diff options
Diffstat (limited to 'src/video_core/renderer_opengl')
10 files changed, 43 insertions, 1 deletions
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_device.cpp b/src/video_core/renderer_opengl/gl_device.cpp index 03d234f2f..33e63c17d 100644 --- a/src/video_core/renderer_opengl/gl_device.cpp +++ b/src/video_core/renderer_opengl/gl_device.cpp @@ -194,6 +194,7 @@ Device::Device(Core::Frontend::EmuWindow& emu_window) { has_bool_ref_bug = true; } } + has_lmem_perf_bug = is_nvidia; strict_context_required = emu_window.StrictContextRequired(); // Blocks AMD and Intel OpenGL drivers on Windows from using asynchronous shader compilation. diff --git a/src/video_core/renderer_opengl/gl_device.h b/src/video_core/renderer_opengl/gl_device.h index ad27264e5..a5a6bbbba 100644 --- a/src/video_core/renderer_opengl/gl_device.h +++ b/src/video_core/renderer_opengl/gl_device.h @@ -192,6 +192,10 @@ public: return supports_conditional_barriers; } + bool HasLmemPerfBug() const { + return has_lmem_perf_bug; + } + private: static bool TestVariableAoffi(); static bool TestPreciseBug(); @@ -238,6 +242,7 @@ private: bool can_report_memory{}; bool strict_context_required{}; bool supports_conditional_barriers{}; + bool has_lmem_perf_bug{}; std::string vendor_name; }; 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 fc711c44a..edf527f2d 100644 --- a/src/video_core/renderer_opengl/gl_rasterizer.cpp +++ b/src/video_core/renderer_opengl/gl_rasterizer.cpp @@ -222,6 +222,9 @@ void RasterizerOpenGL::PrepareDraw(bool is_indexed, Func&& draw_func) { gpu.TickWork(); std::scoped_lock lock{buffer_cache.mutex, texture_cache.mutex}; + if (pipeline->UsesLocalMemory()) { + program_manager.LocalMemoryWarmup(); + } pipeline->SetEngine(maxwell3d, gpu_memory); pipeline->Configure(is_indexed); @@ -371,6 +374,9 @@ void RasterizerOpenGL::DispatchCompute() { if (!pipeline) { return; } + if (pipeline->UsesLocalMemory()) { + program_manager.LocalMemoryWarmup(); + } pipeline->SetEngine(kepler_compute, gpu_memory); pipeline->Configure(); const auto& qmd{kepler_compute->launch_description}; diff --git a/src/video_core/renderer_opengl/gl_shader_cache.cpp b/src/video_core/renderer_opengl/gl_shader_cache.cpp index 3f077311e..0329ed820 100644 --- a/src/video_core/renderer_opengl/gl_shader_cache.cpp +++ b/src/video_core/renderer_opengl/gl_shader_cache.cpp @@ -85,7 +85,9 @@ Shader::RuntimeInfo MakeRuntimeInfo(const GraphicsPipelineKey& key, case Shader::Stage::VertexB: case Shader::Stage::Geometry: if (!use_assembly_shaders && key.xfb_enabled != 0) { - info.xfb_varyings = VideoCommon::MakeTransformFeedbackVaryings(key.xfb_state); + auto [varyings, count] = VideoCommon::MakeTransformFeedbackVaryings(key.xfb_state); + info.xfb_varyings = varyings; + info.xfb_count = count; } break; case Shader::Stage::TessellationEval: diff --git a/src/video_core/renderer_opengl/gl_shader_manager.cpp b/src/video_core/renderer_opengl/gl_shader_manager.cpp index 98841ae65..03d4b9d06 100644 --- a/src/video_core/renderer_opengl/gl_shader_manager.cpp +++ b/src/video_core/renderer_opengl/gl_shader_manager.cpp @@ -3,7 +3,9 @@ #include <glad/glad.h> +#include "video_core/host_shaders/opengl_lmem_warmup_comp.h" #include "video_core/renderer_opengl/gl_shader_manager.h" +#include "video_core/renderer_opengl/gl_shader_util.h" namespace OpenGL { @@ -17,6 +19,10 @@ ProgramManager::ProgramManager(const Device& device) { if (device.UseAssemblyShaders()) { glEnable(GL_COMPUTE_PROGRAM_NV); } + if (device.HasLmemPerfBug()) { + lmem_warmup_program = + CreateProgram(HostShaders::OPENGL_LMEM_WARMUP_COMP, GL_COMPUTE_SHADER); + } } void ProgramManager::BindComputeProgram(GLuint program) { @@ -98,6 +104,13 @@ void ProgramManager::BindAssemblyPrograms(std::span<const OGLAssemblyProgram, NU void ProgramManager::RestoreGuestCompute() {} +void ProgramManager::LocalMemoryWarmup() { + if (lmem_warmup_program.handle != 0) { + BindComputeProgram(lmem_warmup_program.handle); + glDispatchCompute(1, 1, 1); + } +} + void ProgramManager::BindPipeline() { if (!is_pipeline_bound) { is_pipeline_bound = true; diff --git a/src/video_core/renderer_opengl/gl_shader_manager.h b/src/video_core/renderer_opengl/gl_shader_manager.h index 07ffab77f..852d8c88e 100644 --- a/src/video_core/renderer_opengl/gl_shader_manager.h +++ b/src/video_core/renderer_opengl/gl_shader_manager.h @@ -30,6 +30,8 @@ public: void RestoreGuestCompute(); + void LocalMemoryWarmup(); + private: void BindPipeline(); @@ -44,6 +46,7 @@ private: u32 current_stage_mask = 0; std::array<GLuint, NUM_STAGES> current_programs{}; GLuint current_assembly_compute_program = 0; + OGLProgram lmem_warmup_program; }; } // namespace OpenGL |