82c2601555
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.
70 lines
2.2 KiB
C++
70 lines
2.2 KiB
C++
// Copyright 2018 yuzu Emulator Project
|
|
// Licensed under GPLv2 or any later version
|
|
// Refer to the license.txt file included.
|
|
|
|
#pragma once
|
|
|
|
#include <array>
|
|
#include <string>
|
|
#include <string_view>
|
|
#include <utility>
|
|
#include <vector>
|
|
#include "common/common_types.h"
|
|
#include "video_core/engines/maxwell_3d.h"
|
|
#include "video_core/engines/shader_type.h"
|
|
#include "video_core/shader/registry.h"
|
|
#include "video_core/shader/shader_ir.h"
|
|
|
|
namespace OpenGL {
|
|
|
|
class Device;
|
|
|
|
using Maxwell = Tegra::Engines::Maxwell3D::Regs;
|
|
using SamplerEntry = VideoCommon::Shader::SamplerEntry;
|
|
using ImageEntry = VideoCommon::Shader::ImageEntry;
|
|
|
|
class ConstBufferEntry : public VideoCommon::Shader::ConstBuffer {
|
|
public:
|
|
explicit ConstBufferEntry(u32 max_offset_, bool is_indirect_, u32 index_)
|
|
: ConstBuffer{max_offset_, is_indirect_}, index{index_} {}
|
|
|
|
u32 GetIndex() const {
|
|
return index;
|
|
}
|
|
|
|
private:
|
|
u32 index = 0;
|
|
};
|
|
|
|
struct GlobalMemoryEntry {
|
|
constexpr explicit GlobalMemoryEntry(u32 cbuf_index_, u32 cbuf_offset_, bool is_read_,
|
|
bool is_written_)
|
|
: cbuf_index{cbuf_index_}, cbuf_offset{cbuf_offset_}, is_read{is_read_}, is_written{
|
|
is_written_} {}
|
|
|
|
u32 cbuf_index = 0;
|
|
u32 cbuf_offset = 0;
|
|
bool is_read = false;
|
|
bool is_written = false;
|
|
};
|
|
|
|
struct ShaderEntries {
|
|
std::vector<ConstBufferEntry> const_buffers;
|
|
std::vector<GlobalMemoryEntry> global_memory_entries;
|
|
std::vector<SamplerEntry> samplers;
|
|
std::vector<ImageEntry> images;
|
|
std::size_t shader_length{};
|
|
u32 clip_distances{};
|
|
u32 enabled_uniform_buffers{};
|
|
};
|
|
|
|
ShaderEntries MakeEntries(const Device& device, const VideoCommon::Shader::ShaderIR& ir,
|
|
Tegra::Engines::ShaderType stage);
|
|
|
|
std::string DecompileShader(const Device& device, const VideoCommon::Shader::ShaderIR& ir,
|
|
const VideoCommon::Shader::Registry& registry,
|
|
Tegra::Engines::ShaderType stage, std::string_view identifier,
|
|
std::string_view suffix = {});
|
|
|
|
} // namespace OpenGL
|