atomic cas use prefetchw if available

remove useless memorybarrier
remove double membarrier in wait pm4 cmd
add int64 cvar
use int64 cvar for x64 feature mask
Rework some functions that were frontend bound according to vtune placing some of their code in different noinline functions, profiling after indicating l1 cache misses decreased and perf of func increased
remove long vpinsrd dep chain code for conversion.h, instead do normal load+bswap or movbe if avail
Much faster entry table via split_map, code size could be improved though
GetResolveInfo was very large and had impact on icache, mark callees as noinline + msvc pragma optimize small
use log2 shifts instead of integer divides in memory
minor optimizations in PhysicalHeap::EnableAccessCallbacks, the majority of time in the function is spent looping, NOT calling Protect! Someone should optimize this function and rework the algo completely
remove wonky scheduling log message, it was spammy and unhelpful
lock count was unnecessary for criticalsection mutex, criticalsection is already a recursive mutex
brief notes i gotta run

src/xenia/gpu/d3d12/d3d12_command_processor.h

@@ -45,7 +45,10 @@
 namespace xe {
 namespace gpu {
 namespace d3d12 {
-
+struct MemExportRange {
+  uint32_t base_address_dwords;
+  uint32_t size_dwords;
+};
 class D3D12CommandProcessor final : public CommandProcessor {
  public:
 #include "../pm4_command_processor_declare.h"
@@ -287,8 +290,21 @@ class D3D12CommandProcessor final : public CommandProcessor {
   bool IssueDraw(xenos::PrimitiveType primitive_type, uint32_t index_count,
                  IndexBufferInfo* index_buffer_info,
                  bool major_mode_explicit) override;
+  XE_COLD
+  XE_NOINLINE
+  bool HandleMemexportGuestDMA(ID3D12Resource*& scratch_index_buffer,
+                               D3D12_INDEX_BUFFER_VIEW& index_buffer_view,
+                               uint32_t guest_index_base,
+                               bool& retflag);
+  XE_NOINLINE
+  XE_COLD
+  bool GatherMemexportRangesAndMakeResident(bool& retflag);
+  XE_NOINLINE
+  XE_COLD
+  void HandleMemexportDrawOrdering_AndReadback();
   bool IssueCopy() override;
-
+  XE_NOINLINE
+  bool IssueCopy_ReadbackResolvePath();
   void InitializeTrace() override;
 
  private:
@@ -363,6 +379,8 @@ class D3D12CommandProcessor final : public CommandProcessor {
   };
   // Gets the indices of optional root parameters. Returns the total parameter
   // count.
+  XE_NOINLINE
+  XE_COLD
   static uint32_t GetRootBindfulExtraParameterIndices(
       const DxbcShader* vertex_shader, const DxbcShader* pixel_shader,
       RootBindfulExtraParameterIndices& indices_out);
@@ -437,6 +455,18 @@ class D3D12CommandProcessor final : public CommandProcessor {
   bool UpdateBindings(const D3D12Shader* vertex_shader,
                       const D3D12Shader* pixel_shader,
                       ID3D12RootSignature* root_signature);
+  XE_COLD
+  XE_NOINLINE
+  void UpdateBindings_UpdateRootBindful();
+  XE_NOINLINE
+  XE_COLD
+  bool UpdateBindings_BindfulPath(
+      const size_t texture_layout_uid_vertex,
+      const std::vector<xe::gpu::DxbcShader::TextureBinding>& textures_vertex,
+      const size_t texture_layout_uid_pixel,
+      const std::vector<xe::gpu::DxbcShader::TextureBinding>* textures_pixel,
+      const size_t sampler_count_vertex, const size_t sampler_count_pixel,
+      bool& retflag);
 
   // Returns dword count for one element for a memexport format, or 0 if it's
   // not supported by the D3D12 command processor (if it's smaller that 1 dword,
@@ -743,6 +773,9 @@ class D3D12CommandProcessor final : public CommandProcessor {
 
   draw_util::GetViewportInfoArgs previous_viewport_info_args_;
   draw_util::ViewportInfo previous_viewport_info_;
+  // scratch memexport data
+  MemExportRange memexport_ranges_[512];
+  uint32_t memexport_range_count_ = 0;
 };
 
 }  // namespace d3d12