinates (0-320)
+    u16 touch_y; ///< Touchpad Y-position in native 3DS pixel coordinates (0-240)
 
     s16 circle_pad_x; ///< Circle pad X-position in native 3DS pixel coordinates (-156 - 156)
     s16 circle_pad_y; ///< Circle pad Y-position in native 3DS pixel coordinates (-156 - 156)
 
-   /**
-    * Clip the provided coordinates to be inside the touchscreen area.
-    */
-    std::tuple<unsigned,unsigned> ClipToTouchScreen(unsigned new_x, unsigned new_y);
+    /**
+     * Clip the provided coordinates to be inside the touchscreen area.
+     */
+    std::tuple<unsigned, unsigned> ClipToTouchScreen(unsigned new_x, unsigned new_y);
 
     Service::HID::PadState pad_state;
 };
diff --git a/src/common/file_util.cpp b/src/common/file_util.cpp
index bc83ab737..c8723a4b3 100644
--- a/src/common/file_util.cpp
+++ b/src/common/file_util.cpp
@@ -2,73 +2,70 @@
 // Licensed under GPLv2 or any later version
 // Refer to the license.txt file included.
 
+#include "common/file_util.h"
 #include "common/assert.h"
 #include "common/common_funcs.h"
 #include "common/common_paths.h"
-#include "common/file_util.h"
 #include "common/logging/log.h"
 
 #ifdef _WIN32
-    #include <windows.h>
-    #include <shlobj.h> // for SHGetFolderPath
-    #include <shellapi.h>
-    #include <commdlg.h> // for GetSaveFileName
-    #include <io.h>
-    #include <direct.h> // getcwd
-    #include <tchar.h>
-
-    #include "common/string_util.h"
-
-    // 64 bit offsets for windows
-    #define fseeko _fseeki64
-    #define ftello _ftelli64
-    #define atoll _atoi64
-    #define stat64 _stat64
-    #define fstat64 _fstat64
-    #define fileno _fileno
+#include <windows.h>
+#include <commdlg.h> // for GetSaveFileName
+#include <direct.h>  // getcwd
+#include <io.h>
+#include <shellapi.h>
+#include <shlobj.h> // for SHGetFolderPath
+#include <tchar.h>
+
+#include "common/string_util.h"
+
+// 64 bit offsets for windows
+#define fseeko _fseeki64
+#define ftello _ftelli64
+#define atoll _atoi64
+#define stat64 _stat64
+#define fstat64 _fstat64
+#define fileno _fileno
 #else
-    #ifdef __APPLE__
-        #include <sys/param.h>
-    #endif
-    #include <cctype>
-    #include <cerrno>
-    #include <cstdlib>
-    #include <cstring>
-    #include <dirent.h>
-    #include <pwd.h>
-    #include <unistd.h>
+#ifdef __APPLE__
+#include <sys/param.h>
+#endif
+#include <cctype>
+#include <cerrno>
+#include <cstdlib>
+#include <cstring>
+#include <dirent.h>
+#include <pwd.h>
+#include <unistd.h>
 #endif
 
 #if defined(__APPLE__)
-    #include <CoreFoundation/CFString.h>
-    #include <CoreFoundation/CFURL.h>
-    #include <CoreFoundation/CFBundle.h>
+#include <CoreFoundation/CFBundle.h>
+#include <CoreFoundation/CFString.h>
+#include <CoreFoundation/CFURL.h>
 #endif
 
 #include <algorithm>
 #include <sys/stat.h>
 
 #ifndef S_ISDIR
-    #define S_ISDIR(m)  (((m)&S_IFMT) == S_IFDIR)
+#define S_ISDIR(m) (((m)&S_IFMT) == S_IFDIR)
 #endif
 
 #ifdef BSD4_4
-    #define stat64 stat
-    #define fstat64 fstat
+#define stat64 stat
+#define fstat64 fstat
 #endif
 
 // This namespace has various generic functions related to files and paths.
 // The code still needs a ton of cleanup.
 // REMEMBER: strdup considered harmful!
-namespace FileUtil
-{
+namespace FileUtil {
 
 // Remove any ending forward slashes from directory paths
 // Modifies argument.
-static void StripTailDirSlashes(std::string &fname)
-{
-    if (fname.length() > 1)
-    {
+static void StripTailDirSlashes(std::string& fname) {
+    if (fname.length() > 1) {
         size_t i = fname.length();
         while (i > 0 && fname[i - 1] == DIR_SEP_CHR)
             --i;
@@ -78,8 +75,7 @@ static void StripTailDirSlashes(std::string &fname)
 }
 
 // Returns true if file filename exists
-bool Exists(const std::string &filename)
-{
+bool Exists(const std::string& filename) {
     struct stat64 file_info;
 
     std::string copy(filename);
@@ -99,8 +95,7 @@ bool Exists(const std::string &filename)
 }
 
 // Returns true if filename is a directory
-bool IsDirectory(const std::string &filename)
-{
+bool IsDirectory(const std::string& filename) {
     struct stat64 file_info;
 
     std::string copy(filename);
@@ -117,8 +112,8 @@ bool IsDirectory(const std::string &filename)
 #endif
 
     if (result < 0) {
-        LOG_WARNING(Common_Filesystem, "stat failed on %s: %s",
-                 filename.c_str(), GetLastErrorMsg());
+        LOG_WARNING(Common_Filesystem, "stat failed on %s: %s", filename.c_str(),
+                    GetLastErrorMsg());
         return false;
     }
 
@@ -127,36 +122,32 @@ bool IsDirectory(const std::string &filename)
 
 // Deletes a given filename, return true on success
 // Doesn't supports deleting a directory
-bool Delete(const std::string &filename)
-{
+bool Delete(const std::string& filename) {
     LOG_INFO(Common_Filesystem, "file %s", filename.c_str());
 
     // Return true because we care about the file no
     // being there, not the actual delete.
-    if (!Exists(filename))
-    {
+    if (!Exists(filename)) {
         LOG_WARNING(Common_Filesystem, "%s does not exist", filename.c_str());
         return true;
     }
 
     // We can't delete a directory
-    if (IsDirectory(filename))
-    {
+    if (IsDirectory(filename)) {
         LOG_ERROR(Common_Filesystem, "Failed: %s is a directory", filename.c_str());
         return false;
     }
 
 #ifdef _WIN32
-    if (!DeleteFileW(Common::UTF8ToUTF16W(filename).c_str()))
-    {
-        LOG_ERROR(Common_Filesystem, "DeleteFile failed on %s: %s",
-                 filename.c_str(), GetLastErrorMsg());
+    if (!DeleteFileW(Common::UTF8ToUTF16W(filename).c_str())) {
+        LOG_ERROR(Common_Filesystem, "DeleteFile failed on %s: %s", filename.c_str(),
+                  GetLastErrorMsg());
         return false;
     }
 #else
     if (unlink(filename.c_str()) == -1) {
-        LOG_ERROR(Common_Filesystem, "unlink failed on %s: %s",
-                 filename.c_str(), GetLastErrorMsg());
+        LOG_ERROR(Common_Filesystem, "unlink failed on %s: %s", filename.c_str(),
+                  GetLastErrorMsg());
         return false;
     }
 #endif
@@ -165,16 +156,15 @@ bool Delete(const std::string &filename)
 }
 
 // Returns true if successful, or path already exists.
-bool CreateDir(const std::string &path)
-{
+bool CreateDir(const std::string& path) {
     LOG_TRACE(Common_Filesystem, "directory %s", path.c_str());
 #ifdef _WIN32
     if (::CreateDirectoryW(Common::UTF8ToUTF16W(path).c_str(), nullptr))
         return true;
     DWORD error = GetLastError();
-    if (error == ERROR_ALREADY_EXISTS)
-    {
-        LOG_WARNING(Common_Filesystem, "CreateDirectory failed on %s: already exists", path.c_str());
+    if (error == ERROR_ALREADY_EXISTS) {
+        LOG_WARNING(Common_Filesystem, "CreateDirectory failed on %s: already exists",
+                    path.c_str());
         return true;
     }
     LOG_ERROR(Common_Filesystem, "CreateDirectory failed on %s: %i", path.c_str(), error);
@@ -185,8 +175,7 @@ bool CreateDir(const std::string &path)
 
     int err = errno;
 
-    if (err == EEXIST)
-    {
+    if (err == EEXIST) {
         LOG_WARNING(Common_Filesystem, "mkdir failed on %s: already exists", path.c_str());
         return true;
     }
@@ -197,20 +186,17 @@ bool CreateDir(const std::string &path)
 }
 
 // Creates the full path of fullPath returns true on success
-bool CreateFullPath(const std::string &fullPath)
-{
+bool CreateFullPath(const std::string& fullPath) {
     int panicCounter = 100;
     LOG_TRACE(Common_Filesystem, "path %s", fullPath.c_str());
 
-    if (FileUtil::Exists(fullPath))
-    {
+    if (FileUtil::Exists(fullPath)) {
         LOG_WARNING(Common_Filesystem, "path exists %s", fullPath.c_str());
         return true;
     }
 
     size_t position = 0;
-    while (true)
-    {
+    while (true) {
         // Find next sub path
         position = fullPath.find(DIR_SEP_CHR, position);
 
@@ -227,8 +213,7 @@ bool CreateFullPath(const std::string &fullPath)
 
         // A safety check
         panicCounter--;
-        if (panicCounter <= 0)
-        {
+        if (panicCounter <= 0) {
             LOG_ERROR(Common, "CreateFullPath: directory structure is too deep");
             return false;
         }
@@ -236,15 +221,12 @@ bool CreateFullPath(const std::string &fullPath)
     }
 }
 
-
 // Deletes a directory filename, returns true on success
-bool DeleteDir(const std::string &filename)
-{
+bool DeleteDir(const std::string& filename) {
     LOG_INFO(Common_Filesystem, "directory %s", filename.c_str());
 
     // check if a directory
-    if (!FileUtil::IsDirectory(filename))
-    {
+    if (!FileUtil::IsDirectory(filename)) {
         LOG_ERROR(Common_Filesystem, "Not a directory %s", filename.c_str());
         return false;
     }
@@ -262,83 +244,73 @@ bool DeleteDir(const std::string &filename)
 }
 
 // renames file srcFilename to destFilename, returns true on success
-bool Rename(const std::string &srcFilename, const std::string &destFilename)
-{
-    LOG_TRACE(Common_Filesystem, "%s --> %s",
-            srcFilename.c_str(), destFilename.c_str());
+bool Rename(const std::string& srcFilename, const std::string& destFilename) {
+    LOG_TRACE(Common_Filesystem, "%s --> %s", srcFilename.c_str(), destFilename.c_str());
 #ifdef _WIN32
-    if (_wrename(Common::UTF8ToUTF16W(srcFilename).c_str(), Common::UTF8ToUTF16W(destFilename).c_str()) == 0)
+    if (_wrename(Common::UTF8ToUTF16W(srcFilename).c_str(),
+                 Common::UTF8ToUTF16W(destFilename).c_str()) == 0)
         return true;
 #else
     if (rename(srcFilename.c_str(), destFilename.c_str()) == 0)
         return true;
 #endif
-    LOG_ERROR(Common_Filesystem, "failed %s --> %s: %s",
-              srcFilename.c_str(), destFilename.c_str(), GetLastErrorMsg());
+    LOG_ERROR(Common_Filesystem, "failed %s --> %s: %s", srcFilename.c_str(), destFilename.c_str(),
+              GetLastErrorMsg());
     return false;
 }
 
 // copies file srcFilename to destFilename, returns true on success
-bool Copy(const std::string &srcFilename, const std::string &destFilename)
-{
-    LOG_TRACE(Common_Filesystem, "%s --> %s",
-            srcFilename.c_str(), destFilename.c_str());
+bool Copy(const std::string& srcFilename, const std::string& destFilename) {
+    LOG_TRACE(Common_Filesystem, "%s --> %s", srcFilename.c_str(), destFilename.c_str());
 #ifdef _WIN32
-    if (CopyFileW(Common::UTF8ToUTF16W(srcFilename).c_str(), Common::UTF8ToUTF16W(destFilename).c_str(), FALSE))
+    if (CopyFileW(Common::UTF8ToUTF16W(srcFilename).c_str(),
+                  Common::UTF8ToUTF16W(destFilename).c_str(), FALSE))
         return true;
 
-    LOG_ERROR(Common_Filesystem, "failed %s --> %s: %s",
-            srcFilename.c_str(), destFilename.c_str(), GetLastErrorMsg());
+    LOG_ERROR(Common_Filesystem, "failed %s --> %s: %s", srcFilename.c_str(), destFilename.c_str(),
+              GetLastErrorMsg());
     return false;
 #else
 
-    // buffer size
+// buffer size
 #define BSIZE 1024
 
     char buffer[BSIZE];
 
     // Open input file
-    FILE *input = fopen(srcFilename.c_str(), "rb");
-    if (!input)
-    {
-        LOG_ERROR(Common_Filesystem, "opening input failed %s --> %s: %s",
-                srcFilename.c_str(), destFilename.c_str(), GetLastErrorMsg());
+    FILE* input = fopen(srcFilename.c_str(), "rb");
+    if (!input) {
+        LOG_ERROR(Common_Filesystem, "opening input failed %s --> %s: %s", srcFilename.c_str(),
+                  destFilename.c_str(), GetLastErrorMsg());
         return false;
     }
 
     // open output file
-    FILE *output = fopen(destFilename.c_str(), "wb");
-    if (!output)
-    {
+    FILE* output = fopen(destFilename.c_str(), "wb");
+    if (!output) {
         fclose(input);
-        LOG_ERROR(Common_Filesystem, "opening output failed %s --> %s: %s",
-                srcFilename.c_str(), destFilename.c_str(), GetLastErrorMsg());
+        LOG_ERROR(Common_Filesystem, "opening output failed %s --> %s: %s", srcFilename.c_str(),
+                  destFilename.c_str(), GetLastErrorMsg());
         return false;
     }
 
     // copy loop
-    while (!feof(input))
-    {
+    while (!feof(input)) {
         // read input
         int rnum = fread(buffer, sizeof(char), BSIZE, input);
-        if (rnum != BSIZE)
-        {
-            if (ferror(input) != 0)
-            {
-                LOG_ERROR(Common_Filesystem,
-                        "failed reading from source, %s --> %s: %s",
-                        srcFilename.c_str(), destFilename.c_str(), GetLastErrorMsg());
+        if (rnum != BSIZE) {
+            if (ferror(input) != 0) {
+                LOG_ERROR(Common_Filesystem, "failed reading from source, %s --> %s: %s",
+                          srcFilename.c_str(), destFilename.c_str(), GetLastErrorMsg());
                 goto bail;
             }
         }
 
         // write output
         int wnum = fwrite(buffer, sizeof(char), rnum, output);
-        if (wnum != rnum)
-        {
-            LOG_ERROR(Common_Filesystem,
-                    "failed writing to output, %s --> %s: %s",
-                    srcFilename.c_str(), destFilename.c_str(), GetLastErrorMsg());
+        if (wnum != rnum) {
+            LOG_ERROR(Common_Filesystem, "failed writing to output, %s --> %s: %s",
+                      srcFilename.c_str(), destFilename.c_str(), GetLastErrorMsg());
             goto bail;
         }
     }
@@ -356,16 +328,13 @@ bail:
 }
 
 // Returns the size of filename (64bit)
-u64 GetSize(const std::string &filename)
-{
-    if (!Exists(filename))
-    {
+u64 GetSize(const std::string& filename) {
+    if (!Exists(filename)) {
         LOG_ERROR(Common_Filesystem, "failed %s: No such file", filename.c_str());
         return 0;
     }
 
-    if (IsDirectory(filename))
-    {
+    if (IsDirectory(filename)) {
         LOG_ERROR(Common_Filesystem, "failed %s: is a directory", filename.c_str());
         return 0;
     }
@@ -377,65 +346,54 @@ u64 GetSize(const std::string &filename)
     if (stat64(filename.c_str(), &buf) == 0)
 #endif
     {
-        LOG_TRACE(Common_Filesystem, "%s: %lld",
-                filename.c_str(), (long long)buf.st_size);
+        LOG_TRACE(Common_Filesystem, "%s: %lld", filename.c_str(), (long long)buf.st_size);
         return buf.st_size;
     }
 
-    LOG_ERROR(Common_Filesystem, "Stat failed %s: %s",
-            filename.c_str(), GetLastErrorMsg());
+    LOG_ERROR(Common_Filesystem, "Stat failed %s: %s", filename.c_str(), GetLastErrorMsg());
     return 0;
 }
 
 // Overloaded GetSize, accepts file descriptor
-u64 GetSize(const int fd)
-{
+u64 GetSize(const int fd) {
     struct stat64 buf;
     if (fstat64(fd, &buf) != 0) {
-        LOG_ERROR(Common_Filesystem, "GetSize: stat failed %i: %s",
-            fd, GetLastErrorMsg());
+        LOG_ERROR(Common_Filesystem, "GetSize: stat failed %i: %s", fd, GetLastErrorMsg());
         return 0;
     }
     return buf.st_size;
 }
 
 // Overloaded GetSize, accepts FILE*
-u64 GetSize(FILE *f)
-{
+u64 GetSize(FILE* f) {
     // can't use off_t here because it can be 32-bit
     u64 pos = ftello(f);
     if (fseeko(f, 0, SEEK_END) != 0) {
-        LOG_ERROR(Common_Filesystem, "GetSize: seek failed %p: %s",
-              f, GetLastErrorMsg());
+        LOG_ERROR(Common_Filesystem, "GetSize: seek failed %p: %s", f, GetLastErrorMsg());
         return 0;
     }
     u64 size = ftello(f);
     if ((size != pos) && (fseeko(f, pos, SEEK_SET) != 0)) {
-        LOG_ERROR(Common_Filesystem, "GetSize: seek failed %p: %s",
-              f, GetLastErrorMsg());
+        LOG_ERROR(Common_Filesystem, "GetSize: seek failed %p: %s", f, GetLastErrorMsg());
         return 0;
     }
     return size;
 }
 
 // creates an empty file filename, returns true on success
-bool CreateEmptyFile(const std::string &filename)
-{
+bool CreateEmptyFile(const std::string& filename) {
     LOG_TRACE(Common_Filesystem, "%s", filename.c_str());
 
-    if (!FileUtil::IOFile(filename, "wb"))
-    {
-        LOG_ERROR(Common_Filesystem, "failed %s: %s",
-                  filename.c_str(), GetLastErrorMsg());
+    if (!FileUtil::IOFile(filename, "wb")) {
+        LOG_ERROR(Common_Filesystem, "failed %s: %s", filename.c_str(), GetLastErrorMsg());
         return false;
     }
 
     return true;
 }
 
-
-bool ForeachDirectoryEntry(unsigned* num_entries_out, const std::string &directory, DirectoryEntryCallable callback)
-{
+bool ForeachDirectoryEntry(unsigned* num_entries_out, const std::string& directory,
+                           DirectoryEntryCallable callback) {
     LOG_TRACE(Common_Filesystem, "directory %s", directory.c_str());
 
     // How many files + directories we found
@@ -457,7 +415,7 @@ bool ForeachDirectoryEntry(unsigned* num_entries_out, const std::string &directo
     do {
         const std::string virtual_name(Common::UTF16ToUTF8(ffd.cFileName));
 #else
-    DIR *dirp = opendir(directory.c_str());
+    DIR* dirp = opendir(directory.c_str());
     if (!dirp)
         return false;
 
@@ -493,8 +451,8 @@ bool ForeachDirectoryEntry(unsigned* num_entries_out, const std::string &directo
     return true;
 }
 
-unsigned ScanDirectoryTree(const std::string &directory, FSTEntry& parent_entry, unsigned int recursion)
-{
+unsigned ScanDirectoryTree(const std::string& directory, FSTEntry& parent_entry,
+                           unsigned int recursion) {
     const auto callback = [recursion, &parent_entry](unsigned* num_entries_out,
                                                      const std::string& directory,
                                                      const std::string& virtual_name) -> bool {
@@ -526,11 +484,8 @@ unsigned ScanDirectoryTree(const std::string &directory, FSTEntry& parent_entry,
     return ForeachDirectoryEntry(&num_entries, directory, callback) ? num_entries : 0;
 }
 
-
-bool DeleteDirRecursively(const std::string &directory, unsigned int recursion)
-{
-    const auto callback = [recursion](unsigned* num_entries_out,
-                                      const std::string& directory,
+bool DeleteDirRecursively(const std::string& directory, unsigned int recursion) {
+    const auto callback = [recursion](unsigned* num_entries_out, const std::string& directory,
                                       const std::string& virtual_name) -> bool {
         std::string new_path = directory + DIR_SEP_CHR + virtual_name;
 
@@ -551,53 +506,53 @@ bool DeleteDirRecursively(const std::string &directory, unsigned int recursion)
 }
 
 // Create directory and copy contents (does not overwrite existing files)
-void CopyDir(const std::string &source_path, const std::string &dest_path)
-{
+void CopyDir(const std::string& source_path, const std::string& dest_path) {
 #ifndef _WIN32
-    if (source_path == dest_path) return;
-    if (!FileUtil::Exists(source_path)) return;
-    if (!FileUtil::Exists(dest_path)) FileUtil::CreateFullPath(dest_path);
-
-    DIR *dirp = opendir(source_path.c_str());
-    if (!dirp) return;
+    if (source_path == dest_path)
+        return;
+    if (!FileUtil::Exists(source_path))
+        return;
+    if (!FileUtil::Exists(dest_path))
+        FileUtil::CreateFullPath(dest_path);
+
+    DIR* dirp = opendir(source_path.c_str());
+    if (!dirp)
+        return;
 
     while (struct dirent* result = readdir(dirp)) {
         const std::string virtualName(result->d_name);
         // check for "." and ".."
         if (((virtualName[0] == '.') && (virtualName[1] == '\0')) ||
-            ((virtualName[0] == '.') && (virtualName[1] == '.') &&
-            (virtualName[2] == '\0')))
+            ((virtualName[0] == '.') && (virtualName[1] == '.') && (virtualName[2] == '\0')))
             continue;
 
         std::string source, dest;
         source = source_path + virtualName;
         dest = dest_path + virtualName;
-        if (IsDirectory(source))
-        {
+        if (IsDirectory(source)) {
             source += '/';
             dest += '/';
-            if (!FileUtil::Exists(dest)) FileUtil::CreateFullPath(dest);
+            if (!FileUtil::Exists(dest))
+                FileUtil::CreateFullPath(dest);
             CopyDir(source, dest);
-        }
-        else if (!FileUtil::Exists(dest)) FileUtil::Copy(source, dest);
+        } else if (!FileUtil::Exists(dest))
+            FileUtil::Copy(source, dest);
     }
     closedir(dirp);
 #endif
 }
 
 // Returns the current directory
-std::string GetCurrentDir()
-{
-    // Get the current working directory (getcwd uses malloc)
+std::string GetCurrentDir() {
+// Get the current working directory (getcwd uses malloc)
 #ifdef _WIN32
-    wchar_t *dir;
+    wchar_t* dir;
     if (!(dir = _wgetcwd(nullptr, 0))) {
 #else
-    char *dir;
+    char* dir;
     if (!(dir = getcwd(nullptr, 0))) {
 #endif
-        LOG_ERROR(Common_Filesystem, "GetCurrentDirectory failed: %s",
-                GetLastErrorMsg());
+        LOG_ERROR(Common_Filesystem, "GetCurrentDirectory failed: %s", GetLastErrorMsg());
         return nullptr;
     }
 #ifdef _WIN32
@@ -610,8 +565,7 @@ std::string GetCurrentDir()
 }
 
 // Sets the current directory to the given directory
-bool SetCurrentDir(const std::string &directory)
-{
+bool SetCurrentDir(const std::string& directory) {
 #ifdef _WIN32
     return _wchdir(Common::UTF8ToUTF16W(directory).c_str()) == 0;
 #else
@@ -620,8 +574,7 @@ bool SetCurrentDir(const std::string &directory)
 }
 
 #if defined(__APPLE__)
-std::string GetBundleDirectory()
-{
+std::string GetBundleDirectory() {
     CFURLRef BundleRef;
     char AppBundlePath[MAXPATHLEN];
     // Get the main bundle for the app
@@ -636,11 +589,9 @@ std::string GetBundleDirectory()
 #endif
 
 #ifdef _WIN32
-std::string& GetExeDirectory()
-{
+std::string& GetExeDirectory() {
     static std::string exe_path;
-    if (exe_path.empty())
-    {
+    if (exe_path.empty()) {
         wchar_t wchar_exe_path[2048];
         GetModuleFileNameW(nullptr, wchar_exe_path, 2048);
         exe_path = Common::UTF16ToUTF8(wchar_exe_path);
@@ -660,7 +611,8 @@ static const std::string& GetHomeDirectory() {
             home_path = envvar;
         } else {
             auto pw = getpwuid(getuid());
-            ASSERT_MSG(pw, "$HOME isn’t defined, and the current user can’t be found in /etc/passwd.");
+            ASSERT_MSG(pw,
+                       "$HOME isn’t defined, and the current user can’t be found in /etc/passwd.");
             home_path = pw->pw_dir;
         }
     }
@@ -699,11 +651,10 @@ static const std::string GetUserDirectory(const std::string& envvar) {
 }
 #endif
 
-std::string GetSysDirectory()
-{
+std::string GetSysDirectory() {
     std::string sysDir;
 
-#if defined (__APPLE__)
+#if defined(__APPLE__)
     sysDir = GetBundleDirectory();
     sysDir += DIR_SEP;
     sysDir += SYSDATA_DIR;
@@ -718,123 +669,114 @@ std::string GetSysDirectory()
 
 // Returns a string with a Citra data dir or file in the user's home
 // directory. To be used in "multi-user" mode (that is, installed).
-const std::string& GetUserPath(const unsigned int DirIDX, const std::string &newPath)
-{
+const std::string& GetUserPath(const unsigned int DirIDX, const std::string& newPath) {
     static std::string paths[NUM_PATH_INDICES];
 
     // Set up all paths and files on the first run
-    if (paths[D_USER_IDX].empty())
-    {
+    if (paths[D_USER_IDX].empty()) {
 #ifdef _WIN32
-        paths[D_USER_IDX]   = GetExeDirectory() + DIR_SEP USERDATA_DIR DIR_SEP;
+        paths[D_USER_IDX] = GetExeDirectory() + DIR_SEP USERDATA_DIR DIR_SEP;
         paths[D_CONFIG_IDX] = paths[D_USER_IDX] + CONFIG_DIR DIR_SEP;
-        paths[D_CACHE_IDX]  = paths[D_USER_IDX] + CACHE_DIR DIR_SEP;
+        paths[D_CACHE_IDX] = paths[D_USER_IDX] + CACHE_DIR DIR_SEP;
 #else
         if (FileUtil::Exists(ROOT_DIR DIR_SEP USERDATA_DIR)) {
-            paths[D_USER_IDX]   = ROOT_DIR DIR_SEP USERDATA_DIR DIR_SEP;
+            paths[D_USER_IDX] = ROOT_DIR DIR_SEP USERDATA_DIR DIR_SEP;
             paths[D_CONFIG_IDX] = paths[D_USER_IDX] + CONFIG_DIR DIR_SEP;
-            paths[D_CACHE_IDX]  = paths[D_USER_IDX] + CACHE_DIR DIR_SEP;
+            paths[D_CACHE_IDX] = paths[D_USER_IDX] + CACHE_DIR DIR_SEP;
         } else {
-            std::string data_dir   = GetUserDirectory("XDG_DATA_HOME");
+            std::string data_dir = GetUserDirectory("XDG_DATA_HOME");
             std::string config_dir = GetUserDirectory("XDG_CONFIG_HOME");
-            std::string cache_dir  = GetUserDirectory("XDG_CACHE_HOME");
+            std::string cache_dir = GetUserDirectory("XDG_CACHE_HOME");
 
-            paths[D_USER_IDX]   = data_dir   + DIR_SEP EMU_DATA_DIR DIR_SEP;
+            paths[D_USER_IDX] = data_dir + DIR_SEP EMU_DATA_DIR DIR_SEP;
             paths[D_CONFIG_IDX] = config_dir + DIR_SEP EMU_DATA_DIR DIR_SEP;
-            paths[D_CACHE_IDX]  = cache_dir  + DIR_SEP EMU_DATA_DIR DIR_SEP;
+            paths[D_CACHE_IDX] = cache_dir + DIR_SEP EMU_DATA_DIR DIR_SEP;
         }
 #endif
 
-        paths[D_GAMECONFIG_IDX]     = paths[D_USER_IDX] + GAMECONFIG_DIR DIR_SEP;
-        paths[D_MAPS_IDX]           = paths[D_USER_IDX] + MAPS_DIR DIR_SEP;
-        paths[D_SDMC_IDX]           = paths[D_USER_IDX] + SDMC_DIR DIR_SEP;
-        paths[D_NAND_IDX]           = paths[D_USER_IDX] + NAND_DIR DIR_SEP;
-        paths[D_SYSDATA_IDX]        = paths[D_USER_IDX] + SYSDATA_DIR DIR_SEP;
-        paths[D_SHADERCACHE_IDX]    = paths[D_USER_IDX] + SHADERCACHE_DIR DIR_SEP;
-        paths[D_SHADERS_IDX]        = paths[D_USER_IDX] + SHADERS_DIR DIR_SEP;
-        paths[D_STATESAVES_IDX]     = paths[D_USER_IDX] + STATESAVES_DIR DIR_SEP;
-        paths[D_SCREENSHOTS_IDX]    = paths[D_USER_IDX] + SCREENSHOTS_DIR DIR_SEP;
-        paths[D_DUMP_IDX]           = paths[D_USER_IDX] + DUMP_DIR DIR_SEP;
-        paths[D_DUMPFRAMES_IDX]     = paths[D_DUMP_IDX] + DUMP_FRAMES_DIR DIR_SEP;
-        paths[D_DUMPAUDIO_IDX]      = paths[D_DUMP_IDX] + DUMP_AUDIO_DIR DIR_SEP;
-        paths[D_DUMPTEXTURES_IDX]   = paths[D_DUMP_IDX] + DUMP_TEXTURES_DIR DIR_SEP;
-        paths[D_LOGS_IDX]           = paths[D_USER_IDX] + LOGS_DIR DIR_SEP;
+        paths[D_GAMECONFIG_IDX] = paths[D_USER_IDX] + GAMECONFIG_DIR DIR_SEP;
+        paths[D_MAPS_IDX] = paths[D_USER_IDX] + MAPS_DIR DIR_SEP;
+        paths[D_SDMC_IDX] = paths[D_USER_IDX] + SDMC_DIR DIR_SEP;
+        paths[D_NAND_IDX] = paths[D_USER_IDX] + NAND_DIR DIR_SEP;
+        paths[D_SYSDATA_IDX] = paths[D_USER_IDX] + SYSDATA_DIR DIR_SEP;
+        paths[D_SHADERCACHE_IDX] = paths[D_USER_IDX] + SHADERCACHE_DIR DIR_SEP;
+        paths[D_SHADERS_IDX] = paths[D_USER_IDX] + SHADERS_DIR DIR_SEP;
+        paths[D_STATESAVES_IDX] = paths[D_USER_IDX] + STATESAVES_DIR DIR_SEP;
+        paths[D_SCREENSHOTS_IDX] = paths[D_USER_IDX] + SCREENSHOTS_DIR DIR_SEP;
+        paths[D_DUMP_IDX] = paths[D_USER_IDX] + DUMP_DIR DIR_SEP;
+        paths[D_DUMPFRAMES_IDX] = paths[D_DUMP_IDX] + DUMP_FRAMES_DIR DIR_SEP;
+        paths[D_DUMPAUDIO_IDX] = paths[D_DUMP_IDX] + DUMP_AUDIO_DIR DIR_SEP;
+        paths[D_DUMPTEXTURES_IDX] = paths[D_DUMP_IDX] + DUMP_TEXTURES_DIR DIR_SEP;
+        paths[D_LOGS_IDX] = paths[D_USER_IDX] + LOGS_DIR DIR_SEP;
         paths[F_DEBUGGERCONFIG_IDX] = paths[D_CONFIG_IDX] + DEBUGGER_CONFIG;
-        paths[F_LOGGERCONFIG_IDX]   = paths[D_CONFIG_IDX] + LOGGER_CONFIG;
-        paths[F_MAINLOG_IDX]        = paths[D_LOGS_IDX] + MAIN_LOG;
+        paths[F_LOGGERCONFIG_IDX] = paths[D_CONFIG_IDX] + LOGGER_CONFIG;
+        paths[F_MAINLOG_IDX] = paths[D_LOGS_IDX] + MAIN_LOG;
     }
 
-    if (!newPath.empty())
-    {
-        if (!FileUtil::IsDirectory(newPath))
-        {
+    if (!newPath.empty()) {
+        if (!FileUtil::IsDirectory(newPath)) {
             LOG_ERROR(Common_Filesystem, "Invalid path specified %s", newPath.c_str());
             return paths[DirIDX];
-        }
-        else
-        {
+        } else {
             paths[DirIDX] = newPath;
         }
 
-        switch (DirIDX)
-        {
+        switch (DirIDX) {
         case D_ROOT_IDX:
-            paths[D_USER_IDX]           = paths[D_ROOT_IDX] + DIR_SEP;
-            paths[D_SYSCONF_IDX]        = paths[D_USER_IDX] + SYSCONF_DIR + DIR_SEP;
-            paths[F_SYSCONF_IDX]        = paths[D_SYSCONF_IDX] + SYSCONF;
+            paths[D_USER_IDX] = paths[D_ROOT_IDX] + DIR_SEP;
+            paths[D_SYSCONF_IDX] = paths[D_USER_IDX] + SYSCONF_DIR + DIR_SEP;
+            paths[F_SYSCONF_IDX] = paths[D_SYSCONF_IDX] + SYSCONF;
             break;
 
         case D_USER_IDX:
-            paths[D_USER_IDX]           = paths[D_ROOT_IDX] + DIR_SEP;
-            paths[D_CONFIG_IDX]         = paths[D_USER_IDX] + CONFIG_DIR DIR_SEP;
-            paths[D_GAMECONFIG_IDX]     = paths[D_USER_IDX] + GAMECONFIG_DIR DIR_SEP;
-            paths[D_MAPS_IDX]           = paths[D_USER_IDX] + MAPS_DIR DIR_SEP;
-            paths[D_CACHE_IDX]          = paths[D_USER_IDX] + CACHE_DIR DIR_SEP;
-            paths[D_SDMC_IDX]           = paths[D_USER_IDX] + SDMC_DIR DIR_SEP;
-            paths[D_NAND_IDX]           = paths[D_USER_IDX] + NAND_DIR DIR_SEP;
-            paths[D_SHADERCACHE_IDX]    = paths[D_USER_IDX] + SHADERCACHE_DIR DIR_SEP;
-            paths[D_SHADERS_IDX]        = paths[D_USER_IDX] + SHADERS_DIR DIR_SEP;
-            paths[D_STATESAVES_IDX]     = paths[D_USER_IDX] + STATESAVES_DIR DIR_SEP;
-            paths[D_SCREENSHOTS_IDX]    = paths[D_USER_IDX] + SCREENSHOTS_DIR DIR_SEP;
-            paths[D_DUMP_IDX]           = paths[D_USER_IDX] + DUMP_DIR DIR_SEP;
-            paths[D_DUMPFRAMES_IDX]     = paths[D_DUMP_IDX] + DUMP_FRAMES_DIR DIR_SEP;
-            paths[D_DUMPAUDIO_IDX]      = paths[D_DUMP_IDX] + DUMP_AUDIO_DIR DIR_SEP;
-            paths[D_DUMPTEXTURES_IDX]   = paths[D_DUMP_IDX] + DUMP_TEXTURES_DIR DIR_SEP;
-            paths[D_LOGS_IDX]           = paths[D_USER_IDX] + LOGS_DIR DIR_SEP;
-            paths[D_SYSCONF_IDX]        = paths[D_USER_IDX] + SYSCONF_DIR DIR_SEP;
-            paths[F_EMUCONFIG_IDX]      = paths[D_CONFIG_IDX] + EMU_CONFIG;
+            paths[D_USER_IDX] = paths[D_ROOT_IDX] + DIR_SEP;
+            paths[D_CONFIG_IDX] = paths[D_USER_IDX] + CONFIG_DIR DIR_SEP;
+            paths[D_GAMECONFIG_IDX] = paths[D_USER_IDX] + GAMECONFIG_DIR DIR_SEP;
+            paths[D_MAPS_IDX] = paths[D_USER_IDX] + MAPS_DIR DIR_SEP;
+            paths[D_CACHE_IDX] = paths[D_USER_IDX] + CACHE_DIR DIR_SEP;
+            paths[D_SDMC_IDX] = paths[D_USER_IDX] + SDMC_DIR DIR_SEP;
+            paths[D_NAND_IDX] = paths[D_USER_IDX] + NAND_DIR DIR_SEP;
+            paths[D_SHADERCACHE_IDX] = paths[D_USER_IDX] + SHADERCACHE_DIR DIR_SEP;
+            paths[D_SHADERS_IDX] = paths[D_USER_IDX] + SHADERS_DIR DIR_SEP;
+            paths[D_STATESAVES_IDX] = paths[D_USER_IDX] + STATESAVES_DIR DIR_SEP;
+            paths[D_SCREENSHOTS_IDX] = paths[D_USER_IDX] + SCREENSHOTS_DIR DIR_SEP;
+            paths[D_DUMP_IDX] = paths[D_USER_IDX] + DUMP_DIR DIR_SEP;
+            paths[D_DUMPFRAMES_IDX] = paths[D_DUMP_IDX] + DUMP_FRAMES_DIR DIR_SEP;
+            paths[D_DUMPAUDIO_IDX] = paths[D_DUMP_IDX] + DUMP_AUDIO_DIR DIR_SEP;
+            paths[D_DUMPTEXTURES_IDX] = paths[D_DUMP_IDX] + DUMP_TEXTURES_DIR DIR_SEP;
+            paths[D_LOGS_IDX] = paths[D_USER_IDX] + LOGS_DIR DIR_SEP;
+            paths[D_SYSCONF_IDX] = paths[D_USER_IDX] + SYSCONF_DIR DIR_SEP;
+            paths[F_EMUCONFIG_IDX] = paths[D_CONFIG_IDX] + EMU_CONFIG;
             paths[F_DEBUGGERCONFIG_IDX] = paths[D_CONFIG_IDX] + DEBUGGER_CONFIG;
-            paths[F_LOGGERCONFIG_IDX]   = paths[D_CONFIG_IDX] + LOGGER_CONFIG;
-            paths[F_MAINLOG_IDX]        = paths[D_LOGS_IDX] + MAIN_LOG;
+            paths[F_LOGGERCONFIG_IDX] = paths[D_CONFIG_IDX] + LOGGER_CONFIG;
+            paths[F_MAINLOG_IDX] = paths[D_LOGS_IDX] + MAIN_LOG;
             break;
 
         case D_CONFIG_IDX:
-            paths[F_EMUCONFIG_IDX]      = paths[D_CONFIG_IDX] + EMU_CONFIG;
+            paths[F_EMUCONFIG_IDX] = paths[D_CONFIG_IDX] + EMU_CONFIG;
             paths[F_DEBUGGERCONFIG_IDX] = paths[D_CONFIG_IDX] + DEBUGGER_CONFIG;
-            paths[F_LOGGERCONFIG_IDX]   = paths[D_CONFIG_IDX] + LOGGER_CONFIG;
+            paths[F_LOGGERCONFIG_IDX] = paths[D_CONFIG_IDX] + LOGGER_CONFIG;
             break;
 
         case D_DUMP_IDX:
-            paths[D_DUMPFRAMES_IDX]     = paths[D_DUMP_IDX] + DUMP_FRAMES_DIR DIR_SEP;
-            paths[D_DUMPAUDIO_IDX]      = paths[D_DUMP_IDX] + DUMP_AUDIO_DIR DIR_SEP;
-            paths[D_DUMPTEXTURES_IDX]   = paths[D_DUMP_IDX] + DUMP_TEXTURES_DIR DIR_SEP;
+            paths[D_DUMPFRAMES_IDX] = paths[D_DUMP_IDX] + DUMP_FRAMES_DIR DIR_SEP;
+            paths[D_DUMPAUDIO_IDX] = paths[D_DUMP_IDX] + DUMP_AUDIO_DIR DIR_SEP;
+            paths[D_DUMPTEXTURES_IDX] = paths[D_DUMP_IDX] + DUMP_TEXTURES_DIR DIR_SEP;
             break;
 
         case D_LOGS_IDX:
-            paths[F_MAINLOG_IDX]        = paths[D_LOGS_IDX] + MAIN_LOG;
+            paths[F_MAINLOG_IDX] = paths[D_LOGS_IDX] + MAIN_LOG;
         }
     }
 
     return paths[DirIDX];
 }
 
-size_t WriteStringToFile(bool text_file, const std::string &str, const char *filename)
-{
+size_t WriteStringToFile(bool text_file, const std::string& str, const char* filename) {
     return FileUtil::IOFile(filename, text_file ? "w" : "wb").WriteBytes(str.data(), str.size());
 }
 
-size_t ReadFileToString(bool text_file, const char *filename, std::string &str)
-{
+size_t ReadFileToString(bool text_file, const char* filename, std::string& str) {
     IOFile file(filename, text_file ? "r" : "rb");
 
     if (!file)
@@ -886,42 +828,36 @@ void SplitFilename83(const std::string& filename, std::array<char, 9>& short_nam
     }
 }
 
-IOFile::IOFile()
-{
+IOFile::IOFile() {
 }
 
-IOFile::IOFile(const std::string& filename, const char openmode[])
-{
+IOFile::IOFile(const std::string& filename, const char openmode[]) {
     Open(filename, openmode);
 }
 
-IOFile::~IOFile()
-{
+IOFile::~IOFile() {
     Close();
 }
 
-IOFile::IOFile(IOFile&& other)
-{
+IOFile::IOFile(IOFile&& other) {
     Swap(other);
 }
 
-IOFile& IOFile::operator=(IOFile&& other)
-{
+IOFile& IOFile::operator=(IOFile&& other) {
     Swap(other);
     return *this;
 }
 
-void IOFile::Swap(IOFile& other)
-{
+void IOFile::Swap(IOFile& other) {
     std::swap(m_file, other.m_file);
     std::swap(m_good, other.m_good);
 }
 
-bool IOFile::Open(const std::string& filename, const char openmode[])
-{
+bool IOFile::Open(const std::string& filename, const char openmode[]) {
     Close();
 #ifdef _WIN32
-    _wfopen_s(&m_file, Common::UTF8ToUTF16W(filename).c_str(), Common::UTF8ToUTF16W(openmode).c_str());
+    _wfopen_s(&m_file, Common::UTF8ToUTF16W(filename).c_str(),
+              Common::UTF8ToUTF16W(openmode).c_str());
 #else
     m_file = fopen(filename.c_str(), openmode);
 #endif
@@ -930,8 +866,7 @@ bool IOFile::Open(const std::string& filename, const char openmode[])
     return m_good;
 }
 
-bool IOFile::Close()
-{
+bool IOFile::Close() {
     if (!IsOpen() || 0 != std::fclose(m_file))
         m_good = false;
 
@@ -939,50 +874,46 @@ bool IOFile::Close()
     return m_good;
 }
 
-u64 IOFile::GetSize() const
-{
+u64 IOFile::GetSize() const {
     if (IsOpen())
         return FileUtil::GetSize(m_file);
 
     return 0;
 }
 
-bool IOFile::Seek(s64 off, int origin)
-{
+bool IOFile::Seek(s64 off, int origin) {
     if (!IsOpen() || 0 != fseeko(m_file, off, origin))
         m_good = false;
 
     return m_good;
 }
 
-u64 IOFile::Tell() const
-{
+u64 IOFile::Tell() const {
     if (IsOpen())
         return ftello(m_file);
 
     return -1;
 }
 
-bool IOFile::Flush()
-{
+bool IOFile::Flush() {
     if (!IsOpen() || 0 != std::fflush(m_file))
         m_good = false;
 
     return m_good;
 }
 
-bool IOFile::Resize(u64 size)
-{
-    if (!IsOpen() || 0 !=
+bool IOFile::Resize(u64 size) {
+    if (!IsOpen() ||
+        0 !=
 #ifdef _WIN32
-        // ector: _chsize sucks, not 64-bit safe
-        // F|RES: changed to _chsize_s. i think it is 64-bit safe
-        _chsize_s(_fileno(m_file), size)
+            // ector: _chsize sucks, not 64-bit safe
+            // F|RES: changed to _chsize_s. i think it is 64-bit safe
+            _chsize_s(_fileno(m_file), size)
 #else
-        // TODO: handle 64bit and growing
-        ftruncate(fileno(m_file), size)
+            // TODO: handle 64bit and growing
+            ftruncate(fileno(m_file), size)
 #endif
-    )
+            )
         m_good = false;
 
     return m_good;
diff --git a/src/common/file_util.h b/src/common/file_util.h
index 7ad7ee829..b15021a63 100644
--- a/src/common/file_util.h
+++ b/src/common/file_util.h
@@ -5,9 +5,9 @@
 #pragma once
 
 #include <array>
+#include <cstdio>
 #include <fstream>
 #include <functional>
-#include <cstdio>
 #include <string>
 #include <type_traits>
 #include <vector>
@@ -51,75 +51,75 @@ enum {
     NUM_PATH_INDICES
 };
 
-namespace FileUtil
-{
+namespace FileUtil {
 
 // FileSystem tree node/
-struct FSTEntry
-{
+struct FSTEntry {
     bool isDirectory;
-    u64 size;                       // file length or number of entries from children
-    std::string physicalName;       // name on disk
-    std::string virtualName;        // name in FST names table
+    u64 size;                 // file length or number of entries from children
+    std::string physicalName; // name on disk
+    std::string virtualName;  // name in FST names table
     std::vector<FSTEntry> children;
 };
 
 // Returns true if file filename exists
-bool Exists(const std::string &filename);
+bool Exists(const std::string& filename);
 
 // Returns true if filename is a directory
-bool IsDirectory(const std::string &filename);
+bool IsDirectory(const std::string& filename);
 
 // Returns the size of filename (64bit)
-u64 GetSize(const std::string &filename);
+u64 GetSize(const std::string& filename);
 
 // Overloaded GetSize, accepts file descriptor
 u64 GetSize(const int fd);
 
 // Overloaded GetSize, accepts FILE*
-u64 GetSize(FILE *f);
+u64 GetSize(FILE* f);
 
 // Returns true if successful, or path already exists.
-bool CreateDir(const std::string &filename);
+bool CreateDir(const std::string& filename);
 
 // Creates the full path of fullPath returns true on success
-bool CreateFullPath(const std::string &fullPath);
+bool CreateFullPath(const std::string& fullPath);
 
 // Deletes a given filename, return true on success
 // Doesn't supports deleting a directory
-bool Delete(const std::string &filename);
+bool Delete(const std::string& filename);
 
 // Deletes a directory filename, returns true on success
-bool DeleteDir(const std::string &filename);
+bool DeleteDir(const std::string& filename);
 
 // renames file srcFilename to destFilename, returns true on success
-bool Rename(const std::string &srcFilename, const std::string &destFilename);
+bool Rename(const std::string& srcFilename, const std::string& destFilename);
 
 // copies file srcFilename to destFilename, returns true on success
-bool Copy(const std::string &srcFilename, const std::string &destFilename);
+bool Copy(const std::string& srcFilename, const std::string& destFilename);
 
 // creates an empty file filename, returns true on success
-bool CreateEmptyFile(const std::string &filename);
+bool CreateEmptyFile(const std::string& filename);
 
 /**
- * @param num_entries_out to be assigned by the callable with the number of iterated directory entries, never null
+ * @param num_entries_out to be assigned by the callable with the number of iterated directory
+ * entries, never null
  * @param directory the path to the enclosing directory
  * @param virtual_name the entry name, without any preceding directory info
  * @return whether handling the entry succeeded
  */
-using DirectoryEntryCallable = std::function<bool(unsigned* num_entries_out,
-                                                 const std::string& directory,
-                                                 const std::string& virtual_name)>;
+using DirectoryEntryCallable = std::function<bool(
+    unsigned* num_entries_out, const std::string& directory, const std::string& virtual_name)>;
 
 /**
  * Scans a directory, calling the callback for each file/directory contained within.
  * If the callback returns failure, scanning halts and this function returns failure as well
- * @param num_entries_out assigned by the function with the number of iterated directory entries, can be null
+ * @param num_entries_out assigned by the function with the number of iterated directory entries,
+ * can be null
  * @param directory the directory to scan
  * @param callback The callback which will be called for each entry
  * @return whether scanning the directory succeeded
  */
-bool ForeachDirectoryEntry(unsigned* num_entries_out, const std::string &directory, DirectoryEntryCallable callback);
+bool ForeachDirectoryEntry(unsigned* num_entries_out, const std::string& directory,
+                           DirectoryEntryCallable callback);
 
 /**
  * Scans the directory tree, storing the results.
@@ -128,23 +128,24 @@ bool ForeachDirectoryEntry(unsigned* num_entries_out, const std::string &directo
  * @param recursion Number of children directories to read before giving up.
  * @return the total number of files/directories found
  */
-unsigned ScanDirectoryTree(const std::string &directory, FSTEntry& parent_entry, unsigned int recursion = 0);
+unsigned ScanDirectoryTree(const std::string& directory, FSTEntry& parent_entry,
+                           unsigned int recursion = 0);
 
 // deletes the given directory and anything under it. Returns true on success.
-bool DeleteDirRecursively(const std::string &directory, unsigned int recursion = 256);
+bool DeleteDirRecursively(const std::string& directory, unsigned int recursion = 256);
 
 // Returns the current directory
 std::string GetCurrentDir();
 
 // Create directory and copy contents (does not overwrite existing files)
-void CopyDir(const std::string &source_path, const std::string &dest_path);
+void CopyDir(const std::string& source_path, const std::string& dest_path);
 
 // Set the current directory to given directory
-bool SetCurrentDir(const std::string &directory);
+bool SetCurrentDir(const std::string& directory);
 
 // Returns a pointer to a string with a Citra data dir in the user's home
 // directory. To be used in "multi-user" mode (that is, installed).
-const std::string& GetUserPath(const unsigned int DirIDX, const std::string &newPath="");
+const std::string& GetUserPath(const unsigned int DirIDX, const std::string& newPath = "");
 
 // Returns the path to where the sys file are
 std::string GetSysDirectory();
@@ -154,11 +155,11 @@ std::string GetBundleDirectory();
 #endif
 
 #ifdef _WIN32
-std::string &GetExeDirectory();
+std::string& GetExeDirectory();
 #endif
 
-size_t WriteStringToFile(bool text_file, const std::string &str, const char *filename);
-size_t ReadFileToString(bool text_file, const char *filename, std::string &str);
+size_t WriteStringToFile(bool text_file, const std::string& str, const char* filename);
+size_t ReadFileToString(bool text_file, const char* filename, std::string& str);
 
 /**
  * Splits the filename into 8.3 format
@@ -173,8 +174,7 @@ void SplitFilename83(const std::string& filename, std::array<char, 9>& short_nam
 // simple wrapper for cstdlib file functions to
 // hopefully will make error checking easier
 // and make forgetting an fclose() harder
-class IOFile : public NonCopyable
-{
+class IOFile : public NonCopyable {
 public:
     IOFile();
     IOFile(const std::string& filename, const char openmode[]);
@@ -190,11 +190,12 @@ public:
     bool Close();
 
     template <typename T>
-    size_t ReadArray(T* data, size_t length)
-    {
-        static_assert(std::is_standard_layout<T>(), "Given array does not consist of standard layout objects");
+    size_t ReadArray(T* data, size_t length) {
+        static_assert(std::is_standard_layout<T>(),
+                      "Given array does not consist of standard layout objects");
 #if (__GNUC__ >= 5) || defined(__clang__) || defined(_MSC_VER)
-        static_assert(std::is_trivially_copyable<T>(), "Given array does not consist of trivially copyable objects");
+        static_assert(std::is_trivially_copyable<T>(),
+                      "Given array does not consist of trivially copyable objects");
 #endif
 
         if (!IsOpen()) {
@@ -210,11 +211,12 @@ public:
     }
 
     template <typename T>
-    size_t WriteArray(const T* data, size_t length)
-    {
-        static_assert(std::is_standard_layout<T>(), "Given array does not consist of standard layout objects");
+    size_t WriteArray(const T* data, size_t length) {
+        static_assert(std::is_standard_layout<T>(),
+                      "Given array does not consist of standard layout objects");
 #if (__GNUC__ >= 5) || defined(__clang__) || defined(_MSC_VER)
-        static_assert(std::is_trivially_copyable<T>(), "Given array does not consist of trivially copyable objects");
+        static_assert(std::is_trivially_copyable<T>(),
+                      "Given array does not consist of trivially copyable objects");
 #endif
 
         if (!IsOpen()) {
@@ -229,27 +231,31 @@ public:
         return items_written;
     }
 
-    size_t ReadBytes(void* data, size_t length)
-    {
+    size_t ReadBytes(void* data, size_t length) {
         return ReadArray(reinterpret_cast<char*>(data), length);
     }
 
-    size_t WriteBytes(const void* data, size_t length)
-    {
+    size_t WriteBytes(const void* data, size_t length) {
         return WriteArray(reinterpret_cast<const char*>(data), length);
     }
 
-    template<typename T>
+    template <typename T>
     size_t WriteObject(const T& object) {
         static_assert(!std::is_pointer<T>::value, "Given object is a pointer");
         return WriteArray(&object, 1);
     }
 
-    bool IsOpen() const { return nullptr != m_file; }
+    bool IsOpen() const {
+        return nullptr != m_file;
+    }
 
     // m_good is set to false when a read, write or other function fails
-    bool IsGood() const { return m_good; }
-    explicit operator bool() const { return IsGood(); }
+    bool IsGood() const {
+        return m_good;
+    }
+    explicit operator bool() const {
+        return IsGood();
+    }
 
     bool Seek(s64 off, int origin);
     u64 Tell() const;
@@ -258,19 +264,21 @@ public:
     bool Flush();
 
     // clear error state
-    void Clear() { m_good = true; std::clearerr(m_file); }
+    void Clear() {
+        m_good = true;
+        std::clearerr(m_file);
+    }
 
 private:
     std::FILE* m_file = nullptr;
     bool m_good = true;
 };
 
-}  // namespace
+} // namespace
 
 // To deal with Windows being dumb at unicode:
 template <typename T>
-void OpenFStream(T& fstream, const std::string& filename, std::ios_base::openmode openmode)
-{
+void OpenFStream(T& fstream, const std::string& filename, std::ios_base::openmode openmode) {
 #ifdef _MSC_VER
     fstream.open(Common::UTF8ToTStr(filename).c_str(), openmode);
 #else
diff --git a/src/common/hash.cpp b/src/common/hash.cpp
index c49c2f60e..a46c92553 100644
--- a/src/common/hash.cpp
+++ b/src/common/hash.cpp
@@ -36,7 +36,7 @@ static FORCE_INLINE u64 fmix64(u64 k) {
 // platforms (MurmurHash3_x64_128). It was taken from:
 // https://code.google.com/p/smhasher/source/browse/trunk/MurmurHash3.cpp
 void MurmurHash3_128(const void* key, int len, u32 seed, void* out) {
-    const u8 * data = (const u8*)key;
+    const u8* data = (const u8*)key;
     const int nblocks = len / 16;
 
     u64 h1 = seed;
@@ -47,52 +47,84 @@ void MurmurHash3_128(const void* key, int len, u32 seed, void* out) {
 
     // Body
 
-    const u64 * blocks = (const u64 *)(data);
+    const u64* blocks = (const u64*)(data);
 
     for (int i = 0; i < nblocks; i++) {
-        u64 k1 = getblock64(blocks,i*2+0);
-        u64 k2 = getblock64(blocks,i*2+1);
-
-        k1 *= c1; k1  = _rotl64(k1,31); k1 *= c2; h1 ^= k1;
-
-        h1 = _rotl64(h1,27); h1 += h2; h1 = h1*5+0x52dce729;
-
-        k2 *= c2; k2  = _rotl64(k2,33); k2 *= c1; h2 ^= k2;
-
-        h2 = _rotl64(h2,31); h2 += h1; h2 = h2*5+0x38495ab5;
+        u64 k1 = getblock64(blocks, i * 2 + 0);
+        u64 k2 = getblock64(blocks, i * 2 + 1);
+
+        k1 *= c1;
+        k1 = _rotl64(k1, 31);
+        k1 *= c2;
+        h1 ^= k1;
+
+        h1 = _rotl64(h1, 27);
+        h1 += h2;
+        h1 = h1 * 5 + 0x52dce729;
+
+        k2 *= c2;
+        k2 = _rotl64(k2, 33);
+        k2 *= c1;
+        h2 ^= k2;
+
+        h2 = _rotl64(h2, 31);
+        h2 += h1;
+        h2 = h2 * 5 + 0x38495ab5;
     }
 
     // Tail
 
-    const u8 * tail = (const u8*)(data + nblocks*16);
+    const u8* tail = (const u8*)(data + nblocks * 16);
 
     u64 k1 = 0;
     u64 k2 = 0;
 
     switch (len & 15) {
-    case 15: k2 ^= ((u64)tail[14]) << 48;
-    case 14: k2 ^= ((u64)tail[13]) << 40;
-    case 13: k2 ^= ((u64)tail[12]) << 32;
-    case 12: k2 ^= ((u64)tail[11]) << 24;
-    case 11: k2 ^= ((u64)tail[10]) << 16;
-    case 10: k2 ^= ((u64)tail[ 9]) << 8;
-    case  9: k2 ^= ((u64)tail[ 8]) << 0;
-        k2 *= c2; k2  = _rotl64(k2,33); k2 *= c1; h2 ^= k2;
-
-    case  8: k1 ^= ((u64)tail[ 7]) << 56;
-    case  7: k1 ^= ((u64)tail[ 6]) << 48;
-    case  6: k1 ^= ((u64)tail[ 5]) << 40;
-    case  5: k1 ^= ((u64)tail[ 4]) << 32;
-    case  4: k1 ^= ((u64)tail[ 3]) << 24;
-    case  3: k1 ^= ((u64)tail[ 2]) << 16;
-    case  2: k1 ^= ((u64)tail[ 1]) << 8;
-    case  1: k1 ^= ((u64)tail[ 0]) << 0;
-        k1 *= c1; k1  = _rotl64(k1,31); k1 *= c2; h1 ^= k1;
+    case 15:
+        k2 ^= ((u64)tail[14]) << 48;
+    case 14:
+        k2 ^= ((u64)tail[13]) << 40;
+    case 13:
+        k2 ^= ((u64)tail[12]) << 32;
+    case 12:
+        k2 ^= ((u64)tail[11]) << 24;
+    case 11:
+        k2 ^= ((u64)tail[10]) << 16;
+    case 10:
+        k2 ^= ((u64)tail[9]) << 8;
+    case 9:
+        k2 ^= ((u64)tail[8]) << 0;
+        k2 *= c2;
+        k2 = _rotl64(k2, 33);
+        k2 *= c1;
+        h2 ^= k2;
+
+    case 8:
+        k1 ^= ((u64)tail[7]) << 56;
+    case 7:
+        k1 ^= ((u64)tail[6]) << 48;
+    case 6:
+        k1 ^= ((u64)tail[5]) << 40;
+    case 5:
+        k1 ^= ((u64)tail[4]) << 32;
+    case 4:
+        k1 ^= ((u64)tail[3]) << 24;
+    case 3:
+        k1 ^= ((u64)tail[2]) << 16;
+    case 2:
+        k1 ^= ((u64)tail[1]) << 8;
+    case 1:
+        k1 ^= ((u64)tail[0]) << 0;
+        k1 *= c1;
+        k1 = _rotl64(k1, 31);
+        k1 *= c2;
+        h1 ^= k1;
     };
 
     // Finalization
 
-    h1 ^= len; h2 ^= len;
+    h1 ^= len;
+    h2 ^= len;
 
     h1 += h2;
     h2 += h1;
diff --git a/src/common/key_map.cpp b/src/common/key_map.cpp
index ad311d66b..e882f5f52 100644
--- a/src/common/key_map.cpp
+++ b/src/common/key_map.cpp
@@ -13,11 +13,25 @@ namespace KeyMap {
 //     and map it directly to EmuWindow::ButtonPressed.
 //     It should go the analog input way like circle pad does.
 const std::array<KeyTarget, Settings::NativeInput::NUM_INPUTS> mapping_targets = {{
-    Service::HID::PAD_A, Service::HID::PAD_B, Service::HID::PAD_X, Service::HID::PAD_Y,
-    Service::HID::PAD_L, Service::HID::PAD_R, Service::HID::PAD_ZL, Service::HID::PAD_ZR,
-    Service::HID::PAD_START, Service::HID::PAD_SELECT, Service::HID::PAD_NONE,
-    Service::HID::PAD_UP, Service::HID::PAD_DOWN, Service::HID::PAD_LEFT, Service::HID::PAD_RIGHT,
-    Service::HID::PAD_C_UP, Service::HID::PAD_C_DOWN, Service::HID::PAD_C_LEFT, Service::HID::PAD_C_RIGHT,
+    Service::HID::PAD_A,
+    Service::HID::PAD_B,
+    Service::HID::PAD_X,
+    Service::HID::PAD_Y,
+    Service::HID::PAD_L,
+    Service::HID::PAD_R,
+    Service::HID::PAD_ZL,
+    Service::HID::PAD_ZR,
+    Service::HID::PAD_START,
+    Service::HID::PAD_SELECT,
+    Service::HID::PAD_NONE,
+    Service::HID::PAD_UP,
+    Service::HID::PAD_DOWN,
+    Service::HID::PAD_LEFT,
+    Service::HID::PAD_RIGHT,
+    Service::HID::PAD_C_UP,
+    Service::HID::PAD_C_DOWN,
+    Service::HID::PAD_C_LEFT,
+    Service::HID::PAD_C_RIGHT,
 
     IndirectTarget::CirclePadUp,
     IndirectTarget::CirclePadDown,
@@ -49,7 +63,8 @@ static void UpdateCirclePad(EmuWindow& emu_window) {
         --y;
 
     float modifier = circle_pad_modifier ? Settings::values.pad_circle_modifier_scale : 1.0;
-    emu_window.CirclePadUpdated(x * modifier * (y == 0 ? 1.0 : SQRT_HALF), y * modifier * (x == 0 ? 1.0 : SQRT_HALF));
+    emu_window.CirclePadUpdated(x * modifier * (y == 0 ? 1.0 : SQRT_HALF),
+                                y * modifier * (x == 0 ? 1.0 : SQRT_HALF));
 }
 
 int NewDeviceId() {
@@ -103,7 +118,7 @@ void PressKey(EmuWindow& emu_window, HostDeviceKey key) {
     }
 }
 
-void ReleaseKey(EmuWindow& emu_window,HostDeviceKey key) {
+void ReleaseKey(EmuWindow& emu_window, HostDeviceKey key) {
     auto target = key_map.find(key);
     if (target == key_map.end())
         return;
@@ -135,5 +150,4 @@ void ReleaseKey(EmuWindow& emu_window,HostDeviceKey key) {
         }
     }
 }
-
 }
diff --git a/src/common/key_map.h b/src/common/key_map.h
index b62f017c6..040794578 100644
--- a/src/common/key_map.h
+++ b/src/common/key_map.h
@@ -55,14 +55,12 @@ struct HostDeviceKey {
     int key_code;
     int device_id; ///< Uniquely identifies a host device
 
-    bool operator<(const HostDeviceKey &other) const {
-        return std::tie(key_code, device_id) <
-               std::tie(other.key_code, other.device_id);
+    bool operator<(const HostDeviceKey& other) const {
+        return std::tie(key_code, device_id) < std::tie(other.key_code, other.device_id);
     }
 
-    bool operator==(const HostDeviceKey &other) const {
-        return std::tie(key_code, device_id) ==
-               std::tie(other.key_code, other.device_id);
+    bool operator==(const HostDeviceKey& other) const {
+        return std::tie(key_code, device_id) == std::tie(other.key_code, other.device_id);
     }
 };
 
@@ -92,5 +90,4 @@ void PressKey(EmuWindow& emu_window, HostDeviceKey key);
  * Maps a key release action and call the corresponding function in EmuWindow
  */
 void ReleaseKey(EmuWindow& emu_window, HostDeviceKey key);
-
 }
diff --git a/src/common/linear_disk_cache.h b/src/common/linear_disk_cache.h
index 48529cf42..94c695163 100644
--- a/src/common/linear_disk_cache.h
+++ b/src/common/linear_disk_cache.h
@@ -4,31 +4,30 @@
 
 #pragma once
 
-#include "common/common_types.h"
 #include <fstream>
+#include "common/common_types.h"
 
 // defined in Version.cpp
-extern const char *scm_rev_git_str;
+extern const char* scm_rev_git_str;
 
 // On disk format:
-//header{
+// header{
 // u32 'DCAC';
 // u32 version;  // svn_rev
 // u16 sizeof(key_type);
 // u16 sizeof(value_type);
 //}
 
-//key_value_pair{
+// key_value_pair{
 // u32 value_size;
 // key_type   key;
 // value_type[value_size]   value;
 //}
 
 template <typename K, typename V>
-class LinearDiskCacheReader
-{
+class LinearDiskCacheReader {
 public:
-    virtual void Read(const K &key, const V *value, u32 value_size) = 0;
+    virtual void Read(const K& key, const V* value, u32 value_size) = 0;
 };
 
 // Dead simple unsorted key-value store with append functionality.
@@ -44,12 +43,10 @@ public:
 // K : the key type
 // V : value array type
 template <typename K, typename V>
-class LinearDiskCache
-{
+class LinearDiskCache {
 public:
     // return number of read entries
-    u32 OpenAndRead(const char *filename, LinearDiskCacheReader<K, V> &reader)
-    {
+    u32 OpenAndRead(const char* filename, LinearDiskCacheReader<K, V>& reader) {
         using std::ios_base;
 
         // close any currently opened file
@@ -65,20 +62,19 @@ public:
         std::fstream::pos_type start_pos = m_file.tellg();
         std::streamoff file_size = end_pos - start_pos;
 
-        if (m_file.is_open() && ValidateHeader())
-        {
+        if (m_file.is_open() && ValidateHeader()) {
             // good header, read some key/value pairs
             K key;
 
-            V *value = nullptr;
+            V* value = nullptr;
             u32 value_size;
             u32 entry_number;
 
             std::fstream::pos_type last_pos = m_file.tellg();
 
-            while (Read(&value_size))
-            {
-                std::streamoff next_extent = (last_pos - start_pos) + sizeof(value_size) + value_size;
+            while (Read(&value_size)) {
+                std::streamoff next_extent =
+                    (last_pos - start_pos) + sizeof(value_size) + value_size;
                 if (next_extent > file_size)
                     break;
 
@@ -86,15 +82,10 @@ public:
                 value = new V[value_size];
 
                 // read key/value and pass to reader
-                if (Read(&key) &&
-                    Read(value, value_size) &&
-                    Read(&entry_number) &&
-                    entry_number == m_num_entries+1)
-                 {
+                if (Read(&key) && Read(value, value_size) && Read(&entry_number) &&
+                    entry_number == m_num_entries + 1) {
                     reader.Read(key, value, value_size);
-                }
-                else
-                {
+                } else {
                     break;
                 }
 
@@ -116,13 +107,11 @@ public:
         return 0;
     }
 
-    void Sync()
-    {
+    void Sync() {
         m_file.flush();
     }
 
-    void Close()
-    {
+    void Close() {
         if (m_file.is_open())
             m_file.close();
         // clear any error flags
@@ -130,9 +119,9 @@ public:
     }
 
     // Appends a key-value pair to the store.
-    void Append(const K &key, const V *value, u32 value_size)
-    {
-        // TODO: Should do a check that we don't already have "key"? (I think each caller does that already.)
+    void Append(const K& key, const V* value, u32 value_size) {
+        // TODO: Should do a check that we don't already have "key"? (I think each caller does that
+        // already.)
         Write(&value_size);
         Write(&key);
         Write(value, value_size);
@@ -141,38 +130,29 @@ public:
     }
 
 private:
-    void WriteHeader()
-    {
+    void WriteHeader() {
         Write(&m_header);
     }
 
-    bool ValidateHeader()
-    {
+    bool ValidateHeader() {
         char file_header[sizeof(Header)];
 
-        return (Read(file_header, sizeof(Header))
-            && !memcmp((const char*)&m_header, file_header, sizeof(Header)));
+        return (Read(file_header, sizeof(Header)) &&
+                !memcmp((const char*)&m_header, file_header, sizeof(Header)));
     }
 
     template <typename D>
-    bool Write(const D *data, u32 count = 1)
-    {
+    bool Write(const D* data, u32 count = 1) {
         return m_file.write((const char*)data, count * sizeof(D)).good();
     }
 
     template <typename D>
-    bool Read(const D *data, u32 count = 1)
-    {
+    bool Read(const D* data, u32 count = 1) {
         return m_file.read((char*)data, count * sizeof(D)).good();
     }
 
-    struct Header
-    {
-        Header()
-            : id(*(u32*)"DCAC")
-            , key_t_size(sizeof(K))
-            , value_t_size(sizeof(V))
-        {
+    struct Header {
+        Header() : id(*(u32*)"DCAC"), key_t_size(sizeof(K)), value_t_size(sizeof(V)) {
             memcpy(ver, scm_rev_git_str, 40);
         }
 
diff --git a/src/common/logging/backend.cpp b/src/common/logging/backend.cpp
index 0b2fabec9..b3d6598e4 100644
--- a/src/common/logging/backend.cpp
+++ b/src/common/logging/backend.cpp
@@ -16,73 +16,79 @@
 namespace Log {
 
 /// Macro listing all log classes. Code should define CLS and SUB as desired before invoking this.
-#define ALL_LOG_CLASSES() \
-        CLS(Log) \
-        CLS(Common) \
-        SUB(Common, Filesystem) \
-        SUB(Common, Memory) \
-        CLS(Core) \
-        SUB(Core, ARM11) \
-        SUB(Core, Timing) \
-        CLS(Config) \
-        CLS(Debug) \
-        SUB(Debug, Emulated) \
-        SUB(Debug, GPU) \
-        SUB(Debug, Breakpoint) \
-        SUB(Debug, GDBStub) \
-        CLS(Kernel) \
-        SUB(Kernel, SVC) \
-        CLS(Service) \
-        SUB(Service, SRV) \
-        SUB(Service, FRD) \
-        SUB(Service, FS) \
-        SUB(Service, ERR) \
-        SUB(Service, APT) \
-        SUB(Service, GSP) \
-        SUB(Service, AC) \
-        SUB(Service, AM) \
-        SUB(Service, PTM) \
-        SUB(Service, LDR) \
-        SUB(Service, NDM) \
-        SUB(Service, NIM) \
-        SUB(Service, NWM) \
-        SUB(Service, CAM) \
-        SUB(Service, CECD) \
-        SUB(Service, CFG) \
-        SUB(Service, DSP) \
-        SUB(Service, DLP) \
-        SUB(Service, HID) \
-        SUB(Service, SOC) \
-        SUB(Service, IR) \
-        SUB(Service, Y2R) \
-        CLS(HW) \
-        SUB(HW, Memory) \
-        SUB(HW, LCD) \
-        SUB(HW, GPU) \
-        CLS(Frontend) \
-        CLS(Render) \
-        SUB(Render, Software) \
-        SUB(Render, OpenGL) \
-        CLS(Audio) \
-        SUB(Audio, DSP) \
-        SUB(Audio, Sink) \
-        CLS(Loader)
+#define ALL_LOG_CLASSES()                                                                          \
+    CLS(Log)                                                                                       \
+    CLS(Common)                                                                                    \
+    SUB(Common, Filesystem)                                                                        \
+    SUB(Common, Memory)                                                                            \
+    CLS(Core)                                                                                      \
+    SUB(Core, ARM11)                                                                               \
+    SUB(Core, Timing)                                                                              \
+    CLS(Config)                                                                                    \
+    CLS(Debug)                                                                                     \
+    SUB(Debug, Emulated)                                                                           \
+    SUB(Debug, GPU)                                                                                \
+    SUB(Debug, Breakpoint)                                                                         \
+    SUB(Debug, GDBStub)                                                                            \
+    CLS(Kernel)                                                                                    \
+    SUB(Kernel, SVC)                                                                               \
+    CLS(Service)                                                                                   \
+    SUB(Service, SRV)                                                                              \
+    SUB(Service, FRD)                                                                              \
+    SUB(Service, FS)                                                                               \
+    SUB(Service, ERR)                                                                              \
+    SUB(Service, APT)                                                                              \
+    SUB(Service, GSP)                                                                              \
+    SUB(Service, AC)                                                                               \
+    SUB(Service, AM)                                                                               \
+    SUB(Service, PTM)                                                                              \
+    SUB(Service, LDR)                                                                              \
+    SUB(Service, NDM)                                                                              \
+    SUB(Service, NIM)                                                                              \
+    SUB(Service, NWM)                                                                              \
+    SUB(Service, CAM)                                                                              \
+    SUB(Service, CECD)                                                                             \
+    SUB(Service, CFG)                                                                              \
+    SUB(Service, DSP)                                                                              \
+    SUB(Service, DLP)                                                                              \
+    SUB(Service, HID)                                                                              \
+    SUB(Service, SOC)                                                                              \
+    SUB(Service, IR)                                                                               \
+    SUB(Service, Y2R)                                                                              \
+    CLS(HW)                                                                                        \
+    SUB(HW, Memory)                                                                                \
+    SUB(HW, LCD)                                                                                   \
+    SUB(HW, GPU)                                                                                   \
+    CLS(Frontend)                                                                                  \
+    CLS(Render)                                                                                    \
+    SUB(Render, Software)                                                                          \
+    SUB(Render, OpenGL)                                                                            \
+    CLS(Audio)                                                                                     \
+    SUB(Audio, DSP)                                                                                \
+    SUB(Audio, Sink)                                                                               \
+    CLS(Loader)
 
 // GetClassName is a macro defined by Windows.h, grrr...
 const char* GetLogClassName(Class log_class) {
     switch (log_class) {
-#define CLS(x) case Class::x: return #x;
-#define SUB(x, y) case Class::x##_##y: return #x "." #y;
+#define CLS(x)                                                                                     \
+    case Class::x:                                                                                 \
+        return #x;
+#define SUB(x, y)                                                                                  \
+    case Class::x##_##y:                                                                           \
+        return #x "." #y;
         ALL_LOG_CLASSES()
 #undef CLS
 #undef SUB
-        case Class::Count:
-            UNREACHABLE();
+    case Class::Count:
+        UNREACHABLE();
     }
 }
 
 const char* GetLevelName(Level log_level) {
-#define LVL(x) case Level::x: return #x
+#define LVL(x)                                                                                     \
+    case Level::x:                                                                                 \
+        return #x
     switch (log_level) {
         LVL(Trace);
         LVL(Debug);
@@ -90,15 +96,14 @@ const char* GetLevelName(Level log_level) {
         LVL(Warning);
         LVL(Error);
         LVL(Critical);
-        case Level::Count:
-            UNREACHABLE();
+    case Level::Count:
+        UNREACHABLE();
     }
 #undef LVL
 }
 
-Entry CreateEntry(Class log_class, Level log_level,
-                        const char* filename, unsigned int line_nr, const char* function,
-                        const char* format, va_list args) {
+Entry CreateEntry(Class log_class, Level log_level, const char* filename, unsigned int line_nr,
+                  const char* function, const char* format, va_list args) {
     using std::chrono::steady_clock;
     using std::chrono::duration_cast;
 
@@ -111,7 +116,8 @@ Entry CreateEntry(Class log_class, Level log_level,
     entry.log_class = log_class;
     entry.log_level = log_level;
 
-    snprintf(formatting_buffer.data(), formatting_buffer.size(), "%s:%s:%u", filename, function, line_nr);
+    snprintf(formatting_buffer.data(), formatting_buffer.size(), "%s:%s:%u", filename, function,
+             line_nr);
     entry.location = std::string(formatting_buffer.data());
 
     vsnprintf(formatting_buffer.data(), formatting_buffer.size(), format, args);
@@ -126,19 +132,16 @@ void SetFilter(Filter* new_filter) {
     filter = new_filter;
 }
 
-void LogMessage(Class log_class, Level log_level,
-                const char* filename, unsigned int line_nr, const char* function,
-                const char* format, ...) {
+void LogMessage(Class log_class, Level log_level, const char* filename, unsigned int line_nr,
+                const char* function, const char* format, ...) {
     if (filter != nullptr && !filter->CheckMessage(log_class, log_level))
         return;
 
     va_list args;
     va_start(args, format);
-    Entry entry = CreateEntry(log_class, log_level,
-            filename, line_nr, function, format, args);
+    Entry entry = CreateEntry(log_class, log_level, filename, line_nr, function, format, args);
     va_end(args);
 
     PrintColoredMessage(entry);
 }
-
 }
diff --git a/src/common/logging/backend.h b/src/common/logging/backend.h
index 795d42ebd..3fe88e4f6 100644
--- a/src/common/logging/backend.h
+++ b/src/common/logging/backend.h
@@ -44,10 +44,8 @@ const char* GetLogClassName(Class log_class);
 const char* GetLevelName(Level log_level);
 
 /// Creates a log entry by formatting the given source location, and message.
-Entry CreateEntry(Class log_class, Level log_level,
-                        const char* filename, unsigned int line_nr, const char* function,
-                        const char* format, va_list args);
+Entry CreateEntry(Class log_class, Level log_level, const char* filename, unsigned int line_nr,
+                  const char* function, const char* format, va_list args);
 
 void SetFilter(Filter* filter);
-
 }
diff --git a/src/common/logging/filter.cpp b/src/common/logging/filter.cpp
index 55cc8888a..186e0b621 100644
--- a/src/common/logging/filter.cpp
+++ b/src/common/logging/filter.cpp
@@ -4,8 +4,8 @@
 
 #include <algorithm>
 
-#include "common/logging/filter.h"
 #include "common/logging/backend.h"
+#include "common/logging/filter.h"
 #include "common/string_util.h"
 
 namespace Log {
@@ -63,11 +63,11 @@ static Class GetClassByName(const It begin, const It end) {
 }
 
 bool Filter::ParseFilterRule(const std::string::const_iterator begin,
-        const std::string::const_iterator end) {
+                             const std::string::const_iterator end) {
     auto level_separator = std::find(begin, end, ':');
     if (level_separator == end) {
         LOG_ERROR(Log, "Invalid log filter. Must specify a log level after `:`: %s",
-                std::string(begin, end).c_str());
+                  std::string(begin, end).c_str());
         return false;
     }
 
@@ -95,5 +95,4 @@ bool Filter::ParseFilterRule(const std::string::const_iterator begin,
 bool Filter::CheckMessage(Class log_class, Level level) const {
     return static_cast<u8>(level) >= static_cast<u8>(class_levels[static_cast<size_t>(log_class)]);
 }
-
 }
diff --git a/src/common/logging/filter.h b/src/common/logging/filter.h
index a2b4eca43..db526fead 100644
--- a/src/common/logging/filter.h
+++ b/src/common/logging/filter.h
@@ -42,7 +42,8 @@ public:
      *  - `Service.FS:Trace` -- Sets the level of the Service.FS class to Trace.
      */
     void ParseFilterString(const std::string& filter_str);
-    bool ParseFilterRule(const std::string::const_iterator start, const std::string::const_iterator end);
+    bool ParseFilterRule(const std::string::const_iterator start,
+                         const std::string::const_iterator end);
 
     /// Matches class/level combination against the filter, returning true if it passed.
     bool CheckMessage(Class log_class, Level level) const;
@@ -50,5 +51,4 @@ public:
 private:
     std::array<Level, (size_t)Class::Count> class_levels;
 };
-
 }
diff --git a/src/common/logging/log.h b/src/common/logging/log.h
index c6910b1c7..a4b4750de 100644
--- a/src/common/logging/log.h
+++ b/src/common/logging/log.h
@@ -28,71 +28,73 @@ typedef u8 ClassType;
 /**
  * Specifies the sub-system that generated the log message.
  *
- * @note If you add a new entry here, also add a corresponding one to `ALL_LOG_CLASSES` in backend.cpp.
+ * @note If you add a new entry here, also add a corresponding one to `ALL_LOG_CLASSES` in
+ * backend.cpp.
  */
 enum class Class : ClassType {
-    Log,                        ///< Messages about the log system itself
-    Common,                     ///< Library routines
-    Common_Filesystem,          ///< Filesystem interface library
-    Common_Memory,              ///< Memory mapping and management functions
-    Core,                       ///< LLE emulation core
-    Core_ARM11,                 ///< ARM11 CPU core
-    Core_Timing,                ///< CoreTiming functions
-    Config,                     ///< Emulator configuration (including commandline)
-    Debug,                      ///< Debugging tools
-    Debug_Emulated,             ///< Debug messages from the emulated programs
-    Debug_GPU,                  ///< GPU debugging tools
-    Debug_Breakpoint,           ///< Logging breakpoints and watchpoints
-    Debug_GDBStub,              ///< GDB Stub
-    Kernel,                     ///< The HLE implementation of the CTR kernel
-    Kernel_SVC,                 ///< Kernel system calls
-    Service,                    ///< HLE implementation of system services. Each major service
-                                ///  should have its own subclass.
-    Service_SRV,                ///< The SRV (Service Directory) implementation
-    Service_FRD,                ///< The FRD (Friends) service
-    Service_FS,                 ///< The FS (Filesystem) service implementation
-    Service_ERR,                ///< The ERR (Error) port implementation
-    Service_APT,                ///< The APT (Applets) service
-    Service_GSP,                ///< The GSP (GPU control) service
-    Service_AC,                 ///< The AC (WiFi status) service
-    Service_AM,                 ///< The AM (Application manager) service
-    Service_PTM,                ///< The PTM (Power status & misc.) service
-    Service_LDR,                ///< The LDR (3ds dll loader) service
-    Service_NDM,                ///< The NDM (Network daemon manager) service
-    Service_NIM,                ///< The NIM (Network interface manager) service
-    Service_NWM,                ///< The NWM (Network wlan manager) service
-    Service_CAM,                ///< The CAM (Camera) service
-    Service_CECD,               ///< The CECD (StreetPass) service
-    Service_CFG,                ///< The CFG (Configuration) service
-    Service_DSP,                ///< The DSP (DSP control) service
-    Service_DLP,                ///< The DLP (Download Play) service
-    Service_HID,                ///< The HID (Human interface device) service
-    Service_SOC,                ///< The SOC (Socket) service
-    Service_IR,                 ///< The IR service
-    Service_Y2R,                ///< The Y2R (YUV to RGB conversion) service
-    HW,                         ///< Low-level hardware emulation
-    HW_Memory,                  ///< Memory-map and address translation
-    HW_LCD,                     ///< LCD register emulation
-    HW_GPU,                     ///< GPU control emulation
-    Frontend,                   ///< Emulator UI
-    Render,                     ///< Emulator video output and hardware acceleration
-    Render_Software,            ///< Software renderer backend
-    Render_OpenGL,              ///< OpenGL backend
-    Audio,                      ///< Audio emulation
-    Audio_DSP,                  ///< The HLE implementation of the DSP
-    Audio_Sink,                 ///< Emulator audio output backend
-    Loader,                     ///< ROM loader
+    Log,               ///< Messages about the log system itself
+    Common,            ///< Library routines
+    Common_Filesystem, ///< Filesystem interface library
+    Common_Memory,     ///< Memory mapping and management functions
+    Core,              ///< LLE emulation core
+    Core_ARM11,        ///< ARM11 CPU core
+    Core_Timing,       ///< CoreTiming functions
+    Config,            ///< Emulator configuration (including commandline)
+    Debug,             ///< Debugging tools
+    Debug_Emulated,    ///< Debug messages from the emulated programs
+    Debug_GPU,         ///< GPU debugging tools
+    Debug_Breakpoint,  ///< Logging breakpoints and watchpoints
+    Debug_GDBStub,     ///< GDB Stub
+    Kernel,            ///< The HLE implementation of the CTR kernel
+    Kernel_SVC,        ///< Kernel system calls
+    Service,           ///< HLE implementation of system services. Each major service
+                       ///  should have its own subclass.
+    Service_SRV,       ///< The SRV (Service Directory) implementation
+    Service_FRD,       ///< The FRD (Friends) service
+    Service_FS,        ///< The FS (Filesystem) service implementation
+    Service_ERR,       ///< The ERR (Error) port implementation
+    Service_APT,       ///< The APT (Applets) service
+    Service_GSP,       ///< The GSP (GPU control) service
+    Service_AC,        ///< The AC (WiFi status) service
+    Service_AM,        ///< The AM (Application manager) service
+    Service_PTM,       ///< The PTM (Power status & misc.) service
+    Service_LDR,       ///< The LDR (3ds dll loader) service
+    Service_NDM,       ///< The NDM (Network daemon manager) service
+    Service_NIM,       ///< The NIM (Network interface manager) service
+    Service_NWM,       ///< The NWM (Network wlan manager) service
+    Service_CAM,       ///< The CAM (Camera) service
+    Service_CECD,      ///< The CECD (StreetPass) service
+    Service_CFG,       ///< The CFG (Configuration) service
+    Service_DSP,       ///< The DSP (DSP control) service
+    Service_DLP,       ///< The DLP (Download Play) service
+    Service_HID,       ///< The HID (Human interface device) service
+    Service_SOC,       ///< The SOC (Socket) service
+    Service_IR,        ///< The IR service
+    Service_Y2R,       ///< The Y2R (YUV to RGB conversion) service
+    HW,                ///< Low-level hardware emulation
+    HW_Memory,         ///< Memory-map and address translation
+    HW_LCD,            ///< LCD register emulation
+    HW_GPU,            ///< GPU control emulation
+    Frontend,          ///< Emulator UI
+    Render,            ///< Emulator video output and hardware acceleration
+    Render_Software,   ///< Software renderer backend
+    Render_OpenGL,     ///< OpenGL backend
+    Audio,             ///< Audio emulation
+    Audio_DSP,         ///< The HLE implementation of the DSP
+    Audio_Sink,        ///< Emulator audio output backend
+    Loader,            ///< ROM loader
 
     Count ///< Total number of logging classes
 };
 
 /// Logs a message to the global logger.
-void LogMessage(Class log_class, Level log_level,
-    const char* filename, unsigned int line_nr, const char* function,
+void LogMessage(Class log_class, Level log_level, const char* filename, unsigned int line_nr,
+                const char* function,
 #ifdef _MSC_VER
-    _Printf_format_string_
+                _Printf_format_string_
 #endif
-    const char* format, ...)
+                const char* format,
+                ...)
 #ifdef __GNUC__
     __attribute__((format(printf, 6, 7)))
 #endif
@@ -100,17 +102,23 @@ void LogMessage(Class log_class, Level log_level,
 
 } // namespace Log
 
-#define LOG_GENERIC(log_class, log_level, ...) \
+#define LOG_GENERIC(log_class, log_level, ...)                                                     \
     ::Log::LogMessage(log_class, log_level, __FILE__, __LINE__, __func__, __VA_ARGS__)
 
 #ifdef _DEBUG
-#define LOG_TRACE(   log_class, ...) LOG_GENERIC(::Log::Class::log_class, ::Log::Level::Trace,    __VA_ARGS__)
+#define LOG_TRACE(log_class, ...)                                                                  \
+    LOG_GENERIC(::Log::Class::log_class, ::Log::Level::Trace, __VA_ARGS__)
 #else
-#define LOG_TRACE(   log_class, ...) (void(0))
+#define LOG_TRACE(log_class, ...) (void(0))
 #endif
 
-#define LOG_DEBUG(   log_class, ...) LOG_GENERIC(::Log::Class::log_class, ::Log::Level::Debug,    __VA_ARGS__)
-#define LOG_INFO(    log_class, ...) LOG_GENERIC(::Log::Class::log_class, ::Log::Level::Info,     __VA_ARGS__)
-#define LOG_WARNING( log_class, ...) LOG_GENERIC(::Log::Class::log_class, ::Log::Level::Warning,  __VA_ARGS__)
-#define LOG_ERROR(   log_class, ...) LOG_GENERIC(::Log::Class::log_class, ::Log::Level::Error,    __VA_ARGS__)
-#define LOG_CRITICAL(log_class, ...) LOG_GENERIC(::Log::Class::log_class, ::Log::Level::Critical, __VA_ARGS__)
+#define LOG_DEBUG(log_class, ...)                                                                  \
+    LOG_GENERIC(::Log::Class::log_class, ::Log::Level::Debug, __VA_ARGS__)
+#define LOG_INFO(log_class, ...)                                                                   \
+    LOG_GENERIC(::Log::Class::log_class, ::Log::Level::Info, __VA_ARGS__)
+#define LOG_WARNING(log_class, ...)                                                                \
+    LOG_GENERIC(::Log::Class::log_class, ::Log::Level::Warning, __VA_ARGS__)
+#define LOG_ERROR(log_class, ...)                                                                  \
+    LOG_GENERIC(::Log::Class::log_class, ::Log::Level::Error, __VA_ARGS__)
+#define LOG_CRITICAL(log_class, ...)                                                               \
+    LOG_GENERIC(::Log::Class::log_class, ::Log::Level::Critical, __VA_ARGS__)
diff --git a/src/common/logging/text_formatter.cpp b/src/common/logging/text_formatter.cpp
index de195b0f7..955358553 100644
--- a/src/common/logging/text_formatter.cpp
+++ b/src/common/logging/text_formatter.cpp
@@ -6,8 +6,8 @@
 #include <cstdio>
 
 #ifdef _WIN32
-#   define WIN32_LEAN_AND_MEAN
-#   include <Windows.h>
+#define WIN32_LEAN_AND_MEAN
+#include <Windows.h>
 #endif
 
 #include "common/logging/backend.h"
@@ -44,15 +44,14 @@ const char* TrimSourcePath(const char* path, const char* root) {
 }
 
 void FormatLogMessage(const Entry& entry, char* out_text, size_t text_len) {
-    unsigned int time_seconds    = static_cast<unsigned int>(entry.timestamp.count() / 1000000);
+    unsigned int time_seconds = static_cast<unsigned int>(entry.timestamp.count() / 1000000);
     unsigned int time_fractional = static_cast<unsigned int>(entry.timestamp.count() % 1000000);
 
     const char* class_name = GetLogClassName(entry.log_class);
     const char* level_name = GetLevelName(entry.log_level);
 
-    snprintf(out_text, text_len, "[%4u.%06u] %s <%s> %s: %s",
-        time_seconds, time_fractional, class_name, level_name,
-        TrimSourcePath(entry.location.c_str()), entry.message.c_str());
+    snprintf(out_text, text_len, "[%4u.%06u] %s <%s> %s: %s", time_seconds, time_fractional,
+             class_name, level_name, TrimSourcePath(entry.location.c_str()), entry.message.c_str());
 }
 
 void PrintMessage(const Entry& entry) {
@@ -72,38 +71,50 @@ void PrintColoredMessage(const Entry& entry) {
     WORD color = 0;
     switch (entry.log_level) {
     case Level::Trace: // Grey
-        color = FOREGROUND_INTENSITY; break;
+        color = FOREGROUND_INTENSITY;
+        break;
     case Level::Debug: // Cyan
-        color = FOREGROUND_GREEN | FOREGROUND_BLUE; break;
+        color = FOREGROUND_GREEN | FOREGROUND_BLUE;
+        break;
     case Level::Info: // Bright gray
-        color = FOREGROUND_RED | FOREGROUND_GREEN | FOREGROUND_BLUE; break;
+        color = FOREGROUND_RED | FOREGROUND_GREEN | FOREGROUND_BLUE;
+        break;
     case Level::Warning: // Bright yellow
-        color = FOREGROUND_RED | FOREGROUND_GREEN | FOREGROUND_INTENSITY; break;
+        color = FOREGROUND_RED | FOREGROUND_GREEN | FOREGROUND_INTENSITY;
+        break;
     case Level::Error: // Bright red
-        color = FOREGROUND_RED | FOREGROUND_INTENSITY; break;
+        color = FOREGROUND_RED | FOREGROUND_INTENSITY;
+        break;
     case Level::Critical: // Bright magenta
-        color = FOREGROUND_RED | FOREGROUND_BLUE | FOREGROUND_INTENSITY; break;
+        color = FOREGROUND_RED | FOREGROUND_BLUE | FOREGROUND_INTENSITY;
+        break;
     case Level::Count:
         UNREACHABLE();
     }
 
     SetConsoleTextAttribute(console_handle, color);
 #else
-#   define ESC "\x1b"
+#define ESC "\x1b"
     const char* color = "";
     switch (entry.log_level) {
     case Level::Trace: // Grey
-        color = ESC "[1;30m"; break;
+        color = ESC "[1;30m";
+        break;
     case Level::Debug: // Cyan
-        color = ESC "[0;36m"; break;
+        color = ESC "[0;36m";
+        break;
     case Level::Info: // Bright gray
-        color = ESC "[0;37m"; break;
+        color = ESC "[0;37m";
+        break;
     case Level::Warning: // Bright yellow
-        color = ESC "[1;33m"; break;
+        color = ESC "[1;33m";
+        break;
     case Level::Error: // Bright red
-        color = ESC "[1;31m"; break;
+        color = ESC "[1;31m";
+        break;
     case Level::Critical: // Bright magenta
-        color = ESC "[1;35m"; break;
+        color = ESC "[1;35m";
+        break;
     case Level::Count:
         UNREACHABLE();
     }
@@ -117,8 +128,7 @@ void PrintColoredMessage(const Entry& entry) {
     SetConsoleTextAttribute(console_handle, original_info.wAttributes);
 #else
     fputs(ESC "[0m", stderr);
-#   undef ESC
+#undef ESC
 #endif
 }
-
 }
diff --git a/src/common/logging/text_formatter.h b/src/common/logging/text_formatter.h
index 5b82f043f..0da102bc6 100644
--- a/src/common/logging/text_formatter.h
+++ b/src/common/logging/text_formatter.h
@@ -28,5 +28,4 @@ void FormatLogMessage(const Entry& entry, char* out_text, size_t text_len);
 void PrintMessage(const Entry& entry);
 /// Prints the same message as `PrintMessage`, but colored acoording to the severity level.
 void PrintColoredMessage(const Entry& entry);
-
 }
diff --git a/src/common/math_util.h b/src/common/math_util.h
index d44b06e74..696bd43ea 100644
--- a/src/common/math_util.h
+++ b/src/common/math_util.h
@@ -8,33 +8,38 @@
 #include <cstdlib>
 #include <type_traits>
 
-namespace MathUtil
-{
+namespace MathUtil {
 
-inline bool IntervalsIntersect(unsigned start0, unsigned length0, unsigned start1, unsigned length1) {
+inline bool IntervalsIntersect(unsigned start0, unsigned length0, unsigned start1,
+                               unsigned length1) {
     return (std::max(start0, start1) < std::min(start0 + length0, start1 + length1));
 }
 
-template<typename T>
-inline T Clamp(const T val, const T& min, const T& max)
-{
+template <typename T>
+inline T Clamp(const T val, const T& min, const T& max) {
     return std::max(min, std::min(max, val));
 }
 
-template<class T>
-struct Rectangle
-{
+template <class T>
+struct Rectangle {
     T left;
     T top;
     T right;
     T bottom;
 
-    Rectangle() {}
+    Rectangle() {
+    }
 
-    Rectangle(T left, T top, T right, T bottom) : left(left), top(top), right(right), bottom(bottom) {}
+    Rectangle(T left, T top, T right, T bottom)
+        : left(left), top(top), right(right), bottom(bottom) {
+    }
 
-    T GetWidth() const { return std::abs(static_cast<typename std::make_signed<T>::type>(right - left)); }
-    T GetHeight() const { return std::abs(static_cast<typename std::make_signed<T>::type>(bottom - top)); }
+    T GetWidth() const {
+        return std::abs(static_cast<typename std::make_signed<T>::type>(right - left));
+    }
+    T GetHeight() const {
+        return std::abs(static_cast<typename std::make_signed<T>::type>(bottom - top));
+    }
 };
 
-}  // namespace MathUtil
+} // namespace MathUtil
diff --git a/src/common/memory_util.cpp b/src/common/memory_util.cpp
index 07c7f79c8..7d352f00f 100644
--- a/src/common/memory_util.cpp
+++ b/src/common/memory_util.cpp
@@ -2,31 +2,29 @@
 // Licensed under GPLv2 or any later version
 // Refer to the license.txt file included.
 
-
-#include "common/logging/log.h"
 #include "common/memory_util.h"
+#include "common/logging/log.h"
 
 #ifdef _WIN32
-    #include <windows.h>
-    #include <psapi.h>
-    #include "common/common_funcs.h"
-    #include "common/string_util.h"
+#include <windows.h>
+#include <psapi.h>
+#include "common/common_funcs.h"
+#include "common/string_util.h"
 #else
-    #include <cstdlib>
-    #include <sys/mman.h>
+#include <cstdlib>
+#include <sys/mman.h>
 #endif
 
 #if !defined(_WIN32) && defined(ARCHITECTURE_X64) && !defined(MAP_32BIT)
 #include <unistd.h>
-#define PAGE_MASK     (getpagesize() - 1)
+#define PAGE_MASK (getpagesize() - 1)
 #define round_page(x) ((((unsigned long)(x)) + PAGE_MASK) & ~(PAGE_MASK))
 #endif
 
 // This is purposely not a full wrapper for virtualalloc/mmap, but it
 // provides exactly the primitive operations that Dolphin needs.
 
-void* AllocateExecutableMemory(size_t size, bool low)
-{
+void* AllocateExecutableMemory(size_t size, bool low) {
 #if defined(_WIN32)
     void* ptr = VirtualAlloc(nullptr, size, MEM_COMMIT, PAGE_EXECUTE_READWRITE);
 #else
@@ -39,31 +37,27 @@ void* AllocateExecutableMemory(size_t size, bool low)
     // effect of discarding already mapped pages that happen to be in the
     // requested virtual memory range (such as the emulated RAM, sometimes).
     if (low && (!map_hint))
-        map_hint = (char*)round_page(512*1024*1024); /* 0.5 GB rounded up to the next page */
+        map_hint = (char*)round_page(512 * 1024 * 1024); /* 0.5 GB rounded up to the next page */
 #endif
-    void* ptr = mmap(map_hint, size, PROT_READ | PROT_WRITE | PROT_EXEC,
-        MAP_ANON | MAP_PRIVATE
+    void* ptr = mmap(map_hint, size, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_ANON | MAP_PRIVATE
 #if defined(ARCHITECTURE_X64) && defined(MAP_32BIT)
-        | (low ? MAP_32BIT : 0)
+                                                                             | (low ? MAP_32BIT : 0)
 #endif
-        , -1, 0);
+                                                                             ,
+                     -1, 0);
 #endif /* defined(_WIN32) */
 
 #ifdef _WIN32
-    if (ptr == nullptr)
-    {
+    if (ptr == nullptr) {
 #else
-    if (ptr == MAP_FAILED)
-    {
+    if (ptr == MAP_FAILED) {
         ptr = nullptr;
 #endif
         LOG_ERROR(Common_Memory, "Failed to allocate executable memory");
     }
 #if !defined(_WIN32) && defined(ARCHITECTURE_X64) && !defined(MAP_32BIT)
-    else
-    {
-        if (low)
-        {
+    else {
+        if (low) {
             map_hint += size;
             map_hint = (char*)round_page(map_hint); /* round up to the next page */
         }
@@ -78,13 +72,11 @@ void* AllocateExecutableMemory(size_t size, bool low)
     return ptr;
 }
 
-void* AllocateMemoryPages(size_t size)
-{
+void* AllocateMemoryPages(size_t size) {
 #ifdef _WIN32
     void* ptr = VirtualAlloc(nullptr, size, MEM_COMMIT, PAGE_READWRITE);
 #else
-    void* ptr = mmap(nullptr, size, PROT_READ | PROT_WRITE,
-            MAP_ANON | MAP_PRIVATE, -1, 0);
+    void* ptr = mmap(nullptr, size, PROT_READ | PROT_WRITE, MAP_ANON | MAP_PRIVATE, -1, 0);
 
     if (ptr == MAP_FAILED)
         ptr = nullptr;
@@ -96,10 +88,9 @@ void* AllocateMemoryPages(size_t size)
     return ptr;
 }
 
-void* AllocateAlignedMemory(size_t size,size_t alignment)
-{
+void* AllocateAlignedMemory(size_t size, size_t alignment) {
 #ifdef _WIN32
-    void* ptr =  _aligned_malloc(size,alignment);
+    void* ptr = _aligned_malloc(size, alignment);
 #else
     void* ptr = nullptr;
 #ifdef ANDROID
@@ -116,10 +107,8 @@ void* AllocateAlignedMemory(size_t size,size_t alignment)
     return ptr;
 }
 
-void FreeMemoryPages(void* ptr, size_t size)
-{
-    if (ptr)
-    {
+void FreeMemoryPages(void* ptr, size_t size) {
+    if (ptr) {
 #ifdef _WIN32
         if (!VirtualFree(ptr, 0, MEM_RELEASE))
             LOG_ERROR(Common_Memory, "FreeMemoryPages failed!\n%s", GetLastErrorMsg());
@@ -129,20 +118,17 @@ void FreeMemoryPages(void* ptr, size_t size)
     }
 }
 
-void FreeAlignedMemory(void* ptr)
-{
-    if (ptr)
-    {
+void FreeAlignedMemory(void* ptr) {
+    if (ptr) {
 #ifdef _WIN32
-    _aligned_free(ptr);
+        _aligned_free(ptr);
 #else
-    free(ptr);
+        free(ptr);
 #endif
     }
 }
 
-void WriteProtectMemory(void* ptr, size_t size, bool allowExecute)
-{
+void WriteProtectMemory(void* ptr, size_t size, bool allowExecute) {
 #ifdef _WIN32
     DWORD oldValue;
     if (!VirtualProtect(ptr, size, allowExecute ? PAGE_EXECUTE_READ : PAGE_READONLY, &oldValue))
@@ -152,19 +138,19 @@ void WriteProtectMemory(void* ptr, size_t size, bool allowExecute)
 #endif
 }
 
-void UnWriteProtectMemory(void* ptr, size_t size, bool allowExecute)
-{
+void UnWriteProtectMemory(void* ptr, size_t size, bool allowExecute) {
 #ifdef _WIN32
     DWORD oldValue;
-    if (!VirtualProtect(ptr, size, allowExecute ? PAGE_EXECUTE_READWRITE : PAGE_READWRITE, &oldValue))
+    if (!VirtualProtect(ptr, size, allowExecute ? PAGE_EXECUTE_READWRITE : PAGE_READWRITE,
+                        &oldValue))
         LOG_ERROR(Common_Memory, "UnWriteProtectMemory failed!\n%s", GetLastErrorMsg());
 #else
-    mprotect(ptr, size, allowExecute ? (PROT_READ | PROT_WRITE | PROT_EXEC) : PROT_WRITE | PROT_READ);
+    mprotect(ptr, size,
+             allowExecute ? (PROT_READ | PROT_WRITE | PROT_EXEC) : PROT_WRITE | PROT_READ);
 #endif
 }
 
-std::string MemUsage()
-{
+std::string MemUsage() {
 #ifdef _WIN32
 #pragma comment(lib, "psapi")
     DWORD processID = GetCurrentProcessId();
@@ -175,10 +161,12 @@ std::string MemUsage()
     // Print information about the memory usage of the process.
 
     hProcess = OpenProcess(PROCESS_QUERY_INFORMATION | PROCESS_VM_READ, FALSE, processID);
-    if (nullptr == hProcess) return "MemUsage Error";
+    if (nullptr == hProcess)
+        return "MemUsage Error";
 
     if (GetProcessMemoryInfo(hProcess, &pmc, sizeof(pmc)))
-        Ret = Common::StringFromFormat("%s K", Common::ThousandSeparate(pmc.WorkingSetSize / 1024, 7).c_str());
+        Ret = Common::StringFromFormat(
+            "%s K", Common::ThousandSeparate(pmc.WorkingSetSize / 1024, 7).c_str());
 
     CloseHandle(hProcess);
     return Ret;
diff --git a/src/common/memory_util.h b/src/common/memory_util.h
index 9bf37c44f..76ca5a30c 100644
--- a/src/common/memory_util.h
+++ b/src/common/memory_util.h
@@ -10,10 +10,12 @@
 void* AllocateExecutableMemory(size_t size, bool low = true);
 void* AllocateMemoryPages(size_t size);
 void FreeMemoryPages(void* ptr, size_t size);
-void* AllocateAlignedMemory(size_t size,size_t alignment);
+void* AllocateAlignedMemory(size_t size, size_t alignment);
 void FreeAlignedMemory(void* ptr);
 void WriteProtectMemory(void* ptr, size_t size, bool executable = false);
 void UnWriteProtectMemory(void* ptr, size_t size, bool allowExecute = false);
 std::string MemUsage();
 
-inline int GetPageSize() { return 4096; }
+inline int GetPageSize() {
+    return 4096;
+}
diff --git a/src/common/microprofile.h b/src/common/microprofile.h
index 670a58fe5..54e7f3cc4 100644
--- a/src/common/microprofile.h
+++ b/src/common/microprofile.h
@@ -13,7 +13,7 @@
 #define MICROPROFILE_WEBSERVER 0
 #define MICROPROFILE_GPU_TIMERS 0 // TODO: Implement timer queries when we upgrade to OpenGL 3.3
 #define MICROPROFILE_CONTEXT_SWITCH_TRACE 0
-#define MICROPROFILE_PER_THREAD_BUFFER_SIZE (2048<<13) // 16 MB
+#define MICROPROFILE_PER_THREAD_BUFFER_SIZE (2048 << 13) // 16 MB
 
 #ifdef _WIN32
 // This isn't defined by the standard library in MSVC2015
diff --git a/src/common/misc.cpp b/src/common/misc.cpp
index d2a049b63..5938e6289 100644
--- a/src/common/misc.cpp
+++ b/src/common/misc.cpp
@@ -12,23 +12,21 @@
 #endif
 
 // Neither Android nor OS X support TLS
-#if  defined(__APPLE__) || (ANDROID && __clang__)
+#if defined(__APPLE__) || (ANDROID && __clang__)
 #define __thread
 #endif
 
 // Generic function to get last error message.
 // Call directly after the command or use the error num.
 // This function might change the error code.
-const char* GetLastErrorMsg()
-{
+const char* GetLastErrorMsg() {
     static const size_t buff_size = 255;
 
 #ifdef _WIN32
     static __declspec(thread) char err_str[buff_size] = {};
 
     FormatMessageA(FORMAT_MESSAGE_FROM_SYSTEM, nullptr, GetLastError(),
-        MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT),
-        err_str, buff_size, nullptr);
+                   MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT), err_str, buff_size, nullptr);
 #else
     static __thread char err_str[buff_size] = {};
 
diff --git a/src/common/platform.h b/src/common/platform.h
index 9ba4db11b..c62fb7c8f 100644
--- a/src/common/platform.h
+++ b/src/common/platform.h
@@ -28,7 +28,7 @@
 // Platform detection
 
 #if defined(ARCHITECTURE_x86_64) || defined(__aarch64__)
-    #define EMU_ARCH_BITS 64
+#define EMU_ARCH_BITS 64
 #elif defined(__i386) || defined(_M_IX86) || defined(__arm__) || defined(_M_ARM)
-    #define EMU_ARCH_BITS 32
+#define EMU_ARCH_BITS 32
 #endif
diff --git a/src/common/profiler.cpp b/src/common/profiler.cpp
index 49eb3f40c..992ec25b2 100644
--- a/src/common/profiler.cpp
+++ b/src/common/profiler.cpp
@@ -14,7 +14,7 @@ namespace Common {
 namespace Profiling {
 
 ProfilingManager::ProfilingManager()
-        : last_frame_end(Clock::now()), this_frame_start(Clock::now()) {
+    : last_frame_end(Clock::now()), this_frame_start(Clock::now()) {
 }
 
 void ProfilingManager::BeginFrame() {
@@ -31,7 +31,7 @@ void ProfilingManager::FinishFrame() {
 }
 
 TimingResultsAggregator::TimingResultsAggregator(size_t window_size)
-        : max_window_size(window_size), window_size(0) {
+    : max_window_size(window_size), window_size(0) {
     interframe_times.resize(window_size, Duration::zero());
     frame_times.resize(window_size, Duration::zero());
 }
diff --git a/src/common/scope_exit.h b/src/common/scope_exit.h
index 08f09a8c8..73b2a262e 100644
--- a/src/common/scope_exit.h
+++ b/src/common/scope_exit.h
@@ -4,20 +4,25 @@
 
 #pragma once
 
-#include "common/common_funcs.h"
 #include <utility>
+#include "common/common_funcs.h"
 
 namespace detail {
-    template <typename Func>
-    struct ScopeExitHelper {
-        explicit ScopeExitHelper(Func&& func) : func(std::move(func)) {}
-        ~ScopeExitHelper() { func(); }
+template <typename Func>
+struct ScopeExitHelper {
+    explicit ScopeExitHelper(Func&& func) : func(std::move(func)) {
+    }
+    ~ScopeExitHelper() {
+        func();
+    }
 
-        Func func;
-    };
+    Func func;
+};
 
-    template <typename Func>
-    ScopeExitHelper<Func> ScopeExit(Func&& func) { return ScopeExitHelper<Func>(std::move(func)); }
+template <typename Func>
+ScopeExitHelper<Func> ScopeExit(Func&& func) {
+    return ScopeExitHelper<Func>(std::move(func));
+}
 }
 
 /**
diff --git a/src/common/string_util.cpp b/src/common/string_util.cpp
index f0aa072db..9ccd6f135 100644
--- a/src/common/string_util.cpp
+++ b/src/common/string_util.cpp
@@ -14,11 +14,11 @@
 #include "common/string_util.h"
 
 #ifdef _MSC_VER
-    #include <Windows.h>
-    #include <codecvt>
-    #include "common/common_funcs.h"
+#include <Windows.h>
+#include <codecvt>
+#include "common/common_funcs.h"
 #else
-    #include <iconv.h>
+#include <iconv.h>
 #endif
 
 namespace Common {
@@ -36,9 +36,8 @@ std::string ToUpper(std::string str) {
 }
 
 // faster than sscanf
-bool AsciiToHex(const char* _szValue, u32& result)
-{
-    char *endptr = nullptr;
+bool AsciiToHex(const char* _szValue, u32& result) {
+    char* endptr = nullptr;
     const u32 value = strtoul(_szValue, &endptr, 16);
 
     if (!endptr || *endptr)
@@ -48,8 +47,7 @@ bool AsciiToHex(const char* _szValue, u32& result)
     return true;
 }
 
-bool CharArrayFromFormatV(char* out, int outsize, const char* format, va_list args)
-{
+bool CharArrayFromFormatV(char* out, int outsize, const char* format, va_list args) {
     int writtenCount;
 
 #ifdef _MSC_VER
@@ -84,22 +82,18 @@ bool CharArrayFromFormatV(char* out, int outsize, const char* format, va_list ar
     writtenCount = vsnprintf(out, outsize, format, args);
 #endif
 
-    if (writtenCount > 0 && writtenCount < outsize)
-    {
+    if (writtenCount > 0 && writtenCount < outsize) {
         out[writtenCount] = '\0';
         return true;
-    }
-    else
-    {
+    } else {
         out[outsize - 1] = '\0';
         return false;
     }
 }
 
-std::string StringFromFormat(const char* format, ...)
-{
+std::string StringFromFormat(const char* format, ...) {
     va_list args;
-    char *buf = nullptr;
+    char* buf = nullptr;
 #ifdef _WIN32
     int required = 0;
 
@@ -124,21 +118,17 @@ std::string StringFromFormat(const char* format, ...)
 }
 
 // For Debugging. Read out an u8 array.
-std::string ArrayToString(const u8 *data, u32 size, int line_len, bool spaces)
-{
+std::string ArrayToString(const u8* data, u32 size, int line_len, bool spaces) {
     std::ostringstream oss;
     oss << std::setfill('0') << std::hex;
 
-    for (int line = 0; size; ++data, --size)
-    {
+    for (int line = 0; size; ++data, --size) {
         oss << std::setw(2) << (int)*data;
 
-        if (line_len == ++line)
-        {
+        if (line_len == ++line) {
             oss << '\n';
             line = 0;
-        }
-        else if (spaces)
+        } else if (spaces)
             oss << ' ';
     }
 
@@ -146,8 +136,7 @@ std::string ArrayToString(const u8 *data, u32 size, int line_len, bool spaces)
 }
 
 // Turns "  hej " into "hej". Also handles tabs.
-std::string StripSpaces(const std::string &str)
-{
+std::string StripSpaces(const std::string& str) {
     const size_t s = str.find_first_not_of(" \t\r\n");
 
     if (str.npos != s)
@@ -159,17 +148,15 @@ std::string StripSpaces(const std::string &str)
 // "\"hello\"" is turned to "hello"
 // This one assumes that the string has already been space stripped in both
 // ends, as done by StripSpaces above, for example.
-std::string StripQuotes(const std::string& s)
-{
+std::string StripQuotes(const std::string& s) {
     if (s.size() && '\"' == s[0] && '\"' == *s.rbegin())
         return s.substr(1, s.size() - 2);
     else
         return s;
 }
 
-bool TryParse(const std::string &str, u32 *const output)
-{
-    char *endptr = nullptr;
+bool TryParse(const std::string& str, u32* const output) {
+    char* endptr = nullptr;
 
     // Reset errno to a value other than ERANGE
     errno = 0;
@@ -183,8 +170,7 @@ bool TryParse(const std::string &str, u32 *const output)
         return false;
 
 #if ULONG_MAX > UINT_MAX
-    if (value >= 0x100000000ull
-        && value <= 0xFFFFFFFF00000000ull)
+    if (value >= 0x100000000ull && value <= 0xFFFFFFFF00000000ull)
         return false;
 #endif
 
@@ -192,8 +178,7 @@ bool TryParse(const std::string &str, u32 *const output)
     return true;
 }
 
-bool TryParse(const std::string &str, bool *const output)
-{
+bool TryParse(const std::string& str, bool* const output) {
     if ("1" == str || "true" == ToLower(str))
         *output = true;
     else if ("0" == str || "false" == ToLower(str))
@@ -204,22 +189,21 @@ bool TryParse(const std::string &str, bool *const output)
     return true;
 }
 
-std::string StringFromBool(bool value)
-{
+std::string StringFromBool(bool value) {
     return value ? "True" : "False";
 }
 
-bool SplitPath(const std::string& full_path, std::string* _pPath, std::string* _pFilename, std::string* _pExtension)
-{
+bool SplitPath(const std::string& full_path, std::string* _pPath, std::string* _pFilename,
+               std::string* _pExtension) {
     if (full_path.empty())
         return false;
 
     size_t dir_end = full_path.find_last_of("/"
-    // windows needs the : included for something like just "C:" to be considered a directory
+// windows needs the : included for something like just "C:" to be considered a directory
 #ifdef _WIN32
-        ":"
+                                            ":"
 #endif
-    );
+                                            );
     if (std::string::npos == dir_end)
         dir_end = 0;
     else
@@ -241,8 +225,8 @@ bool SplitPath(const std::string& full_path, std::string* _pPath, std::string* _
     return true;
 }
 
-void BuildCompleteFilename(std::string& _CompleteFilename, const std::string& _Path, const std::string& _Filename)
-{
+void BuildCompleteFilename(std::string& _CompleteFilename, const std::string& _Path,
+                           const std::string& _Filename) {
     _CompleteFilename = _Path;
 
     // check for seperator
@@ -253,8 +237,7 @@ void BuildCompleteFilename(std::string& _CompleteFilename, const std::string& _P
     _CompleteFilename += _Filename;
 }
 
-void SplitString(const std::string& str, const char delim, std::vector<std::string>& output)
-{
+void SplitString(const std::string& str, const char delim, std::vector<std::string>& output) {
     std::istringstream iss(str);
     output.resize(1);
 
@@ -264,8 +247,7 @@ void SplitString(const std::string& str, const char delim, std::vector<std::stri
     output.pop_back();
 }
 
-std::string TabsToSpaces(int tab_size, const std::string &in)
-{
+std::string TabsToSpaces(int tab_size, const std::string& in) {
     const std::string spaces(tab_size, ' ');
     std::string out(in);
 
@@ -276,15 +258,13 @@ std::string TabsToSpaces(int tab_size, const std::string &in)
     return out;
 }
 
-std::string ReplaceAll(std::string result, const std::string& src, const std::string& dest)
-{
+std::string ReplaceAll(std::string result, const std::string& src, const std::string& dest) {
     size_t pos = 0;
 
     if (src == dest)
         return result;
 
-    while ((pos = result.find(src, pos)) != std::string::npos)
-    {
+    while ((pos = result.find(src, pos)) != std::string::npos) {
         result.replace(pos, src.size(), dest);
         pos += dest.length();
     }
@@ -294,8 +274,7 @@ std::string ReplaceAll(std::string result, const std::string& src, const std::st
 
 #ifdef _MSC_VER
 
-std::string UTF16ToUTF8(const std::u16string& input)
-{
+std::string UTF16ToUTF8(const std::u16string& input) {
 #if _MSC_VER >= 1900
     // Workaround for missing char16_t/char32_t instantiations in MSVC2015
     std::wstring_convert<std::codecvt_utf8_utf16<__int16>, __int16> convert;
@@ -307,8 +286,7 @@ std::string UTF16ToUTF8(const std::u16string& input)
 #endif
 }
 
-std::u16string UTF8ToUTF16(const std::string& input)
-{
+std::u16string UTF8ToUTF16(const std::string& input) {
 #if _MSC_VER >= 1900
     // Workaround for missing char16_t/char32_t instantiations in MSVC2015
     std::wstring_convert<std::codecvt_utf8_utf16<__int16>, __int16> convert;
@@ -320,57 +298,56 @@ std::u16string UTF8ToUTF16(const std::string& input)
 #endif
 }
 
-static std::wstring CPToUTF16(u32 code_page, const std::string& input)
-{
-    auto const size = MultiByteToWideChar(code_page, 0, input.data(), static_cast<int>(input.size()), nullptr, 0);
+static std::wstring CPToUTF16(u32 code_page, const std::string& input) {
+    auto const size =
+        MultiByteToWideChar(code_page, 0, input.data(), static_cast<int>(input.size()), nullptr, 0);
 
     std::wstring output;
     output.resize(size);
 
-    if (size == 0 || size != MultiByteToWideChar(code_page, 0, input.data(), static_cast<int>(input.size()), &output[0], static_cast<int>(output.size())))
+    if (size == 0 ||
+        size != MultiByteToWideChar(code_page, 0, input.data(), static_cast<int>(input.size()),
+                                    &output[0], static_cast<int>(output.size())))
         output.clear();
 
     return output;
 }
 
-std::string UTF16ToUTF8(const std::wstring& input)
-{
-    auto const size = WideCharToMultiByte(CP_UTF8, 0, input.data(), static_cast<int>(input.size()), nullptr, 0, nullptr, nullptr);
+std::string UTF16ToUTF8(const std::wstring& input) {
+    auto const size = WideCharToMultiByte(CP_UTF8, 0, input.data(), static_cast<int>(input.size()),
+                                          nullptr, 0, nullptr, nullptr);
 
     std::string output;
     output.resize(size);
 
-    if (size == 0 || size != WideCharToMultiByte(CP_UTF8, 0, input.data(), static_cast<int>(input.size()), &output[0], static_cast<int>(output.size()), nullptr, nullptr))
+    if (size == 0 ||
+        size != WideCharToMultiByte(CP_UTF8, 0, input.data(), static_cast<int>(input.size()),
+                                    &output[0], static_cast<int>(output.size()), nullptr, nullptr))
         output.clear();
 
     return output;
 }
 
-std::wstring UTF8ToUTF16W(const std::string &input)
-{
+std::wstring UTF8ToUTF16W(const std::string& input) {
     return CPToUTF16(CP_UTF8, input);
 }
 
-std::string SHIFTJISToUTF8(const std::string& input)
-{
+std::string SHIFTJISToUTF8(const std::string& input) {
     return UTF16ToUTF8(CPToUTF16(932, input));
 }
 
-std::string CP1252ToUTF8(const std::string& input)
-{
+std::string CP1252ToUTF8(const std::string& input) {
     return UTF16ToUTF8(CPToUTF16(1252, input));
 }
 
 #else
 
 template <typename T>
-static std::string CodeToUTF8(const char* fromcode, const std::basic_string<T>& input)
-{
+static std::string CodeToUTF8(const char* fromcode, const std::basic_string<T>& input) {
     std::string result;
 
     iconv_t const conv_desc = iconv_open("UTF-8", fromcode);
-    if ((iconv_t)(-1) == conv_desc)
-    {
+    if ((iconv_t)(-1) == conv_desc) {
         LOG_ERROR(Common, "Iconv initialization failure [%s]: %s", fromcode, strerror(errno));
         iconv_close(conv_desc);
         return {};
@@ -388,24 +365,18 @@ static std::string CodeToUTF8(const char* fromcode, const std::basic_string<T>&
     auto dst_buffer = &out_buffer[0];
     size_t dst_bytes = out_buffer.size();
 
-    while (0 != src_bytes)
-    {
-        size_t const iconv_result = iconv(conv_desc, (char**)(&src_buffer), &src_bytes,
-            &dst_buffer, &dst_bytes);
+    while (0 != src_bytes) {
+        size_t const iconv_result =
+            iconv(conv_desc, (char**)(&src_buffer), &src_bytes, &dst_buffer, &dst_bytes);
 
-        if (static_cast<size_t>(-1) == iconv_result)
-        {
-            if (EILSEQ == errno || EINVAL == errno)
-            {
+        if (static_cast<size_t>(-1) == iconv_result) {
+            if (EILSEQ == errno || EINVAL == errno) {
                 // Try to skip the bad character
-                if (0 != src_bytes)
-                {
+                if (0 != src_bytes) {
                     --src_bytes;
                     ++src_buffer;
                 }
-            }
-            else
-            {
+            } else {
                 LOG_ERROR(Common, "iconv failure [%s]: %s", fromcode, strerror(errno));
                 break;
             }
@@ -420,13 +391,11 @@ static std::string CodeToUTF8(const char* fromcode, const std::basic_string<T>&
     return result;
 }
 
-std::u16string UTF8ToUTF16(const std::string& input)
-{
+std::u16string UTF8ToUTF16(const std::string& input) {
     std::u16string result;
 
     iconv_t const conv_desc = iconv_open("UTF-16LE", "UTF-8");
-    if ((iconv_t)(-1) == conv_desc)
-    {
+    if ((iconv_t)(-1) == conv_desc) {
         LOG_ERROR(Common, "Iconv initialization failure [UTF-8]: %s", strerror(errno));
         iconv_close(conv_desc);
         return {};
@@ -444,24 +413,18 @@ std::u16string UTF8ToUTF16(const std::string& input)
     char* dst_buffer = (char*)(&out_buffer[0]);
     size_t dst_bytes = out_buffer.size();
 
-    while (0 != src_bytes)
-    {
-        size_t const iconv_result = iconv(conv_desc, &src_buffer, &src_bytes,
-                                          &dst_buffer, &dst_bytes);
+    while (0 != src_bytes) {
+        size_t const iconv_result =
+            iconv(conv_desc, &src_buffer, &src_bytes, &dst_buffer, &dst_bytes);
 
-        if (static_cast<size_t>(-1) == iconv_result)
-        {
-            if (EILSEQ == errno || EINVAL == errno)
-            {
+        if (static_cast<size_t>(-1) == iconv_result) {
+            if (EILSEQ == errno || EINVAL == errno) {
                 // Try to skip the bad character
-                if (0 != src_bytes)
-                {
+                if (0 != src_bytes) {
                     --src_bytes;
                     ++src_buffer;
                 }
-            }
-            else
-            {
+            } else {
                 LOG_ERROR(Common, "iconv failure [UTF-8]: %s", strerror(errno));
                 break;
             }
@@ -476,32 +439,28 @@ std::u16string UTF8ToUTF16(const std::string& input)
     return result;
 }
 
-std::string UTF16ToUTF8(const std::u16string& input)
-{
+std::string UTF16ToUTF8(const std::u16string& input) {
     return CodeToUTF8("UTF-16LE", input);
 }
 
-std::string CP1252ToUTF8(const std::string& input)
-{
-    //return CodeToUTF8("CP1252//TRANSLIT", input);
-    //return CodeToUTF8("CP1252//IGNORE", input);
+std::string CP1252ToUTF8(const std::string& input) {
+    // return CodeToUTF8("CP1252//TRANSLIT", input);
+    // return CodeToUTF8("CP1252//IGNORE", input);
     return CodeToUTF8("CP1252", input);
 }
 
-std::string SHIFTJISToUTF8(const std::string& input)
-{
-    //return CodeToUTF8("CP932", input);
+std::string SHIFTJISToUTF8(const std::string& input) {
+    // return CodeToUTF8("CP932", input);
     return CodeToUTF8("SJIS", input);
 }
 
 #endif
 
-std::string StringFromFixedZeroTerminatedBuffer(const char * buffer, size_t max_len) {
+std::string StringFromFixedZeroTerminatedBuffer(const char* buffer, size_t max_len) {
     size_t len = 0;
     while (len < max_len && buffer[len] != '\0')
         ++len;
 
     return std::string(buffer, len);
 }
-
 }
diff --git a/src/common/string_util.h b/src/common/string_util.h
index 89d9f133e..6ffd735f4 100644
--- a/src/common/string_util.h
+++ b/src/common/string_util.h
@@ -25,9 +25,8 @@ std::string StringFromFormat(const char* format, ...);
 // Cheap!
 bool CharArrayFromFormatV(char* out, int outsize, const char* format, va_list args);
 
-template<size_t Count>
-inline void CharArrayFromFormat(char (& out)[Count], const char* format, ...)
-{
+template <size_t Count>
+inline void CharArrayFromFormat(char (&out)[Count], const char* format, ...) {
     va_list args;
     va_start(args, format);
     CharArrayFromFormatV(out, Count, format, args);
@@ -35,15 +34,14 @@ inline void CharArrayFromFormat(char (& out)[Count], const char* format, ...)
 }
 
 // Good
-std::string ArrayToString(const u8 *data, u32 size, int line_len = 20, bool spaces = true);
+std::string ArrayToString(const u8* data, u32 size, int line_len = 20, bool spaces = true);
 
-std::string StripSpaces(const std::string &s);
-std::string StripQuotes(const std::string &s);
+std::string StripSpaces(const std::string& s);
+std::string StripQuotes(const std::string& s);
 
 // Thousand separator. Turns 12345678 into 12,345,678
 template <typename I>
-std::string ThousandSeparate(I value, int spaces = 0)
-{
+std::string ThousandSeparate(I value, int spaces = 0) {
     std::ostringstream oss;
 
 // std::locale("") seems to be broken on many platforms
@@ -57,35 +55,34 @@ std::string ThousandSeparate(I value, int spaces = 0)
 
 std::string StringFromBool(bool value);
 
-bool TryParse(const std::string &str, bool *output);
-bool TryParse(const std::string &str, u32 *output);
+bool TryParse(const std::string& str, bool* output);
+bool TryParse(const std::string& str, u32* output);
 
 template <typename N>
-static bool TryParse(const std::string &str, N *const output)
-{
+static bool TryParse(const std::string& str, N* const output) {
     std::istringstream iss(str);
 
     N tmp = 0;
-    if (iss >> tmp)
-    {
+    if (iss >> tmp) {
         *output = tmp;
         return true;
-    }
-    else
+    } else
         return false;
 }
 
 // TODO: kill this
 bool AsciiToHex(const char* _szValue, u32& result);
 
-std::string TabsToSpaces(int tab_size, const std::string &in);
+std::string TabsToSpaces(int tab_size, const std::string& in);
 
 void SplitString(const std::string& str, char delim, std::vector<std::string>& output);
 
 // "C:/Windows/winhelp.exe" to "C:/Windows/", "winhelp", ".exe"
-bool SplitPath(const std::string& full_path, std::string* _pPath, std::string* _pFilename, std::string* _pExtension);
+bool SplitPath(const std::string& full_path, std::string* _pPath, std::string* _pFilename,
+               std::string* _pExtension);
 
-void BuildCompleteFilename(std::string& _CompleteFilename, const std::string& _Path, const std::string& _Filename);
+void BuildCompleteFilename(std::string& _CompleteFilename, const std::string& _Path,
+                           const std::string& _Filename);
 std::string ReplaceAll(std::string result, const std::string& src, const std::string& dest);
 
 std::string UTF16ToUTF8(const std::u16string& input);
@@ -99,17 +96,21 @@ std::string UTF16ToUTF8(const std::wstring& input);
 std::wstring UTF8ToUTF16W(const std::string& str);
 
 #ifdef _UNICODE
-inline std::string TStrToUTF8(const std::wstring& str)
-{ return UTF16ToUTF8(str); }
+inline std::string TStrToUTF8(const std::wstring& str) {
+    return UTF16ToUTF8(str);
+}
 
-inline std::wstring UTF8ToTStr(const std::string& str)
-{ return UTF8ToUTF16W(str); }
+inline std::wstring UTF8ToTStr(const std::string& str) {
+    return UTF8ToUTF16W(str);
+}
 #else
-inline std::string TStrToUTF8(const std::string& str)
-{ return str; }
+inline std::string TStrToUTF8(const std::string& str) {
+    return str;
+}
 
-inline std::string UTF8ToTStr(const std::string& str)
-{ return str; }
+inline std::string UTF8ToTStr(const std::string& str) {
+    return str;
+}
 #endif
 
 #endif
@@ -134,5 +135,4 @@ bool ComparePartialString(InIt begin, InIt end, const char* other) {
  * NUL-terminated then the string ends at max_len characters.
  */
 std::string StringFromFixedZeroTerminatedBuffer(const char* buffer, size_t max_len);
-
 }
diff --git a/src/common/swap.h b/src/common/swap.h
index 1749bd7a4..1794144fb 100644
--- a/src/common/swap.h
+++ b/src/common/swap.h
@@ -18,11 +18,11 @@
 #pragma once
 
 #if defined(_MSC_VER)
-    #include <cstdlib>
+#include <cstdlib>
 #elif defined(__linux__)
-    #include <byteswap.h>
+#include <byteswap.h>
 #elif defined(__FreeBSD__)
-    #include <sys/endian.h>
+#include <sys/endian.h>
 #endif
 
 #include <cstring>
@@ -61,38 +61,73 @@
 namespace Common {
 
 #ifdef _MSC_VER
-inline u16 swap16(u16 _data) {return _byteswap_ushort(_data);}
-inline u32 swap32(u32 _data) {return _byteswap_ulong (_data);}
-inline u64 swap64(u64 _data) {return _byteswap_uint64(_data);}
+inline u16 swap16(u16 _data) {
+    return _byteswap_ushort(_data);
+}
+inline u32 swap32(u32 _data) {
+    return _byteswap_ulong(_data);
+}
+inline u64 swap64(u64 _data) {
+    return _byteswap_uint64(_data);
+}
 #elif _M_ARM
-inline u16 swap16 (u16 _data) { u32 data = _data; __asm__ ("rev16 %0, %1\n" : "=l" (data) : "l" (data)); return (u16)data;}
-inline u32 swap32 (u32 _data) {__asm__ ("rev %0, %1\n" : "=l" (_data) : "l" (_data)); return _data;}
-inline u64 swap64(u64 _data) {return ((u64)swap32(_data) << 32) | swap32(_data >> 32);}
+inline u16 swap16(u16 _data) {
+    u32 data = _data;
+    __asm__("rev16 %0, %1\n" : "=l"(data) : "l"(data));
+    return (u16)data;
+}
+inline u32 swap32(u32 _data) {
+    __asm__("rev %0, %1\n" : "=l"(_data) : "l"(_data));
+    return _data;
+}
+inline u64 swap64(u64 _data) {
+    return ((u64)swap32(_data) << 32) | swap32(_data >> 32);
+}
 #elif __linux__
-inline u16 swap16(u16 _data) {return bswap_16(_data);}
-inline u32 swap32(u32 _data) {return bswap_32(_data);}
-inline u64 swap64(u64 _data) {return bswap_64(_data);}
+inline u16 swap16(u16 _data) {
+    return bswap_16(_data);
+}
+inline u32 swap32(u32 _data) {
+    return bswap_32(_data);
+}
+inline u64 swap64(u64 _data) {
+    return bswap_64(_data);
+}
 #elif __APPLE__
-inline __attribute__((always_inline)) u16 swap16(u16 _data)
-{return (_data >> 8) | (_data << 8);}
-inline __attribute__((always_inline)) u32 swap32(u32 _data)
-{return __builtin_bswap32(_data);}
-inline __attribute__((always_inline)) u64 swap64(u64 _data)
-{return __builtin_bswap64(_data);}
+inline __attribute__((always_inline)) u16 swap16(u16 _data) {
+    return (_data >> 8) | (_data << 8);
+}
+inline __attribute__((always_inline)) u32 swap32(u32 _data) {
+    return __builtin_bswap32(_data);
+}
+inline __attribute__((always_inline)) u64 swap64(u64 _data) {
+    return __builtin_bswap64(_data);
+}
 #elif __FreeBSD__
-inline u16 swap16(u16 _data) {return bswap16(_data);}
-inline u32 swap32(u32 _data) {return bswap32(_data);}
-inline u64 swap64(u64 _data) {return bswap64(_data);}
+inline u16 swap16(u16 _data) {
+    return bswap16(_data);
+}
+inline u32 swap32(u32 _data) {
+    return bswap32(_data);
+}
+inline u64 swap64(u64 _data) {
+    return bswap64(_data);
+}
 #else
 // Slow generic implementation.
-inline u16 swap16(u16 data) {return (data >> 8) | (data << 8);}
-inline u32 swap32(u32 data) {return (swap16(data) << 16) | swap16(data >> 16);}
-inline u64 swap64(u64 data) {return ((u64)swap32(data) << 32) | swap32(data >> 32);}
+inline u16 swap16(u16 data) {
+    return (data >> 8) | (data << 8);
+}
+inline u32 swap32(u32 data) {
+    return (swap16(data) << 16) | swap16(data >> 16);
+}
+inline u64 swap64(u64 data) {
+    return ((u64)swap32(data) << 32) | swap32(data >> 32);
+}
 #endif
 
 inline float swapf(float f) {
-    static_assert(sizeof(u32) == sizeof(float),
-                  "float must be the same size as uint32_t.");
+    static_assert(sizeof(u32) == sizeof(float), "float must be the same size as uint32_t.");
 
     u32 value;
     std::memcpy(&value, &f, sizeof(u32));
@@ -104,8 +139,7 @@ inline float swapf(float f) {
 }
 
 inline double swapd(double f) {
-    static_assert(sizeof(u64) == sizeof(double),
-                  "double must be the same size as uint64_t.");
+    static_assert(sizeof(u64) == sizeof(double), "double must be the same size as uint64_t.");
 
     u64 value;
     std::memcpy(&value, &f, sizeof(u64));
@@ -116,8 +150,7 @@ inline double swapd(double f) {
     return f;
 }
 
-}  // Namespace Common
-
+} // Namespace Common
 
 template <typename T, typename F>
 struct swap_struct_t {
@@ -129,251 +162,272 @@ protected:
     static T swap(T v) {
         return F::swap(v);
     }
+
 public:
     T const swap() const {
         return swap(value);
-
     }
     swap_struct_t() = default;
-    swap_struct_t(const T &v): value(swap(v)) {}
+    swap_struct_t(const T& v) : value(swap(v)) {
+    }
 
     template <typename S>
-    swapped_t& operator=(const S &source) {
+    swapped_t& operator=(const S& source) {
         value = swap((T)source);
         return *this;
     }
 
-    operator s8() const { return (s8)swap(); }
-    operator u8() const { return (u8)swap(); }
-    operator s16() const { return (s16)swap(); }
-    operator u16() const { return (u16)swap(); }
-    operator s32() const { return (s32)swap(); }
-    operator u32() const { return (u32)swap(); }
-    operator s64() const { return (s64)swap(); }
-    operator u64() const { return (u64)swap(); }
-    operator float() const { return (float)swap(); }
-    operator double() const { return (double)swap(); }
+    operator s8() const {
+        return (s8)swap();
+    }
+    operator u8() const {
+        return (u8)swap();
+    }
+    operator s16() const {
+        return (s16)swap();
+    }
+    operator u16() const {
+        return (u16)swap();
+    }
+    operator s32() const {
+        return (s32)swap();
+    }
+    operator u32() const {
+        return (u32)swap();
+    }
+    operator s64() const {
+        return (s64)swap();
+    }
+    operator u64() const {
+        return (u64)swap();
+    }
+    operator float() const {
+        return (float)swap();
+    }
+    operator double() const {
+        return (double)swap();
+    }
 
     // +v
-    swapped_t operator +() const {
+    swapped_t operator+() const {
         return +swap();
     }
     // -v
-    swapped_t operator -() const {
+    swapped_t operator-() const {
         return -swap();
     }
 
     // v / 5
-    swapped_t operator/(const swapped_t &i) const {
+    swapped_t operator/(const swapped_t& i) const {
         return swap() / i.swap();
     }
     template <typename S>
-    swapped_t operator/(const S &i) const {
+    swapped_t operator/(const S& i) const {
         return swap() / i;
     }
 
     // v * 5
-    swapped_t operator*(const swapped_t &i) const {
+    swapped_t operator*(const swapped_t& i) const {
         return swap() * i.swap();
     }
     template <typename S>
-    swapped_t operator*(const S &i) const {
+    swapped_t operator*(const S& i) const {
         return swap() * i;
     }
 
     // v + 5
-    swapped_t operator+(const swapped_t &i) const {
+    swapped_t operator+(const swapped_t& i) const {
         return swap() + i.swap();
     }
     template <typename S>
-    swapped_t operator+(const S &i) const {
+    swapped_t operator+(const S& i) const {
         return swap() + (T)i;
     }
     // v - 5
-    swapped_t operator-(const swapped_t &i) const {
+    swapped_t operator-(const swapped_t& i) const {
         return swap() - i.swap();
     }
     template <typename S>
-    swapped_t operator-(const S &i) const {
+    swapped_t operator-(const S& i) const {
         return swap() - (T)i;
     }
 
     // v += 5
-    swapped_t& operator+=(const swapped_t &i) {
+    swapped_t& operator+=(const swapped_t& i) {
         value = swap(swap() + i.swap());
         return *this;
     }
     template <typename S>
-    swapped_t& operator+=(const S &i) {
+    swapped_t& operator+=(const S& i) {
         value = swap(swap() + (T)i);
         return *this;
     }
     // v -= 5
-    swapped_t& operator-=(const swapped_t &i) {
+    swapped_t& operator-=(const swapped_t& i) {
         value = swap(swap() - i.swap());
         return *this;
     }
     template <typename S>
-    swapped_t& operator-=(const S &i) {
+    swapped_t& operator-=(const S& i) {
         value = swap(swap() - (T)i);
         return *this;
     }
 
     // ++v
     swapped_t& operator++() {
-        value = swap(swap()+1);
+        value = swap(swap() + 1);
         return *this;
     }
     // --v
-    swapped_t& operator--()  {
-        value = swap(swap()-1);
+    swapped_t& operator--() {
+        value = swap(swap() - 1);
         return *this;
     }
 
     // v++
     swapped_t operator++(int) {
         swapped_t old = *this;
-        value = swap(swap()+1);
+        value = swap(swap() + 1);
         return old;
     }
     // v--
     swapped_t operator--(int) {
         swapped_t old = *this;
-        value = swap(swap()-1);
+        value = swap(swap() - 1);
         return old;
     }
     // Comparaison
     // v == i
-    bool operator==(const swapped_t &i) const {
+    bool operator==(const swapped_t& i) const {
         return swap() == i.swap();
     }
     template <typename S>
-    bool operator==(const S &i) const {
+    bool operator==(const S& i) const {
         return swap() == i;
     }
 
     // v != i
-    bool operator!=(const swapped_t &i) const {
+    bool operator!=(const swapped_t& i) const {
         return swap() != i.swap();
     }
     template <typename S>
-    bool operator!=(const S &i) const {
+    bool operator!=(const S& i) const {
         return swap() != i;
     }
 
     // v > i
-    bool operator>(const swapped_t &i) const {
+    bool operator>(const swapped_t& i) const {
         return swap() > i.swap();
     }
     template <typename S>
-    bool operator>(const S &i) const {
+    bool operator>(const S& i) const {
         return swap() > i;
     }
 
     // v < i
-    bool operator<(const swapped_t &i) const {
+    bool operator<(const swapped_t& i) const {
         return swap() < i.swap();
     }
     template <typename S>
-    bool operator<(const S &i) const {
+    bool operator<(const S& i) const {
         return swap() < i;
     }
 
     // v >= i
-    bool operator>=(const swapped_t &i) const {
+    bool operator>=(const swapped_t& i) const {
         return swap() >= i.swap();
     }
     template <typename S>
-    bool operator>=(const S &i) const {
+    bool operator>=(const S& i) const {
         return swap() >= i;
     }
 
     // v <= i
-    bool operator<=(const swapped_t &i) const {
+    bool operator<=(const swapped_t& i) const {
         return swap() <= i.swap();
     }
     template <typename S>
-    bool operator<=(const S &i) const {
+    bool operator<=(const S& i) const {
         return swap() <= i;
     }
 
     // logical
-    swapped_t operator !() const {
+    swapped_t operator!() const {
         return !swap();
     }
 
     // bitmath
-    swapped_t operator ~() const {
+    swapped_t operator~() const {
         return ~swap();
     }
 
-    swapped_t operator &(const swapped_t &b) const {
+    swapped_t operator&(const swapped_t& b) const {
         return swap() & b.swap();
     }
     template <typename S>
-    swapped_t operator &(const S &b) const {
+    swapped_t operator&(const S& b) const {
         return swap() & b;
     }
-    swapped_t& operator &=(const swapped_t &b) {
+    swapped_t& operator&=(const swapped_t& b) {
         value = swap(swap() & b.swap());
         return *this;
     }
     template <typename S>
-    swapped_t& operator &=(const S b) {
+    swapped_t& operator&=(const S b) {
         value = swap(swap() & b);
         return *this;
     }
 
-    swapped_t operator |(const swapped_t &b) const {
+    swapped_t operator|(const swapped_t& b) const {
         return swap() | b.swap();
     }
     template <typename S>
-    swapped_t operator |(const S &b) const {
+    swapped_t operator|(const S& b) const {
         return swap() | b;
     }
-    swapped_t& operator |=(const swapped_t &b) {
+    swapped_t& operator|=(const swapped_t& b) {
         value = swap(swap() | b.swap());
         return *this;
     }
     template <typename S>
-    swapped_t& operator |=(const S &b) {
+    swapped_t& operator|=(const S& b) {
         value = swap(swap() | b);
         return *this;
     }
 
-    swapped_t operator ^(const swapped_t &b) const {
+    swapped_t operator^(const swapped_t& b) const {
         return swap() ^ b.swap();
     }
     template <typename S>
-    swapped_t operator ^(const S &b) const {
+    swapped_t operator^(const S& b) const {
         return swap() ^ b;
     }
-    swapped_t& operator ^=(const swapped_t &b) {
+    swapped_t& operator^=(const swapped_t& b) {
         value = swap(swap() ^ b.swap());
         return *this;
     }
     template <typename S>
-    swapped_t& operator ^=(const S &b) {
+    swapped_t& operator^=(const S& b) {
         value = swap(swap() ^ b);
         return *this;
     }
 
     template <typename S>
-    swapped_t operator <<(const S &b) const {
+    swapped_t operator<<(const S& b) const {
         return swap() << b;
     }
     template <typename S>
-    swapped_t& operator <<=(const S &b) const {
+    swapped_t& operator<<=(const S& b) const {
         value = swap(swap() << b);
         return *this;
     }
 
     template <typename S>
-    swapped_t operator >>(const S &b) const {
+    swapped_t operator>>(const S& b) const {
         return swap() >> b;
     }
     template <typename S>
-    swapped_t& operator >>=(const S &b) const {
+    swapped_t& operator>>=(const S& b) const {
         value = swap(swap() >> b);
         return *this;
     }
@@ -381,129 +435,126 @@ public:
     // Member
     /** todo **/
 
-
     // Arithmetics
     template <typename S, typename T2, typename F2>
-    friend S operator+(const S &p, const swapped_t v);
+    friend S operator+(const S& p, const swapped_t v);
 
     template <typename S, typename T2, typename F2>
-    friend S operator-(const S &p, const swapped_t v);
+    friend S operator-(const S& p, const swapped_t v);
 
     template <typename S, typename T2, typename F2>
-    friend S operator/(const S &p, const swapped_t v);
+    friend S operator/(const S& p, const swapped_t v);
 
     template <typename S, typename T2, typename F2>
-    friend S operator*(const S &p, const swapped_t v);
+    friend S operator*(const S& p, const swapped_t v);
 
     template <typename S, typename T2, typename F2>
-    friend S operator%(const S &p, const swapped_t v);
+    friend S operator%(const S& p, const swapped_t v);
 
     // Arithmetics + assignements
     template <typename S, typename T2, typename F2>
-    friend S operator+=(const S &p, const swapped_t v);
+    friend S operator+=(const S& p, const swapped_t v);
 
     template <typename S, typename T2, typename F2>
-    friend S operator-=(const S &p, const swapped_t v);
+    friend S operator-=(const S& p, const swapped_t v);
 
     // Bitmath
     template <typename S, typename T2, typename F2>
-    friend S operator&(const S &p, const swapped_t v);
+    friend S operator&(const S& p, const swapped_t v);
 
     // Comparison
     template <typename S, typename T2, typename F2>
-    friend bool operator<(const S &p, const swapped_t v);
+    friend bool operator<(const S& p, const swapped_t v);
 
     template <typename S, typename T2, typename F2>
-    friend bool operator>(const S &p, const swapped_t v);
+    friend bool operator>(const S& p, const swapped_t v);
 
     template <typename S, typename T2, typename F2>
-    friend bool operator<=(const S &p, const swapped_t v);
+    friend bool operator<=(const S& p, const swapped_t v);
 
     template <typename S, typename T2, typename F2>
-    friend bool operator>=(const S &p, const swapped_t v);
+    friend bool operator>=(const S& p, const swapped_t v);
 
     template <typename S, typename T2, typename F2>
-    friend bool operator!=(const S &p, const swapped_t v);
+    friend bool operator!=(const S& p, const swapped_t v);
 
     template <typename S, typename T2, typename F2>
-    friend bool operator==(const S &p, const swapped_t v);
+    friend bool operator==(const S& p, const swapped_t v);
 };
 
-
 // Arithmetics
 template <typename S, typename T, typename F>
-S operator+(const S &i, const swap_struct_t<T, F> v) {
+S operator+(const S& i, const swap_struct_t<T, F> v) {
     return i + v.swap();
 }
 
 template <typename S, typename T, typename F>
-S operator-(const S &i, const swap_struct_t<T, F> v) {
+S operator-(const S& i, const swap_struct_t<T, F> v) {
     return i - v.swap();
 }
 
 template <typename S, typename T, typename F>
-S operator/(const S &i, const swap_struct_t<T, F> v) {
+S operator/(const S& i, const swap_struct_t<T, F> v) {
     return i / v.swap();
 }
 
 template <typename S, typename T, typename F>
-S operator*(const S &i, const swap_struct_t<T, F> v) {
+S operator*(const S& i, const swap_struct_t<T, F> v) {
     return i * v.swap();
 }
 
 template <typename S, typename T, typename F>
-S operator%(const S &i, const swap_struct_t<T, F> v) {
+S operator%(const S& i, const swap_struct_t<T, F> v) {
     return i % v.swap();
 }
 
 // Arithmetics + assignements
 template <typename S, typename T, typename F>
-S &operator+=(S &i, const swap_struct_t<T, F> v) {
+S& operator+=(S& i, const swap_struct_t<T, F> v) {
     i += v.swap();
     return i;
 }
 
 template <typename S, typename T, typename F>
-S &operator-=(S &i, const swap_struct_t<T, F> v) {
+S& operator-=(S& i, const swap_struct_t<T, F> v) {
     i -= v.swap();
     return i;
 }
 
 // Logical
 template <typename S, typename T, typename F>
-S operator&(const S &i, const swap_struct_t<T, F> v) {
+S operator&(const S& i, const swap_struct_t<T, F> v) {
     return i & v.swap();
 }
 
 template <typename S, typename T, typename F>
-S operator&(const swap_struct_t<T, F> v, const S &i) {
+S operator&(const swap_struct_t<T, F> v, const S& i) {
     return (S)(v.swap() & i);
 }
 
-
 // Comparaison
 template <typename S, typename T, typename F>
-bool operator<(const S &p, const swap_struct_t<T, F> v) {
+bool operator<(const S& p, const swap_struct_t<T, F> v) {
     return p < v.swap();
 }
 template <typename S, typename T, typename F>
-bool operator>(const S &p, const swap_struct_t<T, F> v) {
+bool operator>(const S& p, const swap_struct_t<T, F> v) {
     return p > v.swap();
 }
 template <typename S, typename T, typename F>
-bool operator<=(const S &p, const swap_struct_t<T, F> v) {
+bool operator<=(const S& p, const swap_struct_t<T, F> v) {
     return p <= v.swap();
 }
 template <typename S, typename T, typename F>
-bool operator>=(const S &p, const swap_struct_t<T, F> v) {
+bool operator>=(const S& p, const swap_struct_t<T, F> v) {
     return p >= v.swap();
 }
 template <typename S, typename T, typename F>
-bool operator!=(const S &p, const swap_struct_t<T, F> v) {
+bool operator!=(const S& p, const swap_struct_t<T, F> v) {
     return p != v.swap();
 }
 template <typename S, typename T, typename F>
-bool operator==(const S &p, const swap_struct_t<T, F> v) {
+bool operator==(const S& p, const swap_struct_t<T, F> v) {
     return p == v.swap();
 }
 
@@ -554,30 +605,30 @@ typedef s64 s64_le;
 typedef float float_le;
 typedef double double_le;
 
-typedef swap_struct_t<u64, swap_64_t<u64> > u64_be;
-typedef swap_struct_t<s64, swap_64_t<s64> > s64_be;
+typedef swap_struct_t<u64, swap_64_t<u64>> u64_be;
+typedef swap_struct_t<s64, swap_64_t<s64>> s64_be;
 
-typedef swap_struct_t<u32, swap_32_t<u32> > u32_be;
-typedef swap_struct_t<s32, swap_32_t<s32> > s32_be;
+typedef swap_struct_t<u32, swap_32_t<u32>> u32_be;
+typedef swap_struct_t<s32, swap_32_t<s32>> s32_be;
 
-typedef swap_struct_t<u16, swap_16_t<u16> > u16_be;
-typedef swap_struct_t<s16, swap_16_t<s16> > s16_be;
+typedef swap_struct_t<u16, swap_16_t<u16>> u16_be;
+typedef swap_struct_t<s16, swap_16_t<s16>> s16_be;
 
-typedef swap_struct_t<float, swap_float_t<float> > float_be;
-typedef swap_struct_t<double, swap_double_t<double> > double_be;
+typedef swap_struct_t<float, swap_float_t<float>> float_be;
+typedef swap_struct_t<double, swap_double_t<double>> double_be;
 #else
 
-typedef swap_struct_t<u64, swap_64_t<u64> > u64_le;
-typedef swap_struct_t<s64, swap_64_t<s64> > s64_le;
+typedef swap_struct_t<u64, swap_64_t<u64>> u64_le;
+typedef swap_struct_t<s64, swap_64_t<s64>> s64_le;
 
-typedef swap_struct_t<u32, swap_32_t<u32> > u32_le;
-typedef swap_struct_t<s32, swap_32_t<s32> > s32_le;
+typedef swap_struct_t<u32, swap_32_t<u32>> u32_le;
+typedef swap_struct_t<s32, swap_32_t<s32>> s32_le;
 
-typedef swap_struct_t<u16, swap_16_t<u16> > u16_le;
-typedef swap_struct_t< s16, swap_16_t<s16> > s16_le;
+typedef swap_struct_t<u16, swap_16_t<u16>> u16_le;
+typedef swap_struct_t<s16, swap_16_t<s16>> s16_le;
 
-typedef swap_struct_t<float, swap_float_t<float> > float_le;
-typedef swap_struct_t<double, swap_double_t<double> > double_le;
+typedef swap_struct_t<float, swap_float_t<float>> float_le;
+typedef swap_struct_t<double, swap_double_t<double>> double_le;
 
 typedef u32 u32_be;
 typedef u16 u16_be;
diff --git a/src/common/symbols.cpp b/src/common/symbols.cpp
index db8340043..c4d16af85 100644
--- a/src/common/symbols.cpp
+++ b/src/common/symbols.cpp
@@ -6,49 +6,41 @@
 
 TSymbolsMap g_symbols;
 
-namespace Symbols
-{
-    bool HasSymbol(u32 address)
-    {
-        return g_symbols.find(address) != g_symbols.end();
-    }
+namespace Symbols {
+bool HasSymbol(u32 address) {
+    return g_symbols.find(address) != g_symbols.end();
+}
+
+void Add(u32 address, const std::string& name, u32 size, u32 type) {
+    if (!HasSymbol(address)) {
+        TSymbol symbol;
+        symbol.address = address;
+        symbol.name = name;
+        symbol.size = size;
+        symbol.type = type;
 
-    void Add(u32 address, const std::string& name, u32 size, u32 type)
-    {
-        if (!HasSymbol(address))
-        {
-            TSymbol symbol;
-            symbol.address = address;
-            symbol.name = name;
-            symbol.size = size;
-            symbol.type = type;
-
-            g_symbols.emplace(address, symbol);
-        }
+        g_symbols.emplace(address, symbol);
     }
+}
 
-    TSymbol GetSymbol(u32 address)
-    {
-        const auto iter = g_symbols.find(address);
+TSymbol GetSymbol(u32 address) {
+    const auto iter = g_symbols.find(address);
 
-        if (iter != g_symbols.end())
-            return iter->second;
+    if (iter != g_symbols.end())
+        return iter->second;
 
-        return {};
-    }
+    return {};
+}
 
-    const std::string GetName(u32 address)
-    {
-        return GetSymbol(address).name;
-    }
+const std::string GetName(u32 address) {
+    return GetSymbol(address).name;
+}
 
-    void Remove(u32 address)
-    {
-        g_symbols.erase(address);
-    }
+void Remove(u32 address) {
+    g_symbols.erase(address);
+}
 
-    void Clear()
-    {
-        g_symbols.clear();
-    }
+void Clear() {
+    g_symbols.clear();
+}
 }
diff --git a/src/common/symbols.h b/src/common/symbols.h
index 5ed16009c..6044c9db6 100644
--- a/src/common/symbols.h
+++ b/src/common/symbols.h
@@ -10,25 +10,22 @@
 
 #include "common/common_types.h"
 
-struct TSymbol
-{
-    u32     address = 0;
+struct TSymbol {
+    u32 address = 0;
     std::string name;
-    u32     size = 0;
-    u32     type = 0;
+    u32 size = 0;
+    u32 type = 0;
 };
 
 typedef std::map<u32, TSymbol> TSymbolsMap;
 typedef std::pair<u32, TSymbol> TSymbolsPair;
 
-namespace Symbols
-{
-    bool HasSymbol(u32 address);
+namespace Symbols {
+bool HasSymbol(u32 address);
 
-    void Add(u32 address, const std::string& name, u32 size, u32 type);
-    TSymbol GetSymbol(u32 address);
-    const std::string GetName(u32 address);
-    void Remove(u32 address);
-    void Clear();
+void Add(u32 address, const std::string& name, u32 size, u32 type);
+TSymbol GetSymbol(u32 address);
+const std::string GetName(u32 address);
+void Remove(u32 address);
+void Clear();
 }
-
diff --git a/src/common/synchronized_wrapper.h b/src/common/synchronized_wrapper.h
index 07105a198..8dc4ddeac 100644
--- a/src/common/synchronized_wrapper.h
+++ b/src/common/synchronized_wrapper.h
@@ -12,14 +12,14 @@ namespace Common {
 /**
  * Wraps an object, only allowing access to it via a locking reference wrapper. Good to ensure no
  * one forgets to lock a mutex before acessing an object. To access the wrapped object construct a
- * SyncronizedRef on this wrapper. Inspired by Rust's Mutex type (http://doc.rust-lang.org/std/sync/struct.Mutex.html).
+ * SyncronizedRef on this wrapper. Inspired by Rust's Mutex type
+ * (http://doc.rust-lang.org/std/sync/struct.Mutex.html).
  */
 template <typename T>
 class SynchronizedWrapper {
 public:
     template <typename... Args>
-    SynchronizedWrapper(Args&&... args) :
-        data(std::forward<Args>(args)...) {
+    SynchronizedWrapper(Args&&... args) : data(std::forward<Args>(args)...) {
     }
 
 private:
@@ -58,11 +58,19 @@ public:
         return *this;
     }
 
-    T& operator*() { return wrapper->data; }
-    const T& operator*() const { return wrapper->data; }
+    T& operator*() {
+        return wrapper->data;
+    }
+    const T& operator*() const {
+        return wrapper->data;
+    }
 
-    T* operator->() { return &wrapper->data; }
-    const T* operator->() const { return &wrapper->data; }
+    T* operator->() {
+        return &wrapper->data;
+    }
+    const T* operator->() const {
+        return &wrapper->data;
+    }
 
 private:
     SynchronizedWrapper<T>* wrapper;
diff --git a/src/common/thread.cpp b/src/common/thread.cpp
index 7bbf080bc..bee607ce9 100644
--- a/src/common/thread.cpp
+++ b/src/common/thread.cpp
@@ -5,27 +5,25 @@
 #include "common/thread.h"
 
 #ifdef __APPLE__
-    #include <mach/mach.h>
+#include <mach/mach.h>
 #elif defined(_WIN32)
-    #include <Windows.h>
+#include <Windows.h>
 #else
-    #if defined(BSD4_4) || defined(__OpenBSD__)
-        #include <pthread_np.h>
-    #else
-        #include <pthread.h>
-    #endif
-    #include <sched.h>
+#if defined(BSD4_4) || defined(__OpenBSD__)
+#include <pthread_np.h>
+#else
+#include <pthread.h>
+#endif
+#include <sched.h>
 #endif
 
 #ifndef _WIN32
-    #include <unistd.h>
+#include <unistd.h>
 #endif
 
-namespace Common
-{
+namespace Common {
 
-int CurrentThreadId()
-{
+int CurrentThreadId() {
 #ifdef _MSC_VER
     return GetCurrentThreadId();
 #elif defined __APPLE__
@@ -37,26 +35,22 @@ int CurrentThreadId()
 
 #ifdef _WIN32
 // Supporting functions
-void SleepCurrentThread(int ms)
-{
+void SleepCurrentThread(int ms) {
     Sleep(ms);
 }
 #endif
 
 #ifdef _MSC_VER
 
-void SetThreadAffinity(std::thread::native_handle_type thread, u32 mask)
-{
+void SetThreadAffinity(std::thread::native_handle_type thread, u32 mask) {
     SetThreadAffinityMask(thread, mask);
 }
 
-void SetCurrentThreadAffinity(u32 mask)
-{
+void SetCurrentThreadAffinity(u32 mask) {
     SetThreadAffinityMask(GetCurrentThread(), mask);
 }
 
-void SwitchCurrentThread()
-{
+void SwitchCurrentThread() {
     SwitchToThread();
 }
 
@@ -66,40 +60,34 @@ void SwitchCurrentThread()
 
 // This is implemented much nicer in upcoming msvc++, see:
 // http://msdn.microsoft.com/en-us/library/xcb2z8hs(VS.100).aspx
-void SetCurrentThreadName(const char* szThreadName)
-{
+void SetCurrentThreadName(const char* szThreadName) {
     static const DWORD MS_VC_EXCEPTION = 0x406D1388;
 
-    #pragma pack(push,8)
-    struct THREADNAME_INFO
-    {
-        DWORD dwType; // must be 0x1000
-        LPCSTR szName; // pointer to name (in user addr space)
+#pragma pack(push, 8)
+    struct THREADNAME_INFO {
+        DWORD dwType;     // must be 0x1000
+        LPCSTR szName;    // pointer to name (in user addr space)
         DWORD dwThreadID; // thread ID (-1=caller thread)
-        DWORD dwFlags; // reserved for future use, must be zero
+        DWORD dwFlags;    // reserved for future use, must be zero
     } info;
-    #pragma pack(pop)
+#pragma pack(pop)
 
     info.dwType = 0x1000;
     info.szName = szThreadName;
-    info.dwThreadID = -1; //dwThreadID;
+    info.dwThreadID = -1; // dwThreadID;
     info.dwFlags = 0;
 
-    __try
-    {
-        RaiseException(MS_VC_EXCEPTION, 0, sizeof(info)/sizeof(ULONG_PTR), (ULONG_PTR*)&info);
+    __try {
+        RaiseException(MS_VC_EXCEPTION, 0, sizeof(info) / sizeof(ULONG_PTR), (ULONG_PTR*)&info);
+    } __except (EXCEPTION_CONTINUE_EXECUTION) {
     }
-    __except(EXCEPTION_CONTINUE_EXECUTION)
-    {}
 }
 
 #else // !MSVC_VER, so must be POSIX threads
 
-void SetThreadAffinity(std::thread::native_handle_type thread, u32 mask)
-{
+void SetThreadAffinity(std::thread::native_handle_type thread, u32 mask) {
 #ifdef __APPLE__
-    thread_policy_set(pthread_mach_thread_np(thread),
-        THREAD_AFFINITY_POLICY, (integer_t *)&mask, 1);
+    thread_policy_set(pthread_mach_thread_np(thread), THREAD_AFFINITY_POLICY, (integer_t*)&mask, 1);
 #elif (defined __linux__ || defined BSD4_4) && !(defined ANDROID)
     cpu_set_t cpu_set;
     CPU_ZERO(&cpu_set);
@@ -112,27 +100,23 @@ void SetThreadAffinity(std::thread::native_handle_type thread, u32 mask)
 #endif
 }
 
-void SetCurrentThreadAffinity(u32 mask)
-{
+void SetCurrentThreadAffinity(u32 mask) {
     SetThreadAffinity(pthread_self(), mask);
 }
 
 #ifndef _WIN32
-void SleepCurrentThread(int ms)
-{
+void SleepCurrentThread(int ms) {
     usleep(1000 * ms);
 }
 
-void SwitchCurrentThread()
-{
+void SwitchCurrentThread() {
     usleep(1000 * 1);
 }
 #endif
 
 // MinGW with the POSIX threading model does not support pthread_setname_np
 #if !defined(_WIN32) || defined(_MSC_VER)
-void SetCurrentThreadName(const char* szThreadName)
-{
+void SetCurrentThreadName(const char* szThreadName) {
 #ifdef __APPLE__
     pthread_setname_np(szThreadName);
 #elif defined(__OpenBSD__)
diff --git a/src/common/thread.h b/src/common/thread.h
index bbfa8befa..b189dc764 100644
--- a/src/common/thread.h
+++ b/src/common/thread.h
@@ -4,10 +4,10 @@
 
 #pragma once
 
-#include <cstddef>
-#include <thread>
 #include <condition_variable>
+#include <cstddef>
 #include <mutex>
+#include <thread>
 
 #include "common/common_types.h"
 
@@ -17,17 +17,17 @@
 // backwards compat support.
 // WARNING: This only works correctly with POD types.
 #if defined(__clang__)
-#   if !__has_feature(cxx_thread_local)
-#       define thread_local __thread
-#   endif
+#if !__has_feature(cxx_thread_local)
+#define thread_local __thread
+#endif
 #elif defined(__GNUC__)
-#   if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 8)
-#       define thread_local __thread
-#   endif
+#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 8)
+#define thread_local __thread
+#endif
 #elif defined(_MSC_VER)
-#   if _MSC_VER < 1900
-#       define thread_local __declspec(thread)
-#   endif
+#if _MSC_VER < 1900
+#define thread_local __declspec(thread)
+#endif
 #endif
 
 namespace Common {
@@ -39,7 +39,8 @@ void SetCurrentThreadAffinity(u32 mask);
 
 class Event {
 public:
-    Event() : is_set(false) {}
+    Event() : is_set(false) {
+    }
 
     void Set() {
         std::lock_guard<std::mutex> lk(mutex);
@@ -51,13 +52,14 @@ public:
 
     void Wait() {
         std::unique_lock<std::mutex> lk(mutex);
-        condvar.wait(lk, [&]{ return is_set; });
+        condvar.wait(lk, [&] { return is_set; });
         is_set = false;
     }
 
     void Reset() {
         std::unique_lock<std::mutex> lk(mutex);
-        // no other action required, since wait loops on the predicate and any lingering signal will get cleared on the first iteration
+        // no other action required, since wait loops on the predicate and any lingering signal will
+        // get cleared on the first iteration
         is_set = false;
     }
 
@@ -69,7 +71,8 @@ private:
 
 class Barrier {
 public:
-    explicit Barrier(size_t count_) : count(count_), waiting(0), generation(0) {}
+    explicit Barrier(size_t count_) : count(count_), waiting(0), generation(0) {
+    }
 
     /// Blocks until all "count" threads have called Sync()
     void Sync() {
@@ -81,7 +84,8 @@ public:
             waiting = 0;
             condvar.notify_all();
         } else {
-            condvar.wait(lk, [this, current_generation]{ return current_generation != generation; });
+            condvar.wait(lk,
+                         [this, current_generation] { return current_generation != generation; });
         }
     }
 
@@ -94,7 +98,7 @@ private:
 };
 
 void SleepCurrentThread(int ms);
-void SwitchCurrentThread();    // On Linux, this is equal to sleep 1ms
+void SwitchCurrentThread(); // On Linux, this is equal to sleep 1ms
 
 // Use this function during a spin-wait to make the current thread
 // relax while another thread is working. This may be more efficient
@@ -103,6 +107,6 @@ inline void YieldCPU() {
     std::this_thread::yield();
 }
 
-void SetCurrentThreadName(const char *name);
+void SetCurrentThreadName(const char* name);
 
 } // namespace Common
diff --git a/src/common/thread_queue_list.h b/src/common/thread_queue_list.h
index 12455d7c4..0dcf785b6 100644
--- a/src/common/thread_queue_list.h
+++ b/src/common/thread_queue_list.h
@@ -11,7 +11,7 @@
 
 namespace Common {
 
-template<class T, unsigned int N>
+template <class T, unsigned int N>
 struct ThreadQueueList {
     // TODO(yuriks): If performance proves to be a problem, the std::deques can be replaced with
     //               (dynamically resizable) circular buffers to remove their overhead when
@@ -39,7 +39,7 @@ struct ThreadQueueList {
     }
 
     T get_first() {
-        Queue *cur = first;
+        Queue* cur = first;
         while (cur != nullptr) {
             if (!cur->data.empty()) {
                 return cur->data.front();
@@ -51,7 +51,7 @@ struct ThreadQueueList {
     }
 
     T pop_first() {
-        Queue *cur = first;
+        Queue* cur = first;
         while (cur != nullptr) {
             if (!cur->data.empty()) {
                 auto tmp = std::move(cur->data.front());
@@ -65,8 +65,8 @@ struct ThreadQueueList {
     }
 
     T pop_first_better(Priority priority) {
-        Queue *cur = first;
-        Queue *stop = &queues[priority];
+        Queue* cur = first;
+        Queue* stop = &queues[priority];
         while (cur < stop) {
             if (!cur->data.empty()) {
                 auto tmp = std::move(cur->data.front());
@@ -80,12 +80,12 @@ struct ThreadQueueList {
     }
 
     void push_front(Priority priority, const T& thread_id) {
-        Queue *cur = &queues[priority];
+        Queue* cur = &queues[priority];
         cur->data.push_front(thread_id);
     }
 
     void push_back(Priority priority, const T& thread_id) {
-        Queue *cur = &queues[priority];
+        Queue* cur = &queues[priority];
         cur->data.push_back(thread_id);
     }
 
@@ -96,12 +96,12 @@ struct ThreadQueueList {
     }
 
     void remove(Priority priority, const T& thread_id) {
-        Queue *cur = &queues[priority];
+        Queue* cur = &queues[priority];
         boost::remove_erase(cur->data, thread_id);
     }
 
     void rotate(Priority priority) {
-        Queue *cur = &queues[priority];
+        Queue* cur = &queues[priority];
 
         if (cur->data.size() > 1) {
             cur->data.push_back(std::move(cur->data.front()));
@@ -115,7 +115,7 @@ struct ThreadQueueList {
     }
 
     bool empty(Priority priority) const {
-        const Queue *cur = &queues[priority];
+        const Queue* cur = &queues[priority];
         return cur->data.empty();
     }
 
@@ -139,7 +139,7 @@ private:
     }
 
     void link(Priority priority) {
-        Queue *cur = &queues[priority];
+        Queue* cur = &queues[priority];
 
         for (int i = priority - 1; i >= 0; --i) {
             if (queues[i].next_nonempty != UnlinkedTag()) {
diff --git a/src/common/timer.cpp b/src/common/timer.cpp
index b99835ac7..27560eb0b 100644
--- a/src/common/timer.cpp
+++ b/src/common/timer.cpp
@@ -16,11 +16,9 @@
 #include "common/string_util.h"
 #include "common/timer.h"
 
-namespace Common
-{
+namespace Common {
 
-u32 Timer::GetTimeMs()
-{
+u32 Timer::GetTimeMs() {
 #ifdef _WIN32
     return timeGetTime();
 #else
@@ -35,32 +33,27 @@ u32 Timer::GetTimeMs()
 // --------------------------------------------
 
 // Set initial values for the class
-Timer::Timer()
-    : m_LastTime(0), m_StartTime(0), m_Running(false)
-{
+Timer::Timer() : m_LastTime(0), m_StartTime(0), m_Running(false) {
     Update();
 }
 
 // Write the starting time
-void Timer::Start()
-{
+void Timer::Start() {
     m_StartTime = GetTimeMs();
     m_Running = true;
 }
 
 // Stop the timer
-void Timer::Stop()
-{
+void Timer::Stop() {
     // Write the final time
     m_LastTime = GetTimeMs();
     m_Running = false;
 }
 
 // Update the last time variable
-void Timer::Update()
-{
+void Timer::Update() {
     m_LastTime = GetTimeMs();
-    //TODO(ector) - QPF
+    // TODO(ector) - QPF
 }
 
 // -------------------------------------
@@ -68,34 +61,32 @@ void Timer::Update()
 // -------------------------------------
 
 // Get the number of milliseconds since the last Update()
-u64 Timer::GetTimeDifference()
-{
+u64 Timer::GetTimeDifference() {
     return GetTimeMs() - m_LastTime;
 }
 
 // Add the time difference since the last Update() to the starting time.
 // This is used to compensate for a paused game.
-void Timer::AddTimeDifference()
-{
+void Timer::AddTimeDifference() {
     m_StartTime += GetTimeDifference();
 }
 
 // Get the time elapsed since the Start()
-u64 Timer::GetTimeElapsed()
-{
+u64 Timer::GetTimeElapsed() {
     // If we have not started yet, return 1 (because then I don't
     // have to change the FPS calculation in CoreRerecording.cpp .
-    if (m_StartTime == 0) return 1;
+    if (m_StartTime == 0)
+        return 1;
 
     // Return the final timer time if the timer is stopped
-    if (!m_Running) return (m_LastTime - m_StartTime);
+    if (!m_Running)
+        return (m_LastTime - m_StartTime);
 
     return (GetTimeMs() - m_StartTime);
 }
 
 // Get the formatted time elapsed since the Start()
-std::string Timer::GetTimeElapsedFormatted() const
-{
+std::string Timer::GetTimeElapsedFormatted() const {
     // If we have not started yet, return zero
     if (m_StartTime == 0)
         return "00:00:00:000";
@@ -114,50 +105,46 @@ std::string Timer::GetTimeElapsedFormatted() const
     // Hours
     u32 Hours = Minutes / 60;
 
-    std::string TmpStr = StringFromFormat("%02i:%02i:%02i:%03i",
-        Hours, Minutes % 60, Seconds % 60, Milliseconds % 1000);
+    std::string TmpStr = StringFromFormat("%02i:%02i:%02i:%03i", Hours, Minutes % 60, Seconds % 60,
+                                          Milliseconds % 1000);
     return TmpStr;
 }
 
 // Get current time
-void Timer::IncreaseResolution()
-{
+void Timer::IncreaseResolution() {
 #ifdef _WIN32
     timeBeginPeriod(1);
 #endif
 }
 
-void Timer::RestoreResolution()
-{
+void Timer::RestoreResolution() {
 #ifdef _WIN32
     timeEndPeriod(1);
 #endif
 }
 
 // Get the number of seconds since January 1 1970
-u64 Timer::GetTimeSinceJan1970()
-{
+u64 Timer::GetTimeSinceJan1970() {
     time_t ltime;
     time(&ltime);
-    return((u64)ltime);
+    return ((u64)ltime);
 }
 
-u64 Timer::GetLocalTimeSinceJan1970()
-{
+u64 Timer::GetLocalTimeSinceJan1970() {
     time_t sysTime, tzDiff, tzDST;
-    struct tm * gmTime;
+    struct tm* gmTime;
 
     time(&sysTime);
 
     // Account for DST where needed
     gmTime = localtime(&sysTime);
-    if(gmTime->tm_isdst == 1)
+    if (gmTime->tm_isdst == 1)
         tzDST = 3600;
     else
         tzDST = 0;
 
     // Lazy way to get local time in sec
-    gmTime    = gmtime(&sysTime);
+    gmTime = gmtime(&sysTime);
     tzDiff = sysTime - mktime(gmTime);
 
     return (u64)(sysTime + tzDiff + tzDST);
@@ -165,10 +152,9 @@ u64 Timer::GetLocalTimeSinceJan1970()
 
 // Return the current time formatted as Minutes:Seconds:Milliseconds
 // in the form 00:00:000.
-std::string Timer::GetTimeFormatted()
-{
+std::string Timer::GetTimeFormatted() {
     time_t sysTime;
-    struct tm * gmTime;
+    struct tm* gmTime;
     char tmp[13];
 
     time(&sysTime);
@@ -176,7 +162,7 @@ std::string Timer::GetTimeFormatted()
 
     strftime(tmp, 6, "%M:%S", gmTime);
 
-    // Now tack on the milliseconds
+// Now tack on the milliseconds
 #ifdef _WIN32
     struct timeb tp;
     (void)::ftime(&tp);
@@ -190,8 +176,7 @@ std::string Timer::GetTimeFormatted()
 
 // Returns a timestamp with decimals for precise time comparisons
 // ----------------
-double Timer::GetDoubleTime()
-{
+double Timer::GetDoubleTime() {
 #ifdef _WIN32
     struct timeb tp;
     (void)::ftime(&tp);
diff --git a/src/common/timer.h b/src/common/timer.h
index b5f0f2585..78d37426b 100644
--- a/src/common/timer.h
+++ b/src/common/timer.h
@@ -4,13 +4,11 @@
 
 #pragma once
 
-#include "common/common_types.h"
 #include <string>
+#include "common/common_types.h"
 
-namespace Common
-{
-class Timer
-{
+namespace Common {
+class Timer {
 public:
     Timer();
 
@@ -18,7 +16,8 @@ public:
     void Stop();
     void Update();
 
-    // The time difference is always returned in milliseconds, regardless of alternative internal representation
+    // The time difference is always returned in milliseconds, regardless of alternative internal
+    // representation
     u64 GetTimeDifference();
     void AddTimeDifference();
 
diff --git a/src/common/vector_math.h b/src/common/vector_math.h
index cfb9481b6..b2d630829 100644
--- a/src/common/vector_math.h
+++ b/src/common/vector_math.h
@@ -1,7 +1,6 @@
 // Licensed under GPLv2 or any later version
 // Refer to the license.txt file included.
 
-
 // Copyright 2014 Tony Wasserka
 // All rights reserved.
 //
@@ -36,158 +35,178 @@
 
 namespace Math {
 
-template<typename T> class Vec2;
-template<typename T> class Vec3;
-template<typename T> class Vec4;
+template <typename T>
+class Vec2;
+template <typename T>
+class Vec3;
+template <typename T>
+class Vec4;
 
-template<typename T>
+template <typename T>
 static inline Vec2<T> MakeVec(const T& x, const T& y);
-template<typename T>
+template <typename T>
 static inline Vec3<T> MakeVec(const T& x, const T& y, const T& z);
-template<typename T>
+template <typename T>
 static inline Vec4<T> MakeVec(const T& x, const T& y, const T& z, const T& w);
 
-
-template<typename T>
+template <typename T>
 class Vec2 {
 public:
     T x;
     T y;
 
-    T* AsArray() { return &x; }
+    T* AsArray() {
+        return &x;
+    }
 
     Vec2() = default;
-    Vec2(const T a[2]) : x(a[0]), y(a[1]) {}
-    Vec2(const T& _x, const T& _y) : x(_x), y(_y) {}
+    Vec2(const T a[2]) : x(a[0]), y(a[1]) {
+    }
+    Vec2(const T& _x, const T& _y) : x(_x), y(_y) {
+    }
 
-    template<typename T2>
+    template <typename T2>
     Vec2<T2> Cast() const {
         return Vec2<T2>((T2)x, (T2)y);
     }
 
-    static Vec2 AssignToAll(const T& f)
-    {
+    static Vec2 AssignToAll(const T& f) {
         return Vec2<T>(f, f);
     }
 
-    void Write(T a[2])
-    {
-        a[0] = x; a[1] = y;
+    void Write(T a[2]) {
+        a[0] = x;
+        a[1] = y;
     }
 
-    Vec2<decltype(T{}+T{})> operator +(const Vec2& other) const
-    {
-        return MakeVec(x+other.x, y+other.y);
+    Vec2<decltype(T{} + T{})> operator+(const Vec2& other) const {
+        return MakeVec(x + other.x, y + other.y);
     }
-    void operator += (const Vec2 &other)
-    {
-        x+=other.x; y+=other.y;
+    void operator+=(const Vec2& other) {
+        x += other.x;
+        y += other.y;
     }
-    Vec2<decltype(T{}-T{})> operator -(const Vec2& other) const
-    {
-        return MakeVec(x-other.x, y-other.y);
+    Vec2<decltype(T{} - T{})> operator-(const Vec2& other) const {
+        return MakeVec(x - other.x, y - other.y);
     }
-    void operator -= (const Vec2& other)
-    {
-        x-=other.x; y-=other.y;
+    void operator-=(const Vec2& other) {
+        x -= other.x;
+        y -= other.y;
     }
-    template<typename Q = T,class = typename std::enable_if<std::is_signed<Q>::value>::type>
-    Vec2<decltype(-T{})> operator -() const
-    {
-        return MakeVec(-x,-y);
+    template <typename Q = T, class = typename std::enable_if<std::is_signed<Q>::value>::type>
+    Vec2<decltype(-T{})> operator-() const {
+        return MakeVec(-x, -y);
     }
-    Vec2<decltype(T{}*T{})> operator * (const Vec2& other) const
-    {
-        return MakeVec(x*other.x, y*other.y);
+    Vec2<decltype(T{} * T{})> operator*(const Vec2& other) const {
+        return MakeVec(x * other.x, y * other.y);
     }
-    template<typename V>
-    Vec2<decltype(T{}*V{})> operator * (const V& f) const
-    {
-        return MakeVec(x*f,y*f);
+    template <typename V>
+    Vec2<decltype(T{} * V{})> operator*(const V& f) const {
+        return MakeVec(x * f, y * f);
     }
-    template<typename V>
-    void operator *= (const V& f)
-    {
-        x*=f; y*=f;
+    template <typename V>
+    void operator*=(const V& f) {
+        x *= f;
+        y *= f;
     }
-    template<typename V>
-    Vec2<decltype(T{}/V{})> operator / (const V& f) const
-    {
-        return MakeVec(x/f,y/f);
+    template <typename V>
+    Vec2<decltype(T{} / V{})> operator/(const V& f) const {
+        return MakeVec(x / f, y / f);
     }
-    template<typename V>
-    void operator /= (const V& f)
-    {
+    template <typename V>
+    void operator/=(const V& f) {
         *this = *this / f;
     }
 
-    T Length2() const
-    {
-        return x*x + y*y;
+    T Length2() const {
+        return x * x + y * y;
     }
 
     // Only implemented for T=float
     float Length() const;
     void SetLength(const float l);
     Vec2 WithLength(const float l) const;
-    float Distance2To(Vec2 &other);
+    float Distance2To(Vec2& other);
     Vec2 Normalized() const;
     float Normalize(); // returns the previous length, which is often useful
 
-    T& operator [] (int i) //allow vector[1] = 3   (vector.y=3)
+    T& operator[](int i) // allow vector[1] = 3   (vector.y=3)
     {
         return *((&x) + i);
     }
-    T operator [] (const int i) const
-    {
+    T operator[](const int i) const {
         return *((&x) + i);
     }
 
-    void SetZero()
-    {
-        x=0; y=0;
+    void SetZero() {
+        x = 0;
+        y = 0;
     }
 
     // Common aliases: UV (texel coordinates), ST (texture coordinates)
-    T& u() { return x; }
-    T& v() { return y; }
-    T& s() { return x; }
-    T& t() { return y; }
+    T& u() {
+        return x;
+    }
+    T& v() {
+        return y;
+    }
+    T& s() {
+        return x;
+    }
+    T& t() {
+        return y;
+    }
 
-    const T& u() const { return x; }
-    const T& v() const { return y; }
-    const T& s() const { return x; }
-    const T& t() const { return y; }
+    const T& u() const {
+        return x;
+    }
+    const T& v() const {
+        return y;
+    }
+    const T& s() const {
+        return x;
+    }
+    const T& t() const {
+        return y;
+    }
 
     // swizzlers - create a subvector of specific components
-    const Vec2 yx() const { return Vec2(y, x); }
-    const Vec2 vu() const { return Vec2(y, x); }
-    const Vec2 ts() const { return Vec2(y, x); }
+    const Vec2 yx() const {
+        return Vec2(y, x);
+    }
+    const Vec2 vu() const {
+        return Vec2(y, x);
+    }
+    const Vec2 ts() const {
+        return Vec2(y, x);
+    }
 };
 
-template<typename T, typename V>
-Vec2<T> operator * (const V& f, const Vec2<T>& vec)
-{
-    return Vec2<T>(f*vec.x,f*vec.y);
+template <typename T, typename V>
+Vec2<T> operator*(const V& f, const Vec2<T>& vec) {
+    return Vec2<T>(f * vec.x, f * vec.y);
 }
 
 typedef Vec2<float> Vec2f;
 
-template<typename T>
-class Vec3
-{
+template <typename T>
+class Vec3 {
 public:
     T x;
     T y;
     T z;
 
-    T* AsArray() { return &x; }
+    T* AsArray() {
+        return &x;
+    }
 
     Vec3() = default;
-    Vec3(const T a[3]) : x(a[0]), y(a[1]), z(a[2]) {}
-    Vec3(const T& _x, const T& _y, const T& _z) : x(_x), y(_y), z(_z) {}
+    Vec3(const T a[3]) : x(a[0]), y(a[1]), z(a[2]) {
+    }
+    Vec3(const T& _x, const T& _y, const T& _z) : x(_x), y(_y), z(_z) {
+    }
 
-    template<typename T2>
+    template <typename T2>
     Vec3<T2> Cast() const {
         return MakeVec<T2>((T2)x, (T2)y, (T2)z);
     }
@@ -196,126 +215,161 @@ public:
     static Vec3 FromRGB(unsigned int rgb);
     unsigned int ToRGB() const; // alpha bits set to zero
 
-    static Vec3 AssignToAll(const T& f)
-    {
+    static Vec3 AssignToAll(const T& f) {
         return MakeVec(f, f, f);
     }
 
-    void Write(T a[3])
-    {
-        a[0] = x; a[1] = y; a[2] = z;
+    void Write(T a[3]) {
+        a[0] = x;
+        a[1] = y;
+        a[2] = z;
     }
 
-    Vec3<decltype(T{}+T{})> operator +(const Vec3 &other) const
-    {
-        return MakeVec(x+other.x, y+other.y, z+other.z);
+    Vec3<decltype(T{} + T{})> operator+(const Vec3& other) const {
+        return MakeVec(x + other.x, y + other.y, z + other.z);
     }
-    void operator += (const Vec3 &other)
-    {
-        x+=other.x; y+=other.y; z+=other.z;
+    void operator+=(const Vec3& other) {
+        x += other.x;
+        y += other.y;
+        z += other.z;
     }
-    Vec3<decltype(T{}-T{})> operator -(const Vec3 &other) const
-    {
-        return MakeVec(x-other.x, y-other.y, z-other.z);
+    Vec3<decltype(T{} - T{})> operator-(const Vec3& other) const {
+        return MakeVec(x - other.x, y - other.y, z - other.z);
     }
-    void operator -= (const Vec3 &other)
-    {
-        x-=other.x; y-=other.y; z-=other.z;
+    void operator-=(const Vec3& other) {
+        x -= other.x;
+        y -= other.y;
+        z -= other.z;
     }
-    template<typename Q = T,class = typename std::enable_if<std::is_signed<Q>::value>::type>
-    Vec3<decltype(-T{})> operator -() const
-    {
-        return MakeVec(-x,-y,-z);
+    template <typename Q = T, class = typename std::enable_if<std::is_signed<Q>::value>::type>
+    Vec3<decltype(-T{})> operator-() const {
+        return MakeVec(-x, -y, -z);
     }
-    Vec3<decltype(T{}*T{})> operator * (const Vec3 &other) const
-    {
-        return MakeVec(x*other.x, y*other.y, z*other.z);
+    Vec3<decltype(T{} * T{})> operator*(const Vec3& other) const {
+        return MakeVec(x * other.x, y * other.y, z * other.z);
     }
-    template<typename V>
-    Vec3<decltype(T{}*V{})> operator * (const V& f) const
-    {
-        return MakeVec(x*f,y*f,z*f);
+    template <typename V>
+    Vec3<decltype(T{} * V{})> operator*(const V& f) const {
+        return MakeVec(x * f, y * f, z * f);
     }
-    template<typename V>
-    void operator *= (const V& f)
-    {
-        x*=f; y*=f; z*=f;
+    template <typename V>
+    void operator*=(const V& f) {
+        x *= f;
+        y *= f;
+        z *= f;
     }
-    template<typename V>
-    Vec3<decltype(T{}/V{})> operator / (const V& f) const
-    {
-        return MakeVec(x/f,y/f,z/f);
+    template <typename V>
+    Vec3<decltype(T{} / V{})> operator/(const V& f) const {
+        return MakeVec(x / f, y / f, z / f);
     }
-    template<typename V>
-    void operator /= (const V& f)
-    {
+    template <typename V>
+    void operator/=(const V& f) {
         *this = *this / f;
     }
 
-    T Length2() const
-    {
-        return x*x + y*y + z*z;
+    T Length2() const {
+        return x * x + y * y + z * z;
     }
 
     // Only implemented for T=float
     float Length() const;
     void SetLength(const float l);
     Vec3 WithLength(const float l) const;
-    float Distance2To(Vec3 &other);
+    float Distance2To(Vec3& other);
     Vec3 Normalized() const;
     float Normalize(); // returns the previous length, which is often useful
 
-    T& operator [] (int i) //allow vector[2] = 3   (vector.z=3)
+    T& operator[](int i) // allow vector[2] = 3   (vector.z=3)
     {
         return *((&x) + i);
     }
-    T operator [] (const int i) const
-    {
+    T operator[](const int i) const {
         return *((&x) + i);
     }
 
-    void SetZero()
-    {
-        x=0; y=0; z=0;
+    void SetZero() {
+        x = 0;
+        y = 0;
+        z = 0;
     }
 
     // Common aliases: UVW (texel coordinates), RGB (colors), STQ (texture coordinates)
-    T& u() { return x; }
-    T& v() { return y; }
-    T& w() { return z; }
+    T& u() {
+        return x;
+    }
+    T& v() {
+        return y;
+    }
+    T& w() {
+        return z;
+    }
 
-    T& r() { return x; }
-    T& g() { return y; }
-    T& b() { return z; }
+    T& r() {
+        return x;
+    }
+    T& g() {
+        return y;
+    }
+    T& b() {
+        return z;
+    }
 
-    T& s() { return x; }
-    T& t() { return y; }
-    T& q() { return z; }
+    T& s() {
+        return x;
+    }
+    T& t() {
+        return y;
+    }
+    T& q() {
+        return z;
+    }
 
-    const T& u() const { return x; }
-    const T& v() const { return y; }
-    const T& w() const { return z; }
+    const T& u() const {
+        return x;
+    }
+    const T& v() const {
+        return y;
+    }
+    const T& w() const {
+        return z;
+    }
 
-    const T& r() const { return x; }
-    const T& g() const { return y; }
-    const T& b() const { return z; }
+    const T& r() const {
+        return x;
+    }
+    const T& g() const {
+        return y;
+    }
+    const T& b() const {
+        return z;
+    }
 
-    const T& s() const { return x; }
-    const T& t() const { return y; }
-    const T& q() const { return z; }
+    const T& s() const {
+        return x;
+    }
+    const T& t() const {
+        return y;
+    }
+    const T& q() const {
+        return z;
+    }
 
-    // swizzlers - create a subvector of specific components
-    // e.g. Vec2 uv() { return Vec2(x,y); }
-    // _DEFINE_SWIZZLER2 defines a single such function, DEFINE_SWIZZLER2 defines all of them for all component names (x<->r) and permutations (xy<->yx)
-#define _DEFINE_SWIZZLER2(a, b, name) const Vec2<T> name() const { return Vec2<T>(a, b); }
-#define DEFINE_SWIZZLER2(a, b, a2, b2, a3, b3, a4, b4) \
-    _DEFINE_SWIZZLER2(a, b, a##b); \
-    _DEFINE_SWIZZLER2(a, b, a2##b2); \
-    _DEFINE_SWIZZLER2(a, b, a3##b3); \
-    _DEFINE_SWIZZLER2(a, b, a4##b4); \
-    _DEFINE_SWIZZLER2(b, a, b##a); \
-    _DEFINE_SWIZZLER2(b, a, b2##a2); \
-    _DEFINE_SWIZZLER2(b, a, b3##a3); \
+// swizzlers - create a subvector of specific components
+// e.g. Vec2 uv() { return Vec2(x,y); }
+// _DEFINE_SWIZZLER2 defines a single such function, DEFINE_SWIZZLER2 defines all of them for all
+// component names (x<->r) and permutations (xy<->yx)
+#define _DEFINE_SWIZZLER2(a, b, name)                                                              \
+    const Vec2<T> name() const {                                                                   \
+        return Vec2<T>(a, b);                                                                      \
+    }
+#define DEFINE_SWIZZLER2(a, b, a2, b2, a3, b3, a4, b4)                                             \
+    _DEFINE_SWIZZLER2(a, b, a##b);                                                                 \
+    _DEFINE_SWIZZLER2(a, b, a2##b2);                                                               \
+    _DEFINE_SWIZZLER2(a, b, a3##b3);                                                               \
+    _DEFINE_SWIZZLER2(a, b, a4##b4);                                                               \
+    _DEFINE_SWIZZLER2(b, a, b##a);                                                                 \
+    _DEFINE_SWIZZLER2(b, a, b2##a2);                                                               \
+    _DEFINE_SWIZZLER2(b, a, b3##a3);                                                               \
     _DEFINE_SWIZZLER2(b, a, b4##a4)
 
     DEFINE_SWIZZLER2(x, y, r, g, u, v, s, t);
@@ -325,41 +379,42 @@ public:
 #undef _DEFINE_SWIZZLER2
 };
 
-template<typename T, typename V>
-Vec3<T> operator * (const V& f, const Vec3<T>& vec)
-{
-    return Vec3<T>(f*vec.x,f*vec.y,f*vec.z);
+template <typename T, typename V>
+Vec3<T> operator*(const V& f, const Vec3<T>& vec) {
+    return Vec3<T>(f * vec.x, f * vec.y, f * vec.z);
 }
 
-template<>
+template <>
 inline float Vec3<float>::Length() const {
     return std::sqrt(x * x + y * y + z * z);
 }
 
-template<>
+template <>
 inline Vec3<float> Vec3<float>::Normalized() const {
     return *this / Length();
 }
 
-
 typedef Vec3<float> Vec3f;
 
-template<typename T>
-class Vec4
-{
+template <typename T>
+class Vec4 {
 public:
     T x;
     T y;
     T z;
     T w;
 
-    T* AsArray() { return &x; }
+    T* AsArray() {
+        return &x;
+    }
 
     Vec4() = default;
-    Vec4(const T a[4]) : x(a[0]), y(a[1]), z(a[2]), w(a[3]) {}
-    Vec4(const T& _x, const T& _y, const T& _z, const T& _w) : x(_x), y(_y), z(_z), w(_w) {}
+    Vec4(const T a[4]) : x(a[0]), y(a[1]), z(a[2]), w(a[3]) {
+    }
+    Vec4(const T& _x, const T& _y, const T& _z, const T& _w) : x(_x), y(_y), z(_z), w(_w) {
+    }
 
-    template<typename T2>
+    template <typename T2>
     Vec4<T2> Cast() const {
         return Vec4<T2>((T2)x, (T2)y, (T2)z, (T2)w);
     }
@@ -372,81 +427,79 @@ public:
         return Vec4<T>(f, f, f, f);
     }
 
-    void Write(T a[4])
-    {
-        a[0] = x; a[1] = y; a[2] = z; a[3] = w;
+    void Write(T a[4]) {
+        a[0] = x;
+        a[1] = y;
+        a[2] = z;
+        a[3] = w;
     }
 
-    Vec4<decltype(T{}+T{})> operator +(const Vec4& other) const
-    {
-        return MakeVec(x+other.x, y+other.y, z+other.z, w+other.w);
+    Vec4<decltype(T{} + T{})> operator+(const Vec4& other) const {
+        return MakeVec(x + other.x, y + other.y, z + other.z, w + other.w);
     }
-    void operator += (const Vec4& other)
-    {
-        x+=other.x; y+=other.y; z+=other.z; w+=other.w;
+    void operator+=(const Vec4& other) {
+        x += other.x;
+        y += other.y;
+        z += other.z;
+        w += other.w;
     }
-    Vec4<decltype(T{}-T{})> operator -(const Vec4 &other) const
-    {
-        return MakeVec(x-other.x, y-other.y, z-other.z, w-other.w);
+    Vec4<decltype(T{} - T{})> operator-(const Vec4& other) const {
+        return MakeVec(x - other.x, y - other.y, z - other.z, w - other.w);
     }
-    void operator -= (const Vec4 &other)
-    {
-        x-=other.x; y-=other.y; z-=other.z; w-=other.w;
+    void operator-=(const Vec4& other) {
+        x -= other.x;
+        y -= other.y;
+        z -= other.z;
+        w -= other.w;
     }
-    template<typename Q = T,class = typename std::enable_if<std::is_signed<Q>::value>::type>
-    Vec4<decltype(-T{})> operator -() const
-    {
-        return MakeVec(-x,-y,-z,-w);
+    template <typename Q = T, class = typename std::enable_if<std::is_signed<Q>::value>::type>
+    Vec4<decltype(-T{})> operator-() const {
+        return MakeVec(-x, -y, -z, -w);
     }
-    Vec4<decltype(T{}*T{})> operator * (const Vec4 &other) const
-    {
-        return MakeVec(x*other.x, y*other.y, z*other.z, w*other.w);
+    Vec4<decltype(T{} * T{})> operator*(const Vec4& other) const {
+        return MakeVec(x * other.x, y * other.y, z * other.z, w * other.w);
     }
-    template<typename V>
-    Vec4<decltype(T{}*V{})> operator * (const V& f) const
-    {
-        return MakeVec(x*f,y*f,z*f,w*f);
+    template <typename V>
+    Vec4<decltype(T{} * V{})> operator*(const V& f) const {
+        return MakeVec(x * f, y * f, z * f, w * f);
     }
-    template<typename V>
-    void operator *= (const V& f)
-    {
-        x*=f; y*=f; z*=f; w*=f;
+    template <typename V>
+    void operator*=(const V& f) {
+        x *= f;
+        y *= f;
+        z *= f;
+        w *= f;
     }
-    template<typename V>
-    Vec4<decltype(T{}/V{})> operator / (const V& f) const
-    {
-        return MakeVec(x/f,y/f,z/f,w/f);
+    template <typename V>
+    Vec4<decltype(T{} / V{})> operator/(const V& f) const {
+        return MakeVec(x / f, y / f, z / f, w / f);
     }
-    template<typename V>
-    void operator /= (const V& f)
-    {
+    template <typename V>
+    void operator/=(const V& f) {
         *this = *this / f;
     }
 
-    T Length2() const
-    {
-        return x*x + y*y + z*z + w*w;
+    T Length2() const {
+        return x * x + y * y + z * z + w * w;
     }
 
     // Only implemented for T=float
     float Length() const;
     void SetLength(const float l);
     Vec4 WithLength(const float l) const;
-    float Distance2To(Vec4 &other);
+    float Distance2To(Vec4& other);
     Vec4 Normalized() const;
     float Normalize(); // returns the previous length, which is often useful
 
-    T& operator [] (int i) //allow vector[2] = 3   (vector.z=3)
+    T& operator[](int i) // allow vector[2] = 3   (vector.z=3)
     {
         return *((&x) + i);
     }
-    T operator [] (const int i) const
-    {
+    T operator[](const int i) const {
         return *((&x) + i);
     }
 
-    void SetZero()
-    {
+    void SetZero() {
         x = 0;
         y = 0;
         z = 0;
@@ -454,30 +507,50 @@ public:
     }
 
     // Common alias: RGBA (colors)
-    T& r() { return x; }
-    T& g() { return y; }
-    T& b() { return z; }
-    T& a() { return w; }
-
-    const T& r() const { return x; }
-    const T& g() const { return y; }
-    const T& b() const { return z; }
-    const T& a() const { return w; }
-
-    // Swizzlers - Create a subvector of specific components
-    // e.g. Vec2 uv() { return Vec2(x,y); }
-
-    // _DEFINE_SWIZZLER2 defines a single such function
-    // DEFINE_SWIZZLER2_COMP1 defines one-component functions for all component names (x<->r)
-    // DEFINE_SWIZZLER2_COMP2 defines two component functions for all component names (x<->r) and permutations (xy<->yx)
-#define _DEFINE_SWIZZLER2(a, b, name) const Vec2<T> name() const { return Vec2<T>(a, b); }
-#define DEFINE_SWIZZLER2_COMP1(a, a2) \
-    _DEFINE_SWIZZLER2(a, a, a##a); \
+    T& r() {
+        return x;
+    }
+    T& g() {
+        return y;
+    }
+    T& b() {
+        return z;
+    }
+    T& a() {
+        return w;
+    }
+
+    const T& r() const {
+        return x;
+    }
+    const T& g() const {
+        return y;
+    }
+    const T& b() const {
+        return z;
+    }
+    const T& a() const {
+        return w;
+    }
+
+// Swizzlers - Create a subvector of specific components
+// e.g. Vec2 uv() { return Vec2(x,y); }
+
+// _DEFINE_SWIZZLER2 defines a single such function
+// DEFINE_SWIZZLER2_COMP1 defines one-component functions for all component names (x<->r)
+// DEFINE_SWIZZLER2_COMP2 defines two component functions for all component names (x<->r) and
+// permutations (xy<->yx)
+#define _DEFINE_SWIZZLER2(a, b, name)                                                              \
+    const Vec2<T> name() const {                                                                   \
+        return Vec2<T>(a, b);                                                                      \
+    }
+#define DEFINE_SWIZZLER2_COMP1(a, a2)                                                              \
+    _DEFINE_SWIZZLER2(a, a, a##a);                                                                 \
     _DEFINE_SWIZZLER2(a, a, a2##a2)
-#define DEFINE_SWIZZLER2_COMP2(a, b, a2, b2) \
-    _DEFINE_SWIZZLER2(a, b, a##b); \
-    _DEFINE_SWIZZLER2(a, b, a2##b2); \
-    _DEFINE_SWIZZLER2(b, a, b##a); \
+#define DEFINE_SWIZZLER2_COMP2(a, b, a2, b2)                                                       \
+    _DEFINE_SWIZZLER2(a, b, a##b);                                                                 \
+    _DEFINE_SWIZZLER2(a, b, a2##b2);                                                               \
+    _DEFINE_SWIZZLER2(b, a, b##a);                                                                 \
     _DEFINE_SWIZZLER2(b, a, b2##a2)
 
     DEFINE_SWIZZLER2_COMP2(x, y, r, g);
@@ -494,22 +567,25 @@ public:
 #undef DEFINE_SWIZZLER2_COMP2
 #undef _DEFINE_SWIZZLER2
 
-#define _DEFINE_SWIZZLER3(a, b, c, name) const Vec3<T> name() const { return Vec3<T>(a, b, c); }
-#define DEFINE_SWIZZLER3_COMP1(a, a2) \
-    _DEFINE_SWIZZLER3(a, a, a, a##a##a); \
+#define _DEFINE_SWIZZLER3(a, b, c, name)                                                           \
+    const Vec3<T> name() const {                                                                   \
+        return Vec3<T>(a, b, c);                                                                   \
+    }
+#define DEFINE_SWIZZLER3_COMP1(a, a2)                                                              \
+    _DEFINE_SWIZZLER3(a, a, a, a##a##a);                                                           \
     _DEFINE_SWIZZLER3(a, a, a, a2##a2##a2)
-#define DEFINE_SWIZZLER3_COMP3(a, b, c, a2, b2, c2) \
-    _DEFINE_SWIZZLER3(a, b, c, a##b##c); \
-    _DEFINE_SWIZZLER3(a, c, b, a##c##b); \
-    _DEFINE_SWIZZLER3(b, a, c, b##a##c); \
-    _DEFINE_SWIZZLER3(b, c, a, b##c##a); \
-    _DEFINE_SWIZZLER3(c, a, b, c##a##b); \
-    _DEFINE_SWIZZLER3(c, b, a, c##b##a); \
-    _DEFINE_SWIZZLER3(a, b, c, a2##b2##c2); \
-    _DEFINE_SWIZZLER3(a, c, b, a2##c2##b2); \
-    _DEFINE_SWIZZLER3(b, a, c, b2##a2##c2); \
-    _DEFINE_SWIZZLER3(b, c, a, b2##c2##a2); \
-    _DEFINE_SWIZZLER3(c, a, b, c2##a2##b2); \
+#define DEFINE_SWIZZLER3_COMP3(a, b, c, a2, b2, c2)                                                \
+    _DEFINE_SWIZZLER3(a, b, c, a##b##c);                                                           \
+    _DEFINE_SWIZZLER3(a, c, b, a##c##b);                                                           \
+    _DEFINE_SWIZZLER3(b, a, c, b##a##c);                                                           \
+    _DEFINE_SWIZZLER3(b, c, a, b##c##a);                                                           \
+    _DEFINE_SWIZZLER3(c, a, b, c##a##b);                                                           \
+    _DEFINE_SWIZZLER3(c, b, a, c##b##a);                                                           \
+    _DEFINE_SWIZZLER3(a, b, c, a2##b2##c2);                                                        \
+    _DEFINE_SWIZZLER3(a, c, b, a2##c2##b2);                                                        \
+    _DEFINE_SWIZZLER3(b, a, c, b2##a2##c2);                                                        \
+    _DEFINE_SWIZZLER3(b, c, a, b2##c2##a2);                                                        \
+    _DEFINE_SWIZZLER3(c, a, b, c2##a2##b2);                                                        \
     _DEFINE_SWIZZLER3(c, b, a, c2##b2##a2)
 
     DEFINE_SWIZZLER3_COMP3(x, y, z, r, g, b);
@@ -525,123 +601,104 @@ public:
 #undef _DEFINE_SWIZZLER3
 };
 
-
-template<typename T, typename V>
-Vec4<decltype(V{}*T{})> operator * (const V& f, const Vec4<T>& vec)
-{
-    return MakeVec(f*vec.x,f*vec.y,f*vec.z,f*vec.w);
+template <typename T, typename V>
+Vec4<decltype(V{} * T{})> operator*(const V& f, const Vec4<T>& vec) {
+    return MakeVec(f * vec.x, f * vec.y, f * vec.z, f * vec.w);
 }
 
 typedef Vec4<float> Vec4f;
 
-
-template<typename T>
-static inline decltype(T{}*T{}+T{}*T{}) Dot(const Vec2<T>& a, const Vec2<T>& b)
-{
-    return a.x*b.x + a.y*b.y;
+template <typename T>
+static inline decltype(T{} * T{} + T{} * T{}) Dot(const Vec2<T>& a, const Vec2<T>& b) {
+    return a.x * b.x + a.y * b.y;
 }
 
-template<typename T>
-static inline decltype(T{}*T{}+T{}*T{}) Dot(const Vec3<T>& a, const Vec3<T>& b)
-{
-    return a.x*b.x + a.y*b.y + a.z*b.z;
+template <typename T>
+static inline decltype(T{} * T{} + T{} * T{}) Dot(const Vec3<T>& a, const Vec3<T>& b) {
+    return a.x * b.x + a.y * b.y + a.z * b.z;
 }
 
-template<typename T>
-static inline decltype(T{}*T{}+T{}*T{}) Dot(const Vec4<T>& a, const Vec4<T>& b)
-{
-    return a.x*b.x + a.y*b.y + a.z*b.z + a.w*b.w;
+template <typename T>
+static inline decltype(T{} * T{} + T{} * T{}) Dot(const Vec4<T>& a, const Vec4<T>& b) {
+    return a.x * b.x + a.y * b.y + a.z * b.z + a.w * b.w;
 }
 
-template<typename T>
-static inline Vec3<decltype(T{}*T{}-T{}*T{})> Cross(const Vec3<T>& a, const Vec3<T>& b)
-{
-    return MakeVec(a.y*b.z-a.z*b.y, a.z*b.x-a.x*b.z, a.x*b.y-a.y*b.x);
+template <typename T>
+static inline Vec3<decltype(T{} * T{} - T{} * T{})> Cross(const Vec3<T>& a, const Vec3<T>& b) {
+    return MakeVec(a.y * b.z - a.z * b.y, a.z * b.x - a.x * b.z, a.x * b.y - a.y * b.x);
 }
 
 // linear interpolation via float: 0.0=begin, 1.0=end
-template<typename X>
-static inline decltype(X{}*float{}+X{}*float{}) Lerp(const X& begin, const X& end, const float t)
-{
-    return begin*(1.f-t) + end*t;
+template <typename X>
+static inline decltype(X{} * float{} + X{} * float{}) Lerp(const X& begin, const X& end,
+                                                           const float t) {
+    return begin * (1.f - t) + end * t;
 }
 
 // linear interpolation via int: 0=begin, base=end
-template<typename X, int base>
-static inline decltype((X{}*int{}+X{}*int{}) / base) LerpInt(const X& begin, const X& end, const int t)
-{
-    return (begin*(base-t) + end*t) / base;
+template <typename X, int base>
+static inline decltype((X{} * int{} + X{} * int{}) / base) LerpInt(const X& begin, const X& end,
+                                                                   const int t) {
+    return (begin * (base - t) + end * t) / base;
 }
 
 // Utility vector factories
-template<typename T>
-static inline Vec2<T> MakeVec(const T& x, const T& y)
-{
+template <typename T>
+static inline Vec2<T> MakeVec(const T& x, const T& y) {
     return Vec2<T>{x, y};
 }
 
-template<typename T>
-static inline Vec3<T> MakeVec(const T& x, const T& y, const T& z)
-{
+template <typename T>
+static inline Vec3<T> MakeVec(const T& x, const T& y, const T& z) {
     return Vec3<T>{x, y, z};
 }
 
-template<typename T>
-static inline Vec4<T> MakeVec(const T& x, const T& y, const Vec2<T>& zw)
-{
+template <typename T>
+static inline Vec4<T> MakeVec(const T& x, const T& y, const Vec2<T>& zw) {
     return MakeVec(x, y, zw[0], zw[1]);
 }
 
-template<typename T>
-static inline Vec3<T> MakeVec(const Vec2<T>& xy, const T& z)
-{
+template <typename T>
+static inline Vec3<T> MakeVec(const Vec2<T>& xy, const T& z) {
     return MakeVec(xy[0], xy[1], z);
 }
 
-template<typename T>
-static inline Vec3<T> MakeVec(const T& x, const Vec2<T>& yz)
-{
+template <typename T>
+static inline Vec3<T> MakeVec(const T& x, const Vec2<T>& yz) {
     return MakeVec(x, yz[0], yz[1]);
 }
 
-template<typename T>
-static inline Vec4<T> MakeVec(const T& x, const T& y, const T& z, const T& w)
-{
+template <typename T>
+static inline Vec4<T> MakeVec(const T& x, const T& y, const T& z, const T& w) {
     return Vec4<T>{x, y, z, w};
 }
 
-template<typename T>
-static inline Vec4<T> MakeVec(const Vec2<T>& xy, const T& z, const T& w)
-{
+template <typename T>
+static inline Vec4<T> MakeVec(const Vec2<T>& xy, const T& z, const T& w) {
     return MakeVec(xy[0], xy[1], z, w);
 }
 
-template<typename T>
-static inline Vec4<T> MakeVec(const T& x, const Vec2<T>& yz, const T& w)
-{
+template <typename T>
+static inline Vec4<T> MakeVec(const T& x, const Vec2<T>& yz, const T& w) {
     return MakeVec(x, yz[0], yz[1], w);
 }
 
 // NOTE: This has priority over "Vec2<Vec2<T>> MakeVec(const Vec2<T>& x, const Vec2<T>& y)".
 //       Even if someone wanted to use an odd object like Vec2<Vec2<T>>, the compiler would error
 //       out soon enough due to misuse of the returned structure.
-template<typename T>
-static inline Vec4<T> MakeVec(const Vec2<T>& xy, const Vec2<T>& zw)
-{
+template <typename T>
+static inline Vec4<T> MakeVec(const Vec2<T>& xy, const Vec2<T>& zw) {
     return MakeVec(xy[0], xy[1], zw[0], zw[1]);
 }
 
-template<typename T>
-static inline Vec4<T> MakeVec(const Vec3<T>& xyz, const T& w)
-{
+template <typename T>
+static inline Vec4<T> MakeVec(const Vec3<T>& xyz, const T& w) {
     return MakeVec(xyz[0], xyz[1], xyz[2], w);
 }
 
-template<typename T>
-static inline Vec4<T> MakeVec(const T& x, const Vec3<T>& yzw)
-{
+template <typename T>
+static inline Vec4<T> MakeVec(const T& x, const Vec3<T>& yzw) {
     return MakeVec(x, yzw[0], yzw[1], yzw[2]);
 }
 
-
 } // namespace
diff --git a/src/common/x64/abi.cpp b/src/common/x64/abi.cpp
index 955eb86ce..504b9c940 100644
--- a/src/common/x64/abi.cpp
+++ b/src/common/x64/abi.cpp
@@ -22,7 +22,8 @@ using namespace Gen;
 
 // Shared code between Win64 and Unix64
 
-void XEmitter::ABI_CalculateFrameSize(BitSet32 mask, size_t rsp_alignment, size_t needed_frame_size, size_t* shadowp, size_t* subtractionp, size_t* xmm_offsetp) {
+void XEmitter::ABI_CalculateFrameSize(BitSet32 mask, size_t rsp_alignment, size_t needed_frame_size,
+                                      size_t* shadowp, size_t* subtractionp, size_t* xmm_offsetp) {
     size_t shadow = 0;
 #if defined(_WIN32)
     shadow = 0x20;
@@ -49,17 +50,19 @@ void XEmitter::ABI_CalculateFrameSize(BitSet32 mask, size_t rsp_alignment, size_
     *xmm_offsetp = subtraction - xmm_base_subtraction;
 }
 
-size_t XEmitter::ABI_PushRegistersAndAdjustStack(BitSet32 mask, size_t rsp_alignment, size_t needed_frame_size) {
+size_t XEmitter::ABI_PushRegistersAndAdjustStack(BitSet32 mask, size_t rsp_alignment,
+                                                 size_t needed_frame_size) {
     size_t shadow, subtraction, xmm_offset;
-    ABI_CalculateFrameSize(mask, rsp_alignment, needed_frame_size, &shadow, &subtraction, &xmm_offset);
+    ABI_CalculateFrameSize(mask, rsp_alignment, needed_frame_size, &shadow, &subtraction,
+                           &xmm_offset);
 
-    for (int r : mask & ABI_ALL_GPRS)
+    for (int r : mask& ABI_ALL_GPRS)
         PUSH((X64Reg)r);
 
     if (subtraction)
         SUB(64, R(RSP), subtraction >= 0x80 ? Imm32((u32)subtraction) : Imm8((u8)subtraction));
 
-    for (int x : mask & ABI_ALL_FPRS) {
+    for (int x : mask& ABI_ALL_FPRS) {
         MOVAPD(MDisp(RSP, (int)xmm_offset), (X64Reg)(x - 16));
         xmm_offset += 16;
     }
@@ -67,12 +70,14 @@ size_t XEmitter::ABI_PushRegistersAndAdjustStack(BitSet32 mask, size_t rsp_align
     return shadow;
 }
 
-void XEmitter::ABI_PopRegistersAndAdjustStack(BitSet32 mask, size_t rsp_alignment, size_t needed_frame_size) {
+void XEmitter::ABI_PopRegistersAndAdjustStack(BitSet32 mask, size_t rsp_alignment,
+                                              size_t needed_frame_size) {
     size_t shadow, subtraction, xmm_offset;
-    ABI_CalculateFrameSize(mask, rsp_alignment, needed_frame_size, &shadow, &subtraction, &xmm_offset);
+    ABI_CalculateFrameSize(mask, rsp_alignment, needed_frame_size, &shadow, &subtraction,
+                           &xmm_offset);
 
-    for (int x : mask & ABI_ALL_FPRS) {
-        MOVAPD((X64Reg) (x - 16), MDisp(RSP, (int)xmm_offset));
+    for (int x : mask& ABI_ALL_FPRS) {
+        MOVAPD((X64Reg)(x - 16), MDisp(RSP, (int)xmm_offset));
         xmm_offset += 16;
     }
 
@@ -86,10 +91,9 @@ void XEmitter::ABI_PopRegistersAndAdjustStack(BitSet32 mask, size_t rsp_alignmen
 }
 
 // Common functions
-void XEmitter::ABI_CallFunction(const void *func) {
+void XEmitter::ABI_CallFunction(const void* func) {
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -98,11 +102,10 @@ void XEmitter::ABI_CallFunction(const void *func) {
     }
 }
 
-void XEmitter::ABI_CallFunctionC16(const void *func, u16 param1) {
+void XEmitter::ABI_CallFunctionC16(const void* func, u16 param1) {
     MOV(32, R(ABI_PARAM1), Imm32((u32)param1));
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -111,25 +114,23 @@ void XEmitter::ABI_CallFunctionC16(const void *func, u16 param1) {
     }
 }
 
-void XEmitter::ABI_CallFunctionCC16(const void *func, u32 param1, u16 param2) {
+void XEmitter::ABI_CallFunctionCC16(const void* func, u32 param1, u16 param2) {
     MOV(32, R(ABI_PARAM1), Imm32(param1));
     MOV(32, R(ABI_PARAM2), Imm32((u32)param2));
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-        && distance <  0xFFFFFFFF80000000ULL) {
-            // Far call
-            MOV(64, R(RAX), ImmPtr(func));
-            CALLptr(R(RAX));
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
+        // Far call
+        MOV(64, R(RAX), ImmPtr(func));
+        CALLptr(R(RAX));
     } else {
         CALL(func);
     }
 }
 
-void XEmitter::ABI_CallFunctionC(const void *func, u32 param1) {
+void XEmitter::ABI_CallFunctionC(const void* func, u32 param1) {
     MOV(32, R(ABI_PARAM1), Imm32(param1));
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -138,12 +139,11 @@ void XEmitter::ABI_CallFunctionC(const void *func, u32 param1) {
     }
 }
 
-void XEmitter::ABI_CallFunctionCC(const void *func, u32 param1, u32 param2) {
+void XEmitter::ABI_CallFunctionCC(const void* func, u32 param1, u32 param2) {
     MOV(32, R(ABI_PARAM1), Imm32(param1));
     MOV(32, R(ABI_PARAM2), Imm32(param2));
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -152,13 +152,12 @@ void XEmitter::ABI_CallFunctionCC(const void *func, u32 param1, u32 param2) {
     }
 }
 
-void XEmitter::ABI_CallFunctionCCC(const void *func, u32 param1, u32 param2, u32 param3) {
+void XEmitter::ABI_CallFunctionCCC(const void* func, u32 param1, u32 param2, u32 param3) {
     MOV(32, R(ABI_PARAM1), Imm32(param1));
     MOV(32, R(ABI_PARAM2), Imm32(param2));
     MOV(32, R(ABI_PARAM3), Imm32(param3));
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -167,13 +166,12 @@ void XEmitter::ABI_CallFunctionCCC(const void *func, u32 param1, u32 param2, u32
     }
 }
 
-void XEmitter::ABI_CallFunctionCCP(const void *func, u32 param1, u32 param2, void *param3) {
+void XEmitter::ABI_CallFunctionCCP(const void* func, u32 param1, u32 param2, void* param3) {
     MOV(32, R(ABI_PARAM1), Imm32(param1));
     MOV(32, R(ABI_PARAM2), Imm32(param2));
     MOV(64, R(ABI_PARAM3), ImmPtr(param3));
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -182,14 +180,14 @@ void XEmitter::ABI_CallFunctionCCP(const void *func, u32 param1, u32 param2, voi
     }
 }
 
-void XEmitter::ABI_CallFunctionCCCP(const void *func, u32 param1, u32 param2, u32 param3, void *param4) {
+void XEmitter::ABI_CallFunctionCCCP(const void* func, u32 param1, u32 param2, u32 param3,
+                                    void* param4) {
     MOV(32, R(ABI_PARAM1), Imm32(param1));
     MOV(32, R(ABI_PARAM2), Imm32(param2));
     MOV(32, R(ABI_PARAM3), Imm32(param3));
     MOV(64, R(ABI_PARAM4), ImmPtr(param4));
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -198,11 +196,10 @@ void XEmitter::ABI_CallFunctionCCCP(const void *func, u32 param1, u32 param2, u3
     }
 }
 
-void XEmitter::ABI_CallFunctionP(const void *func, void *param1) {
+void XEmitter::ABI_CallFunctionP(const void* func, void* param1) {
     MOV(64, R(ABI_PARAM1), ImmPtr(param1));
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -211,13 +208,12 @@ void XEmitter::ABI_CallFunctionP(const void *func, void *param1) {
     }
 }
 
-void XEmitter::ABI_CallFunctionPA(const void *func, void *param1, const Gen::OpArg &arg2) {
+void XEmitter::ABI_CallFunctionPA(const void* func, void* param1, const Gen::OpArg& arg2) {
     MOV(64, R(ABI_PARAM1), ImmPtr(param1));
     if (!arg2.IsSimpleReg(ABI_PARAM2))
         MOV(32, R(ABI_PARAM2), arg2);
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -226,15 +222,15 @@ void XEmitter::ABI_CallFunctionPA(const void *func, void *param1, const Gen::OpA
     }
 }
 
-void XEmitter::ABI_CallFunctionPAA(const void *func, void *param1, const Gen::OpArg &arg2, const Gen::OpArg &arg3) {
+void XEmitter::ABI_CallFunctionPAA(const void* func, void* param1, const Gen::OpArg& arg2,
+                                   const Gen::OpArg& arg3) {
     MOV(64, R(ABI_PARAM1), ImmPtr(param1));
     if (!arg2.IsSimpleReg(ABI_PARAM2))
         MOV(32, R(ABI_PARAM2), arg2);
     if (!arg3.IsSimpleReg(ABI_PARAM3))
         MOV(32, R(ABI_PARAM3), arg3);
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -243,13 +239,12 @@ void XEmitter::ABI_CallFunctionPAA(const void *func, void *param1, const Gen::Op
     }
 }
 
-void XEmitter::ABI_CallFunctionPPC(const void *func, void *param1, void *param2, u32 param3) {
+void XEmitter::ABI_CallFunctionPPC(const void* func, void* param1, void* param2, u32 param3) {
     MOV(64, R(ABI_PARAM1), ImmPtr(param1));
     MOV(64, R(ABI_PARAM2), ImmPtr(param2));
     MOV(32, R(ABI_PARAM3), Imm32(param3));
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -259,12 +254,11 @@ void XEmitter::ABI_CallFunctionPPC(const void *func, void *param1, void *param2,
 }
 
 // Pass a register as a parameter.
-void XEmitter::ABI_CallFunctionR(const void *func, X64Reg reg1) {
+void XEmitter::ABI_CallFunctionR(const void* func, X64Reg reg1) {
     if (reg1 != ABI_PARAM1)
         MOV(32, R(ABI_PARAM1), R(reg1));
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -274,7 +268,7 @@ void XEmitter::ABI_CallFunctionR(const void *func, X64Reg reg1) {
 }
 
 // Pass two registers as parameters.
-void XEmitter::ABI_CallFunctionRR(const void *func, X64Reg reg1, X64Reg reg2) {
+void XEmitter::ABI_CallFunctionRR(const void* func, X64Reg reg1, X64Reg reg2) {
     if (reg2 != ABI_PARAM1) {
         if (reg1 != ABI_PARAM1)
             MOV(64, R(ABI_PARAM1), R(reg1));
@@ -287,8 +281,7 @@ void XEmitter::ABI_CallFunctionRR(const void *func, X64Reg reg1, X64Reg reg2) {
             MOV(64, R(ABI_PARAM1), R(reg1));
     }
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -297,14 +290,12 @@ void XEmitter::ABI_CallFunctionRR(const void *func, X64Reg reg1, X64Reg reg2) {
     }
 }
 
-void XEmitter::ABI_CallFunctionAC(const void *func, const Gen::OpArg &arg1, u32 param2)
-{
+void XEmitter::ABI_CallFunctionAC(const void* func, const Gen::OpArg& arg1, u32 param2) {
     if (!arg1.IsSimpleReg(ABI_PARAM1))
         MOV(32, R(ABI_PARAM1), arg1);
     MOV(32, R(ABI_PARAM2), Imm32(param2));
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -313,15 +304,14 @@ void XEmitter::ABI_CallFunctionAC(const void *func, const Gen::OpArg &arg1, u32
     }
 }
 
-void XEmitter::ABI_CallFunctionACC(const void *func, const Gen::OpArg &arg1, u32 param2, u32 param3)
-{
+void XEmitter::ABI_CallFunctionACC(const void* func, const Gen::OpArg& arg1, u32 param2,
+                                   u32 param3) {
     if (!arg1.IsSimpleReg(ABI_PARAM1))
         MOV(32, R(ABI_PARAM1), arg1);
     MOV(32, R(ABI_PARAM2), Imm32(param2));
     MOV(64, R(ABI_PARAM3), Imm64(param3));
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -330,13 +320,11 @@ void XEmitter::ABI_CallFunctionACC(const void *func, const Gen::OpArg &arg1, u32
     }
 }
 
-void XEmitter::ABI_CallFunctionA(const void *func, const Gen::OpArg &arg1)
-{
+void XEmitter::ABI_CallFunctionA(const void* func, const Gen::OpArg& arg1) {
     if (!arg1.IsSimpleReg(ABI_PARAM1))
         MOV(32, R(ABI_PARAM1), arg1);
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
@@ -345,15 +333,14 @@ void XEmitter::ABI_CallFunctionA(const void *func, const Gen::OpArg &arg1)
     }
 }
 
-void XEmitter::ABI_CallFunctionAA(const void *func, const Gen::OpArg &arg1, const Gen::OpArg &arg2)
-{
+void XEmitter::ABI_CallFunctionAA(const void* func, const Gen::OpArg& arg1,
+                                  const Gen::OpArg& arg2) {
     if (!arg1.IsSimpleReg(ABI_PARAM1))
         MOV(32, R(ABI_PARAM1), arg1);
     if (!arg2.IsSimpleReg(ABI_PARAM2))
         MOV(32, R(ABI_PARAM2), arg2);
     u64 distance = u64(func) - (u64(code) + 5);
-    if (distance >= 0x0000000080000000ULL
-     && distance <  0xFFFFFFFF80000000ULL) {
+    if (distance >= 0x0000000080000000ULL && distance < 0xFFFFFFFF80000000ULL) {
         // Far call
         MOV(64, R(RAX), ImmPtr(func));
         CALLptr(R(RAX));
diff --git a/src/common/x64/abi.h b/src/common/x64/abi.h
index de6d62fdd..eaaf81d89 100644
--- a/src/common/x64/abi.h
+++ b/src/common/x64/abi.h
@@ -12,7 +12,8 @@
 
 // Windows 64-bit
 // * 4-reg "fastcall" variant, very new-skool stack handling
-// * Callee moves stack pointer, to make room for shadow regs for the biggest function _it itself calls_
+// * Callee moves stack pointer, to make room for shadow regs for the biggest function _it itself
+// calls_
 // * Parameters passed in RCX, RDX, ... further parameters are MOVed into the allocated stack space.
 // Scratch:      RAX RCX RDX R8 R9 R10 R11
 // Callee-save:  RBX RSI RDI RBP R12 R13 R14 R15
@@ -35,10 +36,10 @@
 #define ABI_PARAM4 R9
 
 // xmm0-xmm15 use the upper 16 bits in the functions that push/pop registers.
-#define ABI_ALL_CALLER_SAVED \
-    (BitSet32 { RAX, RCX, RDX, R8, R9, R10, R11, \
-                XMM0+16, XMM1+16, XMM2+16, XMM3+16, XMM4+16, XMM5+16 })
-#else //64-bit Unix / OS X
+#define ABI_ALL_CALLER_SAVED                                                                       \
+    (BitSet32{RAX, RCX, RDX, R8, R9, R10, R11, XMM0 + 16, XMM1 + 16, XMM2 + 16, XMM3 + 16,         \
+              XMM4 + 16, XMM5 + 16})
+#else // 64-bit Unix / OS X
 
 #define ABI_PARAM1 RDI
 #define ABI_PARAM2 RSI
@@ -49,9 +50,7 @@
 
 // TODO: Avoid pushing all 16 XMM registers when possible. Most functions we call probably
 // don't actually clobber them.
-#define ABI_ALL_CALLER_SAVED \
-    (BitSet32 { RAX, RCX, RDX, RDI, RSI, R8, R9, R10, R11 } | \
-     ABI_ALL_FPRS)
+#define ABI_ALL_CALLER_SAVED (BitSet32{RAX, RCX, RDX, RDI, RSI, R8, R9, R10, R11} | ABI_ALL_FPRS)
 #endif // WIN32
 
 #define ABI_ALL_CALLEE_SAVED (~ABI_ALL_CALLER_SAVED)
diff --git a/src/common/x64/cpu_detect.cpp b/src/common/x64/cpu_detect.cpp
index d9c430c67..19f1a4030 100644
--- a/src/common/x64/cpu_detect.cpp
+++ b/src/common/x64/cpu_detect.cpp
@@ -15,8 +15,8 @@ namespace Common {
 #ifndef _MSC_VER
 
 #ifdef __FreeBSD__
-#include <sys/types.h>
 #include <machine/cpufunc.h>
+#include <sys/types.h>
 #endif
 
 static inline void __cpuidex(int info[4], int function_id, int subfunction_id) {
@@ -26,15 +26,9 @@ static inline void __cpuidex(int info[4], int function_id, int subfunction_id) {
 #else
     info[0] = function_id;    // eax
     info[2] = subfunction_id; // ecx
-    __asm__(
-        "cpuid"
-        : "=a" (info[0]),
-        "=b" (info[1]),
-        "=c" (info[2]),
-        "=d" (info[3])
-        : "a" (function_id),
-        "c" (subfunction_id)
-        );
+    __asm__("cpuid"
+            : "=a"(info[0]), "=b"(info[1]), "=c"(info[2]), "=d"(info[3])
+            : "a"(function_id), "c"(subfunction_id));
 #endif
 }
 
@@ -88,14 +82,22 @@ static CPUCaps Detect() {
     if (max_std_fn >= 1) {
         __cpuid(cpu_id, 0x00000001);
 
-        if ((cpu_id[3] >> 25) & 1) caps.sse = true;
-        if ((cpu_id[3] >> 26) & 1) caps.sse2 = true;
-        if ((cpu_id[2]) & 1) caps.sse3 = true;
-        if ((cpu_id[2] >> 9) & 1) caps.ssse3 = true;
-        if ((cpu_id[2] >> 19) & 1) caps.sse4_1 = true;
-        if ((cpu_id[2] >> 20) & 1) caps.sse4_2 = true;
-        if ((cpu_id[2] >> 22) & 1) caps.movbe = true;
-        if ((cpu_id[2] >> 25) & 1) caps.aes = true;
+        if ((cpu_id[3] >> 25) & 1)
+            caps.sse = true;
+        if ((cpu_id[3] >> 26) & 1)
+            caps.sse2 = true;
+        if ((cpu_id[2]) & 1)
+            caps.sse3 = true;
+        if ((cpu_id[2] >> 9) & 1)
+            caps.ssse3 = true;
+        if ((cpu_id[2] >> 19) & 1)
+            caps.sse4_1 = true;
+        if ((cpu_id[2] >> 20) & 1)
+            caps.sse4_2 = true;
+        if ((cpu_id[2] >> 22) & 1)
+            caps.movbe = true;
+        if ((cpu_id[2] >> 25) & 1)
+            caps.aes = true;
 
         if ((cpu_id[3] >> 24) & 1) {
             caps.fxsave_fxrstor = true;
@@ -140,10 +142,14 @@ static CPUCaps Detect() {
     if (max_ex_fn >= 0x80000001) {
         // Check for more features
         __cpuid(cpu_id, 0x80000001);
-        if (cpu_id[2] & 1) caps.lahf_sahf_64 = true;
-        if ((cpu_id[2] >> 5) & 1) caps.lzcnt = true;
-        if ((cpu_id[2] >> 16) & 1) caps.fma4 = true;
-        if ((cpu_id[3] >> 29) & 1) caps.long_mode = true;
+        if (cpu_id[2] & 1)
+            caps.lahf_sahf_64 = true;
+        if ((cpu_id[2] >> 5) & 1)
+            caps.lzcnt = true;
+        if ((cpu_id[2] >> 16) & 1)
+            caps.fma4 = true;
+        if ((cpu_id[3] >> 29) & 1)
+            caps.long_mode = true;
     }
 
     return caps;
@@ -162,24 +168,38 @@ std::string GetCPUCapsString() {
     sum += caps.brand_string;
     sum += ")";
 
-    if (caps.sse) sum += ", SSE";
+    if (caps.sse)
+        sum += ", SSE";
     if (caps.sse2) {
         sum += ", SSE2";
-        if (!caps.flush_to_zero) sum += " (without DAZ)";
+        if (!caps.flush_to_zero)
+            sum += " (without DAZ)";
     }
 
-    if (caps.sse3) sum += ", SSE3";
-    if (caps.ssse3) sum += ", SSSE3";
-    if (caps.sse4_1) sum += ", SSE4.1";
-    if (caps.sse4_2) sum += ", SSE4.2";
-    if (caps.avx) sum += ", AVX";
-    if (caps.avx2) sum += ", AVX2";
-    if (caps.bmi1) sum += ", BMI1";
-    if (caps.bmi2) sum += ", BMI2";
-    if (caps.fma) sum += ", FMA";
-    if (caps.aes) sum += ", AES";
-    if (caps.movbe) sum += ", MOVBE";
-    if (caps.long_mode) sum += ", 64-bit support";
+    if (caps.sse3)
+        sum += ", SSE3";
+    if (caps.ssse3)
+        sum += ", SSSE3";
+    if (caps.sse4_1)
+        sum += ", SSE4.1";
+    if (caps.sse4_2)
+        sum += ", SSE4.2";
+    if (caps.avx)
+        sum += ", AVX";
+    if (caps.avx2)
+        sum += ", AVX2";
+    if (caps.bmi1)
+        sum += ", BMI1";
+    if (caps.bmi2)
+        sum += ", BMI2";
+    if (caps.fma)
+        sum += ", FMA";
+    if (caps.aes)
+        sum += ", AES";
+    if (caps.movbe)
+        sum += ", MOVBE";
+    if (caps.long_mode)
+        sum += ", 64-bit support";
 
     return sum;
 }
diff --git a/src/common/x64/emitter.cpp b/src/common/x64/emitter.cpp
index 5662f7f86..1a9fd6a6b 100644
--- a/src/common/x64/emitter.cpp
+++ b/src/common/x64/emitter.cpp
@@ -26,179 +26,162 @@
 #include "cpu_detect.h"
 #include "emitter.h"
 
-namespace Gen
-{
+namespace Gen {
 
-struct NormalOpDef
-{
+struct NormalOpDef {
     u8 toRm8, toRm32, fromRm8, fromRm32, imm8, imm32, simm8, eaximm8, eaximm32, ext;
 };
 
 // 0xCC is code for invalid combination of immediates
-static const NormalOpDef normalops[11] =
-{
-    {0x00, 0x01, 0x02, 0x03, 0x80, 0x81, 0x83, 0x04, 0x05, 0}, //ADD
-    {0x10, 0x11, 0x12, 0x13, 0x80, 0x81, 0x83, 0x14, 0x15, 2}, //ADC
+static const NormalOpDef normalops[11] = {
+    {0x00, 0x01, 0x02, 0x03, 0x80, 0x81, 0x83, 0x04, 0x05, 0}, // ADD
+    {0x10, 0x11, 0x12, 0x13, 0x80, 0x81, 0x83, 0x14, 0x15, 2}, // ADC
 
-    {0x28, 0x29, 0x2A, 0x2B, 0x80, 0x81, 0x83, 0x2C, 0x2D, 5}, //SUB
-    {0x18, 0x19, 0x1A, 0x1B, 0x80, 0x81, 0x83, 0x1C, 0x1D, 3}, //SBB
+    {0x28, 0x29, 0x2A, 0x2B, 0x80, 0x81, 0x83, 0x2C, 0x2D, 5}, // SUB
+    {0x18, 0x19, 0x1A, 0x1B, 0x80, 0x81, 0x83, 0x1C, 0x1D, 3}, // SBB
 
-    {0x20, 0x21, 0x22, 0x23, 0x80, 0x81, 0x83, 0x24, 0x25, 4}, //AND
-    {0x08, 0x09, 0x0A, 0x0B, 0x80, 0x81, 0x83, 0x0C, 0x0D, 1}, //OR
+    {0x20, 0x21, 0x22, 0x23, 0x80, 0x81, 0x83, 0x24, 0x25, 4}, // AND
+    {0x08, 0x09, 0x0A, 0x0B, 0x80, 0x81, 0x83, 0x0C, 0x0D, 1}, // OR
 
-    {0x30, 0x31, 0x32, 0x33, 0x80, 0x81, 0x83, 0x34, 0x35, 6}, //XOR
-    {0x88, 0x89, 0x8A, 0x8B, 0xC6, 0xC7, 0xCC, 0xCC, 0xCC, 0}, //MOV
+    {0x30, 0x31, 0x32, 0x33, 0x80, 0x81, 0x83, 0x34, 0x35, 6}, // XOR
+    {0x88, 0x89, 0x8A, 0x8B, 0xC6, 0xC7, 0xCC, 0xCC, 0xCC, 0}, // MOV
 
-    {0x84, 0x85, 0x84, 0x85, 0xF6, 0xF7, 0xCC, 0xA8, 0xA9, 0}, //TEST (to == from)
-    {0x38, 0x39, 0x3A, 0x3B, 0x80, 0x81, 0x83, 0x3C, 0x3D, 7}, //CMP
+    {0x84, 0x85, 0x84, 0x85, 0xF6, 0xF7, 0xCC, 0xA8, 0xA9, 0}, // TEST (to == from)
+    {0x38, 0x39, 0x3A, 0x3B, 0x80, 0x81, 0x83, 0x3C, 0x3D, 7}, // CMP
 
-    {0x86, 0x87, 0x86, 0x87, 0xCC, 0xCC, 0xCC, 0xCC, 0xCC, 7}, //XCHG
+    {0x86, 0x87, 0x86, 0x87, 0xCC, 0xCC, 0xCC, 0xCC, 0xCC, 7}, // XCHG
 };
 
-enum NormalSSEOps
-{
-    sseCMP         = 0xC2,
-    sseADD         = 0x58, //ADD
-    sseSUB         = 0x5C, //SUB
-    sseAND         = 0x54, //AND
-    sseANDN        = 0x55, //ANDN
-    sseOR          = 0x56,
-    sseXOR         = 0x57,
-    sseMUL         = 0x59, //MUL
-    sseDIV         = 0x5E, //DIV
-    sseMIN         = 0x5D, //MIN
-    sseMAX         = 0x5F, //MAX
-    sseCOMIS       = 0x2F, //COMIS
-    sseUCOMIS      = 0x2E, //UCOMIS
-    sseSQRT        = 0x51, //SQRT
-    sseRSQRT       = 0x52, //RSQRT (NO DOUBLE PRECISION!!!)
-    sseRCP         = 0x53, //RCP
-    sseMOVAPfromRM = 0x28, //MOVAP from RM
-    sseMOVAPtoRM   = 0x29, //MOVAP to RM
-    sseMOVUPfromRM = 0x10, //MOVUP from RM
-    sseMOVUPtoRM   = 0x11, //MOVUP to RM
-    sseMOVLPfromRM= 0x12,
-    sseMOVLPtoRM  = 0x13,
-    sseMOVHPfromRM= 0x16,
-    sseMOVHPtoRM  = 0x17,
-    sseMOVHLPS     = 0x12,
-    sseMOVLHPS     = 0x16,
+enum NormalSSEOps {
+    sseCMP = 0xC2,
+    sseADD = 0x58,  // ADD
+    sseSUB = 0x5C,  // SUB
+    sseAND = 0x54,  // AND
+    sseANDN = 0x55, // ANDN
+    sseOR = 0x56,
+    sseXOR = 0x57,
+    sseMUL = 0x59,         // MUL
+    sseDIV = 0x5E,         // DIV
+    sseMIN = 0x5D,         // MIN
+    sseMAX = 0x5F,         // MAX
+    sseCOMIS = 0x2F,       // COMIS
+    sseUCOMIS = 0x2E,      // UCOMIS
+    sseSQRT = 0x51,        // SQRT
+    sseRSQRT = 0x52,       // RSQRT (NO DOUBLE PRECISION!!!)
+    sseRCP = 0x53,         // RCP
+    sseMOVAPfromRM = 0x28, // MOVAP from RM
+    sseMOVAPtoRM = 0x29,   // MOVAP to RM
+    sseMOVUPfromRM = 0x10, // MOVUP from RM
+    sseMOVUPtoRM = 0x11,   // MOVUP to RM
+    sseMOVLPfromRM = 0x12,
+    sseMOVLPtoRM = 0x13,
+    sseMOVHPfromRM = 0x16,
+    sseMOVHPtoRM = 0x17,
+    sseMOVHLPS = 0x12,
+    sseMOVLHPS = 0x16,
     sseMOVDQfromRM = 0x6F,
-    sseMOVDQtoRM   = 0x7F,
-    sseMASKMOVDQU  = 0xF7,
-    sseLDDQU       = 0xF0,
-    sseSHUF        = 0xC6,
-    sseMOVNTDQ     = 0xE7,
-    sseMOVNTP      = 0x2B,
-    sseHADD        = 0x7C,
+    sseMOVDQtoRM = 0x7F,
+    sseMASKMOVDQU = 0xF7,
+    sseLDDQU = 0xF0,
+    sseSHUF = 0xC6,
+    sseMOVNTDQ = 0xE7,
+    sseMOVNTP = 0x2B,
+    sseHADD = 0x7C,
 };
 
-
-void XEmitter::SetCodePtr(u8 *ptr)
-{
+void XEmitter::SetCodePtr(u8* ptr) {
     code = ptr;
 }
 
-const u8 *XEmitter::GetCodePtr() const
-{
+const u8* XEmitter::GetCodePtr() const {
     return code;
 }
 
-u8 *XEmitter::GetWritableCodePtr()
-{
+u8* XEmitter::GetWritableCodePtr() {
     return code;
 }
 
-void XEmitter::Write8(u8 value)
-{
+void XEmitter::Write8(u8 value) {
     *code++ = value;
 }
 
-void XEmitter::Write16(u16 value)
-{
+void XEmitter::Write16(u16 value) {
     std::memcpy(code, &value, sizeof(u16));
     code += sizeof(u16);
 }
 
-void XEmitter::Write32(u32 value)
-{
+void XEmitter::Write32(u32 value) {
     std::memcpy(code, &value, sizeof(u32));
     code += sizeof(u32);
 }
 
-void XEmitter::Write64(u64 value)
-{
+void XEmitter::Write64(u64 value) {
     std::memcpy(code, &value, sizeof(u64));
     code += sizeof(u64);
 }
 
-void XEmitter::ReserveCodeSpace(int bytes)
-{
+void XEmitter::ReserveCodeSpace(int bytes) {
     for (int i = 0; i < bytes; i++)
         *code++ = 0xCC;
 }
 
-const u8 *XEmitter::AlignCode4()
-{
+const u8* XEmitter::AlignCode4() {
     int c = int((u64)code & 3);
     if (c)
-        ReserveCodeSpace(4-c);
+        ReserveCodeSpace(4 - c);
     return code;
 }
 
-const u8 *XEmitter::AlignCode16()
-{
+const u8* XEmitter::AlignCode16() {
     int c = int((u64)code & 15);
     if (c)
-        ReserveCodeSpace(16-c);
+        ReserveCodeSpace(16 - c);
     return code;
 }
 
-const u8 *XEmitter::AlignCodePage()
-{
+const u8* XEmitter::AlignCodePage() {
     int c = int((u64)code & 4095);
     if (c)
-        ReserveCodeSpace(4096-c);
+        ReserveCodeSpace(4096 - c);
     return code;
 }
 
 // This operation modifies flags; check to see the flags are locked.
 // If the flags are locked, we should immediately and loudly fail before
 // causing a subtle JIT bug.
-void XEmitter::CheckFlags()
-{
+void XEmitter::CheckFlags() {
     ASSERT_MSG(!flags_locked, "Attempt to modify flags while flags locked!");
 }
 
-void XEmitter::WriteModRM(int mod, int reg, int rm)
-{
+void XEmitter::WriteModRM(int mod, int reg, int rm) {
     Write8((u8)((mod << 6) | ((reg & 7) << 3) | (rm & 7)));
 }
 
-void XEmitter::WriteSIB(int scale, int index, int base)
-{
+void XEmitter::WriteSIB(int scale, int index, int base) {
     Write8((u8)((scale << 6) | ((index & 7) << 3) | (base & 7)));
 }
 
-void OpArg::WriteRex(XEmitter *emit, int opBits, int bits, int customOp) const
-{
-    if (customOp == -1)       customOp = operandReg;
+void OpArg::WriteRex(XEmitter* emit, int opBits, int bits, int customOp) const {
+    if (customOp == -1)
+        customOp = operandReg;
 #ifdef ARCHITECTURE_x86_64
     u8 op = 0x40;
     // REX.W (whether operation is a 64-bit operation)
-    if (opBits == 64)         op |= 8;
+    if (opBits == 64)
+        op |= 8;
     // REX.R (whether ModR/M reg field refers to R8-R15.
-    if (customOp & 8)         op |= 4;
+    if (customOp & 8)
+        op |= 4;
     // REX.X (whether ModR/M SIB index field refers to R8-R15)
-    if (indexReg & 8)         op |= 2;
+    if (indexReg & 8)
+        op |= 2;
     // REX.B (whether ModR/M rm or SIB base or opcode reg field refers to R8-R15)
-    if (offsetOrBaseReg & 8)  op |= 1;
+    if (offsetOrBaseReg & 8)
+        op |= 1;
     // Write REX if wr have REX bits to write, or if the operation accesses
     // SIL, DIL, BPL, or SPL.
-    if (op != 0x40 ||
-        (scale == SCALE_NONE && bits == 8 && (offsetOrBaseReg & 0x10c) == 4) ||
-        (opBits == 8 && (customOp & 0x10c) == 4))
-    {
+    if (op != 0x40 || (scale == SCALE_NONE && bits == 8 && (offsetOrBaseReg & 0x10c) == 4) ||
+        (opBits == 8 && (customOp & 0x10c) == 4)) {
         emit->Write8(op);
         // Check the operation doesn't access AH, BH, CH, or DH.
         DEBUG_ASSERT((offsetOrBaseReg & 0x100) == 0);
@@ -214,8 +197,8 @@ void OpArg::WriteRex(XEmitter *emit, int opBits, int bits, int customOp) const
 #endif
 }
 
-void OpArg::WriteVex(XEmitter* emit, X64Reg regOp1, X64Reg regOp2, int L, int pp, int mmmmm, int W) const
-{
+void OpArg::WriteVex(XEmitter* emit, X64Reg regOp1, X64Reg regOp2, int L, int pp, int mmmmm,
+                     int W) const {
     int R = !(regOp1 & 8);
     int X = !(indexReg & 8);
     int B = !(offsetOrBaseReg & 8);
@@ -223,14 +206,11 @@ void OpArg::WriteVex(XEmitter* emit, X64Reg regOp1, X64Reg regOp2, int L, int pp
     int vvvv = (regOp2 == X64Reg::INVALID_REG) ? 0xf : (regOp2 ^ 0xf);
 
     // do we need any VEX fields that only appear in the three-byte form?
-    if (X == 1 && B == 1 && W == 0 && mmmmm == 1)
-    {
+    if (X == 1 && B == 1 && W == 0 && mmmmm == 1) {
         u8 RvvvvLpp = (R << 7) | (vvvv << 3) | (L << 2) | pp;
         emit->Write8(0xC5);
         emit->Write8(RvvvvLpp);
-    }
-    else
-    {
+    } else {
         u8 RXBmmmmm = (R << 7) | (X << 6) | (B << 5) | mmmmm;
         u8 WvvvvLpp = (W << 7) | (vvvv << 3) | (L << 2) | pp;
         emit->Write8(0xC4);
@@ -239,31 +219,27 @@ void OpArg::WriteVex(XEmitter* emit, X64Reg regOp1, X64Reg regOp2, int L, int pp
     }
 }
 
-void OpArg::WriteRest(XEmitter *emit, int extraBytes, X64Reg _operandReg,
-    bool warn_64bit_offset) const
-{
+void OpArg::WriteRest(XEmitter* emit, int extraBytes, X64Reg _operandReg,
+                      bool warn_64bit_offset) const {
     if (_operandReg == INVALID_REG)
-        _operandReg = (X64Reg)this->operandReg;
+        _operandReg = (X64Reg) this->operandReg;
     int mod = 0;
     int ireg = indexReg;
     bool SIB = false;
     int _offsetOrBaseReg = this->offsetOrBaseReg;
 
-    if (scale == SCALE_RIP) //Also, on 32-bit, just an immediate address
+    if (scale == SCALE_RIP) // Also, on 32-bit, just an immediate address
     {
         // Oh, RIP addressing.
         _offsetOrBaseReg = 5;
         emit->WriteModRM(0, _operandReg, _offsetOrBaseReg);
-        //TODO : add some checks
+// TODO : add some checks
 #ifdef ARCHITECTURE_x86_64
         u64 ripAddr = (u64)emit->GetCodePtr() + 4 + extraBytes;
         s64 distance = (s64)offset - (s64)ripAddr;
-        ASSERT_MSG(
-                     (distance < 0x80000000LL &&
-                      distance >=  -0x80000000LL) ||
-                     !warn_64bit_offset,
-                     "WriteRest: op out of range (0x%" PRIx64 " uses 0x%" PRIx64 ")",
-                     ripAddr, offset);
+        ASSERT_MSG((distance < 0x80000000LL && distance >= -0x80000000LL) || !warn_64bit_offset,
+                   "WriteRest: op out of range (0x%" PRIx64 " uses 0x%" PRIx64 ")", ripAddr,
+                   offset);
         s32 offs = (s32)distance;
         emit->Write32((u32)offs);
 #else
@@ -272,66 +248,49 @@ void OpArg::WriteRest(XEmitter *emit, int extraBytes, X64Reg _operandReg,
         return;
     }
 
-    if (scale == 0)
-    {
+    if (scale == 0) {
         // Oh, no memory, Just a reg.
-        mod = 3; //11
-    }
-    else if (scale >= 1)
-    {
-        //Ah good, no scaling.
-        if (scale == SCALE_ATREG && !((_offsetOrBaseReg & 7) == 4 || (_offsetOrBaseReg & 7) == 5))
-        {
-            //Okay, we're good. No SIB necessary.
+        mod = 3; // 11
+    } else if (scale >= 1) {
+        // Ah good, no scaling.
+        if (scale == SCALE_ATREG && !((_offsetOrBaseReg & 7) == 4 || (_offsetOrBaseReg & 7) == 5)) {
+            // Okay, we're good. No SIB necessary.
             int ioff = (int)offset;
-            if (ioff == 0)
-            {
+            if (ioff == 0) {
                 mod = 0;
+            } else if (ioff < -128 || ioff > 127) {
+                mod = 2; // 32-bit displacement
+            } else {
+                mod = 1; // 8-bit displacement
             }
-            else if (ioff<-128 || ioff>127)
-            {
-                mod = 2; //32-bit displacement
-            }
-            else
-            {
-                mod = 1; //8-bit displacement
-            }
-        }
-        else if (scale >= SCALE_NOBASE_2 && scale <= SCALE_NOBASE_8)
-        {
+        } else if (scale >= SCALE_NOBASE_2 && scale <= SCALE_NOBASE_8) {
             SIB = true;
             mod = 0;
             _offsetOrBaseReg = 5;
-        }
-        else //if (scale != SCALE_ATREG)
+        } else // if (scale != SCALE_ATREG)
         {
-            if ((_offsetOrBaseReg & 7) == 4) //this would occupy the SIB encoding :(
+            if ((_offsetOrBaseReg & 7) == 4) // this would occupy the SIB encoding :(
             {
-                //So we have to fake it with SIB encoding :(
+                // So we have to fake it with SIB encoding :(
                 SIB = true;
             }
 
-            if (scale >= SCALE_1 && scale < SCALE_ATREG)
-            {
+            if (scale >= SCALE_1 && scale < SCALE_ATREG) {
                 SIB = true;
             }
 
-            if (scale == SCALE_ATREG && ((_offsetOrBaseReg & 7) == 4))
-            {
+            if (scale == SCALE_ATREG && ((_offsetOrBaseReg & 7) == 4)) {
                 SIB = true;
                 ireg = _offsetOrBaseReg;
             }
 
-            //Okay, we're fine. Just disp encoding.
-            //We need displacement. Which size?
+            // Okay, we're fine. Just disp encoding.
+            // We need displacement. Which size?
             int ioff = (int)(s64)offset;
-            if (ioff < -128 || ioff > 127)
-            {
-                mod = 2; //32-bit displacement
-            }
-            else
-            {
-                mod = 1; //8-bit displacement
+            if (ioff < -128 || ioff > 127) {
+                mod = 2; // 32-bit displacement
+            } else {
+                mod = 1; // 8-bit displacement
             }
         }
     }
@@ -343,36 +302,55 @@ void OpArg::WriteRest(XEmitter *emit, int extraBytes, X64Reg _operandReg,
         oreg = 4;
 
     // TODO(ector): WTF is this if about? I don't remember writing it :-)
-    //if (RIP)
+    // if (RIP)
     //    oreg = 5;
 
-    emit->WriteModRM(mod, _operandReg&7, oreg&7);
+    emit->WriteModRM(mod, _operandReg & 7, oreg & 7);
 
-    if (SIB)
-    {
-        //SIB byte
+    if (SIB) {
+        // SIB byte
         int ss;
-        switch (scale)
-        {
-        case SCALE_NONE: _offsetOrBaseReg = 4; ss = 0; break; //RSP
-        case SCALE_1: ss = 0; break;
-        case SCALE_2: ss = 1; break;
-        case SCALE_4: ss = 2; break;
-        case SCALE_8: ss = 3; break;
-        case SCALE_NOBASE_2: ss = 1; break;
-        case SCALE_NOBASE_4: ss = 2; break;
-        case SCALE_NOBASE_8: ss = 3; break;
-        case SCALE_ATREG: ss = 0; break;
-        default: ASSERT_MSG(0, "Invalid scale for SIB byte"); ss = 0; break;
+        switch (scale) {
+        case SCALE_NONE:
+            _offsetOrBaseReg = 4;
+            ss = 0;
+            break; // RSP
+        case SCALE_1:
+            ss = 0;
+            break;
+        case SCALE_2:
+            ss = 1;
+            break;
+        case SCALE_4:
+            ss = 2;
+            break;
+        case SCALE_8:
+            ss = 3;
+            break;
+        case SCALE_NOBASE_2:
+            ss = 1;
+            break;
+        case SCALE_NOBASE_4:
+            ss = 2;
+            break;
+        case SCALE_NOBASE_8:
+            ss = 3;
+            break;
+        case SCALE_ATREG:
+            ss = 0;
+            break;
+        default:
+            ASSERT_MSG(0, "Invalid scale for SIB byte");
+            ss = 0;
+            break;
         }
-        emit->Write8((u8)((ss << 6) | ((ireg&7)<<3) | (_offsetOrBaseReg&7)));
+        emit->Write8((u8)((ss << 6) | ((ireg & 7) << 3) | (_offsetOrBaseReg & 7)));
     }
 
-    if (mod == 1) //8-bit disp
+    if (mod == 1) // 8-bit disp
     {
         emit->Write8((u8)(s8)(s32)offset);
-    }
-    else if (mod == 2 || (scale >= SCALE_NOBASE_2 && scale <= SCALE_NOBASE_8)) //32-bit disp
+    } else if (mod == 2 || (scale >= SCALE_NOBASE_2 && scale <= SCALE_NOBASE_8)) // 32-bit disp
     {
         emit->Write32((u32)offset);
     }
@@ -382,8 +360,7 @@ void OpArg::WriteRest(XEmitter *emit, int extraBytes, X64Reg _operandReg,
 // R = register# upper bit
 // X = scale amnt upper bit
 // B = base register# upper bit
-void XEmitter::Rex(int w, int r, int x, int b)
-{
+void XEmitter::Rex(int w, int r, int x, int b) {
     w = w ? 1 : 0;
     r = r ? 1 : 0;
     x = x ? 1 : 0;
@@ -393,70 +370,60 @@ void XEmitter::Rex(int w, int r, int x, int b)
         Write8(rx);
 }
 
-void XEmitter::JMP(const u8* addr, bool force5Bytes)
-{
+void XEmitter::JMP(const u8* addr, bool force5Bytes) {
     u64 fn = (u64)addr;
-    if (!force5Bytes)
-    {
+    if (!force5Bytes) {
         s64 distance = (s64)(fn - ((u64)code + 2));
         ASSERT_MSG(distance >= -0x80 && distance < 0x80,
-                 "Jump target too far away, needs force5Bytes = true");
-        //8 bits will do
+                   "Jump target too far away, needs force5Bytes = true");
+        // 8 bits will do
         Write8(0xEB);
         Write8((u8)(s8)distance);
-    }
-    else
-    {
+    } else {
         s64 distance = (s64)(fn - ((u64)code + 5));
 
-        ASSERT_MSG(
-                     distance >= -0x80000000LL && distance < 0x80000000LL,
-                     "Jump target too far away, needs indirect register");
+        ASSERT_MSG(distance >= -0x80000000LL && distance < 0x80000000LL,
+                   "Jump target too far away, needs indirect register");
         Write8(0xE9);
         Write32((u32)(s32)distance);
     }
 }
 
-void XEmitter::JMPptr(const OpArg& arg2)
-{
+void XEmitter::JMPptr(const OpArg& arg2) {
     OpArg arg = arg2;
-    if (arg.IsImm()) ASSERT_MSG(0, "JMPptr - Imm argument");
+    if (arg.IsImm())
+        ASSERT_MSG(0, "JMPptr - Imm argument");
     arg.operandReg = 4;
     arg.WriteRex(this, 0, 0);
     Write8(0xFF);
     arg.WriteRest(this);
 }
 
-//Can be used to trap other processors, before overwriting their code
+// Can be used to trap other processors, before overwriting their code
 // not used in dolphin
-void XEmitter::JMPself()
-{
+void XEmitter::JMPself() {
     Write8(0xEB);
     Write8(0xFE);
 }
 
-void XEmitter::CALLptr(OpArg arg)
-{
-    if (arg.IsImm()) ASSERT_MSG(0, "CALLptr - Imm argument");
+void XEmitter::CALLptr(OpArg arg) {
+    if (arg.IsImm())
+        ASSERT_MSG(0, "CALLptr - Imm argument");
     arg.operandReg = 2;
     arg.WriteRex(this, 0, 0);
     Write8(0xFF);
     arg.WriteRest(this);
 }
 
-void XEmitter::CALL(const void* fnptr)
-{
+void XEmitter::CALL(const void* fnptr) {
     u64 distance = u64(fnptr) - (u64(code) + 5);
-    ASSERT_MSG(
-                 distance < 0x0000000080000000ULL ||
-                 distance >=  0xFFFFFFFF80000000ULL,
-                 "CALL out of range (%p calls %p)", code, fnptr);
+    ASSERT_MSG(distance < 0x0000000080000000ULL || distance >= 0xFFFFFFFF80000000ULL,
+               "CALL out of range (%p calls %p)", code, fnptr);
     Write8(0xE8);
     Write32(u32(distance));
 }
 
-FixupBranch XEmitter::CALL()
-{
+FixupBranch XEmitter::CALL() {
     FixupBranch branch;
     branch.type = 1;
     branch.ptr = code + 5;
@@ -467,38 +434,30 @@ FixupBranch XEmitter::CALL()
     return branch;
 }
 
-FixupBranch XEmitter::J(bool force5bytes)
-{
+FixupBranch XEmitter::J(bool force5bytes) {
     FixupBranch branch;
     branch.type = force5bytes ? 1 : 0;
     branch.ptr = code + (force5bytes ? 5 : 2);
-    if (!force5bytes)
-    {
-        //8 bits will do
+    if (!force5bytes) {
+        // 8 bits will do
         Write8(0xEB);
         Write8(0);
-    }
-    else
-    {
+    } else {
         Write8(0xE9);
         Write32(0);
     }
     return branch;
 }
 
-FixupBranch XEmitter::J_CC(CCFlags conditionCode, bool force5bytes)
-{
+FixupBranch XEmitter::J_CC(CCFlags conditionCode, bool force5bytes) {
     FixupBranch branch;
     branch.type = force5bytes ? 1 : 0;
     branch.ptr = code + (force5bytes ? 6 : 2);
-    if (!force5bytes)
-    {
-        //8 bits will do
+    if (!force5bytes) {
+        // 8 bits will do
         Write8(0x70 + conditionCode);
         Write8(0);
-    }
-    else
-    {
+    } else {
         Write8(0x0F);
         Write8(0x80 + conditionCode);
         Write32(0);
@@ -506,198 +465,268 @@ FixupBranch XEmitter::J_CC(CCFlags conditionCode, bool force5bytes)
     return branch;
 }
 
-void XEmitter::J_CC(CCFlags conditionCode, const u8* addr, bool force5bytes)
-{
+void XEmitter::J_CC(CCFlags conditionCode, const u8* addr, bool force5bytes) {
     u64 fn = (u64)addr;
     s64 distance = (s64)(fn - ((u64)code + 2));
-    if (distance < -0x80 || distance >= 0x80 || force5bytes)
-    {
+    if (distance < -0x80 || distance >= 0x80 || force5bytes) {
         distance = (s64)(fn - ((u64)code + 6));
-        ASSERT_MSG(
-                     distance >= -0x80000000LL && distance < 0x80000000LL,
-                     "Jump target too far away, needs indirect register");
+        ASSERT_MSG(distance >= -0x80000000LL && distance < 0x80000000LL,
+                   "Jump target too far away, needs indirect register");
         Write8(0x0F);
         Write8(0x80 + conditionCode);
         Write32((u32)(s32)distance);
-    }
-    else
-    {
+    } else {
         Write8(0x70 + conditionCode);
         Write8((u8)(s8)distance);
     }
 }
 
-void XEmitter::SetJumpTarget(const FixupBranch& branch)
-{
-    if (branch.type == 0)
-    {
+void XEmitter::SetJumpTarget(const FixupBranch& branch) {
+    if (branch.type == 0) {
         s64 distance = (s64)(code - branch.ptr);
-        ASSERT_MSG(distance >= -0x80 && distance < 0x80, "Jump target too far away, needs force5Bytes = true");
+        ASSERT_MSG(distance >= -0x80 && distance < 0x80,
+                   "Jump target too far away, needs force5Bytes = true");
         branch.ptr[-1] = (u8)(s8)distance;
-    }
-    else if (branch.type == 1)
-    {
+    } else if (branch.type == 1) {
         s64 distance = (s64)(code - branch.ptr);
-        ASSERT_MSG(distance >= -0x80000000LL && distance < 0x80000000LL, "Jump target too far away, needs indirect register");
+        ASSERT_MSG(distance >= -0x80000000LL && distance < 0x80000000LL,
+                   "Jump target too far away, needs indirect register");
         ((s32*)branch.ptr)[-1] = (s32)distance;
     }
 }
 
-void XEmitter::SetJumpTarget(const FixupBranch& branch, const u8* target)
-{
-    if (branch.type == 0)
-    {
+void XEmitter::SetJumpTarget(const FixupBranch& branch, const u8* target) {
+    if (branch.type == 0) {
         s64 distance = (s64)(target - branch.ptr);
-        ASSERT_MSG(distance >= -0x80 && distance < 0x80, "Jump target too far away, needs force5Bytes = true");
+        ASSERT_MSG(distance >= -0x80 && distance < 0x80,
+                   "Jump target too far away, needs force5Bytes = true");
         branch.ptr[-1] = (u8)(s8)distance;
-    }
-    else if (branch.type == 1)
-    {
+    } else if (branch.type == 1) {
         s64 distance = (s64)(target - branch.ptr);
-        ASSERT_MSG(distance >= -0x80000000LL && distance < 0x80000000LL, "Jump target too far away, needs indirect register");
+        ASSERT_MSG(distance >= -0x80000000LL && distance < 0x80000000LL,
+                   "Jump target too far away, needs indirect register");
         ((s32*)branch.ptr)[-1] = (s32)distance;
     }
 }
 
-//Single byte opcodes
-//There is no PUSHAD/POPAD in 64-bit mode.
-void XEmitter::INT3() {Write8(0xCC);}
-void XEmitter::RET()  {Write8(0xC3);}
-void XEmitter::RET_FAST()  {Write8(0xF3); Write8(0xC3);} //two-byte return (rep ret) - recommended by AMD optimization manual for the case of jumping to a ret
+// Single byte opcodes
+// There is no PUSHAD/POPAD in 64-bit mode.
+void XEmitter::INT3() {
+    Write8(0xCC);
+}
+void XEmitter::RET() {
+    Write8(0xC3);
+}
+void XEmitter::RET_FAST() {
+    Write8(0xF3);
+    Write8(0xC3);
+} // two-byte return (rep ret) - recommended by AMD optimization manual for the case of jumping to a
+  // ret
 
 // The first sign of decadence: optimized NOPs.
-void XEmitter::NOP(size_t size)
-{
+void XEmitter::NOP(size_t size) {
     DEBUG_ASSERT((int)size > 0);
-    while (true)
-    {
-        switch (size)
-        {
+    while (true) {
+        switch (size) {
         case 0:
             return;
         case 1:
             Write8(0x90);
             return;
         case 2:
-            Write8(0x66); Write8(0x90);
+            Write8(0x66);
+            Write8(0x90);
             return;
         case 3:
-            Write8(0x0F); Write8(0x1F); Write8(0x00);
+            Write8(0x0F);
+            Write8(0x1F);
+            Write8(0x00);
             return;
         case 4:
-            Write8(0x0F); Write8(0x1F); Write8(0x40); Write8(0x00);
+            Write8(0x0F);
+            Write8(0x1F);
+            Write8(0x40);
+            Write8(0x00);
             return;
         case 5:
-            Write8(0x0F); Write8(0x1F); Write8(0x44); Write8(0x00);
+            Write8(0x0F);
+            Write8(0x1F);
+            Write8(0x44);
+            Write8(0x00);
             Write8(0x00);
             return;
         case 6:
-            Write8(0x66); Write8(0x0F); Write8(0x1F); Write8(0x44);
-            Write8(0x00); Write8(0x00);
+            Write8(0x66);
+            Write8(0x0F);
+            Write8(0x1F);
+            Write8(0x44);
+            Write8(0x00);
+            Write8(0x00);
             return;
         case 7:
-            Write8(0x0F); Write8(0x1F); Write8(0x80); Write8(0x00);
-            Write8(0x00); Write8(0x00); Write8(0x00);
+            Write8(0x0F);
+            Write8(0x1F);
+            Write8(0x80);
+            Write8(0x00);
+            Write8(0x00);
+            Write8(0x00);
+            Write8(0x00);
             return;
         case 8:
-            Write8(0x0F); Write8(0x1F); Write8(0x84); Write8(0x00);
-            Write8(0x00); Write8(0x00); Write8(0x00); Write8(0x00);
+            Write8(0x0F);
+            Write8(0x1F);
+            Write8(0x84);
+            Write8(0x00);
+            Write8(0x00);
+            Write8(0x00);
+            Write8(0x00);
+            Write8(0x00);
             return;
         case 9:
-            Write8(0x66); Write8(0x0F); Write8(0x1F); Write8(0x84);
-            Write8(0x00); Write8(0x00); Write8(0x00); Write8(0x00);
+            Write8(0x66);
+            Write8(0x0F);
+            Write8(0x1F);
+            Write8(0x84);
+            Write8(0x00);
+            Write8(0x00);
+            Write8(0x00);
+            Write8(0x00);
             Write8(0x00);
             return;
         case 10:
-            Write8(0x66); Write8(0x66); Write8(0x0F); Write8(0x1F);
-            Write8(0x84); Write8(0x00); Write8(0x00); Write8(0x00);
-            Write8(0x00); Write8(0x00);
+            Write8(0x66);
+            Write8(0x66);
+            Write8(0x0F);
+            Write8(0x1F);
+            Write8(0x84);
+            Write8(0x00);
+            Write8(0x00);
+            Write8(0x00);
+            Write8(0x00);
+            Write8(0x00);
             return;
         default:
             // Even though x86 instructions are allowed to be up to 15 bytes long,
             // AMD advises against using NOPs longer than 11 bytes because they
             // carry a performance penalty on CPUs older than AMD family 16h.
-            Write8(0x66); Write8(0x66); Write8(0x66); Write8(0x0F);
-            Write8(0x1F); Write8(0x84); Write8(0x00); Write8(0x00);
-            Write8(0x00); Write8(0x00); Write8(0x00);
+            Write8(0x66);
+            Write8(0x66);
+            Write8(0x66);
+            Write8(0x0F);
+            Write8(0x1F);
+            Write8(0x84);
+            Write8(0x00);
+            Write8(0x00);
+            Write8(0x00);
+            Write8(0x00);
+            Write8(0x00);
             size -= 11;
             continue;
         }
     }
 }
 
-void XEmitter::PAUSE() {Write8(0xF3); NOP();} //use in tight spinloops for energy saving on some cpu
-void XEmitter::CLC()  {CheckFlags(); Write8(0xF8);} //clear carry
-void XEmitter::CMC()  {CheckFlags(); Write8(0xF5);} //flip carry
-void XEmitter::STC()  {CheckFlags(); Write8(0xF9);} //set carry
+void XEmitter::PAUSE() {
+    Write8(0xF3);
+    NOP();
+} // use in tight spinloops for energy saving on some cpu
+void XEmitter::CLC() {
+    CheckFlags();
+    Write8(0xF8);
+} // clear carry
+void XEmitter::CMC() {
+    CheckFlags();
+    Write8(0xF5);
+} // flip carry
+void XEmitter::STC() {
+    CheckFlags();
+    Write8(0xF9);
+} // set carry
 
-//TODO: xchg ah, al ???
-void XEmitter::XCHG_AHAL()
-{
+// TODO: xchg ah, al ???
+void XEmitter::XCHG_AHAL() {
     Write8(0x86);
     Write8(0xe0);
     // alt. 86 c4
 }
 
-//These two can not be executed on early Intel 64-bit CPU:s, only on AMD!
-void XEmitter::LAHF() {Write8(0x9F);}
-void XEmitter::SAHF() {CheckFlags(); Write8(0x9E);}
+// These two can not be executed on early Intel 64-bit CPU:s, only on AMD!
+void XEmitter::LAHF() {
+    Write8(0x9F);
+}
+void XEmitter::SAHF() {
+    CheckFlags();
+    Write8(0x9E);
+}
 
-void XEmitter::PUSHF() {Write8(0x9C);}
-void XEmitter::POPF()  {CheckFlags(); Write8(0x9D);}
+void XEmitter::PUSHF() {
+    Write8(0x9C);
+}
+void XEmitter::POPF() {
+    CheckFlags();
+    Write8(0x9D);
+}
 
-void XEmitter::LFENCE() {Write8(0x0F); Write8(0xAE); Write8(0xE8);}
-void XEmitter::MFENCE() {Write8(0x0F); Write8(0xAE); Write8(0xF0);}
-void XEmitter::SFENCE() {Write8(0x0F); Write8(0xAE); Write8(0xF8);}
+void XEmitter::LFENCE() {
+    Write8(0x0F);
+    Write8(0xAE);
+    Write8(0xE8);
+}
+void XEmitter::MFENCE() {
+    Write8(0x0F);
+    Write8(0xAE);
+    Write8(0xF0);
+}
+void XEmitter::SFENCE() {
+    Write8(0x0F);
+    Write8(0xAE);
+    Write8(0xF8);
+}
 
-void XEmitter::WriteSimple1Byte(int bits, u8 byte, X64Reg reg)
-{
+void XEmitter::WriteSimple1Byte(int bits, u8 byte, X64Reg reg) {
     if (bits == 16)
         Write8(0x66);
     Rex(bits == 64, 0, 0, (int)reg >> 3);
     Write8(byte + ((int)reg & 7));
 }
 
-void XEmitter::WriteSimple2Byte(int bits, u8 byte1, u8 byte2, X64Reg reg)
-{
+void XEmitter::WriteSimple2Byte(int bits, u8 byte1, u8 byte2, X64Reg reg) {
     if (bits == 16)
         Write8(0x66);
-    Rex(bits==64, 0, 0, (int)reg >> 3);
+    Rex(bits == 64, 0, 0, (int)reg >> 3);
     Write8(byte1);
     Write8(byte2 + ((int)reg & 7));
 }
 
-void XEmitter::CWD(int bits)
-{
+void XEmitter::CWD(int bits) {
     if (bits == 16)
         Write8(0x66);
     Rex(bits == 64, 0, 0, 0);
     Write8(0x99);
 }
 
-void XEmitter::CBW(int bits)
-{
+void XEmitter::CBW(int bits) {
     if (bits == 8)
         Write8(0x66);
     Rex(bits == 32, 0, 0, 0);
     Write8(0x98);
 }
 
-//Simple opcodes
-
+// Simple opcodes
 
-//push/pop do not need wide to be 64-bit
-void XEmitter::PUSH(X64Reg reg) {WriteSimple1Byte(32, 0x50, reg);}
-void XEmitter::POP(X64Reg reg)  {WriteSimple1Byte(32, 0x58, reg);}
+// push/pop do not need wide to be 64-bit
+void XEmitter::PUSH(X64Reg reg) {
+    WriteSimple1Byte(32, 0x50, reg);
+}
+void XEmitter::POP(X64Reg reg) {
+    WriteSimple1Byte(32, 0x58, reg);
+}
 
-void XEmitter::PUSH(int bits, const OpArg& reg)
-{
+void XEmitter::PUSH(int bits, const OpArg& reg) {
     if (reg.IsSimpleReg())
         PUSH(reg.GetSimpleReg());
-    else if (reg.IsImm())
-    {
-        switch (reg.GetImmBits())
-        {
+    else if (reg.IsImm()) {
+        switch (reg.GetImmBits()) {
         case 8:
             Write8(0x6A);
             Write8((u8)(s8)reg.offset);
@@ -715,9 +744,7 @@ void XEmitter::PUSH(int bits, const OpArg& reg)
             ASSERT_MSG(0, "PUSH - Bad imm bits");
             break;
         }
-    }
-    else
-    {
+    } else {
         if (bits == 16)
             Write8(0x66);
         reg.WriteRex(this, bits, bits);
@@ -726,44 +753,33 @@ void XEmitter::PUSH(int bits, const OpArg& reg)
     }
 }
 
-void XEmitter::POP(int /*bits*/, const OpArg& reg)
-{
+void XEmitter::POP(int /*bits*/, const OpArg& reg) {
     if (reg.IsSimpleReg())
         POP(reg.GetSimpleReg());
     else
         ASSERT_MSG(0, "POP - Unsupported encoding");
 }
 
-void XEmitter::BSWAP(int bits, X64Reg reg)
-{
-    if (bits >= 32)
-    {
+void XEmitter::BSWAP(int bits, X64Reg reg) {
+    if (bits >= 32) {
         WriteSimple2Byte(bits, 0x0F, 0xC8, reg);
-    }
-    else if (bits == 16)
-    {
+    } else if (bits == 16) {
         ROL(16, R(reg), Imm8(8));
-    }
-    else if (bits == 8)
-    {
+    } else if (bits == 8) {
         // Do nothing - can't bswap a single byte...
-    }
-    else
-    {
+    } else {
         ASSERT_MSG(0, "BSWAP - Wrong number of bits");
     }
 }
 
 // Undefined opcode - reserved
 // If we ever need a way to always cause a non-breakpoint hard exception...
-void XEmitter::UD2()
-{
+void XEmitter::UD2() {
     Write8(0x0F);
     Write8(0x0B);
 }
 
-void XEmitter::PREFETCH(PrefetchLevel level, OpArg arg)
-{
+void XEmitter::PREFETCH(PrefetchLevel level, OpArg arg) {
     ASSERT_MSG(!arg.IsImm(), "PREFETCH - Imm argument");
     arg.operandReg = (u8)level;
     arg.WriteRex(this, 0, 0);
@@ -772,8 +788,7 @@ void XEmitter::PREFETCH(PrefetchLevel level, OpArg arg)
     arg.WriteRest(this);
 }
 
-void XEmitter::SETcc(CCFlags flag, OpArg dest)
-{
+void XEmitter::SETcc(CCFlags flag, OpArg dest) {
     ASSERT_MSG(!dest.IsImm(), "SETcc - Imm argument");
     dest.operandReg = 0;
     dest.WriteRex(this, 0, 8);
@@ -782,8 +797,7 @@ void XEmitter::SETcc(CCFlags flag, OpArg dest)
     dest.WriteRest(this);
 }
 
-void XEmitter::CMOVcc(int bits, X64Reg dest, OpArg src, CCFlags flag)
-{
+void XEmitter::CMOVcc(int bits, X64Reg dest, OpArg src, CCFlags flag) {
     ASSERT_MSG(!src.IsImm(), "CMOVcc - Imm argument");
     ASSERT_MSG(bits != 8, "CMOVcc - 8 bits unsupported");
     if (bits == 16)
@@ -795,34 +809,41 @@ void XEmitter::CMOVcc(int bits, X64Reg dest, OpArg src, CCFlags flag)
     src.WriteRest(this);
 }
 
-void XEmitter::WriteMulDivType(int bits, OpArg src, int ext)
-{
+void XEmitter::WriteMulDivType(int bits, OpArg src, int ext) {
     ASSERT_MSG(!src.IsImm(), "WriteMulDivType - Imm argument");
     CheckFlags();
     src.operandReg = ext;
     if (bits == 16)
         Write8(0x66);
     src.WriteRex(this, bits, bits, 0);
-    if (bits == 8)
-    {
+    if (bits == 8) {
         Write8(0xF6);
-    }
-    else
-    {
+    } else {
         Write8(0xF7);
     }
     src.WriteRest(this);
 }
 
-void XEmitter::MUL(int bits, const OpArg& src)  {WriteMulDivType(bits, src, 4);}
-void XEmitter::DIV(int bits, const OpArg& src)  {WriteMulDivType(bits, src, 6);}
-void XEmitter::IMUL(int bits, const OpArg& src) {WriteMulDivType(bits, src, 5);}
-void XEmitter::IDIV(int bits, const OpArg& src) {WriteMulDivType(bits, src, 7);}
-void XEmitter::NEG(int bits, const OpArg& src)  {WriteMulDivType(bits, src, 3);}
-void XEmitter::NOT(int bits, const OpArg& src)  {WriteMulDivType(bits, src, 2);}
+void XEmitter::MUL(int bits, const OpArg& src) {
+    WriteMulDivType(bits, src, 4);
+}
+void XEmitter::DIV(int bits, const OpArg& src) {
+    WriteMulDivType(bits, src, 6);
+}
+void XEmitter::IMUL(int bits, const OpArg& src) {
+    WriteMulDivType(bits, src, 5);
+}
+void XEmitter::IDIV(int bits, const OpArg& src) {
+    WriteMulDivType(bits, src, 7);
+}
+void XEmitter::NEG(int bits, const OpArg& src) {
+    WriteMulDivType(bits, src, 3);
+}
+void XEmitter::NOT(int bits, const OpArg& src) {
+    WriteMulDivType(bits, src, 2);
+}
 
-void XEmitter::WriteBitSearchType(int bits, X64Reg dest, OpArg src, u8 byte2, bool rep)
-{
+void XEmitter::WriteBitSearchType(int bits, X64Reg dest, OpArg src, u8 byte2, bool rep) {
     ASSERT_MSG(!src.IsImm(), "WriteBitSearchType - Imm argument");
     CheckFlags();
     src.operandReg = (u8)dest;
@@ -836,36 +857,35 @@ void XEmitter::WriteBitSearchType(int bits, X64Reg dest, OpArg src, u8 byte2, bo
     src.WriteRest(this);
 }
 
-void XEmitter::MOVNTI(int bits, const OpArg& dest, X64Reg src)
-{
+void XEmitter::MOVNTI(int bits, const OpArg& dest, X64Reg src) {
     if (bits <= 16)
         ASSERT_MSG(0, "MOVNTI - bits<=16");
     WriteBitSearchType(bits, src, dest, 0xC3);
 }
 
-void XEmitter::BSF(int bits, X64Reg dest, const OpArg& src) {WriteBitSearchType(bits,dest,src,0xBC);} // Bottom bit to top bit
-void XEmitter::BSR(int bits, X64Reg dest, const OpArg& src) {WriteBitSearchType(bits,dest,src,0xBD);} // Top bit to bottom bit
+void XEmitter::BSF(int bits, X64Reg dest, const OpArg& src) {
+    WriteBitSearchType(bits, dest, src, 0xBC);
+} // Bottom bit to top bit
+void XEmitter::BSR(int bits, X64Reg dest, const OpArg& src) {
+    WriteBitSearchType(bits, dest, src, 0xBD);
+} // Top bit to bottom bit
 
-void XEmitter::TZCNT(int bits, X64Reg dest, const OpArg& src)
-{
+void XEmitter::TZCNT(int bits, X64Reg dest, const OpArg& src) {
     CheckFlags();
     if (!Common::GetCPUCaps().bmi1)
         ASSERT_MSG(0, "Trying to use BMI1 on a system that doesn't support it. Bad programmer.");
     WriteBitSearchType(bits, dest, src, 0xBC, true);
 }
-void XEmitter::LZCNT(int bits, X64Reg dest, const OpArg& src)
-{
+void XEmitter::LZCNT(int bits, X64Reg dest, const OpArg& src) {
     CheckFlags();
     if (!Common::GetCPUCaps().lzcnt)
         ASSERT_MSG(0, "Trying to use LZCNT on a system that doesn't support it. Bad programmer.");
     WriteBitSearchType(bits, dest, src, 0xBD, true);
 }
 
-void XEmitter::MOVSX(int dbits, int sbits, X64Reg dest, OpArg src)
-{
+void XEmitter::MOVSX(int dbits, int sbits, X64Reg dest, OpArg src) {
     ASSERT_MSG(!src.IsImm(), "MOVSX - Imm argument");
-    if (dbits == sbits)
-    {
+    if (dbits == sbits) {
         MOV(dbits, R(dest), src);
         return;
     }
@@ -873,66 +893,49 @@ void XEmitter::MOVSX(int dbits, int sbits, X64Reg dest, OpArg src)
     if (dbits == 16)
         Write8(0x66);
     src.WriteRex(this, dbits, sbits);
-    if (sbits == 8)
-    {
+    if (sbits == 8) {
         Write8(0x0F);
         Write8(0xBE);
-    }
-    else if (sbits == 16)
-    {
+    } else if (sbits == 16) {
         Write8(0x0F);
         Write8(0xBF);
-    }
-    else if (sbits == 32 && dbits == 64)
-    {
+    } else if (sbits == 32 && dbits == 64) {
         Write8(0x63);
-    }
-    else
-    {
+    } else {
         Crash();
     }
     src.WriteRest(this);
 }
 
-void XEmitter::MOVZX(int dbits, int sbits, X64Reg dest, OpArg src)
-{
+void XEmitter::MOVZX(int dbits, int sbits, X64Reg dest, OpArg src) {
     ASSERT_MSG(!src.IsImm(), "MOVZX - Imm argument");
-    if (dbits == sbits)
-    {
+    if (dbits == sbits) {
         MOV(dbits, R(dest), src);
         return;
     }
     src.operandReg = (u8)dest;
     if (dbits == 16)
         Write8(0x66);
-    //the 32bit result is automatically zero extended to 64bit
+    // the 32bit result is automatically zero extended to 64bit
     src.WriteRex(this, dbits == 64 ? 32 : dbits, sbits);
-    if (sbits == 8)
-    {
+    if (sbits == 8) {
         Write8(0x0F);
         Write8(0xB6);
-    }
-    else if (sbits == 16)
-    {
+    } else if (sbits == 16) {
         Write8(0x0F);
         Write8(0xB7);
-    }
-    else if (sbits == 32 && dbits == 64)
-    {
+    } else if (sbits == 32 && dbits == 64) {
         Write8(0x8B);
-    }
-    else
-    {
+    } else {
         ASSERT_MSG(0, "MOVZX - Invalid size");
     }
     src.WriteRest(this);
 }
 
-void XEmitter::MOVBE(int bits, const OpArg& dest, const OpArg& src)
-{
-    ASSERT_MSG(Common::GetCPUCaps().movbe, "Generating MOVBE on a system that does not support it.");
-    if (bits == 8)
-    {
+void XEmitter::MOVBE(int bits, const OpArg& dest, const OpArg& src) {
+    ASSERT_MSG(Common::GetCPUCaps().movbe,
+               "Generating MOVBE on a system that does not support it.");
+    if (bits == 8) {
         MOV(bits, dest, src);
         return;
     }
@@ -940,71 +943,60 @@ void XEmitter::MOVBE(int bits, const OpArg& dest, const OpArg& src)
     if (bits == 16)
         Write8(0x66);
 
-    if (dest.IsSimpleReg())
-    {
+    if (dest.IsSimpleReg()) {
         ASSERT_MSG(!src.IsSimpleReg() && !src.IsImm(), "MOVBE: Loading from !mem");
         src.WriteRex(this, bits, bits, dest.GetSimpleReg());
-        Write8(0x0F); Write8(0x38); Write8(0xF0);
+        Write8(0x0F);
+        Write8(0x38);
+        Write8(0xF0);
         src.WriteRest(this, 0, dest.GetSimpleReg());
-    }
-    else if (src.IsSimpleReg())
-    {
+    } else if (src.IsSimpleReg()) {
         ASSERT_MSG(!dest.IsSimpleReg() && !dest.IsImm(), "MOVBE: Storing to !mem");
         dest.WriteRex(this, bits, bits, src.GetSimpleReg());
-        Write8(0x0F); Write8(0x38); Write8(0xF1);
+        Write8(0x0F);
+        Write8(0x38);
+        Write8(0xF1);
         dest.WriteRest(this, 0, src.GetSimpleReg());
-    }
-    else
-    {
+    } else {
         ASSERT_MSG(0, "MOVBE: Not loading or storing to mem");
     }
 }
 
-
-void XEmitter::LEA(int bits, X64Reg dest, OpArg src)
-{
+void XEmitter::LEA(int bits, X64Reg dest, OpArg src) {
     ASSERT_MSG(!src.IsImm(), "LEA - Imm argument");
     src.operandReg = (u8)dest;
     if (bits == 16)
-        Write8(0x66); //TODO: performance warning
+        Write8(0x66); // TODO: performance warning
     src.WriteRex(this, bits, bits);
     Write8(0x8D);
     src.WriteRest(this, 0, INVALID_REG, bits == 64);
 }
 
-//shift can be either imm8 or cl
-void XEmitter::WriteShift(int bits, OpArg dest, const OpArg& shift, int ext)
-{
+// shift can be either imm8 or cl
+void XEmitter::WriteShift(int bits, OpArg dest, const OpArg& shift, int ext) {
     CheckFlags();
     bool writeImm = false;
-    if (dest.IsImm())
-    {
+    if (dest.IsImm()) {
         ASSERT_MSG(0, "WriteShift - can't shift imms");
     }
-    if ((shift.IsSimpleReg() && shift.GetSimpleReg() != ECX) || (shift.IsImm() && shift.GetImmBits() != 8))
-    {
+    if ((shift.IsSimpleReg() && shift.GetSimpleReg() != ECX) ||
+        (shift.IsImm() && shift.GetImmBits() != 8)) {
         ASSERT_MSG(0, "WriteShift - illegal argument");
     }
     dest.operandReg = ext;
     if (bits == 16)
         Write8(0x66);
     dest.WriteRex(this, bits, bits, 0);
-    if (shift.GetImmBits() == 8)
-    {
-        //ok an imm
+    if (shift.GetImmBits() == 8) {
+        // ok an imm
         u8 imm = (u8)shift.offset;
-        if (imm == 1)
-        {
+        if (imm == 1) {
             Write8(bits == 8 ? 0xD0 : 0xD1);
-        }
-        else
-        {
+        } else {
             writeImm = true;
             Write8(bits == 8 ? 0xC0 : 0xC1);
         }
-    }
-    else
-    {
+    } else {
         Write8(bits == 8 ? 0xD2 : 0xD3);
     }
     dest.WriteRest(this, writeImm ? 1 : 0);
@@ -1014,116 +1006,125 @@ void XEmitter::WriteShift(int bits, OpArg dest, const OpArg& shift, int ext)
 
 // large rotates and shift are slower on intel than amd
 // intel likes to rotate by 1, and the op is smaller too
-void XEmitter::ROL(int bits, const OpArg& dest, const OpArg& shift) {WriteShift(bits, dest, shift, 0);}
-void XEmitter::ROR(int bits, const OpArg& dest, const OpArg& shift) {WriteShift(bits, dest, shift, 1);}
-void XEmitter::RCL(int bits, const OpArg& dest, const OpArg& shift) {WriteShift(bits, dest, shift, 2);}
-void XEmitter::RCR(int bits, const OpArg& dest, const OpArg& shift) {WriteShift(bits, dest, shift, 3);}
-void XEmitter::SHL(int bits, const OpArg& dest, const OpArg& shift) {WriteShift(bits, dest, shift, 4);}
-void XEmitter::SHR(int bits, const OpArg& dest, const OpArg& shift) {WriteShift(bits, dest, shift, 5);}
-void XEmitter::SAR(int bits, const OpArg& dest, const OpArg& shift) {WriteShift(bits, dest, shift, 7);}
+void XEmitter::ROL(int bits, const OpArg& dest, const OpArg& shift) {
+    WriteShift(bits, dest, shift, 0);
+}
+void XEmitter::ROR(int bits, const OpArg& dest, const OpArg& shift) {
+    WriteShift(bits, dest, shift, 1);
+}
+void XEmitter::RCL(int bits, const OpArg& dest, const OpArg& shift) {
+    WriteShift(bits, dest, shift, 2);
+}
+void XEmitter::RCR(int bits, const OpArg& dest, const OpArg& shift) {
+    WriteShift(bits, dest, shift, 3);
+}
+void XEmitter::SHL(int bits, const OpArg& dest, const OpArg& shift) {
+    WriteShift(bits, dest, shift, 4);
+}
+void XEmitter::SHR(int bits, const OpArg& dest, const OpArg& shift) {
+    WriteShift(bits, dest, shift, 5);
+}
+void XEmitter::SAR(int bits, const OpArg& dest, const OpArg& shift) {
+    WriteShift(bits, dest, shift, 7);
+}
 
 // index can be either imm8 or register, don't use memory destination because it's slow
-void XEmitter::WriteBitTest(int bits, const OpArg& dest, const OpArg& index, int ext)
-{
+void XEmitter::WriteBitTest(int bits, const OpArg& dest, const OpArg& index, int ext) {
     CheckFlags();
-    if (dest.IsImm())
-    {
+    if (dest.IsImm()) {
         ASSERT_MSG(0, "WriteBitTest - can't test imms");
     }
-    if ((index.IsImm() && index.GetImmBits() != 8))
-    {
+    if ((index.IsImm() && index.GetImmBits() != 8)) {
         ASSERT_MSG(0, "WriteBitTest - illegal argument");
     }
     if (bits == 16)
         Write8(0x66);
-    if (index.IsImm())
-    {
+    if (index.IsImm()) {
         dest.WriteRex(this, bits, bits);
-        Write8(0x0F); Write8(0xBA);
+        Write8(0x0F);
+        Write8(0xBA);
         dest.WriteRest(this, 1, (X64Reg)ext);
         Write8((u8)index.offset);
-    }
-    else
-    {
+    } else {
         X64Reg operand = index.GetSimpleReg();
         dest.WriteRex(this, bits, bits, operand);
-        Write8(0x0F); Write8(0x83 + 8*ext);
+        Write8(0x0F);
+        Write8(0x83 + 8 * ext);
         dest.WriteRest(this, 1, operand);
     }
 }
 
-void XEmitter::BT(int bits, const OpArg& dest, const OpArg& index)  {WriteBitTest(bits, dest, index, 4);}
-void XEmitter::BTS(int bits, const OpArg& dest, const OpArg& index) {WriteBitTest(bits, dest, index, 5);}
-void XEmitter::BTR(int bits, const OpArg& dest, const OpArg& index) {WriteBitTest(bits, dest, index, 6);}
-void XEmitter::BTC(int bits, const OpArg& dest, const OpArg& index) {WriteBitTest(bits, dest, index, 7);}
+void XEmitter::BT(int bits, const OpArg& dest, const OpArg& index) {
+    WriteBitTest(bits, dest, index, 4);
+}
+void XEmitter::BTS(int bits, const OpArg& dest, const OpArg& index) {
+    WriteBitTest(bits, dest, index, 5);
+}
+void XEmitter::BTR(int bits, const OpArg& dest, const OpArg& index) {
+    WriteBitTest(bits, dest, index, 6);
+}
+void XEmitter::BTC(int bits, const OpArg& dest, const OpArg& index) {
+    WriteBitTest(bits, dest, index, 7);
+}
 
-//shift can be either imm8 or cl
-void XEmitter::SHRD(int bits, const OpArg& dest, const OpArg& src, const OpArg& shift)
-{
+// shift can be either imm8 or cl
+void XEmitter::SHRD(int bits, const OpArg& dest, const OpArg& src, const OpArg& shift) {
     CheckFlags();
-    if (dest.IsImm())
-    {
+    if (dest.IsImm()) {
         ASSERT_MSG(0, "SHRD - can't use imms as destination");
     }
-    if (!src.IsSimpleReg())
-    {
+    if (!src.IsSimpleReg()) {
         ASSERT_MSG(0, "SHRD - must use simple register as source");
     }
-    if ((shift.IsSimpleReg() && shift.GetSimpleReg() != ECX) || (shift.IsImm() && shift.GetImmBits() != 8))
-    {
+    if ((shift.IsSimpleReg() && shift.GetSimpleReg() != ECX) ||
+        (shift.IsImm() && shift.GetImmBits() != 8)) {
         ASSERT_MSG(0, "SHRD - illegal shift");
     }
     if (bits == 16)
         Write8(0x66);
     X64Reg operand = src.GetSimpleReg();
     dest.WriteRex(this, bits, bits, operand);
-    if (shift.GetImmBits() == 8)
-    {
-        Write8(0x0F); Write8(0xAC);
+    if (shift.GetImmBits() == 8) {
+        Write8(0x0F);
+        Write8(0xAC);
         dest.WriteRest(this, 1, operand);
         Write8((u8)shift.offset);
-    }
-    else
-    {
-        Write8(0x0F); Write8(0xAD);
+    } else {
+        Write8(0x0F);
+        Write8(0xAD);
         dest.WriteRest(this, 0, operand);
     }
 }
 
-void XEmitter::SHLD(int bits, const OpArg& dest, const OpArg& src, const OpArg& shift)
-{
+void XEmitter::SHLD(int bits, const OpArg& dest, const OpArg& src, const OpArg& shift) {
     CheckFlags();
-    if (dest.IsImm())
-    {
+    if (dest.IsImm()) {
         ASSERT_MSG(0, "SHLD - can't use imms as destination");
     }
-    if (!src.IsSimpleReg())
-    {
+    if (!src.IsSimpleReg()) {
         ASSERT_MSG(0, "SHLD - must use simple register as source");
     }
-    if ((shift.IsSimpleReg() && shift.GetSimpleReg() != ECX) || (shift.IsImm() && shift.GetImmBits() != 8))
-    {
+    if ((shift.IsSimpleReg() && shift.GetSimpleReg() != ECX) ||
+        (shift.IsImm() && shift.GetImmBits() != 8)) {
         ASSERT_MSG(0, "SHLD - illegal shift");
     }
     if (bits == 16)
         Write8(0x66);
     X64Reg operand = src.GetSimpleReg();
     dest.WriteRex(this, bits, bits, operand);
-    if (shift.GetImmBits() == 8)
-    {
-        Write8(0x0F); Write8(0xA4);
+    if (shift.GetImmBits() == 8) {
+        Write8(0x0F);
+        Write8(0xA4);
         dest.WriteRest(this, 1, operand);
         Write8((u8)shift.offset);
-    }
-    else
-    {
-        Write8(0x0F); Write8(0xA5);
+    } else {
+        Write8(0x0F);
+        Write8(0xA5);
         dest.WriteRest(this, 0, operand);
     }
 }
 
-void OpArg::WriteSingleByteOp(XEmitter *emit, u8 op, X64Reg _operandReg, int bits)
-{
+void OpArg::WriteSingleByteOp(XEmitter* emit, u8 op, X64Reg _operandReg, int bits) {
     if (bits == 16)
         emit->Write8(0x66);
 
@@ -1133,12 +1134,11 @@ void OpArg::WriteSingleByteOp(XEmitter *emit, u8 op, X64Reg _operandReg, int bit
     WriteRest(emit);
 }
 
-//operand can either be immediate or register
-void OpArg::WriteNormalOp(XEmitter *emit, bool toRM, NormalOp op, const OpArg& operand, int bits) const
-{
+// operand can either be immediate or register
+void OpArg::WriteNormalOp(XEmitter* emit, bool toRM, NormalOp op, const OpArg& operand,
+                          int bits) const {
     X64Reg _operandReg;
-    if (IsImm())
-    {
+    if (IsImm()) {
         ASSERT_MSG(0, "WriteNormalOp - Imm argument, wrong order");
     }
 
@@ -1147,27 +1147,22 @@ void OpArg::WriteNormalOp(XEmitter *emit, bool toRM, NormalOp op, const OpArg& o
 
     int immToWrite = 0;
 
-    if (operand.IsImm())
-    {
+    if (operand.IsImm()) {
         WriteRex(emit, bits, bits);
 
-        if (!toRM)
-        {
+        if (!toRM) {
             ASSERT_MSG(0, "WriteNormalOp - Writing to Imm (!toRM)");
         }
 
-        if (operand.scale == SCALE_IMM8 && bits == 8)
-        {
+        if (operand.scale == SCALE_IMM8 && bits == 8) {
             // op al, imm8
-            if (!scale && offsetOrBaseReg == AL && normalops[op].eaximm8 != 0xCC)
-            {
+            if (!scale && offsetOrBaseReg == AL && normalops[op].eaximm8 != 0xCC) {
                 emit->Write8(normalops[op].eaximm8);
                 emit->Write8((u8)operand.offset);
                 return;
             }
             // mov reg, imm8
-            if (!scale && op == nrmMOV)
-            {
+            if (!scale && op == nrmMOV) {
                 emit->Write8(0xB0 + (offsetOrBaseReg & 7));
                 emit->Write8((u8)operand.offset);
                 return;
@@ -1175,26 +1170,20 @@ void OpArg::WriteNormalOp(XEmitter *emit, bool toRM, NormalOp op, const OpArg& o
             // op r/m8, imm8
             emit->Write8(normalops[op].imm8);
             immToWrite = 8;
-        }
-        else if ((operand.scale == SCALE_IMM16 && bits == 16) ||
-                 (operand.scale == SCALE_IMM32 && bits == 32) ||
-                 (operand.scale == SCALE_IMM32 && bits == 64))
-        {
+        } else if ((operand.scale == SCALE_IMM16 && bits == 16) ||
+                   (operand.scale == SCALE_IMM32 && bits == 32) ||
+                   (operand.scale == SCALE_IMM32 && bits == 64)) {
             // Try to save immediate size if we can, but first check to see
             // if the instruction supports simm8.
             // op r/m, imm8
             if (normalops[op].simm8 != 0xCC &&
                 ((operand.scale == SCALE_IMM16 && (s16)operand.offset == (s8)operand.offset) ||
-                 (operand.scale == SCALE_IMM32 && (s32)operand.offset == (s8)operand.offset)))
-            {
+                 (operand.scale == SCALE_IMM32 && (s32)operand.offset == (s8)operand.offset))) {
                 emit->Write8(normalops[op].simm8);
                 immToWrite = 8;
-            }
-            else
-            {
+            } else {
                 // mov reg, imm
-                if (!scale && op == nrmMOV && bits != 64)
-                {
+                if (!scale && op == nrmMOV && bits != 64) {
                     emit->Write8(0xB8 + (offsetOrBaseReg & 7));
                     if (bits == 16)
                         emit->Write16((u16)operand.offset);
@@ -1203,8 +1192,7 @@ void OpArg::WriteNormalOp(XEmitter *emit, bool toRM, NormalOp op, const OpArg& o
                     return;
                 }
                 // op eax, imm
-                if (!scale && offsetOrBaseReg == EAX && normalops[op].eaximm32 != 0xCC)
-                {
+                if (!scale && offsetOrBaseReg == EAX && normalops[op].eaximm32 != 0xCC) {
                     emit->Write8(normalops[op].eaximm32);
                     if (bits == 16)
                         emit->Write16((u16)operand.offset);
@@ -1216,54 +1204,41 @@ void OpArg::WriteNormalOp(XEmitter *emit, bool toRM, NormalOp op, const OpArg& o
                 emit->Write8(normalops[op].imm32);
                 immToWrite = bits == 16 ? 16 : 32;
             }
-        }
-        else if ((operand.scale == SCALE_IMM8 && bits == 16) ||
-                 (operand.scale == SCALE_IMM8 && bits == 32) ||
-                 (operand.scale == SCALE_IMM8 && bits == 64))
-        {
+        } else if ((operand.scale == SCALE_IMM8 && bits == 16) ||
+                   (operand.scale == SCALE_IMM8 && bits == 32) ||
+                   (operand.scale == SCALE_IMM8 && bits == 64)) {
             // op r/m, imm8
             emit->Write8(normalops[op].simm8);
             immToWrite = 8;
-        }
-        else if (operand.scale == SCALE_IMM64 && bits == 64)
-        {
-            if (scale)
-            {
+        } else if (operand.scale == SCALE_IMM64 && bits == 64) {
+            if (scale) {
                 ASSERT_MSG(0, "WriteNormalOp - MOV with 64-bit imm requres register destination");
             }
             // mov reg64, imm64
-            else if (op == nrmMOV)
-            {
+            else if (op == nrmMOV) {
                 emit->Write8(0xB8 + (offsetOrBaseReg & 7));
                 emit->Write64((u64)operand.offset);
                 return;
             }
             ASSERT_MSG(0, "WriteNormalOp - Only MOV can take 64-bit imm");
-        }
-        else
-        {
+        } else {
             ASSERT_MSG(0, "WriteNormalOp - Unhandled case");
         }
-        _operandReg = (X64Reg)normalops[op].ext; //pass extension in REG of ModRM
-    }
-    else
-    {
+        _operandReg = (X64Reg)normalops[op].ext; // pass extension in REG of ModRM
+    } else {
         _operandReg = (X64Reg)operand.offsetOrBaseReg;
         WriteRex(emit, bits, bits, _operandReg);
         // op r/m, reg
-        if (toRM)
-        {
+        if (toRM) {
             emit->Write8(bits == 8 ? normalops[op].toRm8 : normalops[op].toRm32);
         }
         // op reg, r/m
-        else
-        {
+        else {
             emit->Write8(bits == 8 ? normalops[op].fromRm8 : normalops[op].fromRm32);
         }
     }
     WriteRest(emit, immToWrite >> 3, _operandReg);
-    switch (immToWrite)
-    {
+    switch (immToWrite) {
     case 0:
         break;
     case 8:
@@ -1280,66 +1255,84 @@ void OpArg::WriteNormalOp(XEmitter *emit, bool toRM, NormalOp op, const OpArg& o
     }
 }
 
-void XEmitter::WriteNormalOp(XEmitter *emit, int bits, NormalOp op, const OpArg& a1, const OpArg& a2)
-{
-    if (a1.IsImm())
-    {
-        //Booh! Can't write to an imm
+void XEmitter::WriteNormalOp(XEmitter* emit, int bits, NormalOp op, const OpArg& a1,
+                             const OpArg& a2) {
+    if (a1.IsImm()) {
+        // Booh! Can't write to an imm
         ASSERT_MSG(0, "WriteNormalOp - a1 cannot be imm");
         return;
     }
-    if (a2.IsImm())
-    {
+    if (a2.IsImm()) {
         a1.WriteNormalOp(emit, true, op, a2, bits);
-    }
-    else
-    {
-        if (a1.IsSimpleReg())
-        {
+    } else {
+        if (a1.IsSimpleReg()) {
             a2.WriteNormalOp(emit, false, op, a1, bits);
-        }
-        else
-        {
-            ASSERT_MSG(a2.IsSimpleReg() || a2.IsImm(), "WriteNormalOp - a1 and a2 cannot both be memory");
+        } else {
+            ASSERT_MSG(a2.IsSimpleReg() || a2.IsImm(),
+                       "WriteNormalOp - a1 and a2 cannot both be memory");
             a1.WriteNormalOp(emit, true, op, a2, bits);
         }
     }
 }
 
-void XEmitter::ADD (int bits, const OpArg& a1, const OpArg& a2) {CheckFlags(); WriteNormalOp(this, bits, nrmADD, a1, a2);}
-void XEmitter::ADC (int bits, const OpArg& a1, const OpArg& a2) {CheckFlags(); WriteNormalOp(this, bits, nrmADC, a1, a2);}
-void XEmitter::SUB (int bits, const OpArg& a1, const OpArg& a2) {CheckFlags(); WriteNormalOp(this, bits, nrmSUB, a1, a2);}
-void XEmitter::SBB (int bits, const OpArg& a1, const OpArg& a2) {CheckFlags(); WriteNormalOp(this, bits, nrmSBB, a1, a2);}
-void XEmitter::AND (int bits, const OpArg& a1, const OpArg& a2) {CheckFlags(); WriteNormalOp(this, bits, nrmAND, a1, a2);}
-void XEmitter::OR  (int bits, const OpArg& a1, const OpArg& a2) {CheckFlags(); WriteNormalOp(this, bits, nrmOR , a1, a2);}
-void XEmitter::XOR (int bits, const OpArg& a1, const OpArg& a2) {CheckFlags(); WriteNormalOp(this, bits, nrmXOR, a1, a2);}
-void XEmitter::MOV (int bits, const OpArg& a1, const OpArg& a2)
-{
+void XEmitter::ADD(int bits, const OpArg& a1, const OpArg& a2) {
+    CheckFlags();
+    WriteNormalOp(this, bits, nrmADD, a1, a2);
+}
+void XEmitter::ADC(int bits, const OpArg& a1, const OpArg& a2) {
+    CheckFlags();
+    WriteNormalOp(this, bits, nrmADC, a1, a2);
+}
+void XEmitter::SUB(int bits, const OpArg& a1, const OpArg& a2) {
+    CheckFlags();
+    WriteNormalOp(this, bits, nrmSUB, a1, a2);
+}
+void XEmitter::SBB(int bits, const OpArg& a1, const OpArg& a2) {
+    CheckFlags();
+    WriteNormalOp(this, bits, nrmSBB, a1, a2);
+}
+void XEmitter::AND(int bits, const OpArg& a1, const OpArg& a2) {
+    CheckFlags();
+    WriteNormalOp(this, bits, nrmAND, a1, a2);
+}
+void XEmitter::OR(int bits, const OpArg& a1, const OpArg& a2) {
+    CheckFlags();
+    WriteNormalOp(this, bits, nrmOR, a1, a2);
+}
+void XEmitter::XOR(int bits, const OpArg& a1, const OpArg& a2) {
+    CheckFlags();
+    WriteNormalOp(this, bits, nrmXOR, a1, a2);
+}
+void XEmitter::MOV(int bits, const OpArg& a1, const OpArg& a2) {
     if (a1.IsSimpleReg() && a2.IsSimpleReg() && a1.GetSimpleReg() == a2.GetSimpleReg())
         LOG_ERROR(Common, "Redundant MOV @ %p - bug in JIT?", code);
     WriteNormalOp(this, bits, nrmMOV, a1, a2);
 }
-void XEmitter::TEST(int bits, const OpArg& a1, const OpArg& a2) {CheckFlags(); WriteNormalOp(this, bits, nrmTEST, a1, a2);}
-void XEmitter::CMP (int bits, const OpArg& a1, const OpArg& a2) {CheckFlags(); WriteNormalOp(this, bits, nrmCMP, a1, a2);}
-void XEmitter::XCHG(int bits, const OpArg& a1, const OpArg& a2) {WriteNormalOp(this, bits, nrmXCHG, a1, a2);}
+void XEmitter::TEST(int bits, const OpArg& a1, const OpArg& a2) {
+    CheckFlags();
+    WriteNormalOp(this, bits, nrmTEST, a1, a2);
+}
+void XEmitter::CMP(int bits, const OpArg& a1, const OpArg& a2) {
+    CheckFlags();
+    WriteNormalOp(this, bits, nrmCMP, a1, a2);
+}
+void XEmitter::XCHG(int bits, const OpArg& a1, const OpArg& a2) {
+    WriteNormalOp(this, bits, nrmXCHG, a1, a2);
+}
 
-void XEmitter::IMUL(int bits, X64Reg regOp, const OpArg& a1, const OpArg& a2)
-{
+void XEmitter::IMUL(int bits, X64Reg regOp, const OpArg& a1, const OpArg& a2) {
     CheckFlags();
-    if (bits == 8)
-    {
+    if (bits == 8) {
         ASSERT_MSG(0, "IMUL - illegal bit size!");
         return;
     }
 
-    if (a1.IsImm())
-    {
+    if (a1.IsImm()) {
         ASSERT_MSG(0, "IMUL - second arg cannot be imm!");
         return;
     }
 
-    if (!a2.IsImm())
-    {
+    if (!a2.IsImm()) {
         ASSERT_MSG(0, "IMUL - third arg must be imm!");
         return;
     }
@@ -1348,46 +1341,34 @@ void XEmitter::IMUL(int bits, X64Reg regOp, const OpArg& a1, const OpArg& a2)
         Write8(0x66);
     a1.WriteRex(this, bits, bits, regOp);
 
-    if (a2.GetImmBits() == 8 ||
-        (a2.GetImmBits() == 16 && (s8)a2.offset == (s16)a2.offset) ||
-        (a2.GetImmBits() == 32 && (s8)a2.offset == (s32)a2.offset))
-    {
+    if (a2.GetImmBits() == 8 || (a2.GetImmBits() == 16 && (s8)a2.offset == (s16)a2.offset) ||
+        (a2.GetImmBits() == 32 && (s8)a2.offset == (s32)a2.offset)) {
         Write8(0x6B);
         a1.WriteRest(this, 1, regOp);
         Write8((u8)a2.offset);
-    }
-    else
-    {
+    } else {
         Write8(0x69);
-        if (a2.GetImmBits() == 16 && bits == 16)
-        {
+        if (a2.GetImmBits() == 16 && bits == 16) {
             a1.WriteRest(this, 2, regOp);
             Write16((u16)a2.offset);
-        }
-        else if (a2.GetImmBits() == 32 && (bits == 32 || bits == 64))
-        {
+        } else if (a2.GetImmBits() == 32 && (bits == 32 || bits == 64)) {
             a1.WriteRest(this, 4, regOp);
             Write32((u32)a2.offset);
-        }
-        else
-        {
+        } else {
             ASSERT_MSG(0, "IMUL - unhandled case!");
         }
     }
 }
 
-void XEmitter::IMUL(int bits, X64Reg regOp, const OpArg& a)
-{
+void XEmitter::IMUL(int bits, X64Reg regOp, const OpArg& a) {
     CheckFlags();
-    if (bits == 8)
-    {
+    if (bits == 8) {
         ASSERT_MSG(0, "IMUL - illegal bit size!");
         return;
     }
 
-    if (a.IsImm())
-    {
-        IMUL(bits, regOp, R(regOp), a) ;
+    if (a.IsImm()) {
+        IMUL(bits, regOp, R(regOp), a);
         return;
     }
 
@@ -1399,9 +1380,7 @@ void XEmitter::IMUL(int bits, X64Reg regOp, const OpArg& a)
     a.WriteRest(this, 0, regOp);
 }
 
-
-void XEmitter::WriteSSEOp(u8 opPrefix, u16 op, X64Reg regOp, OpArg arg, int extrabytes)
-{
+void XEmitter::WriteSSEOp(u8 opPrefix, u16 op, X64Reg regOp, OpArg arg, int extrabytes) {
     if (opPrefix)
         Write8(opPrefix);
     arg.operandReg = regOp;
@@ -1413,13 +1392,11 @@ void XEmitter::WriteSSEOp(u8 opPrefix, u16 op, X64Reg regOp, OpArg arg, int extr
     arg.WriteRest(this, extrabytes);
 }
 
-void XEmitter::WriteAVXOp(u8 opPrefix, u16 op, X64Reg regOp, const OpArg& arg, int extrabytes)
-{
+void XEmitter::WriteAVXOp(u8 opPrefix, u16 op, X64Reg regOp, const OpArg& arg, int extrabytes) {
     WriteAVXOp(opPrefix, op, regOp, INVALID_REG, arg, extrabytes);
 }
 
-static int GetVEXmmmmm(u16 op)
-{
+static int GetVEXmmmmm(u16 op) {
     // Currently, only 0x38 and 0x3A are used as secondary escape byte.
     if ((op >> 8) == 0x3A)
         return 3;
@@ -1429,8 +1406,7 @@ static int GetVEXmmmmm(u16 op)
     return 1;
 }
 
-static int GetVEXpp(u8 opPrefix)
-{
+static int GetVEXpp(u8 opPrefix) {
     if (opPrefix == 0x66)
         return 1;
     if (opPrefix == 0xF3)
@@ -1441,21 +1417,22 @@ static int GetVEXpp(u8 opPrefix)
     return 0;
 }
 
-void XEmitter::WriteAVXOp(u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2, const OpArg& arg, int extrabytes)
-{
+void XEmitter::WriteAVXOp(u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2, const OpArg& arg,
+                          int extrabytes) {
     if (!Common::GetCPUCaps().avx)
         ASSERT_MSG(0, "Trying to use AVX on a system that doesn't support it. Bad programmer.");
     int mmmmm = GetVEXmmmmm(op);
     int pp = GetVEXpp(opPrefix);
-    // FIXME: we currently don't support 256-bit instructions, and "size" is not the vector size here
+    // FIXME: we currently don't support 256-bit instructions, and "size" is not the vector size
+    // here
     arg.WriteVex(this, regOp1, regOp2, 0, pp, mmmmm);
     Write8(op & 0xFF);
     arg.WriteRest(this, extrabytes, regOp1);
 }
 
 // Like the above, but more general; covers GPR-based VEX operations, like BMI1/2
-void XEmitter::WriteVEXOp(int size, u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2, const OpArg& arg, int extrabytes)
-{
+void XEmitter::WriteVEXOp(int size, u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2,
+                          const OpArg& arg, int extrabytes) {
     if (size != 32 && size != 64)
         ASSERT_MSG(0, "VEX GPR instructions only support 32-bit and 64-bit modes!");
     int mmmmm = GetVEXmmmmm(op);
@@ -1465,49 +1442,50 @@ void XEmitter::WriteVEXOp(int size, u8 opPrefix, u16 op, X64Reg regOp1, X64Reg r
     arg.WriteRest(this, extrabytes, regOp1);
 }
 
-void XEmitter::WriteBMI1Op(int size, u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2, const OpArg& arg, int extrabytes)
-{
+void XEmitter::WriteBMI1Op(int size, u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2,
+                           const OpArg& arg, int extrabytes) {
     CheckFlags();
     if (!Common::GetCPUCaps().bmi1)
         ASSERT_MSG(0, "Trying to use BMI1 on a system that doesn't support it. Bad programmer.");
     WriteVEXOp(size, opPrefix, op, regOp1, regOp2, arg, extrabytes);
 }
 
-void XEmitter::WriteBMI2Op(int size, u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2, const OpArg& arg, int extrabytes)
-{
+void XEmitter::WriteBMI2Op(int size, u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2,
+                           const OpArg& arg, int extrabytes) {
     CheckFlags();
     if (!Common::GetCPUCaps().bmi2)
         ASSERT_MSG(0, "Trying to use BMI2 on a system that doesn't support it. Bad programmer.");
     WriteVEXOp(size, opPrefix, op, regOp1, regOp2, arg, extrabytes);
 }
 
-void XEmitter::MOVD_xmm(X64Reg dest, const OpArg &arg) {WriteSSEOp(0x66, 0x6E, dest, arg, 0);}
-void XEmitter::MOVD_xmm(const OpArg &arg, X64Reg src) {WriteSSEOp(0x66, 0x7E, src, arg, 0);}
+void XEmitter::MOVD_xmm(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x6E, dest, arg, 0);
+}
+void XEmitter::MOVD_xmm(const OpArg& arg, X64Reg src) {
+    WriteSSEOp(0x66, 0x7E, src, arg, 0);
+}
 
-void XEmitter::MOVQ_xmm(X64Reg dest, OpArg arg)
-{
+void XEmitter::MOVQ_xmm(X64Reg dest, OpArg arg) {
 #ifdef ARCHITECTURE_x86_64
-        // Alternate encoding
-        // This does not display correctly in MSVC's debugger, it thinks it's a MOVD
-        arg.operandReg = dest;
-        Write8(0x66);
-        arg.WriteRex(this, 64, 0);
-        Write8(0x0f);
-        Write8(0x6E);
-        arg.WriteRest(this, 0);
+    // Alternate encoding
+    // This does not display correctly in MSVC's debugger, it thinks it's a MOVD
+    arg.operandReg = dest;
+    Write8(0x66);
+    arg.WriteRex(this, 64, 0);
+    Write8(0x0f);
+    Write8(0x6E);
+    arg.WriteRest(this, 0);
 #else
-        arg.operandReg = dest;
-        Write8(0xF3);
-        Write8(0x0f);
-        Write8(0x7E);
-        arg.WriteRest(this, 0);
+    arg.operandReg = dest;
+    Write8(0xF3);
+    Write8(0x0f);
+    Write8(0x7E);
+    arg.WriteRest(this, 0);
 #endif
 }
 
-void XEmitter::MOVQ_xmm(OpArg arg, X64Reg src)
-{
-    if (src > 7 || arg.IsSimpleReg())
-    {
+void XEmitter::MOVQ_xmm(OpArg arg, X64Reg src) {
+    if (src > 7 || arg.IsSimpleReg()) {
         // Alternate encoding
         // This does not display correctly in MSVC's debugger, it thinks it's a MOVD
         arg.operandReg = src;
@@ -1516,9 +1494,7 @@ void XEmitter::MOVQ_xmm(OpArg arg, X64Reg src)
         Write8(0x0f);
         Write8(0x7E);
         arg.WriteRest(this, 0);
-    }
-    else
-    {
+    } else {
         arg.operandReg = src;
         arg.WriteRex(this, 0, 0);
         Write8(0x66);
@@ -1528,8 +1504,7 @@ void XEmitter::MOVQ_xmm(OpArg arg, X64Reg src)
     }
 }
 
-void XEmitter::WriteMXCSR(OpArg arg, int ext)
-{
+void XEmitter::WriteMXCSR(OpArg arg, int ext) {
     if (arg.IsImm() || arg.IsSimpleReg())
         ASSERT_MSG(0, "MXCSR - invalid operand");
 
@@ -1540,143 +1515,357 @@ void XEmitter::WriteMXCSR(OpArg arg, int ext)
     arg.WriteRest(this);
 }
 
-void XEmitter::STMXCSR(const OpArg& memloc) {WriteMXCSR(memloc, 3);}
-void XEmitter::LDMXCSR(const OpArg& memloc) {WriteMXCSR(memloc, 2);}
-
-void XEmitter::MOVNTDQ(const OpArg& arg, X64Reg regOp) {WriteSSEOp(0x66, sseMOVNTDQ, regOp, arg);}
-void XEmitter::MOVNTPS(const OpArg& arg, X64Reg regOp) {WriteSSEOp(0x00, sseMOVNTP, regOp, arg);}
-void XEmitter::MOVNTPD(const OpArg& arg, X64Reg regOp) {WriteSSEOp(0x66, sseMOVNTP, regOp, arg);}
-
-void XEmitter::ADDSS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF3, sseADD, regOp, arg);}
-void XEmitter::ADDSD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF2, sseADD, regOp, arg);}
-void XEmitter::SUBSS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF3, sseSUB, regOp, arg);}
-void XEmitter::SUBSD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF2, sseSUB, regOp, arg);}
-void XEmitter::CMPSS(X64Reg regOp, const OpArg& arg, u8 compare)   {WriteSSEOp(0xF3, sseCMP, regOp, arg, 1); Write8(compare);}
-void XEmitter::CMPSD(X64Reg regOp, const OpArg& arg, u8 compare)   {WriteSSEOp(0xF2, sseCMP, regOp, arg, 1); Write8(compare);}
-void XEmitter::MULSS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF3, sseMUL, regOp, arg);}
-void XEmitter::MULSD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF2, sseMUL, regOp, arg);}
-void XEmitter::DIVSS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF3, sseDIV, regOp, arg);}
-void XEmitter::DIVSD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF2, sseDIV, regOp, arg);}
-void XEmitter::MINSS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF3, sseMIN, regOp, arg);}
-void XEmitter::MINSD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF2, sseMIN, regOp, arg);}
-void XEmitter::MAXSS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF3, sseMAX, regOp, arg);}
-void XEmitter::MAXSD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF2, sseMAX, regOp, arg);}
-void XEmitter::SQRTSS(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0xF3, sseSQRT, regOp, arg);}
-void XEmitter::SQRTSD(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0xF2, sseSQRT, regOp, arg);}
-void XEmitter::RCPSS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF3, sseRCP, regOp, arg);}
-void XEmitter::RSQRTSS(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0xF3, sseRSQRT, regOp, arg);}
-
-void XEmitter::ADDPS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x00, sseADD, regOp, arg);}
-void XEmitter::ADDPD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x66, sseADD, regOp, arg);}
-void XEmitter::SUBPS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x00, sseSUB, regOp, arg);}
-void XEmitter::SUBPD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x66, sseSUB, regOp, arg);}
-void XEmitter::CMPPS(X64Reg regOp, const OpArg& arg, u8 compare)   {WriteSSEOp(0x00, sseCMP, regOp, arg, 1); Write8(compare);}
-void XEmitter::CMPPD(X64Reg regOp, const OpArg& arg, u8 compare)   {WriteSSEOp(0x66, sseCMP, regOp, arg, 1); Write8(compare);}
-void XEmitter::ANDPS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x00, sseAND, regOp, arg);}
-void XEmitter::ANDPD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x66, sseAND, regOp, arg);}
-void XEmitter::ANDNPS(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0x00, sseANDN, regOp, arg);}
-void XEmitter::ANDNPD(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0x66, sseANDN, regOp, arg);}
-void XEmitter::ORPS(X64Reg regOp, const OpArg& arg)    {WriteSSEOp(0x00, sseOR, regOp, arg);}
-void XEmitter::ORPD(X64Reg regOp, const OpArg& arg)    {WriteSSEOp(0x66, sseOR, regOp, arg);}
-void XEmitter::XORPS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x00, sseXOR, regOp, arg);}
-void XEmitter::XORPD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x66, sseXOR, regOp, arg);}
-void XEmitter::MULPS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x00, sseMUL, regOp, arg);}
-void XEmitter::MULPD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x66, sseMUL, regOp, arg);}
-void XEmitter::DIVPS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x00, sseDIV, regOp, arg);}
-void XEmitter::DIVPD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x66, sseDIV, regOp, arg);}
-void XEmitter::MINPS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x00, sseMIN, regOp, arg);}
-void XEmitter::MINPD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x66, sseMIN, regOp, arg);}
-void XEmitter::MAXPS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x00, sseMAX, regOp, arg);}
-void XEmitter::MAXPD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0x66, sseMAX, regOp, arg);}
-void XEmitter::SQRTPS(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0x00, sseSQRT, regOp, arg);}
-void XEmitter::SQRTPD(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0x66, sseSQRT, regOp, arg);}
-void XEmitter::RCPPS(X64Reg regOp, const OpArg& arg) { WriteSSEOp(0x00, sseRCP, regOp, arg); }
-void XEmitter::RSQRTPS(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0x00, sseRSQRT, regOp, arg);}
-void XEmitter::SHUFPS(X64Reg regOp, const OpArg& arg, u8 shuffle) {WriteSSEOp(0x00, sseSHUF, regOp, arg,1); Write8(shuffle);}
-void XEmitter::SHUFPD(X64Reg regOp, const OpArg& arg, u8 shuffle) {WriteSSEOp(0x66, sseSHUF, regOp, arg,1); Write8(shuffle);}
-
-void XEmitter::HADDPS(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0xF2, sseHADD, regOp, arg);}
-
-void XEmitter::COMISS(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0x00, sseCOMIS, regOp, arg);} //weird that these should be packed
-void XEmitter::COMISD(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0x66, sseCOMIS, regOp, arg);} //ordered
-void XEmitter::UCOMISS(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0x00, sseUCOMIS, regOp, arg);} //unordered
-void XEmitter::UCOMISD(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0x66, sseUCOMIS, regOp, arg);}
-
-void XEmitter::MOVAPS(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0x00, sseMOVAPfromRM, regOp, arg);}
-void XEmitter::MOVAPD(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0x66, sseMOVAPfromRM, regOp, arg);}
-void XEmitter::MOVAPS(const OpArg& arg, X64Reg regOp)  {WriteSSEOp(0x00, sseMOVAPtoRM, regOp, arg);}
-void XEmitter::MOVAPD(const OpArg& arg, X64Reg regOp)  {WriteSSEOp(0x66, sseMOVAPtoRM, regOp, arg);}
-
-void XEmitter::MOVUPS(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0x00, sseMOVUPfromRM, regOp, arg);}
-void XEmitter::MOVUPD(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0x66, sseMOVUPfromRM, regOp, arg);}
-void XEmitter::MOVUPS(const OpArg& arg, X64Reg regOp)  {WriteSSEOp(0x00, sseMOVUPtoRM, regOp, arg);}
-void XEmitter::MOVUPD(const OpArg& arg, X64Reg regOp)  {WriteSSEOp(0x66, sseMOVUPtoRM, regOp, arg);}
-
-void XEmitter::MOVDQA(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0x66, sseMOVDQfromRM, regOp, arg);}
-void XEmitter::MOVDQA(const OpArg& arg, X64Reg regOp)  {WriteSSEOp(0x66, sseMOVDQtoRM, regOp, arg);}
-void XEmitter::MOVDQU(X64Reg regOp, const OpArg& arg)  {WriteSSEOp(0xF3, sseMOVDQfromRM, regOp, arg);}
-void XEmitter::MOVDQU(const OpArg& arg, X64Reg regOp)  {WriteSSEOp(0xF3, sseMOVDQtoRM, regOp, arg);}
-
-void XEmitter::MOVSS(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF3, sseMOVUPfromRM, regOp, arg);}
-void XEmitter::MOVSD(X64Reg regOp, const OpArg& arg)   {WriteSSEOp(0xF2, sseMOVUPfromRM, regOp, arg);}
-void XEmitter::MOVSS(const OpArg& arg, X64Reg regOp)   {WriteSSEOp(0xF3, sseMOVUPtoRM, regOp, arg);}
-void XEmitter::MOVSD(const OpArg& arg, X64Reg regOp)   {WriteSSEOp(0xF2, sseMOVUPtoRM, regOp, arg);}
-
-void XEmitter::MOVLPS(X64Reg regOp, const OpArg& arg)  { WriteSSEOp(0x00, sseMOVLPfromRM, regOp, arg); }
-void XEmitter::MOVLPD(X64Reg regOp, const OpArg& arg)  { WriteSSEOp(0x66, sseMOVLPfromRM, regOp, arg); }
-void XEmitter::MOVLPS(const OpArg& arg, X64Reg regOp)  { WriteSSEOp(0x00, sseMOVLPtoRM, regOp, arg); }
-void XEmitter::MOVLPD(const OpArg& arg, X64Reg regOp)  { WriteSSEOp(0x66, sseMOVLPtoRM, regOp, arg); }
-
-void XEmitter::MOVHPS(X64Reg regOp, const OpArg& arg)  { WriteSSEOp(0x00, sseMOVHPfromRM, regOp, arg); }
-void XEmitter::MOVHPD(X64Reg regOp, const OpArg& arg)  { WriteSSEOp(0x66, sseMOVHPfromRM, regOp, arg); }
-void XEmitter::MOVHPS(const OpArg& arg, X64Reg regOp)  { WriteSSEOp(0x00, sseMOVHPtoRM, regOp, arg); }
-void XEmitter::MOVHPD(const OpArg& arg, X64Reg regOp)  { WriteSSEOp(0x66, sseMOVHPtoRM, regOp, arg); }
-
-void XEmitter::MOVHLPS(X64Reg regOp1, X64Reg regOp2) {WriteSSEOp(0x00, sseMOVHLPS, regOp1, R(regOp2));}
-void XEmitter::MOVLHPS(X64Reg regOp1, X64Reg regOp2) {WriteSSEOp(0x00, sseMOVLHPS, regOp1, R(regOp2));}
-
-void XEmitter::CVTPS2PD(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0x00, 0x5A, regOp, arg);}
-void XEmitter::CVTPD2PS(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0x66, 0x5A, regOp, arg);}
-
-void XEmitter::CVTSD2SS(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0xF2, 0x5A, regOp, arg);}
-void XEmitter::CVTSS2SD(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0xF3, 0x5A, regOp, arg);}
-void XEmitter::CVTSD2SI(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0xF2, 0x2D, regOp, arg);}
-void XEmitter::CVTSS2SI(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0xF3, 0x2D, regOp, arg);}
-void XEmitter::CVTSI2SD(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0xF2, 0x2A, regOp, arg);}
-void XEmitter::CVTSI2SS(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0xF3, 0x2A, regOp, arg);}
-
-void XEmitter::CVTDQ2PD(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0xF3, 0xE6, regOp, arg);}
-void XEmitter::CVTDQ2PS(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0x00, 0x5B, regOp, arg);}
-void XEmitter::CVTPD2DQ(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0xF2, 0xE6, regOp, arg);}
-void XEmitter::CVTPS2DQ(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0x66, 0x5B, regOp, arg);}
-
-void XEmitter::CVTTSD2SI(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0xF2, 0x2C, regOp, arg);}
-void XEmitter::CVTTSS2SI(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0xF3, 0x2C, regOp, arg);}
-void XEmitter::CVTTPS2DQ(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0xF3, 0x5B, regOp, arg);}
-void XEmitter::CVTTPD2DQ(X64Reg regOp, const OpArg& arg) {WriteSSEOp(0x66, 0xE6, regOp, arg);}
-
-void XEmitter::MASKMOVDQU(X64Reg dest, X64Reg src)  {WriteSSEOp(0x66, sseMASKMOVDQU, dest, R(src));}
-
-void XEmitter::MOVMSKPS(X64Reg dest, const OpArg& arg) {WriteSSEOp(0x00, 0x50, dest, arg);}
-void XEmitter::MOVMSKPD(X64Reg dest, const OpArg& arg) {WriteSSEOp(0x66, 0x50, dest, arg);}
-
-void XEmitter::LDDQU(X64Reg dest, const OpArg& arg)    {WriteSSEOp(0xF2, sseLDDQU, dest, arg);} // For integer data only
+void XEmitter::STMXCSR(const OpArg& memloc) {
+    WriteMXCSR(memloc, 3);
+}
+void XEmitter::LDMXCSR(const OpArg& memloc) {
+    WriteMXCSR(memloc, 2);
+}
+
+void XEmitter::MOVNTDQ(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0x66, sseMOVNTDQ, regOp, arg);
+}
+void XEmitter::MOVNTPS(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0x00, sseMOVNTP, regOp, arg);
+}
+void XEmitter::MOVNTPD(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0x66, sseMOVNTP, regOp, arg);
+}
+
+void XEmitter::ADDSS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, sseADD, regOp, arg);
+}
+void XEmitter::ADDSD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, sseADD, regOp, arg);
+}
+void XEmitter::SUBSS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, sseSUB, regOp, arg);
+}
+void XEmitter::SUBSD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, sseSUB, regOp, arg);
+}
+void XEmitter::CMPSS(X64Reg regOp, const OpArg& arg, u8 compare) {
+    WriteSSEOp(0xF3, sseCMP, regOp, arg, 1);
+    Write8(compare);
+}
+void XEmitter::CMPSD(X64Reg regOp, const OpArg& arg, u8 compare) {
+    WriteSSEOp(0xF2, sseCMP, regOp, arg, 1);
+    Write8(compare);
+}
+void XEmitter::MULSS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, sseMUL, regOp, arg);
+}
+void XEmitter::MULSD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, sseMUL, regOp, arg);
+}
+void XEmitter::DIVSS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, sseDIV, regOp, arg);
+}
+void XEmitter::DIVSD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, sseDIV, regOp, arg);
+}
+void XEmitter::MINSS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, sseMIN, regOp, arg);
+}
+void XEmitter::MINSD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, sseMIN, regOp, arg);
+}
+void XEmitter::MAXSS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, sseMAX, regOp, arg);
+}
+void XEmitter::MAXSD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, sseMAX, regOp, arg);
+}
+void XEmitter::SQRTSS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, sseSQRT, regOp, arg);
+}
+void XEmitter::SQRTSD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, sseSQRT, regOp, arg);
+}
+void XEmitter::RCPSS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, sseRCP, regOp, arg);
+}
+void XEmitter::RSQRTSS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, sseRSQRT, regOp, arg);
+}
+
+void XEmitter::ADDPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseADD, regOp, arg);
+}
+void XEmitter::ADDPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseADD, regOp, arg);
+}
+void XEmitter::SUBPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseSUB, regOp, arg);
+}
+void XEmitter::SUBPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseSUB, regOp, arg);
+}
+void XEmitter::CMPPS(X64Reg regOp, const OpArg& arg, u8 compare) {
+    WriteSSEOp(0x00, sseCMP, regOp, arg, 1);
+    Write8(compare);
+}
+void XEmitter::CMPPD(X64Reg regOp, const OpArg& arg, u8 compare) {
+    WriteSSEOp(0x66, sseCMP, regOp, arg, 1);
+    Write8(compare);
+}
+void XEmitter::ANDPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseAND, regOp, arg);
+}
+void XEmitter::ANDPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseAND, regOp, arg);
+}
+void XEmitter::ANDNPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseANDN, regOp, arg);
+}
+void XEmitter::ANDNPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseANDN, regOp, arg);
+}
+void XEmitter::ORPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseOR, regOp, arg);
+}
+void XEmitter::ORPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseOR, regOp, arg);
+}
+void XEmitter::XORPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseXOR, regOp, arg);
+}
+void XEmitter::XORPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseXOR, regOp, arg);
+}
+void XEmitter::MULPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseMUL, regOp, arg);
+}
+void XEmitter::MULPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseMUL, regOp, arg);
+}
+void XEmitter::DIVPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseDIV, regOp, arg);
+}
+void XEmitter::DIVPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseDIV, regOp, arg);
+}
+void XEmitter::MINPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseMIN, regOp, arg);
+}
+void XEmitter::MINPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseMIN, regOp, arg);
+}
+void XEmitter::MAXPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseMAX, regOp, arg);
+}
+void XEmitter::MAXPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseMAX, regOp, arg);
+}
+void XEmitter::SQRTPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseSQRT, regOp, arg);
+}
+void XEmitter::SQRTPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseSQRT, regOp, arg);
+}
+void XEmitter::RCPPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseRCP, regOp, arg);
+}
+void XEmitter::RSQRTPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseRSQRT, regOp, arg);
+}
+void XEmitter::SHUFPS(X64Reg regOp, const OpArg& arg, u8 shuffle) {
+    WriteSSEOp(0x00, sseSHUF, regOp, arg, 1);
+    Write8(shuffle);
+}
+void XEmitter::SHUFPD(X64Reg regOp, const OpArg& arg, u8 shuffle) {
+    WriteSSEOp(0x66, sseSHUF, regOp, arg, 1);
+    Write8(shuffle);
+}
+
+void XEmitter::HADDPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, sseHADD, regOp, arg);
+}
+
+void XEmitter::COMISS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseCOMIS, regOp, arg);
+} // weird that these should be packed
+void XEmitter::COMISD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseCOMIS, regOp, arg);
+} // ordered
+void XEmitter::UCOMISS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseUCOMIS, regOp, arg);
+} // unordered
+void XEmitter::UCOMISD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseUCOMIS, regOp, arg);
+}
+
+void XEmitter::MOVAPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseMOVAPfromRM, regOp, arg);
+}
+void XEmitter::MOVAPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseMOVAPfromRM, regOp, arg);
+}
+void XEmitter::MOVAPS(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0x00, sseMOVAPtoRM, regOp, arg);
+}
+void XEmitter::MOVAPD(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0x66, sseMOVAPtoRM, regOp, arg);
+}
+
+void XEmitter::MOVUPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseMOVUPfromRM, regOp, arg);
+}
+void XEmitter::MOVUPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseMOVUPfromRM, regOp, arg);
+}
+void XEmitter::MOVUPS(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0x00, sseMOVUPtoRM, regOp, arg);
+}
+void XEmitter::MOVUPD(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0x66, sseMOVUPtoRM, regOp, arg);
+}
+
+void XEmitter::MOVDQA(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseMOVDQfromRM, regOp, arg);
+}
+void XEmitter::MOVDQA(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0x66, sseMOVDQtoRM, regOp, arg);
+}
+void XEmitter::MOVDQU(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, sseMOVDQfromRM, regOp, arg);
+}
+void XEmitter::MOVDQU(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0xF3, sseMOVDQtoRM, regOp, arg);
+}
+
+void XEmitter::MOVSS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, sseMOVUPfromRM, regOp, arg);
+}
+void XEmitter::MOVSD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, sseMOVUPfromRM, regOp, arg);
+}
+void XEmitter::MOVSS(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0xF3, sseMOVUPtoRM, regOp, arg);
+}
+void XEmitter::MOVSD(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0xF2, sseMOVUPtoRM, regOp, arg);
+}
+
+void XEmitter::MOVLPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseMOVLPfromRM, regOp, arg);
+}
+void XEmitter::MOVLPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseMOVLPfromRM, regOp, arg);
+}
+void XEmitter::MOVLPS(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0x00, sseMOVLPtoRM, regOp, arg);
+}
+void XEmitter::MOVLPD(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0x66, sseMOVLPtoRM, regOp, arg);
+}
+
+void XEmitter::MOVHPS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, sseMOVHPfromRM, regOp, arg);
+}
+void XEmitter::MOVHPD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, sseMOVHPfromRM, regOp, arg);
+}
+void XEmitter::MOVHPS(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0x00, sseMOVHPtoRM, regOp, arg);
+}
+void XEmitter::MOVHPD(const OpArg& arg, X64Reg regOp) {
+    WriteSSEOp(0x66, sseMOVHPtoRM, regOp, arg);
+}
+
+void XEmitter::MOVHLPS(X64Reg regOp1, X64Reg regOp2) {
+    WriteSSEOp(0x00, sseMOVHLPS, regOp1, R(regOp2));
+}
+void XEmitter::MOVLHPS(X64Reg regOp1, X64Reg regOp2) {
+    WriteSSEOp(0x00, sseMOVLHPS, regOp1, R(regOp2));
+}
+
+void XEmitter::CVTPS2PD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, 0x5A, regOp, arg);
+}
+void XEmitter::CVTPD2PS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x5A, regOp, arg);
+}
+
+void XEmitter::CVTSD2SS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, 0x5A, regOp, arg);
+}
+void XEmitter::CVTSS2SD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, 0x5A, regOp, arg);
+}
+void XEmitter::CVTSD2SI(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, 0x2D, regOp, arg);
+}
+void XEmitter::CVTSS2SI(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, 0x2D, regOp, arg);
+}
+void XEmitter::CVTSI2SD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, 0x2A, regOp, arg);
+}
+void XEmitter::CVTSI2SS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, 0x2A, regOp, arg);
+}
+
+void XEmitter::CVTDQ2PD(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, 0xE6, regOp, arg);
+}
+void XEmitter::CVTDQ2PS(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x00, 0x5B, regOp, arg);
+}
+void XEmitter::CVTPD2DQ(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, 0xE6, regOp, arg);
+}
+void XEmitter::CVTPS2DQ(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x5B, regOp, arg);
+}
+
+void XEmitter::CVTTSD2SI(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF2, 0x2C, regOp, arg);
+}
+void XEmitter::CVTTSS2SI(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, 0x2C, regOp, arg);
+}
+void XEmitter::CVTTPS2DQ(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0xF3, 0x5B, regOp, arg);
+}
+void XEmitter::CVTTPD2DQ(X64Reg regOp, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xE6, regOp, arg);
+}
+
+void XEmitter::MASKMOVDQU(X64Reg dest, X64Reg src) {
+    WriteSSEOp(0x66, sseMASKMOVDQU, dest, R(src));
+}
+
+void XEmitter::MOVMSKPS(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x00, 0x50, dest, arg);
+}
+void XEmitter::MOVMSKPD(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x50, dest, arg);
+}
+
+void XEmitter::LDDQU(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0xF2, sseLDDQU, dest, arg);
+} // For integer data only
 
 // THESE TWO ARE UNTESTED.
-void XEmitter::UNPCKLPS(X64Reg dest, const OpArg& arg) {WriteSSEOp(0x00, 0x14, dest, arg);}
-void XEmitter::UNPCKHPS(X64Reg dest, const OpArg& arg) {WriteSSEOp(0x00, 0x15, dest, arg);}
+void XEmitter::UNPCKLPS(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x00, 0x14, dest, arg);
+}
+void XEmitter::UNPCKHPS(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x00, 0x15, dest, arg);
+}
 
-void XEmitter::UNPCKLPD(X64Reg dest, const OpArg& arg) {WriteSSEOp(0x66, 0x14, dest, arg);}
-void XEmitter::UNPCKHPD(X64Reg dest, const OpArg& arg) {WriteSSEOp(0x66, 0x15, dest, arg);}
+void XEmitter::UNPCKLPD(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x14, dest, arg);
+}
+void XEmitter::UNPCKHPD(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x15, dest, arg);
+}
 
-void XEmitter::MOVDDUP(X64Reg regOp, const OpArg& arg)
-{
-    if (Common::GetCPUCaps().sse3)
-    {
-        WriteSSEOp(0xF2, 0x12, regOp, arg); //SSE3 movddup
-    }
-    else
-    {
+void XEmitter::MOVDDUP(X64Reg regOp, const OpArg& arg) {
+    if (Common::GetCPUCaps().sse3) {
+        WriteSSEOp(0xF2, 0x12, regOp, arg); // SSE3 movddup
+    } else {
         // Simulate this instruction with SSE2 instructions
         if (!arg.IsSimpleReg(regOp))
             MOVSD(regOp, arg);
@@ -1684,38 +1873,48 @@ void XEmitter::MOVDDUP(X64Reg regOp, const OpArg& arg)
     }
 }
 
-//There are a few more left
+// There are a few more left
 
 // Also some integer instructions are missing
-void XEmitter::PACKSSDW(X64Reg dest, const OpArg& arg) {WriteSSEOp(0x66, 0x6B, dest, arg);}
-void XEmitter::PACKSSWB(X64Reg dest, const OpArg& arg) {WriteSSEOp(0x66, 0x63, dest, arg);}
-void XEmitter::PACKUSWB(X64Reg dest, const OpArg& arg) {WriteSSEOp(0x66, 0x67, dest, arg);}
+void XEmitter::PACKSSDW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x6B, dest, arg);
+}
+void XEmitter::PACKSSWB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x63, dest, arg);
+}
+void XEmitter::PACKUSWB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x67, dest, arg);
+}
 
-void XEmitter::PUNPCKLBW(X64Reg dest, const OpArg &arg) {WriteSSEOp(0x66, 0x60, dest, arg);}
-void XEmitter::PUNPCKLWD(X64Reg dest, const OpArg &arg) {WriteSSEOp(0x66, 0x61, dest, arg);}
-void XEmitter::PUNPCKLDQ(X64Reg dest, const OpArg &arg) {WriteSSEOp(0x66, 0x62, dest, arg);}
-void XEmitter::PUNPCKLQDQ(X64Reg dest, const OpArg &arg) {WriteSSEOp(0x66, 0x6C, dest, arg);}
+void XEmitter::PUNPCKLBW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x60, dest, arg);
+}
+void XEmitter::PUNPCKLWD(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x61, dest, arg);
+}
+void XEmitter::PUNPCKLDQ(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x62, dest, arg);
+}
+void XEmitter::PUNPCKLQDQ(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x6C, dest, arg);
+}
 
-void XEmitter::PSRLW(X64Reg reg, int shift)
-{
+void XEmitter::PSRLW(X64Reg reg, int shift) {
     WriteSSEOp(0x66, 0x71, (X64Reg)2, R(reg));
     Write8(shift);
 }
 
-void XEmitter::PSRLD(X64Reg reg, int shift)
-{
+void XEmitter::PSRLD(X64Reg reg, int shift) {
     WriteSSEOp(0x66, 0x72, (X64Reg)2, R(reg));
     Write8(shift);
 }
 
-void XEmitter::PSRLQ(X64Reg reg, int shift)
-{
+void XEmitter::PSRLQ(X64Reg reg, int shift) {
     WriteSSEOp(0x66, 0x73, (X64Reg)2, R(reg));
     Write8(shift);
 }
 
-void XEmitter::PSRLQ(X64Reg reg, const OpArg& arg)
-{
+void XEmitter::PSRLQ(X64Reg reg, const OpArg& arg) {
     WriteSSEOp(0x66, 0xd3, reg, arg);
 }
 
@@ -1724,20 +1923,17 @@ void XEmitter::PSRLDQ(X64Reg reg, int shift) {
     Write8(shift);
 }
 
-void XEmitter::PSLLW(X64Reg reg, int shift)
-{
+void XEmitter::PSLLW(X64Reg reg, int shift) {
     WriteSSEOp(0x66, 0x71, (X64Reg)6, R(reg));
     Write8(shift);
 }
 
-void XEmitter::PSLLD(X64Reg reg, int shift)
-{
+void XEmitter::PSLLD(X64Reg reg, int shift) {
     WriteSSEOp(0x66, 0x72, (X64Reg)6, R(reg));
     Write8(shift);
 }
 
-void XEmitter::PSLLQ(X64Reg reg, int shift)
-{
+void XEmitter::PSLLQ(X64Reg reg, int shift) {
     WriteSSEOp(0x66, 0x73, (X64Reg)6, R(reg));
     Write8(shift);
 }
@@ -1747,267 +1943,643 @@ void XEmitter::PSLLDQ(X64Reg reg, int shift) {
     Write8(shift);
 }
 
-void XEmitter::PSRAW(X64Reg reg, int shift)
-{
+void XEmitter::PSRAW(X64Reg reg, int shift) {
     WriteSSEOp(0x66, 0x71, (X64Reg)4, R(reg));
     Write8(shift);
 }
 
-void XEmitter::PSRAD(X64Reg reg, int shift)
-{
+void XEmitter::PSRAD(X64Reg reg, int shift) {
     WriteSSEOp(0x66, 0x72, (X64Reg)4, R(reg));
     Write8(shift);
 }
 
-void XEmitter::WriteSSSE3Op(u8 opPrefix, u16 op, X64Reg regOp, const OpArg& arg, int extrabytes)
-{
+void XEmitter::WriteSSSE3Op(u8 opPrefix, u16 op, X64Reg regOp, const OpArg& arg, int extrabytes) {
     if (!Common::GetCPUCaps().ssse3)
         ASSERT_MSG(0, "Trying to use SSSE3 on a system that doesn't support it. Bad programmer.");
     WriteSSEOp(opPrefix, op, regOp, arg, extrabytes);
 }
 
-void XEmitter::WriteSSE41Op(u8 opPrefix, u16 op, X64Reg regOp, const OpArg& arg, int extrabytes)
-{
+void XEmitter::WriteSSE41Op(u8 opPrefix, u16 op, X64Reg regOp, const OpArg& arg, int extrabytes) {
     if (!Common::GetCPUCaps().sse4_1)
         ASSERT_MSG(0, "Trying to use SSE4.1 on a system that doesn't support it. Bad programmer.");
     WriteSSEOp(opPrefix, op, regOp, arg, extrabytes);
 }
 
-void XEmitter::PSHUFB(X64Reg dest, const OpArg& arg)   {WriteSSSE3Op(0x66, 0x3800, dest, arg);}
-void XEmitter::PTEST(X64Reg dest, const OpArg& arg)    {WriteSSE41Op(0x66, 0x3817, dest, arg);}
-void XEmitter::PACKUSDW(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x382b, dest, arg);}
-void XEmitter::DPPS(X64Reg dest, const OpArg& arg, u8 mask) {WriteSSE41Op(0x66, 0x3A40, dest, arg, 1); Write8(mask);}
-
-void XEmitter::PMINSB(X64Reg dest, const OpArg& arg)   {WriteSSE41Op(0x66, 0x3838, dest, arg);}
-void XEmitter::PMINSD(X64Reg dest, const OpArg& arg)   {WriteSSE41Op(0x66, 0x3839, dest, arg);}
-void XEmitter::PMINUW(X64Reg dest, const OpArg& arg)   {WriteSSE41Op(0x66, 0x383a, dest, arg);}
-void XEmitter::PMINUD(X64Reg dest, const OpArg& arg)   {WriteSSE41Op(0x66, 0x383b, dest, arg);}
-void XEmitter::PMAXSB(X64Reg dest, const OpArg& arg)   {WriteSSE41Op(0x66, 0x383c, dest, arg);}
-void XEmitter::PMAXSD(X64Reg dest, const OpArg& arg)   {WriteSSE41Op(0x66, 0x383d, dest, arg);}
-void XEmitter::PMAXUW(X64Reg dest, const OpArg& arg)   {WriteSSE41Op(0x66, 0x383e, dest, arg);}
-void XEmitter::PMAXUD(X64Reg dest, const OpArg& arg)   {WriteSSE41Op(0x66, 0x383f, dest, arg);}
-
-void XEmitter::PMOVSXBW(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3820, dest, arg);}
-void XEmitter::PMOVSXBD(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3821, dest, arg);}
-void XEmitter::PMOVSXBQ(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3822, dest, arg);}
-void XEmitter::PMOVSXWD(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3823, dest, arg);}
-void XEmitter::PMOVSXWQ(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3824, dest, arg);}
-void XEmitter::PMOVSXDQ(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3825, dest, arg);}
-void XEmitter::PMOVZXBW(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3830, dest, arg);}
-void XEmitter::PMOVZXBD(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3831, dest, arg);}
-void XEmitter::PMOVZXBQ(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3832, dest, arg);}
-void XEmitter::PMOVZXWD(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3833, dest, arg);}
-void XEmitter::PMOVZXWQ(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3834, dest, arg);}
-void XEmitter::PMOVZXDQ(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3835, dest, arg);}
-
-void XEmitter::PBLENDVB(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3810, dest, arg);}
-void XEmitter::BLENDVPS(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3814, dest, arg);}
-void XEmitter::BLENDVPD(X64Reg dest, const OpArg& arg) {WriteSSE41Op(0x66, 0x3815, dest, arg);}
-void XEmitter::BLENDPS(X64Reg dest, const OpArg& arg, u8 blend) { WriteSSE41Op(0x66, 0x3A0C, dest, arg, 1); Write8(blend); }
-void XEmitter::BLENDPD(X64Reg dest, const OpArg& arg, u8 blend) { WriteSSE41Op(0x66, 0x3A0D, dest, arg, 1); Write8(blend); }
-
-void XEmitter::ROUNDSS(X64Reg dest, const OpArg& arg, u8 mode) {WriteSSE41Op(0x66, 0x3A0A, dest, arg, 1); Write8(mode);}
-void XEmitter::ROUNDSD(X64Reg dest, const OpArg& arg, u8 mode) {WriteSSE41Op(0x66, 0x3A0B, dest, arg, 1); Write8(mode);}
-void XEmitter::ROUNDPS(X64Reg dest, const OpArg& arg, u8 mode) {WriteSSE41Op(0x66, 0x3A08, dest, arg, 1); Write8(mode);}
-void XEmitter::ROUNDPD(X64Reg dest, const OpArg& arg, u8 mode) {WriteSSE41Op(0x66, 0x3A09, dest, arg, 1); Write8(mode);}
-
-void XEmitter::PAND(X64Reg dest, const OpArg& arg)     {WriteSSEOp(0x66, 0xDB, dest, arg);}
-void XEmitter::PANDN(X64Reg dest, const OpArg& arg)    {WriteSSEOp(0x66, 0xDF, dest, arg);}
-void XEmitter::PXOR(X64Reg dest, const OpArg& arg)     {WriteSSEOp(0x66, 0xEF, dest, arg);}
-void XEmitter::POR(X64Reg dest, const OpArg& arg)      {WriteSSEOp(0x66, 0xEB, dest, arg);}
-
-void XEmitter::PADDB(X64Reg dest, const OpArg& arg)    {WriteSSEOp(0x66, 0xFC, dest, arg);}
-void XEmitter::PADDW(X64Reg dest, const OpArg& arg)    {WriteSSEOp(0x66, 0xFD, dest, arg);}
-void XEmitter::PADDD(X64Reg dest, const OpArg& arg)    {WriteSSEOp(0x66, 0xFE, dest, arg);}
-void XEmitter::PADDQ(X64Reg dest, const OpArg& arg)    {WriteSSEOp(0x66, 0xD4, dest, arg);}
-
-void XEmitter::PADDSB(X64Reg dest, const OpArg& arg)   {WriteSSEOp(0x66, 0xEC, dest, arg);}
-void XEmitter::PADDSW(X64Reg dest, const OpArg& arg)   {WriteSSEOp(0x66, 0xED, dest, arg);}
-void XEmitter::PADDUSB(X64Reg dest, const OpArg& arg)  {WriteSSEOp(0x66, 0xDC, dest, arg);}
-void XEmitter::PADDUSW(X64Reg dest, const OpArg& arg)  {WriteSSEOp(0x66, 0xDD, dest, arg);}
-
-void XEmitter::PSUBB(X64Reg dest, const OpArg& arg)    {WriteSSEOp(0x66, 0xF8, dest, arg);}
-void XEmitter::PSUBW(X64Reg dest, const OpArg& arg)    {WriteSSEOp(0x66, 0xF9, dest, arg);}
-void XEmitter::PSUBD(X64Reg dest, const OpArg& arg)    {WriteSSEOp(0x66, 0xFA, dest, arg);}
-void XEmitter::PSUBQ(X64Reg dest, const OpArg& arg)    {WriteSSEOp(0x66, 0xFB, dest, arg);}
-
-void XEmitter::PSUBSB(X64Reg dest, const OpArg& arg)   {WriteSSEOp(0x66, 0xE8, dest, arg);}
-void XEmitter::PSUBSW(X64Reg dest, const OpArg& arg)   {WriteSSEOp(0x66, 0xE9, dest, arg);}
-void XEmitter::PSUBUSB(X64Reg dest, const OpArg& arg)  {WriteSSEOp(0x66, 0xD8, dest, arg);}
-void XEmitter::PSUBUSW(X64Reg dest, const OpArg& arg)  {WriteSSEOp(0x66, 0xD9, dest, arg);}
-
-void XEmitter::PAVGB(X64Reg dest, const OpArg& arg)    {WriteSSEOp(0x66, 0xE0, dest, arg);}
-void XEmitter::PAVGW(X64Reg dest, const OpArg& arg)    {WriteSSEOp(0x66, 0xE3, dest, arg);}
-
-void XEmitter::PCMPEQB(X64Reg dest, const OpArg& arg)  {WriteSSEOp(0x66, 0x74, dest, arg);}
-void XEmitter::PCMPEQW(X64Reg dest, const OpArg& arg)  {WriteSSEOp(0x66, 0x75, dest, arg);}
-void XEmitter::PCMPEQD(X64Reg dest, const OpArg& arg)  {WriteSSEOp(0x66, 0x76, dest, arg);}
-
-void XEmitter::PCMPGTB(X64Reg dest, const OpArg& arg)  {WriteSSEOp(0x66, 0x64, dest, arg);}
-void XEmitter::PCMPGTW(X64Reg dest, const OpArg& arg)  {WriteSSEOp(0x66, 0x65, dest, arg);}
-void XEmitter::PCMPGTD(X64Reg dest, const OpArg& arg)  {WriteSSEOp(0x66, 0x66, dest, arg);}
-
-void XEmitter::PEXTRW(X64Reg dest, const OpArg& arg, u8 subreg)    {WriteSSEOp(0x66, 0xC5, dest, arg, 1); Write8(subreg);}
-void XEmitter::PINSRW(X64Reg dest, const OpArg& arg, u8 subreg)    {WriteSSEOp(0x66, 0xC4, dest, arg, 1); Write8(subreg);}
-
-void XEmitter::PMADDWD(X64Reg dest, const OpArg& arg)  {WriteSSEOp(0x66, 0xF5, dest, arg); }
-void XEmitter::PSADBW(X64Reg dest, const OpArg& arg)   {WriteSSEOp(0x66, 0xF6, dest, arg);}
-
-void XEmitter::PMAXSW(X64Reg dest, const OpArg& arg)   {WriteSSEOp(0x66, 0xEE, dest, arg); }
-void XEmitter::PMAXUB(X64Reg dest, const OpArg& arg)   {WriteSSEOp(0x66, 0xDE, dest, arg); }
-void XEmitter::PMINSW(X64Reg dest, const OpArg& arg)   {WriteSSEOp(0x66, 0xEA, dest, arg); }
-void XEmitter::PMINUB(X64Reg dest, const OpArg& arg)   {WriteSSEOp(0x66, 0xDA, dest, arg); }
-
-void XEmitter::PMOVMSKB(X64Reg dest, const OpArg& arg)    {WriteSSEOp(0x66, 0xD7, dest, arg); }
-void XEmitter::PSHUFD(X64Reg regOp, const OpArg& arg, u8 shuffle)    {WriteSSEOp(0x66, 0x70, regOp, arg, 1); Write8(shuffle);}
-void XEmitter::PSHUFLW(X64Reg regOp, const OpArg& arg, u8 shuffle)   {WriteSSEOp(0xF2, 0x70, regOp, arg, 1); Write8(shuffle);}
-void XEmitter::PSHUFHW(X64Reg regOp, const OpArg& arg, u8 shuffle)   {WriteSSEOp(0xF3, 0x70, regOp, arg, 1); Write8(shuffle);}
+void XEmitter::PSHUFB(X64Reg dest, const OpArg& arg) {
+    WriteSSSE3Op(0x66, 0x3800, dest, arg);
+}
+void XEmitter::PTEST(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3817, dest, arg);
+}
+void XEmitter::PACKUSDW(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x382b, dest, arg);
+}
+void XEmitter::DPPS(X64Reg dest, const OpArg& arg, u8 mask) {
+    WriteSSE41Op(0x66, 0x3A40, dest, arg, 1);
+    Write8(mask);
+}
+
+void XEmitter::PMINSB(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3838, dest, arg);
+}
+void XEmitter::PMINSD(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3839, dest, arg);
+}
+void XEmitter::PMINUW(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x383a, dest, arg);
+}
+void XEmitter::PMINUD(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x383b, dest, arg);
+}
+void XEmitter::PMAXSB(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x383c, dest, arg);
+}
+void XEmitter::PMAXSD(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x383d, dest, arg);
+}
+void XEmitter::PMAXUW(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x383e, dest, arg);
+}
+void XEmitter::PMAXUD(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x383f, dest, arg);
+}
+
+void XEmitter::PMOVSXBW(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3820, dest, arg);
+}
+void XEmitter::PMOVSXBD(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3821, dest, arg);
+}
+void XEmitter::PMOVSXBQ(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3822, dest, arg);
+}
+void XEmitter::PMOVSXWD(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3823, dest, arg);
+}
+void XEmitter::PMOVSXWQ(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3824, dest, arg);
+}
+void XEmitter::PMOVSXDQ(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3825, dest, arg);
+}
+void XEmitter::PMOVZXBW(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3830, dest, arg);
+}
+void XEmitter::PMOVZXBD(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3831, dest, arg);
+}
+void XEmitter::PMOVZXBQ(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3832, dest, arg);
+}
+void XEmitter::PMOVZXWD(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3833, dest, arg);
+}
+void XEmitter::PMOVZXWQ(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3834, dest, arg);
+}
+void XEmitter::PMOVZXDQ(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3835, dest, arg);
+}
+
+void XEmitter::PBLENDVB(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3810, dest, arg);
+}
+void XEmitter::BLENDVPS(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3814, dest, arg);
+}
+void XEmitter::BLENDVPD(X64Reg dest, const OpArg& arg) {
+    WriteSSE41Op(0x66, 0x3815, dest, arg);
+}
+void XEmitter::BLENDPS(X64Reg dest, const OpArg& arg, u8 blend) {
+    WriteSSE41Op(0x66, 0x3A0C, dest, arg, 1);
+    Write8(blend);
+}
+void XEmitter::BLENDPD(X64Reg dest, const OpArg& arg, u8 blend) {
+    WriteSSE41Op(0x66, 0x3A0D, dest, arg, 1);
+    Write8(blend);
+}
+
+void XEmitter::ROUNDSS(X64Reg dest, const OpArg& arg, u8 mode) {
+    WriteSSE41Op(0x66, 0x3A0A, dest, arg, 1);
+    Write8(mode);
+}
+void XEmitter::ROUNDSD(X64Reg dest, const OpArg& arg, u8 mode) {
+    WriteSSE41Op(0x66, 0x3A0B, dest, arg, 1);
+    Write8(mode);
+}
+void XEmitter::ROUNDPS(X64Reg dest, const OpArg& arg, u8 mode) {
+    WriteSSE41Op(0x66, 0x3A08, dest, arg, 1);
+    Write8(mode);
+}
+void XEmitter::ROUNDPD(X64Reg dest, const OpArg& arg, u8 mode) {
+    WriteSSE41Op(0x66, 0x3A09, dest, arg, 1);
+    Write8(mode);
+}
+
+void XEmitter::PAND(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xDB, dest, arg);
+}
+void XEmitter::PANDN(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xDF, dest, arg);
+}
+void XEmitter::PXOR(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xEF, dest, arg);
+}
+void XEmitter::POR(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xEB, dest, arg);
+}
+
+void XEmitter::PADDB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xFC, dest, arg);
+}
+void XEmitter::PADDW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xFD, dest, arg);
+}
+void XEmitter::PADDD(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xFE, dest, arg);
+}
+void XEmitter::PADDQ(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xD4, dest, arg);
+}
+
+void XEmitter::PADDSB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xEC, dest, arg);
+}
+void XEmitter::PADDSW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xED, dest, arg);
+}
+void XEmitter::PADDUSB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xDC, dest, arg);
+}
+void XEmitter::PADDUSW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xDD, dest, arg);
+}
+
+void XEmitter::PSUBB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xF8, dest, arg);
+}
+void XEmitter::PSUBW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xF9, dest, arg);
+}
+void XEmitter::PSUBD(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xFA, dest, arg);
+}
+void XEmitter::PSUBQ(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xFB, dest, arg);
+}
+
+void XEmitter::PSUBSB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xE8, dest, arg);
+}
+void XEmitter::PSUBSW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xE9, dest, arg);
+}
+void XEmitter::PSUBUSB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xD8, dest, arg);
+}
+void XEmitter::PSUBUSW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xD9, dest, arg);
+}
+
+void XEmitter::PAVGB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xE0, dest, arg);
+}
+void XEmitter::PAVGW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xE3, dest, arg);
+}
+
+void XEmitter::PCMPEQB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x74, dest, arg);
+}
+void XEmitter::PCMPEQW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x75, dest, arg);
+}
+void XEmitter::PCMPEQD(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x76, dest, arg);
+}
+
+void XEmitter::PCMPGTB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x64, dest, arg);
+}
+void XEmitter::PCMPGTW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x65, dest, arg);
+}
+void XEmitter::PCMPGTD(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0x66, dest, arg);
+}
+
+void XEmitter::PEXTRW(X64Reg dest, const OpArg& arg, u8 subreg) {
+    WriteSSEOp(0x66, 0xC5, dest, arg, 1);
+    Write8(subreg);
+}
+void XEmitter::PINSRW(X64Reg dest, const OpArg& arg, u8 subreg) {
+    WriteSSEOp(0x66, 0xC4, dest, arg, 1);
+    Write8(subreg);
+}
+
+void XEmitter::PMADDWD(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xF5, dest, arg);
+}
+void XEmitter::PSADBW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xF6, dest, arg);
+}
+
+void XEmitter::PMAXSW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xEE, dest, arg);
+}
+void XEmitter::PMAXUB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xDE, dest, arg);
+}
+void XEmitter::PMINSW(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xEA, dest, arg);
+}
+void XEmitter::PMINUB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xDA, dest, arg);
+}
+
+void XEmitter::PMOVMSKB(X64Reg dest, const OpArg& arg) {
+    WriteSSEOp(0x66, 0xD7, dest, arg);
+}
+void XEmitter::PSHUFD(X64Reg regOp, const OpArg& arg, u8 shuffle) {
+    WriteSSEOp(0x66, 0x70, regOp, arg, 1);
+    Write8(shuffle);
+}
+void XEmitter::PSHUFLW(X64Reg regOp, const OpArg& arg, u8 shuffle) {
+    WriteSSEOp(0xF2, 0x70, regOp, arg, 1);
+    Write8(shuffle);
+}
+void XEmitter::PSHUFHW(X64Reg regOp, const OpArg& arg, u8 shuffle) {
+    WriteSSEOp(0xF3, 0x70, regOp, arg, 1);
+    Write8(shuffle);
+}
 
 // VEX
-void XEmitter::VADDSD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   {WriteAVXOp(0xF2, sseADD, regOp1, regOp2, arg);}
-void XEmitter::VSUBSD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   {WriteAVXOp(0xF2, sseSUB, regOp1, regOp2, arg);}
-void XEmitter::VMULSD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   {WriteAVXOp(0xF2, sseMUL, regOp1, regOp2, arg);}
-void XEmitter::VDIVSD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   {WriteAVXOp(0xF2, sseDIV, regOp1, regOp2, arg);}
-void XEmitter::VADDPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   {WriteAVXOp(0x66, sseADD, regOp1, regOp2, arg);}
-void XEmitter::VSUBPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   {WriteAVXOp(0x66, sseSUB, regOp1, regOp2, arg);}
-void XEmitter::VMULPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   {WriteAVXOp(0x66, sseMUL, regOp1, regOp2, arg);}
-void XEmitter::VDIVPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   {WriteAVXOp(0x66, sseDIV, regOp1, regOp2, arg);}
-void XEmitter::VSQRTSD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)  {WriteAVXOp(0xF2, sseSQRT, regOp1, regOp2, arg);}
-void XEmitter::VSHUFPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg, u8 shuffle) {WriteAVXOp(0x66, sseSHUF, regOp1, regOp2, arg, 1); Write8(shuffle);}
-void XEmitter::VUNPCKLPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg){WriteAVXOp(0x66, 0x14, regOp1, regOp2, arg);}
-void XEmitter::VUNPCKHPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg){WriteAVXOp(0x66, 0x15, regOp1, regOp2, arg);}
-
-void XEmitter::VANDPS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x00, sseAND, regOp1, regOp2, arg); }
-void XEmitter::VANDPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, sseAND, regOp1, regOp2, arg); }
-void XEmitter::VANDNPS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)  { WriteAVXOp(0x00, sseANDN, regOp1, regOp2, arg); }
-void XEmitter::VANDNPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)  { WriteAVXOp(0x66, sseANDN, regOp1, regOp2, arg); }
-void XEmitter::VORPS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x00, sseOR, regOp1, regOp2, arg); }
-void XEmitter::VORPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, sseOR, regOp1, regOp2, arg); }
-void XEmitter::VXORPS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x00, sseXOR, regOp1, regOp2, arg); }
-void XEmitter::VXORPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, sseXOR, regOp1, regOp2, arg); }
-
-void XEmitter::VPAND(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0xDB, regOp1, regOp2, arg); }
-void XEmitter::VPANDN(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0xDF, regOp1, regOp2, arg); }
-void XEmitter::VPOR(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)     { WriteAVXOp(0x66, 0xEB, regOp1, regOp2, arg); }
-void XEmitter::VPXOR(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0xEF, regOp1, regOp2, arg); }
-
-void XEmitter::VFMADD132PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x3898, regOp1, regOp2, arg); }
-void XEmitter::VFMADD213PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38A8, regOp1, regOp2, arg); }
-void XEmitter::VFMADD231PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38B8, regOp1, regOp2, arg); }
-void XEmitter::VFMADD132PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x3898, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMADD213PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38A8, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMADD231PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38B8, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMADD132SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x3899, regOp1, regOp2, arg); }
-void XEmitter::VFMADD213SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38A9, regOp1, regOp2, arg); }
-void XEmitter::VFMADD231SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38B9, regOp1, regOp2, arg); }
-void XEmitter::VFMADD132SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x3899, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMADD213SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38A9, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMADD231SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38B9, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMSUB132PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x389A, regOp1, regOp2, arg); }
-void XEmitter::VFMSUB213PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38AA, regOp1, regOp2, arg); }
-void XEmitter::VFMSUB231PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38BA, regOp1, regOp2, arg); }
-void XEmitter::VFMSUB132PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x389A, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMSUB213PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38AA, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMSUB231PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38BA, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMSUB132SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x389B, regOp1, regOp2, arg); }
-void XEmitter::VFMSUB213SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38AB, regOp1, regOp2, arg); }
-void XEmitter::VFMSUB231SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38BB, regOp1, regOp2, arg); }
-void XEmitter::VFMSUB132SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x389B, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMSUB213SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38AB, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMSUB231SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)    { WriteAVXOp(0x66, 0x38BB, regOp1, regOp2, arg, 1); }
-void XEmitter::VFNMADD132PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x389C, regOp1, regOp2, arg); }
-void XEmitter::VFNMADD213PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38AC, regOp1, regOp2, arg); }
-void XEmitter::VFNMADD231PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38BC, regOp1, regOp2, arg); }
-void XEmitter::VFNMADD132PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x389C, regOp1, regOp2, arg, 1); }
-void XEmitter::VFNMADD213PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38AC, regOp1, regOp2, arg, 1); }
-void XEmitter::VFNMADD231PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38BC, regOp1, regOp2, arg, 1); }
-void XEmitter::VFNMADD132SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x389D, regOp1, regOp2, arg); }
-void XEmitter::VFNMADD213SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38AD, regOp1, regOp2, arg); }
-void XEmitter::VFNMADD231SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38BD, regOp1, regOp2, arg); }
-void XEmitter::VFNMADD132SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x389D, regOp1, regOp2, arg, 1); }
-void XEmitter::VFNMADD213SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38AD, regOp1, regOp2, arg, 1); }
-void XEmitter::VFNMADD231SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38BD, regOp1, regOp2, arg, 1); }
-void XEmitter::VFNMSUB132PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x389E, regOp1, regOp2, arg); }
-void XEmitter::VFNMSUB213PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38AE, regOp1, regOp2, arg); }
-void XEmitter::VFNMSUB231PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38BE, regOp1, regOp2, arg); }
-void XEmitter::VFNMSUB132PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x389E, regOp1, regOp2, arg, 1); }
-void XEmitter::VFNMSUB213PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38AE, regOp1, regOp2, arg, 1); }
-void XEmitter::VFNMSUB231PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38BE, regOp1, regOp2, arg, 1); }
-void XEmitter::VFNMSUB132SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x389F, regOp1, regOp2, arg); }
-void XEmitter::VFNMSUB213SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38AF, regOp1, regOp2, arg); }
-void XEmitter::VFNMSUB231SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38BF, regOp1, regOp2, arg); }
-void XEmitter::VFNMSUB132SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x389F, regOp1, regOp2, arg, 1); }
-void XEmitter::VFNMSUB213SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38AF, regOp1, regOp2, arg, 1); }
-void XEmitter::VFNMSUB231SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg)   { WriteAVXOp(0x66, 0x38BF, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMADDSUB132PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) { WriteAVXOp(0x66, 0x3896, regOp1, regOp2, arg); }
-void XEmitter::VFMADDSUB213PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) { WriteAVXOp(0x66, 0x38A6, regOp1, regOp2, arg); }
-void XEmitter::VFMADDSUB231PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) { WriteAVXOp(0x66, 0x38B6, regOp1, regOp2, arg); }
-void XEmitter::VFMADDSUB132PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) { WriteAVXOp(0x66, 0x3896, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMADDSUB213PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) { WriteAVXOp(0x66, 0x38A6, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMADDSUB231PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) { WriteAVXOp(0x66, 0x38B6, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMSUBADD132PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) { WriteAVXOp(0x66, 0x3897, regOp1, regOp2, arg); }
-void XEmitter::VFMSUBADD213PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) { WriteAVXOp(0x66, 0x38A7, regOp1, regOp2, arg); }
-void XEmitter::VFMSUBADD231PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) { WriteAVXOp(0x66, 0x38B7, regOp1, regOp2, arg); }
-void XEmitter::VFMSUBADD132PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) { WriteAVXOp(0x66, 0x3897, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMSUBADD213PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) { WriteAVXOp(0x66, 0x38A7, regOp1, regOp2, arg, 1); }
-void XEmitter::VFMSUBADD231PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) { WriteAVXOp(0x66, 0x38B7, regOp1, regOp2, arg, 1); }
-
-void XEmitter::SARX(int bits, X64Reg regOp1, const OpArg& arg, X64Reg regOp2) {WriteBMI2Op(bits, 0xF3, 0x38F7, regOp1, regOp2, arg);}
-void XEmitter::SHLX(int bits, X64Reg regOp1, const OpArg& arg, X64Reg regOp2) {WriteBMI2Op(bits, 0x66, 0x38F7, regOp1, regOp2, arg);}
-void XEmitter::SHRX(int bits, X64Reg regOp1, const OpArg& arg, X64Reg regOp2) {WriteBMI2Op(bits, 0xF2, 0x38F7, regOp1, regOp2, arg);}
-void XEmitter::RORX(int bits, X64Reg regOp, const OpArg& arg, u8 rotate)      {WriteBMI2Op(bits, 0xF2, 0x3AF0, regOp, INVALID_REG, arg, 1); Write8(rotate);}
-void XEmitter::PEXT(int bits, X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {WriteBMI2Op(bits, 0xF3, 0x38F5, regOp1, regOp2, arg);}
-void XEmitter::PDEP(int bits, X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {WriteBMI2Op(bits, 0xF2, 0x38F5, regOp1, regOp2, arg);}
-void XEmitter::MULX(int bits, X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {WriteBMI2Op(bits, 0xF2, 0x38F6, regOp2, regOp1, arg);}
-void XEmitter::BZHI(int bits, X64Reg regOp1, const OpArg& arg, X64Reg regOp2) {WriteBMI2Op(bits, 0x00, 0x38F5, regOp1, regOp2, arg);}
-void XEmitter::BLSR(int bits, X64Reg regOp, const OpArg& arg)                 {WriteBMI1Op(bits, 0x00, 0x38F3, (X64Reg)0x1, regOp, arg);}
-void XEmitter::BLSMSK(int bits, X64Reg regOp, const OpArg& arg)               {WriteBMI1Op(bits, 0x00, 0x38F3, (X64Reg)0x2, regOp, arg);}
-void XEmitter::BLSI(int bits, X64Reg regOp, const OpArg& arg)                 {WriteBMI1Op(bits, 0x00, 0x38F3, (X64Reg)0x3, regOp, arg);}
-void XEmitter::BEXTR(int bits, X64Reg regOp1, const OpArg& arg, X64Reg regOp2){WriteBMI1Op(bits, 0x00, 0x38F7, regOp1, regOp2, arg);}
-void XEmitter::ANDN(int bits, X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {WriteBMI1Op(bits, 0x00, 0x38F2, regOp1, regOp2, arg);}
+void XEmitter::VADDSD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0xF2, sseADD, regOp1, regOp2, arg);
+}
+void XEmitter::VSUBSD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0xF2, sseSUB, regOp1, regOp2, arg);
+}
+void XEmitter::VMULSD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0xF2, sseMUL, regOp1, regOp2, arg);
+}
+void XEmitter::VDIVSD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0xF2, sseDIV, regOp1, regOp2, arg);
+}
+void XEmitter::VADDPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, sseADD, regOp1, regOp2, arg);
+}
+void XEmitter::VSUBPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, sseSUB, regOp1, regOp2, arg);
+}
+void XEmitter::VMULPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, sseMUL, regOp1, regOp2, arg);
+}
+void XEmitter::VDIVPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, sseDIV, regOp1, regOp2, arg);
+}
+void XEmitter::VSQRTSD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0xF2, sseSQRT, regOp1, regOp2, arg);
+}
+void XEmitter::VSHUFPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg, u8 shuffle) {
+    WriteAVXOp(0x66, sseSHUF, regOp1, regOp2, arg, 1);
+    Write8(shuffle);
+}
+void XEmitter::VUNPCKLPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x14, regOp1, regOp2, arg);
+}
+void XEmitter::VUNPCKHPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x15, regOp1, regOp2, arg);
+}
+
+void XEmitter::VANDPS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x00, sseAND, regOp1, regOp2, arg);
+}
+void XEmitter::VANDPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, sseAND, regOp1, regOp2, arg);
+}
+void XEmitter::VANDNPS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x00, sseANDN, regOp1, regOp2, arg);
+}
+void XEmitter::VANDNPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, sseANDN, regOp1, regOp2, arg);
+}
+void XEmitter::VORPS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x00, sseOR, regOp1, regOp2, arg);
+}
+void XEmitter::VORPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, sseOR, regOp1, regOp2, arg);
+}
+void XEmitter::VXORPS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x00, sseXOR, regOp1, regOp2, arg);
+}
+void XEmitter::VXORPD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, sseXOR, regOp1, regOp2, arg);
+}
+
+void XEmitter::VPAND(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0xDB, regOp1, regOp2, arg);
+}
+void XEmitter::VPANDN(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0xDF, regOp1, regOp2, arg);
+}
+void XEmitter::VPOR(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0xEB, regOp1, regOp2, arg);
+}
+void XEmitter::VPXOR(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0xEF, regOp1, regOp2, arg);
+}
+
+void XEmitter::VFMADD132PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x3898, regOp1, regOp2, arg);
+}
+void XEmitter::VFMADD213PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38A8, regOp1, regOp2, arg);
+}
+void XEmitter::VFMADD231PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38B8, regOp1, regOp2, arg);
+}
+void XEmitter::VFMADD132PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x3898, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMADD213PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38A8, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMADD231PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38B8, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMADD132SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x3899, regOp1, regOp2, arg);
+}
+void XEmitter::VFMADD213SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38A9, regOp1, regOp2, arg);
+}
+void XEmitter::VFMADD231SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38B9, regOp1, regOp2, arg);
+}
+void XEmitter::VFMADD132SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x3899, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMADD213SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38A9, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMADD231SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38B9, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMSUB132PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x389A, regOp1, regOp2, arg);
+}
+void XEmitter::VFMSUB213PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38AA, regOp1, regOp2, arg);
+}
+void XEmitter::VFMSUB231PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38BA, regOp1, regOp2, arg);
+}
+void XEmitter::VFMSUB132PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x389A, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMSUB213PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38AA, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMSUB231PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38BA, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMSUB132SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x389B, regOp1, regOp2, arg);
+}
+void XEmitter::VFMSUB213SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38AB, regOp1, regOp2, arg);
+}
+void XEmitter::VFMSUB231SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38BB, regOp1, regOp2, arg);
+}
+void XEmitter::VFMSUB132SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x389B, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMSUB213SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38AB, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMSUB231SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38BB, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFNMADD132PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x389C, regOp1, regOp2, arg);
+}
+void XEmitter::VFNMADD213PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38AC, regOp1, regOp2, arg);
+}
+void XEmitter::VFNMADD231PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38BC, regOp1, regOp2, arg);
+}
+void XEmitter::VFNMADD132PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x389C, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFNMADD213PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38AC, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFNMADD231PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38BC, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFNMADD132SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x389D, regOp1, regOp2, arg);
+}
+void XEmitter::VFNMADD213SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38AD, regOp1, regOp2, arg);
+}
+void XEmitter::VFNMADD231SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38BD, regOp1, regOp2, arg);
+}
+void XEmitter::VFNMADD132SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x389D, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFNMADD213SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38AD, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFNMADD231SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38BD, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFNMSUB132PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x389E, regOp1, regOp2, arg);
+}
+void XEmitter::VFNMSUB213PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38AE, regOp1, regOp2, arg);
+}
+void XEmitter::VFNMSUB231PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38BE, regOp1, regOp2, arg);
+}
+void XEmitter::VFNMSUB132PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x389E, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFNMSUB213PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38AE, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFNMSUB231PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38BE, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFNMSUB132SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x389F, regOp1, regOp2, arg);
+}
+void XEmitter::VFNMSUB213SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38AF, regOp1, regOp2, arg);
+}
+void XEmitter::VFNMSUB231SS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38BF, regOp1, regOp2, arg);
+}
+void XEmitter::VFNMSUB132SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x389F, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFNMSUB213SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38AF, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFNMSUB231SD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38BF, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMADDSUB132PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x3896, regOp1, regOp2, arg);
+}
+void XEmitter::VFMADDSUB213PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38A6, regOp1, regOp2, arg);
+}
+void XEmitter::VFMADDSUB231PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38B6, regOp1, regOp2, arg);
+}
+void XEmitter::VFMADDSUB132PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x3896, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMADDSUB213PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38A6, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMADDSUB231PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38B6, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMSUBADD132PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x3897, regOp1, regOp2, arg);
+}
+void XEmitter::VFMSUBADD213PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38A7, regOp1, regOp2, arg);
+}
+void XEmitter::VFMSUBADD231PS(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38B7, regOp1, regOp2, arg);
+}
+void XEmitter::VFMSUBADD132PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x3897, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMSUBADD213PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38A7, regOp1, regOp2, arg, 1);
+}
+void XEmitter::VFMSUBADD231PD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteAVXOp(0x66, 0x38B7, regOp1, regOp2, arg, 1);
+}
+
+void XEmitter::SARX(int bits, X64Reg regOp1, const OpArg& arg, X64Reg regOp2) {
+    WriteBMI2Op(bits, 0xF3, 0x38F7, regOp1, regOp2, arg);
+}
+void XEmitter::SHLX(int bits, X64Reg regOp1, const OpArg& arg, X64Reg regOp2) {
+    WriteBMI2Op(bits, 0x66, 0x38F7, regOp1, regOp2, arg);
+}
+void XEmitter::SHRX(int bits, X64Reg regOp1, const OpArg& arg, X64Reg regOp2) {
+    WriteBMI2Op(bits, 0xF2, 0x38F7, regOp1, regOp2, arg);
+}
+void XEmitter::RORX(int bits, X64Reg regOp, const OpArg& arg, u8 rotate) {
+    WriteBMI2Op(bits, 0xF2, 0x3AF0, regOp, INVALID_REG, arg, 1);
+    Write8(rotate);
+}
+void XEmitter::PEXT(int bits, X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteBMI2Op(bits, 0xF3, 0x38F5, regOp1, regOp2, arg);
+}
+void XEmitter::PDEP(int bits, X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteBMI2Op(bits, 0xF2, 0x38F5, regOp1, regOp2, arg);
+}
+void XEmitter::MULX(int bits, X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteBMI2Op(bits, 0xF2, 0x38F6, regOp2, regOp1, arg);
+}
+void XEmitter::BZHI(int bits, X64Reg regOp1, const OpArg& arg, X64Reg regOp2) {
+    WriteBMI2Op(bits, 0x00, 0x38F5, regOp1, regOp2, arg);
+}
+void XEmitter::BLSR(int bits, X64Reg regOp, const OpArg& arg) {
+    WriteBMI1Op(bits, 0x00, 0x38F3, (X64Reg)0x1, regOp, arg);
+}
+void XEmitter::BLSMSK(int bits, X64Reg regOp, const OpArg& arg) {
+    WriteBMI1Op(bits, 0x00, 0x38F3, (X64Reg)0x2, regOp, arg);
+}
+void XEmitter::BLSI(int bits, X64Reg regOp, const OpArg& arg) {
+    WriteBMI1Op(bits, 0x00, 0x38F3, (X64Reg)0x3, regOp, arg);
+}
+void XEmitter::BEXTR(int bits, X64Reg regOp1, const OpArg& arg, X64Reg regOp2) {
+    WriteBMI1Op(bits, 0x00, 0x38F7, regOp1, regOp2, arg);
+}
+void XEmitter::ANDN(int bits, X64Reg regOp1, X64Reg regOp2, const OpArg& arg) {
+    WriteBMI1Op(bits, 0x00, 0x38F2, regOp1, regOp2, arg);
+}
 
 // Prefixes
 
-void XEmitter::LOCK()  { Write8(0xF0); }
-void XEmitter::REP()   { Write8(0xF3); }
-void XEmitter::REPNE() { Write8(0xF2); }
-void XEmitter::FSOverride() { Write8(0x64); }
-void XEmitter::GSOverride() { Write8(0x65); }
+void XEmitter::LOCK() {
+    Write8(0xF0);
+}
+void XEmitter::REP() {
+    Write8(0xF3);
+}
+void XEmitter::REPNE() {
+    Write8(0xF2);
+}
+void XEmitter::FSOverride() {
+    Write8(0x64);
+}
+void XEmitter::GSOverride() {
+    Write8(0x65);
+}
 
-void XEmitter::FWAIT()
-{
+void XEmitter::FWAIT() {
     Write8(0x9B);
 }
 
 // TODO: make this more generic
-void XEmitter::WriteFloatLoadStore(int bits, FloatOp op, FloatOp op_80b, const OpArg& arg)
-{
+void XEmitter::WriteFloatLoadStore(int bits, FloatOp op, FloatOp op_80b, const OpArg& arg) {
     int mf = 0;
-    ASSERT_MSG(!(bits == 80 && op_80b == floatINVALID), "WriteFloatLoadStore: 80 bits not supported for this instruction");
-    switch (bits)
-    {
-    case 32: mf = 0; break;
-    case 64: mf = 4; break;
-    case 80: mf = 2; break;
-    default: ASSERT_MSG(0, "WriteFloatLoadStore: invalid bits (should be 32/64/80)");
+    ASSERT_MSG(!(bits == 80 && op_80b == floatINVALID),
+               "WriteFloatLoadStore: 80 bits not supported for this instruction");
+    switch (bits) {
+    case 32:
+        mf = 0;
+        break;
+    case 64:
+        mf = 4;
+        break;
+    case 80:
+        mf = 2;
+        break;
+    default:
+        ASSERT_MSG(0, "WriteFloatLoadStore: invalid bits (should be 32/64/80)");
     }
     Write8(0xd9 | mf);
     // x87 instructions use the reg field of the ModR/M byte as opcode:
     if (bits == 80)
         op = op_80b;
-    arg.WriteRest(this, 0, (X64Reg) op);
+    arg.WriteRest(this, 0, (X64Reg)op);
 }
 
-void XEmitter::FLD(int bits, const OpArg& src) {WriteFloatLoadStore(bits, floatLD, floatLD80, src);}
-void XEmitter::FST(int bits, const OpArg& dest) {WriteFloatLoadStore(bits, floatST, floatINVALID, dest);}
-void XEmitter::FSTP(int bits, const OpArg& dest) {WriteFloatLoadStore(bits, floatSTP, floatSTP80, dest);}
-void XEmitter::FNSTSW_AX() { Write8(0xDF); Write8(0xE0); }
+void XEmitter::FLD(int bits, const OpArg& src) {
+    WriteFloatLoadStore(bits, floatLD, floatLD80, src);
+}
+void XEmitter::FST(int bits, const OpArg& dest) {
+    WriteFloatLoadStore(bits, floatST, floatINVALID, dest);
+}
+void XEmitter::FSTP(int bits, const OpArg& dest) {
+    WriteFloatLoadStore(bits, floatSTP, floatSTP80, dest);
+}
+void XEmitter::FNSTSW_AX() {
+    Write8(0xDF);
+    Write8(0xE0);
+}
 
-void XEmitter::RDTSC() { Write8(0x0F); Write8(0x31); }
+void XEmitter::RDTSC() {
+    Write8(0x0F);
+    Write8(0x31);
+}
 
 void XCodeBlock::PoisonMemory() {
     // x86/64: 0xCC = breakpoint
     memset(region, 0xCC, region_size);
 }
-
 }
diff --git a/src/common/x64/emitter.h b/src/common/x64/emitter.h
index 60a77dfe1..467f7812f 100644
--- a/src/common/x64/emitter.h
+++ b/src/common/x64/emitter.h
@@ -21,8 +21,8 @@
 
 #include "common/assert.h"
 #include "common/bit_set.h"
-#include "common/common_types.h"
 #include "common/code_block.h"
+#include "common/common_types.h"
 
 #if defined(ARCHITECTURE_x86_64) && !defined(_ARCH_64)
 #define _ARCH_64
@@ -34,75 +34,145 @@
 #define PTRBITS 32
 #endif
 
-namespace Gen
-{
-
-enum X64Reg
-{
-    EAX = 0, EBX = 3, ECX = 1, EDX = 2,
-    ESI = 6, EDI = 7, EBP = 5, ESP = 4,
-
-    RAX = 0, RBX = 3, RCX = 1, RDX = 2,
-    RSI = 6, RDI = 7, RBP = 5, RSP = 4,
-    R8  = 8, R9  = 9, R10 = 10,R11 = 11,
-    R12 = 12,R13 = 13,R14 = 14,R15 = 15,
-
-    AL = 0, BL = 3, CL = 1, DL = 2,
-    SIL = 6, DIL = 7, BPL = 5, SPL = 4,
-    AH = 0x104, BH = 0x107, CH = 0x105, DH = 0x106,
-
-    AX = 0, BX = 3, CX = 1, DX = 2,
-    SI = 6, DI = 7, BP = 5, SP = 4,
-
-    XMM0=0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
-    XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15,
-
-    YMM0=0, YMM1, YMM2, YMM3, YMM4, YMM5, YMM6, YMM7,
-    YMM8, YMM9, YMM10, YMM11, YMM12, YMM13, YMM14, YMM15,
+namespace Gen {
+
+enum X64Reg {
+    EAX = 0,
+    EBX = 3,
+    ECX = 1,
+    EDX = 2,
+    ESI = 6,
+    EDI = 7,
+    EBP = 5,
+    ESP = 4,
+
+    RAX = 0,
+    RBX = 3,
+    RCX = 1,
+    RDX = 2,
+    RSI = 6,
+    RDI = 7,
+    RBP = 5,
+    RSP = 4,
+    R8 = 8,
+    R9 = 9,
+    R10 = 10,
+    R11 = 11,
+    R12 = 12,
+    R13 = 13,
+    R14 = 14,
+    R15 = 15,
+
+    AL = 0,
+    BL = 3,
+    CL = 1,
+    DL = 2,
+    SIL = 6,
+    DIL = 7,
+    BPL = 5,
+    SPL = 4,
+    AH = 0x104,
+    BH = 0x107,
+    CH = 0x105,
+    DH = 0x106,
+
+    AX = 0,
+    BX = 3,
+    CX = 1,
+    DX = 2,
+    SI = 6,
+    DI = 7,
+    BP = 5,
+    SP = 4,
+
+    XMM0 = 0,
+    XMM1,
+    XMM2,
+    XMM3,
+    XMM4,
+    XMM5,
+    XMM6,
+    XMM7,
+    XMM8,
+    XMM9,
+    XMM10,
+    XMM11,
+    XMM12,
+    XMM13,
+    XMM14,
+    XMM15,
+
+    YMM0 = 0,
+    YMM1,
+    YMM2,
+    YMM3,
+    YMM4,
+    YMM5,
+    YMM6,
+    YMM7,
+    YMM8,
+    YMM9,
+    YMM10,
+    YMM11,
+    YMM12,
+    YMM13,
+    YMM14,
+    YMM15,
 
     INVALID_REG = 0xFFFFFFFF
 };
 
-enum CCFlags
-{
-    CC_O   = 0,
-    CC_NO  = 1,
-    CC_B   = 2, CC_C   = 2, CC_NAE = 2,
-    CC_NB  = 3, CC_NC  = 3, CC_AE  = 3,
-    CC_Z   = 4, CC_E   = 4,
-    CC_NZ  = 5, CC_NE  = 5,
-    CC_BE  = 6, CC_NA  = 6,
-    CC_NBE = 7, CC_A   = 7,
-    CC_S   = 8,
-    CC_NS  = 9,
-    CC_P   = 0xA, CC_PE  = 0xA,
-    CC_NP  = 0xB, CC_PO  = 0xB,
-    CC_L   = 0xC, CC_NGE = 0xC,
-    CC_NL  = 0xD, CC_GE  = 0xD,
-    CC_LE  = 0xE, CC_NG  = 0xE,
-    CC_NLE = 0xF, CC_G   = 0xF
+enum CCFlags {
+    CC_O = 0,
+    CC_NO = 1,
+    CC_B = 2,
+    CC_C = 2,
+    CC_NAE = 2,
+    CC_NB = 3,
+    CC_NC = 3,
+    CC_AE = 3,
+    CC_Z = 4,
+    CC_E = 4,
+    CC_NZ = 5,
+    CC_NE = 5,
+    CC_BE = 6,
+    CC_NA = 6,
+    CC_NBE = 7,
+    CC_A = 7,
+    CC_S = 8,
+    CC_NS = 9,
+    CC_P = 0xA,
+    CC_PE = 0xA,
+    CC_NP = 0xB,
+    CC_PO = 0xB,
+    CC_L = 0xC,
+    CC_NGE = 0xC,
+    CC_NL = 0xD,
+    CC_GE = 0xD,
+    CC_LE = 0xE,
+    CC_NG = 0xE,
+    CC_NLE = 0xF,
+    CC_G = 0xF
 };
 
-enum
-{
+enum {
     NUMGPRs = 16,
     NUMXMMs = 16,
 };
 
-enum
-{
+enum {
     SCALE_NONE = 0,
     SCALE_1 = 1,
     SCALE_2 = 2,
     SCALE_4 = 4,
     SCALE_8 = 8,
     SCALE_ATREG = 16,
-    //SCALE_NOBASE_1 is not supported and can be replaced with SCALE_ATREG
+    // SCALE_NOBASE_1 is not supported and can be replaced with SCALE_ATREG
     SCALE_NOBASE_2 = 34,
     SCALE_NOBASE_4 = 36,
     SCALE_NOBASE_8 = 40,
     SCALE_RIP = 0xFF,
-    SCALE_IMM8  = 0xF0,
+    SCALE_IMM8 = 0xF0,
     SCALE_IMM16 = 0xF1,
     SCALE_IMM32 = 0xF2,
     SCALE_IMM64 = 0xF3,
@@ -114,7 +184,7 @@ enum NormalOp {
     nrmSUB,
     nrmSBB,
     nrmAND,
-    nrmOR ,
+    nrmOR,
     nrmXOR,
     nrmMOV,
     nrmTEST,
@@ -157,68 +227,74 @@ enum FloatRound {
 class XEmitter;
 
 // RIP addressing does not benefit from micro op fusion on Core arch
-struct OpArg
-{
+struct OpArg {
     friend class XEmitter;
 
-    constexpr OpArg() = default;  // dummy op arg, used for storage
+    constexpr OpArg() = default; // dummy op arg, used for storage
     constexpr OpArg(u64 offset_, int scale_, X64Reg rmReg = RAX, X64Reg scaledReg = RAX)
-        : scale(static_cast<u8>(scale_))
-        , offsetOrBaseReg(static_cast<u16>(rmReg))
-        , indexReg(static_cast<u16>(scaledReg))
-        , offset(offset_)
-    {
+        : scale(static_cast<u8>(scale_)), offsetOrBaseReg(static_cast<u16>(rmReg)),
+          indexReg(static_cast<u16>(scaledReg)), offset(offset_) {
     }
 
-    constexpr bool operator==(const OpArg &b) const
-    {
-        return operandReg      == b.operandReg      &&
-               scale           == b.scale           &&
-               offsetOrBaseReg == b.offsetOrBaseReg &&
-               indexReg        == b.indexReg        &&
-               offset          == b.offset;
+    constexpr bool operator==(const OpArg& b) const {
+        return operandReg == b.operandReg && scale == b.scale &&
+               offsetOrBaseReg == b.offsetOrBaseReg && indexReg == b.indexReg && offset == b.offset;
     }
 
-    void WriteRex(XEmitter *emit, int opBits, int bits, int customOp = -1) const;
-    void WriteVex(XEmitter* emit, X64Reg regOp1, X64Reg regOp2, int L, int pp, int mmmmm, int W = 0) const;
-    void WriteRest(XEmitter *emit, int extraBytes=0, X64Reg operandReg=INVALID_REG, bool warn_64bit_offset = true) const;
-    void WriteSingleByteOp(XEmitter *emit, u8 op, X64Reg operandReg, int bits);
-    void WriteNormalOp(XEmitter *emit, bool toRM, NormalOp op, const OpArg &operand, int bits) const;
-
-    constexpr bool IsImm() const { return scale == SCALE_IMM8 || scale == SCALE_IMM16 || scale == SCALE_IMM32 || scale == SCALE_IMM64; }
-    constexpr bool IsSimpleReg() const { return scale == SCALE_NONE; }
-    constexpr bool IsSimpleReg(X64Reg reg) const
-    {
+    void WriteRex(XEmitter* emit, int opBits, int bits, int customOp = -1) const;
+    void WriteVex(XEmitter* emit, X64Reg regOp1, X64Reg regOp2, int L, int pp, int mmmmm,
+                  int W = 0) const;
+    void WriteRest(XEmitter* emit, int extraBytes = 0, X64Reg operandReg = INVALID_REG,
+                   bool warn_64bit_offset = true) const;
+    void WriteSingleByteOp(XEmitter* emit, u8 op, X64Reg operandReg, int bits);
+    void WriteNormalOp(XEmitter* emit, bool toRM, NormalOp op, const OpArg& operand,
+                       int bits) const;
+
+    constexpr bool IsImm() const {
+        return scale == SCALE_IMM8 || scale == SCALE_IMM16 || scale == SCALE_IMM32 ||
+               scale == SCALE_IMM64;
+    }
+    constexpr bool IsSimpleReg() const {
+        return scale == SCALE_NONE;
+    }
+    constexpr bool IsSimpleReg(X64Reg reg) const {
         return IsSimpleReg() && GetSimpleReg() == reg;
     }
 
-    int GetImmBits() const
-    {
-        switch (scale)
-        {
-        case SCALE_IMM8: return 8;
-        case SCALE_IMM16: return 16;
-        case SCALE_IMM32: return 32;
-        case SCALE_IMM64: return 64;
-        default: return -1;
+    int GetImmBits() const {
+        switch (scale) {
+        case SCALE_IMM8:
+            return 8;
+        case SCALE_IMM16:
+            return 16;
+        case SCALE_IMM32:
+            return 32;
+        case SCALE_IMM64:
+            return 64;
+        default:
+            return -1;
         }
     }
 
     void SetImmBits(int bits) {
-        switch (bits)
-        {
-            case 8: scale = SCALE_IMM8; break;
-            case 16: scale = SCALE_IMM16; break;
-            case 32: scale = SCALE_IMM32; break;
-            case 64: scale = SCALE_IMM64; break;
+        switch (bits) {
+        case 8:
+            scale = SCALE_IMM8;
+            break;
+        case 16:
+            scale = SCALE_IMM16;
+            break;
+        case 32:
+            scale = SCALE_IMM32;
+            break;
+        case 64:
+            scale = SCALE_IMM64;
+            break;
         }
     }
 
-    constexpr X64Reg GetSimpleReg() const
-    {
-        return scale == SCALE_NONE
-               ? static_cast<X64Reg>(offsetOrBaseReg)
-               : INVALID_REG;
+    constexpr X64Reg GetSimpleReg() const {
+        return scale == SCALE_NONE ? static_cast<X64Reg>(offsetOrBaseReg) : INVALID_REG;
     }
 
     constexpr u32 GetImmValue() const {
@@ -234,41 +310,50 @@ private:
     u8 scale = 0;
     u16 offsetOrBaseReg = 0;
     u16 indexReg = 0;
-    u64 offset = 0;  // use RIP-relative as much as possible - 64-bit immediates are not available.
+    u64 offset = 0; // use RIP-relative as much as possible - 64-bit immediates are not available.
     u16 operandReg = 0;
 };
 
 template <typename T>
-inline OpArg M(const T *ptr)       { return OpArg(reinterpret_cast<u64>(ptr), static_cast<int>(SCALE_RIP)); }
-constexpr OpArg R(X64Reg value)    { return OpArg(0, SCALE_NONE, value); }
-constexpr OpArg MatR(X64Reg value) { return OpArg(0, SCALE_ATREG, value); }
+inline OpArg M(const T* ptr) {
+    return OpArg(reinterpret_cast<u64>(ptr), static_cast<int>(SCALE_RIP));
+}
+constexpr OpArg R(X64Reg value) {
+    return OpArg(0, SCALE_NONE, value);
+}
+constexpr OpArg MatR(X64Reg value) {
+    return OpArg(0, SCALE_ATREG, value);
+}
 
-constexpr OpArg MDisp(X64Reg value, int offset)
-{
+constexpr OpArg MDisp(X64Reg value, int offset) {
     return OpArg(static_cast<u32>(offset), SCALE_ATREG, value);
 }
 
-constexpr OpArg MComplex(X64Reg base, X64Reg scaled, int scale, int offset)
-{
+constexpr OpArg MComplex(X64Reg base, X64Reg scaled, int scale, int offset) {
     return OpArg(offset, scale, base, scaled);
 }
 
-constexpr OpArg MScaled(X64Reg scaled, int scale, int offset)
-{
-    return scale == SCALE_1
-           ? OpArg(offset, SCALE_ATREG, scaled)
-           : OpArg(offset, scale | 0x20, RAX, scaled);
+constexpr OpArg MScaled(X64Reg scaled, int scale, int offset) {
+    return scale == SCALE_1 ? OpArg(offset, SCALE_ATREG, scaled)
+                            : OpArg(offset, scale | 0x20, RAX, scaled);
 }
 
-constexpr OpArg MRegSum(X64Reg base, X64Reg offset)
-{
+constexpr OpArg MRegSum(X64Reg base, X64Reg offset) {
     return MComplex(base, offset, 1, 0);
 }
 
-constexpr OpArg Imm8 (u8 imm)  { return OpArg(imm, SCALE_IMM8);  }
-constexpr OpArg Imm16(u16 imm) { return OpArg(imm, SCALE_IMM16); } //rarely used
-constexpr OpArg Imm32(u32 imm) { return OpArg(imm, SCALE_IMM32); }
-constexpr OpArg Imm64(u64 imm) { return OpArg(imm, SCALE_IMM64); }
+constexpr OpArg Imm8(u8 imm) {
+    return OpArg(imm, SCALE_IMM8);
+}
+constexpr OpArg Imm16(u16 imm) {
+    return OpArg(imm, SCALE_IMM16);
+} // rarely used
+constexpr OpArg Imm32(u32 imm) {
+    return OpArg(imm, SCALE_IMM32);
+}
+constexpr OpArg Imm64(u64 imm) {
+    return OpArg(imm, SCALE_IMM64);
+}
 constexpr OpArg UImmAuto(u32 imm) {
     return OpArg(imm, imm >= 128 ? SCALE_IMM32 : SCALE_IMM8);
 }
@@ -277,8 +362,7 @@ constexpr OpArg SImmAuto(s32 imm) {
 }
 
 template <typename T>
-OpArg ImmPtr(const T* imm)
-{
+OpArg ImmPtr(const T* imm) {
 #ifdef _ARCH_64
     return Imm64(reinterpret_cast<u64>(imm));
 #else
@@ -286,36 +370,31 @@ OpArg ImmPtr(const T* imm)
 #endif
 }
 
-inline u32 PtrOffset(const void* ptr, const void* base)
-{
+inline u32 PtrOffset(const void* ptr, const void* base) {
 #ifdef _ARCH_64
-    s64 distance = (s64)ptr-(s64)base;
-    if (distance >= 0x80000000LL ||
-        distance < -0x80000000LL)
-    {
+    s64 distance = (s64)ptr - (s64)base;
+    if (distance >= 0x80000000LL || distance < -0x80000000LL) {
         ASSERT_MSG(0, "pointer offset out of range");
         return 0;
     }
 
     return (u32)distance;
 #else
-    return (u32)ptr-(u32)base;
+    return (u32)ptr - (u32)base;
 #endif
 }
 
-//usage: int a[]; ARRAY_OFFSET(a,10)
-#define ARRAY_OFFSET(array,index) ((u32)((u64)&(array)[index]-(u64)&(array)[0]))
-//usage: struct {int e;} s; STRUCT_OFFSET(s,e)
-#define STRUCT_OFFSET(str,elem) ((u32)((u64)&(str).elem-(u64)&(str)))
+// usage: int a[]; ARRAY_OFFSET(a,10)
+#define ARRAY_OFFSET(array, index) ((u32)((u64) & (array)[index] - (u64) & (array)[0]))
+// usage: struct {int e;} s; STRUCT_OFFSET(s,e)
+#define STRUCT_OFFSET(str, elem) ((u32)((u64) & (str).elem - (u64) & (str)))
 
-struct FixupBranch
-{
-    u8 *ptr;
-    int type; //0 = 8bit 1 = 32bit
+struct FixupBranch {
+    u8* ptr;
+    int type; // 0 = 8bit 1 = 32bit
 };
 
-enum SSECompare
-{
+enum SSECompare {
     EQ = 0,
     LT,
     LE,
@@ -326,11 +405,10 @@ enum SSECompare
     ORD,
 };
 
-class XEmitter
-{
-    friend struct OpArg;  // for Write8 etc
+class XEmitter {
+    friend struct OpArg; // for Write8 etc
 private:
-    u8 *code;
+    u8* code;
     bool flags_locked;
 
     void CheckFlags();
@@ -347,14 +425,19 @@ private:
     void WriteSSSE3Op(u8 opPrefix, u16 op, X64Reg regOp, const OpArg& arg, int extrabytes = 0);
     void WriteSSE41Op(u8 opPrefix, u16 op, X64Reg regOp, const OpArg& arg, int extrabytes = 0);
     void WriteAVXOp(u8 opPrefix, u16 op, X64Reg regOp, const OpArg& arg, int extrabytes = 0);
-    void WriteAVXOp(u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2, const OpArg& arg, int extrabytes = 0);
-    void WriteVEXOp(int size, u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2, const OpArg& arg, int extrabytes = 0);
-    void WriteBMI1Op(int size, u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2, const OpArg& arg, int extrabytes = 0);
-    void WriteBMI2Op(int size, u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2, const OpArg& arg, int extrabytes = 0);
+    void WriteAVXOp(u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2, const OpArg& arg,
+                    int extrabytes = 0);
+    void WriteVEXOp(int size, u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2, const OpArg& arg,
+                    int extrabytes = 0);
+    void WriteBMI1Op(int size, u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2, const OpArg& arg,
+                     int extrabytes = 0);
+    void WriteBMI2Op(int size, u8 opPrefix, u16 op, X64Reg regOp1, X64Reg regOp2, const OpArg& arg,
+                     int extrabytes = 0);
     void WriteFloatLoadStore(int bits, FloatOp op, FloatOp op_80b, const OpArg& arg);
-    void WriteNormalOp(XEmitter *emit, int bits, NormalOp op, const OpArg& a1, const OpArg& a2);
+    void WriteNormalOp(XEmitter* emit, int bits, NormalOp op, const OpArg& a1, const OpArg& a2);
 
-    void ABI_CalculateFrameSize(BitSet32 mask, size_t rsp_alignment, size_t needed_frame_size, size_t* shadowp, size_t* subtractionp, size_t* xmm_offsetp);
+    void ABI_CalculateFrameSize(BitSet32 mask, size_t rsp_alignment, size_t needed_frame_size,
+                                size_t* shadowp, size_t* subtractionp, size_t* xmm_offsetp);
 
 protected:
     void Write8(u8 value);
@@ -363,26 +446,38 @@ protected:
     void Write64(u64 value);
 
 public:
-    XEmitter() { code = nullptr; flags_locked = false; }
-    XEmitter(u8 *code_ptr) { code = code_ptr; flags_locked = false; }
-    virtual ~XEmitter() {}
+    XEmitter() {
+        code = nullptr;
+        flags_locked = false;
+    }
+    XEmitter(u8* code_ptr) {
+        code = code_ptr;
+        flags_locked = false;
+    }
+    virtual ~XEmitter() {
+    }
 
     void WriteModRM(int mod, int rm, int reg);
     void WriteSIB(int scale, int index, int base);
 
-    void SetCodePtr(u8 *ptr);
+    void SetCodePtr(u8* ptr);
     void ReserveCodeSpace(int bytes);
-    const u8 *AlignCode4();
-    const u8 *AlignCode16();
-    const u8 *AlignCodePage();
-    const u8 *GetCodePtr() const;
-    u8 *GetWritableCodePtr();
-
-    void LockFlags() { flags_locked = true; }
-    void UnlockFlags() { flags_locked = false; }
+    const u8* AlignCode4();
+    const u8* AlignCode16();
+    const u8* AlignCodePage();
+    const u8* GetCodePtr() const;
+    u8* GetWritableCodePtr();
+
+    void LockFlags() {
+        flags_locked = true;
+    }
+    void UnlockFlags() {
+        flags_locked = false;
+    }
 
     // Looking for one of these? It's BANNED!! Some instructions are slow on modern CPU
-    // INC, DEC, LOOP, LOOPNE, LOOPE, ENTER, LEAVE, XCHG, XLAT, REP MOVSB/MOVSD, REP SCASD + other string instr.,
+    // INC, DEC, LOOP, LOOPNE, LOOPE, ENTER, LEAVE, XCHG, XLAT, REP MOVSB/MOVSD, REP SCASD + other
+    // string instr.,
     // INC and DEC are slow on Intel Core, but not on AMD. They create a
     // false flag dependency because they only update a subset of the flags.
     // XCHG is SLOW and should be avoided.
@@ -401,11 +496,11 @@ public:
     void CLC();
     void CMC();
 
-    // These two can not be executed in 64-bit mode on early Intel 64-bit CPU:s, only on Core2 and AMD!
+    // These two can not be executed in 64-bit mode on early Intel 64-bit CPU:s, only on Core2 and
+    // AMD!
     void LAHF(); // 3 cycle vector path
     void SAHF(); // direct path fast
 
-
     // Stack control
     void PUSH(X64Reg reg);
     void POP(X64Reg reg);
@@ -422,7 +517,7 @@ public:
 
     void JMP(const u8* addr, bool force5Bytes = false);
     void JMPptr(const OpArg& arg);
-    void JMPself(); //infinite loop!
+    void JMPself(); // infinite loop!
 #ifdef CALL
 #undef CALL
 #endif
@@ -450,12 +545,11 @@ public:
     void BSR(int bits, X64Reg dest, const OpArg& src); // Top bit to bottom bit
 
     // Cache control
-    enum PrefetchLevel
-    {
-        PF_NTA, //Non-temporal (data used once and only once)
-        PF_T0,  //All cache levels
-        PF_T1,  //Levels 2+ (aliased to T0 on AMD)
-        PF_T2,  //Levels 3+ (aliased to T0 on AMD)
+    enum PrefetchLevel {
+        PF_NTA, // Non-temporal (data used once and only once)
+        PF_T0,  // All cache levels
+        PF_T1,  // Levels 2+ (aliased to T0 on AMD)
+        PF_T2,  // Levels 3+ (aliased to T0 on AMD)
     };
     void PREFETCH(PrefetchLevel level, OpArg arg);
     void MOVNTI(int bits, const OpArg& dest, X64Reg src);
@@ -464,8 +558,8 @@ public:
     void MOVNTPD(const OpArg& arg, X64Reg regOp);
 
     // Multiplication / division
-    void MUL(int bits, const OpArg& src); //UNSIGNED
-    void IMUL(int bits, const OpArg& src); //SIGNED
+    void MUL(int bits, const OpArg& src);  // UNSIGNED
+    void IMUL(int bits, const OpArg& src); // SIGNED
     void IMUL(int bits, X64Reg regOp, const OpArg& src);
     void IMUL(int bits, X64Reg regOp, const OpArg& src, const OpArg& imm);
     void DIV(int bits, const OpArg& src);
@@ -492,11 +586,19 @@ public:
 
     // Extend EAX into EDX in various ways
     void CWD(int bits = 16);
-    void CDQ() {CWD(32);}
-    void CQO() {CWD(64);}
+    void CDQ() {
+        CWD(32);
+    }
+    void CQO() {
+        CWD(64);
+    }
     void CBW(int bits = 8);
-    void CWDE() {CBW(16);}
-    void CDQE() {CBW(32);}
+    void CWDE() {
+        CBW(16);
+    }
+    void CDQE() {
+        CBW(32);
+    }
 
     // Load effective address
     void LEA(int bits, X64Reg dest, OpArg src);
@@ -511,7 +613,7 @@ public:
     void CMP(int bits, const OpArg& a1, const OpArg& a2);
 
     // Bit operations
-    void NOT (int bits, const OpArg& src);
+    void NOT(int bits, const OpArg& src);
     void OR(int bits, const OpArg& a1, const OpArg& a2);
     void XOR(int bits, const OpArg& a1, const OpArg& a2);
     void MOV(int bits, const OpArg& a1, const OpArg& a2);
@@ -525,7 +627,8 @@ public:
     void BSWAP(int bits, X64Reg reg);
 
     // Sign/zero extension
-    void MOVSX(int dbits, int sbits, X64Reg dest, OpArg src); //automatically uses MOVSXD if necessary
+    void MOVSX(int dbits, int sbits, X64Reg dest,
+               OpArg src); // automatically uses MOVSXD if necessary
     void MOVZX(int dbits, int sbits, X64Reg dest, OpArg src);
 
     // Available only on Atom or >= Haswell so far. Test with GetCPUCaps().movbe.
@@ -593,13 +696,27 @@ public:
     void CMPSS(X64Reg regOp, const OpArg& arg, u8 compare);
     void CMPSD(X64Reg regOp, const OpArg& arg, u8 compare);
 
-    void CMPEQSS(X64Reg regOp, const OpArg& arg) { CMPSS(regOp, arg, CMP_EQ); }
-    void CMPLTSS(X64Reg regOp, const OpArg& arg) { CMPSS(regOp, arg, CMP_LT); }
-    void CMPLESS(X64Reg regOp, const OpArg& arg) { CMPSS(regOp, arg, CMP_LE); }
-    void CMPUNORDSS(X64Reg regOp, const OpArg& arg) { CMPSS(regOp, arg, CMP_UNORD); }
-    void CMPNEQSS(X64Reg regOp, const OpArg& arg) { CMPSS(regOp, arg, CMP_NEQ); }
-    void CMPNLTSS(X64Reg regOp, const OpArg& arg) { CMPSS(regOp, arg, CMP_NLT); }
-    void CMPORDSS(X64Reg regOp, const OpArg& arg) { CMPSS(regOp, arg, CMP_ORD); }
+    void CMPEQSS(X64Reg regOp, const OpArg& arg) {
+        CMPSS(regOp, arg, CMP_EQ);
+    }
+    void CMPLTSS(X64Reg regOp, const OpArg& arg) {
+        CMPSS(regOp, arg, CMP_LT);
+    }
+    void CMPLESS(X64Reg regOp, const OpArg& arg) {
+        CMPSS(regOp, arg, CMP_LE);
+    }
+    void CMPUNORDSS(X64Reg regOp, const OpArg& arg) {
+        CMPSS(regOp, arg, CMP_UNORD);
+    }
+    void CMPNEQSS(X64Reg regOp, const OpArg& arg) {
+        CMPSS(regOp, arg, CMP_NEQ);
+    }
+    void CMPNLTSS(X64Reg regOp, const OpArg& arg) {
+        CMPSS(regOp, arg, CMP_NLT);
+    }
+    void CMPORDSS(X64Reg regOp, const OpArg& arg) {
+        CMPSS(regOp, arg, CMP_ORD);
+    }
 
     // SSE/SSE2: Floating point packed arithmetic (x4 for float, x2 for double)
     void ADDPS(X64Reg regOp, const OpArg& arg);
@@ -638,10 +755,12 @@ public:
     // SSE/SSE2: Useful alternative to shuffle in some cases.
     void MOVDDUP(X64Reg regOp, const OpArg& arg);
 
-    // SSE3: Horizontal operations in SIMD registers. Very slow! shufps-based code beats it handily on Ivy.
+    // SSE3: Horizontal operations in SIMD registers. Very slow! shufps-based code beats it handily
+    // on Ivy.
     void HADDPS(X64Reg dest, const OpArg& src);
 
-    // SSE4: Further horizontal operations - dot products. These are weirdly flexible, the arg contains both a read mask and a write "mask".
+    // SSE4: Further horizontal operations - dot products. These are weirdly flexible, the arg
+    // contains both a read mask and a write "mask".
     void DPPS(X64Reg dest, const OpArg& src, u8 arg);
 
     void UNPCKLPS(X64Reg dest, const OpArg& src);
@@ -694,11 +813,13 @@ public:
     void MOVD_xmm(const OpArg& arg, X64Reg src);
     void MOVQ_xmm(OpArg arg, X64Reg src);
 
-    // SSE/SSE2: Generates a mask from the high bits of the components of the packed register in question.
+    // SSE/SSE2: Generates a mask from the high bits of the components of the packed register in
+    // question.
     void MOVMSKPS(X64Reg dest, const OpArg& arg);
     void MOVMSKPD(X64Reg dest, const OpArg& arg);
 
-    // SSE2: Selective byte store, mask in src register. EDI/RDI specifies store address. This is a weird one.
+    // SSE2: Selective byte store, mask in src register. EDI/RDI specifies store address. This is a
+    // weird one.
     void MASKMOVDQU(X64Reg dest, X64Reg src);
     void LDDQU(X64Reg dest, const OpArg& src);
 
@@ -729,10 +850,10 @@ public:
     void PACKUSDW(X64Reg dest, const OpArg& arg);
     void PACKUSWB(X64Reg dest, const OpArg& arg);
 
-    void PUNPCKLBW(X64Reg dest, const OpArg &arg);
-    void PUNPCKLWD(X64Reg dest, const OpArg &arg);
-    void PUNPCKLDQ(X64Reg dest, const OpArg &arg);
-    void PUNPCKLQDQ(X64Reg dest, const OpArg &arg);
+    void PUNPCKLBW(X64Reg dest, const OpArg& arg);
+    void PUNPCKLWD(X64Reg dest, const OpArg& arg);
+    void PUNPCKLDQ(X64Reg dest, const OpArg& arg);
+    void PUNPCKLQDQ(X64Reg dest, const OpArg& arg);
 
     void PTEST(X64Reg dest, const OpArg& arg);
     void PAND(X64Reg dest, const OpArg& arg);
@@ -839,25 +960,57 @@ public:
     void ROUNDPS(X64Reg dest, const OpArg& arg, u8 mode);
     void ROUNDPD(X64Reg dest, const OpArg& arg, u8 mode);
 
-    void ROUNDNEARSS(X64Reg dest, const OpArg& arg) { ROUNDSS(dest, arg, FROUND_NEAREST); }
-    void ROUNDFLOORSS(X64Reg dest, const OpArg& arg) { ROUNDSS(dest, arg, FROUND_FLOOR); }
-    void ROUNDCEILSS(X64Reg dest, const OpArg& arg) { ROUNDSS(dest, arg, FROUND_CEIL); }
-    void ROUNDZEROSS(X64Reg dest, const OpArg& arg) { ROUNDSS(dest, arg, FROUND_ZERO); }
+    void ROUNDNEARSS(X64Reg dest, const OpArg& arg) {
+        ROUNDSS(dest, arg, FROUND_NEAREST);
+    }
+    void ROUNDFLOORSS(X64Reg dest, const OpArg& arg) {
+        ROUNDSS(dest, arg, FROUND_FLOOR);
+    }
+    void ROUNDCEILSS(X64Reg dest, const OpArg& arg) {
+        ROUNDSS(dest, arg, FROUND_CEIL);
+    }
+    void ROUNDZEROSS(X64Reg dest, const OpArg& arg) {
+        ROUNDSS(dest, arg, FROUND_ZERO);
+    }
 
-    void ROUNDNEARSD(X64Reg dest, const OpArg& arg) { ROUNDSD(dest, arg, FROUND_NEAREST); }
-    void ROUNDFLOORSD(X64Reg dest, const OpArg& arg) { ROUNDSD(dest, arg, FROUND_FLOOR); }
-    void ROUNDCEILSD(X64Reg dest, const OpArg& arg) { ROUNDSD(dest, arg, FROUND_CEIL); }
-    void ROUNDZEROSD(X64Reg dest, const OpArg& arg) { ROUNDSD(dest, arg, FROUND_ZERO); }
+    void ROUNDNEARSD(X64Reg dest, const OpArg& arg) {
+        ROUNDSD(dest, arg, FROUND_NEAREST);
+    }
+    void ROUNDFLOORSD(X64Reg dest, const OpArg& arg) {
+        ROUNDSD(dest, arg, FROUND_FLOOR);
+    }
+    void ROUNDCEILSD(X64Reg dest, const OpArg& arg) {
+        ROUNDSD(dest, arg, FROUND_CEIL);
+    }
+    void ROUNDZEROSD(X64Reg dest, const OpArg& arg) {
+        ROUNDSD(dest, arg, FROUND_ZERO);
+    }
 
-    void ROUNDNEARPS(X64Reg dest, const OpArg& arg) { ROUNDPS(dest, arg, FROUND_NEAREST); }
-    void ROUNDFLOORPS(X64Reg dest, const OpArg& arg) { ROUNDPS(dest, arg, FROUND_FLOOR); }
-    void ROUNDCEILPS(X64Reg dest, const OpArg& arg) { ROUNDPS(dest, arg, FROUND_CEIL); }
-    void ROUNDZEROPS(X64Reg dest, const OpArg& arg) { ROUNDPS(dest, arg, FROUND_ZERO); }
+    void ROUNDNEARPS(X64Reg dest, const OpArg& arg) {
+        ROUNDPS(dest, arg, FROUND_NEAREST);
+    }
+    void ROUNDFLOORPS(X64Reg dest, const OpArg& arg) {
+        ROUNDPS(dest, arg, FROUND_FLOOR);
+    }
+    void ROUNDCEILPS(X64Reg dest, const OpArg& arg) {
+        ROUNDPS(dest, arg, FROUND_CEIL);
+    }
+    void ROUNDZEROPS(X64Reg dest, const OpArg& arg) {
+        ROUNDPS(dest, arg, FROUND_ZERO);
+    }
 
-    void ROUNDNEARPD(X64Reg dest, const OpArg& arg) { ROUNDPD(dest, arg, FROUND_NEAREST); }
-    void ROUNDFLOORPD(X64Reg dest, const OpArg& arg) { ROUNDPD(dest, arg, FROUND_FLOOR); }
-    void ROUNDCEILPD(X64Reg dest, const OpArg& arg) { ROUNDPD(dest, arg, FROUND_CEIL); }
-    void ROUNDZEROPD(X64Reg dest, const OpArg& arg) { ROUNDPD(dest, arg, FROUND_ZERO); }
+    void ROUNDNEARPD(X64Reg dest, const OpArg& arg) {
+        ROUNDPD(dest, arg, FROUND_NEAREST);
+    }
+    void ROUNDFLOORPD(X64Reg dest, const OpArg& arg) {
+        ROUNDPD(dest, arg, FROUND_FLOOR);
+    }
+    void ROUNDCEILPD(X64Reg dest, const OpArg& arg) {
+        ROUNDPD(dest, arg, FROUND_CEIL);
+    }
+    void ROUNDZEROPD(X64Reg dest, const OpArg& arg) {
+        ROUNDPD(dest, arg, FROUND_ZERO);
+    }
 
     // AVX
     void VADDSD(X64Reg regOp1, X64Reg regOp2, const OpArg& arg);
@@ -981,7 +1134,6 @@ public:
     void ABI_CallFunctionC16(const void* func, u16 param1);
     void ABI_CallFunctionCC16(const void* func, u32 param1, u16 param2);
 
-
     // These only support u32 parameters, but that's enough for a lot of uses.
     // These will destroy the 1 or 2 first "parameter regs".
     void ABI_CallFunctionC(const void* func, u32 param1);
@@ -1012,29 +1164,38 @@ public:
      *
      * @param mask Registers to push on the stack (high 16 bits are XMMs, low 16 bits are GPRs)
      * @param rsp_alignment Current alignment of the stack pointer, must be 0 or 8
-     * @param needed_frame_size Additional space needed, e.g., for function arguments passed on the stack
+     * @param needed_frame_size Additional space needed, e.g., for function arguments passed on the
+     * stack
      * @return Size of the shadow space, i.e., offset of the frame
      */
-    size_t ABI_PushRegistersAndAdjustStack(BitSet32 mask, size_t rsp_alignment, size_t needed_frame_size = 0);
+    size_t ABI_PushRegistersAndAdjustStack(BitSet32 mask, size_t rsp_alignment,
+                                           size_t needed_frame_size = 0);
 
     /**
-     * Restores specified registers and adjusts the stack to its original alignment, i.e., the alignment before
+     * Restores specified registers and adjusts the stack to its original alignment, i.e., the
+     * alignment before
      * the matching PushRegistersAndAdjustStack.
      *
-     * @param mask Registers to restores from the stack (high 16 bits are XMMs, low 16 bits are GPRs)
-     * @param rsp_alignment Original alignment before the matching PushRegistersAndAdjustStack, must be 0 or 8
+     * @param mask Registers to restores from the stack (high 16 bits are XMMs, low 16 bits are
+     * GPRs)
+     * @param rsp_alignment Original alignment before the matching PushRegistersAndAdjustStack, must
+     * be 0 or 8
      * @param needed_frame_size Additional space that was needed
      * @warning Stack must be currently 16-byte aligned
      */
-    void ABI_PopRegistersAndAdjustStack(BitSet32 mask, size_t rsp_alignment, size_t needed_frame_size = 0);
-
-    #ifdef _M_IX86
-    static int ABI_GetNumXMMRegs() { return 8; }
-    #else
-    static int ABI_GetNumXMMRegs() { return 16; }
-    #endif
-};  // class XEmitter
+    void ABI_PopRegistersAndAdjustStack(BitSet32 mask, size_t rsp_alignment,
+                                        size_t needed_frame_size = 0);
 
+#ifdef _M_IX86
+    static int ABI_GetNumXMMRegs() {
+        return 8;
+    }
+#else
+    static int ABI_GetNumXMMRegs() {
+        return 16;
+    }
+#endif
+}; // class XEmitter
 
 // Everything that needs to generate X86 code should inherit from this.
 // You get memory management for free, plus, you can use all the MOV etc functions without
@@ -1045,4 +1206,4 @@ public:
     void PoisonMemory() override;
 };
 
-}  // namespace
+} // namespace