From 82c2601555b59a94d7160f2fd686cb63d32dd423 Mon Sep 17 00:00:00 2001
From: ReinUsesLisp <reinuseslisp@airmail.cc>
Date: Sat, 16 Jan 2021 20:48:58 -0300
Subject: video_core: Reimplement the buffer cache

Reimplement the buffer cache using cached bindings and page level
granularity for modification tracking. This also drops the usage of
shared pointers and virtual functions from the cache.

- Bindings are cached, allowing to skip work when the game changes few
  bits between draws.
- OpenGL Assembly shaders no longer copy when a region has been modified
  from the GPU to emulate constant buffers, instead GL_EXT_memory_object
  is used to alias sub-buffers within the same allocation.
- OpenGL Assembly shaders stream constant buffer data using
  glProgramBufferParametersIuivNV, from NV_parameter_buffer_object. In
  theory this should save one hash table resolve inside the driver
  compared to glBufferSubData.
- A new OpenGL stream buffer is implemented based on fences for drivers
  that are not Nvidia's proprietary, due to their low performance on
  partial glBufferSubData calls synchronized with 3D rendering (that
  some games use a lot).
- Most optimizations are shared between APIs now, allowing Vulkan to
  cache more bindings than before, skipping unnecesarry work.

This commit adds the necessary infrastructure to use Vulkan object from
OpenGL. Overall, it improves performance and fixes some bugs present on
the old cache. There are still some edge cases hit by some games that
harm performance on some vendors, this are planned to be fixed in later
commits.
---
 src/video_core/dirty_flags.cpp | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

(limited to 'src/video_core/dirty_flags.cpp')

diff --git a/src/video_core/dirty_flags.cpp b/src/video_core/dirty_flags.cpp
index b1eaac00c..7149af290 100644
--- a/src/video_core/dirty_flags.cpp
+++ b/src/video_core/dirty_flags.cpp
@@ -12,13 +12,30 @@
 #define NUM(field_name) (sizeof(::Tegra::Engines::Maxwell3D::Regs::field_name) / (sizeof(u32)))
 
 namespace VideoCommon::Dirty {
-
+namespace {
 using Tegra::Engines::Maxwell3D;
 
-void SetupDirtyRenderTargets(Tegra::Engines::Maxwell3D::DirtyState::Tables& tables) {
+void SetupDirtyVertexBuffers(Maxwell3D::DirtyState::Tables& tables) {
+    static constexpr std::size_t num_array = 3;
+    for (std::size_t i = 0; i < Maxwell3D::Regs::NumVertexArrays; ++i) {
+        const std::size_t array_offset = OFF(vertex_array) + i * NUM(vertex_array[0]);
+        const std::size_t limit_offset = OFF(vertex_array_limit) + i * NUM(vertex_array_limit[0]);
+
+        FillBlock(tables, array_offset, num_array, VertexBuffer0 + i, VertexBuffers);
+        FillBlock(tables, limit_offset, NUM(vertex_array_limit), VertexBuffer0 + i, VertexBuffers);
+    }
+}
+
+void SetupIndexBuffer(Maxwell3D::DirtyState::Tables& tables) {
+    FillBlock(tables[0], OFF(index_array), NUM(index_array), IndexBuffer);
+}
+
+void SetupDirtyDescriptors(Maxwell3D::DirtyState::Tables& tables) {
     FillBlock(tables[0], OFF(tic), NUM(tic), Descriptors);
     FillBlock(tables[0], OFF(tsc), NUM(tsc), Descriptors);
+}
 
+void SetupDirtyRenderTargets(Maxwell3D::DirtyState::Tables& tables) {
     static constexpr std::size_t num_per_rt = NUM(rt[0]);
     static constexpr std::size_t begin = OFF(rt);
     static constexpr std::size_t num = num_per_rt * Maxwell3D::Regs::NumRenderTargets;
@@ -41,5 +58,13 @@ void SetupDirtyRenderTargets(Tegra::Engines::Maxwell3D::DirtyState::Tables& tabl
         FillBlock(table, OFF(zeta), NUM(zeta), flag);
     }
 }
+} // Anonymous namespace
+
+void SetupDirtyFlags(Maxwell3D::DirtyState::Tables& tables) {
+    SetupDirtyVertexBuffers(tables);
+    SetupIndexBuffer(tables);
+    SetupDirtyDescriptors(tables);
+    SetupDirtyRenderTargets(tables);
+}
 
 } // namespace VideoCommon::Dirty
-- 
cgit v1.2.3