From 82c2601555b59a94d7160f2fd686cb63d32dd423 Mon Sep 17 00:00:00 2001 From: ReinUsesLisp 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/shader/async_shaders.h | 9 --------- src/video_core/shader/decode/other.cpp | 1 + src/video_core/shader/shader_ir.h | 5 +++++ 3 files changed, 6 insertions(+), 9 deletions(-) (limited to 'src/video_core/shader') diff --git a/src/video_core/shader/async_shaders.h b/src/video_core/shader/async_shaders.h index 0dbb1a31f..7fdff6e56 100644 --- a/src/video_core/shader/async_shaders.h +++ b/src/video_core/shader/async_shaders.h @@ -9,16 +9,7 @@ #include #include -// This header includes both Vulkan and OpenGL headers, this has to be fixed -// Unfortunately, including OpenGL will include Windows.h that defines macros that can cause issues. -// Forcefully include glad early and undefine macros #include -#ifdef CreateEvent -#undef CreateEvent -#endif -#ifdef CreateSemaphore -#undef CreateSemaphore -#endif #include "common/common_types.h" #include "video_core/renderer_opengl/gl_device.h" diff --git a/src/video_core/shader/decode/other.cpp b/src/video_core/shader/decode/other.cpp index d3ea07aac..5f88537bc 100644 --- a/src/video_core/shader/decode/other.cpp +++ b/src/video_core/shader/decode/other.cpp @@ -76,6 +76,7 @@ u32 ShaderIR::DecodeOther(NodeBlock& bb, u32 pc) { case SystemVariable::InvocationId: return Operation(OperationCode::InvocationId); case SystemVariable::Ydirection: + uses_y_negate = true; return Operation(OperationCode::YNegate); case SystemVariable::InvocationInfo: LOG_WARNING(HW_GPU, "S2R instruction with InvocationInfo is incomplete"); diff --git a/src/video_core/shader/shader_ir.h b/src/video_core/shader/shader_ir.h index 0c6ab0f07..1cd7c14d7 100644 --- a/src/video_core/shader/shader_ir.h +++ b/src/video_core/shader/shader_ir.h @@ -139,6 +139,10 @@ public: return uses_legacy_varyings; } + bool UsesYNegate() const { + return uses_y_negate; + } + bool UsesWarps() const { return uses_warps; } @@ -465,6 +469,7 @@ private: bool uses_instance_id{}; bool uses_vertex_id{}; bool uses_legacy_varyings{}; + bool uses_y_negate{}; bool uses_warps{}; bool uses_indexed_samplers{}; -- cgit v1.2.3