From 405eae3734dd6bfb259df0afceecf4de1f1262ce Mon Sep 17 00:00:00 2001
From: ameerj <52414509+ameerj@users.noreply.github.com>
Date: Sun, 25 Jun 2023 18:59:33 -0400
Subject: [PATCH] shaders: Track local memory usage

---
 src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp | 4 ++++
 src/shader_recompiler/shader_info.h                       | 1 +
 src/video_core/renderer_opengl/gl_compute_pipeline.cpp    | 1 +
 src/video_core/renderer_opengl/gl_compute_pipeline.h      | 5 +++++
 src/video_core/renderer_opengl/gl_graphics_pipeline.cpp   | 1 +
 src/video_core/renderer_opengl/gl_graphics_pipeline.h     | 5 +++++
 src/video_core/renderer_opengl/gl_rasterizer.cpp          | 8 ++++++--
 7 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp b/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp
index 5a4195217..70292686f 100644
--- a/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp
+++ b/src/shader_recompiler/ir_opt/collect_shader_info_pass.cpp
@@ -424,6 +424,10 @@ void VisitUsages(Info& info, IR::Inst& inst) {
         info.used_constant_buffer_types |= IR::Type::U32 | IR::Type::U32x2;
         info.used_storage_buffer_types |= IR::Type::U32 | IR::Type::U32x2 | IR::Type::U32x4;
         break;
+    case IR::Opcode::LoadLocal:
+    case IR::Opcode::WriteLocal:
+        info.uses_local_memory = true;
+        break;
     default:
         break;
     }
diff --git a/src/shader_recompiler/shader_info.h b/src/shader_recompiler/shader_info.h
index d308db942..b4b4afd37 100644
--- a/src/shader_recompiler/shader_info.h
+++ b/src/shader_recompiler/shader_info.h
@@ -172,6 +172,7 @@ struct Info {
     bool stores_indexed_attributes{};
 
     bool stores_global_memory{};
+    bool uses_local_memory{};
 
     bool uses_fp16{};
     bool uses_fp64{};
diff --git a/src/video_core/renderer_opengl/gl_compute_pipeline.cpp b/src/video_core/renderer_opengl/gl_compute_pipeline.cpp
index 3151c0db8..f9ca55c36 100644
--- a/src/video_core/renderer_opengl/gl_compute_pipeline.cpp
+++ b/src/video_core/renderer_opengl/gl_compute_pipeline.cpp
@@ -63,6 +63,7 @@ ComputePipeline::ComputePipeline(const Device& device, TextureCache& texture_cac
     writes_global_memory = !use_storage_buffers &&
                            std::ranges::any_of(info.storage_buffers_descriptors,
                                                [](const auto& desc) { return desc.is_written; });
+    uses_local_memory = info.uses_local_memory;
     if (force_context_flush) {
         std::scoped_lock lock{built_mutex};
         built_fence.Create();
diff --git a/src/video_core/renderer_opengl/gl_compute_pipeline.h b/src/video_core/renderer_opengl/gl_compute_pipeline.h
index 9bcc72b59..c26b4fa5e 100644
--- a/src/video_core/renderer_opengl/gl_compute_pipeline.h
+++ b/src/video_core/renderer_opengl/gl_compute_pipeline.h
@@ -59,6 +59,10 @@ public:
         return writes_global_memory;
     }
 
+    [[nodiscard]] bool UsesLocalMemory() const noexcept {
+        return uses_local_memory;
+    }
+
     void SetEngine(Tegra::Engines::KeplerCompute* kepler_compute_,
                    Tegra::MemoryManager* gpu_memory_) {
         kepler_compute = kepler_compute_;
@@ -84,6 +88,7 @@ private:
 
     bool use_storage_buffers{};
     bool writes_global_memory{};
+    bool uses_local_memory{};
 
     std::mutex built_mutex;
     std::condition_variable built_condvar;
diff --git a/src/video_core/renderer_opengl/gl_graphics_pipeline.cpp b/src/video_core/renderer_opengl/gl_graphics_pipeline.cpp
index c58f760b8..23a48c6fe 100644
--- a/src/video_core/renderer_opengl/gl_graphics_pipeline.cpp
+++ b/src/video_core/renderer_opengl/gl_graphics_pipeline.cpp
@@ -215,6 +215,7 @@ GraphicsPipeline::GraphicsPipeline(const Device& device, TextureCache& texture_c
 
         writes_global_memory |= std::ranges::any_of(
             info.storage_buffers_descriptors, [](const auto& desc) { return desc.is_written; });
+        uses_local_memory |= info.uses_local_memory;
     }
     ASSERT(num_textures <= MAX_TEXTURES);
     ASSERT(num_images <= MAX_IMAGES);
diff --git a/src/video_core/renderer_opengl/gl_graphics_pipeline.h b/src/video_core/renderer_opengl/gl_graphics_pipeline.h
index 7bab3be0a..7b3d7eae8 100644
--- a/src/video_core/renderer_opengl/gl_graphics_pipeline.h
+++ b/src/video_core/renderer_opengl/gl_graphics_pipeline.h
@@ -98,6 +98,10 @@ public:
         return writes_global_memory;
     }
 
+    [[nodiscard]] bool UsesLocalMemory() const noexcept {
+        return uses_local_memory;
+    }
+
     [[nodiscard]] bool IsBuilt() noexcept;
 
     template <typename Spec>
@@ -146,6 +150,7 @@ private:
 
     bool use_storage_buffers{};
     bool writes_global_memory{};
+    bool uses_local_memory{};
 
     static constexpr std::size_t XFB_ENTRY_STRIDE = 3;
     GLsizei num_xfb_attribs{};
diff --git a/src/video_core/renderer_opengl/gl_rasterizer.cpp b/src/video_core/renderer_opengl/gl_rasterizer.cpp
index d03288516..edf527f2d 100644
--- a/src/video_core/renderer_opengl/gl_rasterizer.cpp
+++ b/src/video_core/renderer_opengl/gl_rasterizer.cpp
@@ -222,7 +222,9 @@ void RasterizerOpenGL::PrepareDraw(bool is_indexed, Func&& draw_func) {
     gpu.TickWork();
 
     std::scoped_lock lock{buffer_cache.mutex, texture_cache.mutex};
-    program_manager.LocalMemoryWarmup();
+    if (pipeline->UsesLocalMemory()) {
+        program_manager.LocalMemoryWarmup();
+    }
     pipeline->SetEngine(maxwell3d, gpu_memory);
     pipeline->Configure(is_indexed);
 
@@ -372,7 +374,9 @@ void RasterizerOpenGL::DispatchCompute() {
     if (!pipeline) {
         return;
     }
-    program_manager.LocalMemoryWarmup();
+    if (pipeline->UsesLocalMemory()) {
+        program_manager.LocalMemoryWarmup();
+    }
     pipeline->SetEngine(kepler_compute, gpu_memory);
     pipeline->Configure();
     const auto& qmd{kepler_compute->launch_description};