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.
115 lines
3.7 KiB
C++
115 lines
3.7 KiB
C++
// Copyright 2019 yuzu Emulator Project
|
|
// Licensed under GPLv2 or any later version
|
|
// Refer to the license.txt file included.
|
|
|
|
#pragma once
|
|
|
|
#include "video_core/buffer_cache/buffer_cache.h"
|
|
#include "video_core/engines/maxwell_3d.h"
|
|
#include "video_core/renderer_vulkan/vk_compute_pass.h"
|
|
#include "video_core/renderer_vulkan/vk_staging_buffer_pool.h"
|
|
#include "video_core/vulkan_common/vulkan_memory_allocator.h"
|
|
#include "video_core/vulkan_common/vulkan_wrapper.h"
|
|
|
|
namespace Vulkan {
|
|
|
|
class Device;
|
|
class VKDescriptorPool;
|
|
class VKScheduler;
|
|
class VKUpdateDescriptorQueue;
|
|
|
|
class BufferCacheRuntime;
|
|
|
|
class Buffer : public VideoCommon::BufferBase<VideoCore::RasterizerInterface> {
|
|
public:
|
|
explicit Buffer(BufferCacheRuntime&, VideoCommon::NullBufferParams null_params);
|
|
explicit Buffer(BufferCacheRuntime& runtime, VideoCore::RasterizerInterface& rasterizer_,
|
|
VAddr cpu_addr_, u64 size_bytes_);
|
|
|
|
[[nodiscard]] VkBuffer Handle() const noexcept {
|
|
return *buffer;
|
|
}
|
|
|
|
operator VkBuffer() const noexcept {
|
|
return *buffer;
|
|
}
|
|
|
|
private:
|
|
vk::Buffer buffer;
|
|
MemoryCommit commit;
|
|
};
|
|
|
|
class BufferCacheRuntime {
|
|
friend Buffer;
|
|
|
|
using PrimitiveTopology = Tegra::Engines::Maxwell3D::Regs::PrimitiveTopology;
|
|
using IndexFormat = Tegra::Engines::Maxwell3D::Regs::IndexFormat;
|
|
|
|
public:
|
|
explicit BufferCacheRuntime(const Device& device_, MemoryAllocator& memory_manager_,
|
|
VKScheduler& scheduler_, StagingBufferPool& staging_pool_,
|
|
VKUpdateDescriptorQueue& update_descriptor_queue_,
|
|
VKDescriptorPool& descriptor_pool);
|
|
|
|
void Finish();
|
|
|
|
[[nodiscard]] StagingBufferRef UploadStagingBuffer(size_t size);
|
|
|
|
[[nodiscard]] StagingBufferRef DownloadStagingBuffer(size_t size);
|
|
|
|
void CopyBuffer(VkBuffer src_buffer, VkBuffer dst_buffer,
|
|
std::span<const VideoCommon::BufferCopy> copies);
|
|
|
|
void BindIndexBuffer(PrimitiveTopology topology, IndexFormat index_format, u32 num_indices,
|
|
u32 base_vertex, VkBuffer buffer, u32 offset, u32 size);
|
|
|
|
void BindQuadArrayIndexBuffer(u32 first, u32 count);
|
|
|
|
void BindVertexBuffer(u32 index, VkBuffer buffer, u32 offset, u32 size, u32 stride);
|
|
|
|
void BindTransformFeedbackBuffer(u32 index, VkBuffer buffer, u32 offset, u32 size);
|
|
|
|
void BindUniformBuffer(VkBuffer buffer, u32 offset, u32 size) {
|
|
BindBuffer(buffer, offset, size);
|
|
}
|
|
|
|
void BindStorageBuffer(VkBuffer buffer, u32 offset, u32 size,
|
|
[[maybe_unused]] bool is_written) {
|
|
BindBuffer(buffer, offset, size);
|
|
}
|
|
|
|
private:
|
|
void BindBuffer(VkBuffer buffer, u32 offset, u32 size);
|
|
|
|
void ReserveQuadArrayLUT(u32 num_indices, bool wait_for_idle);
|
|
|
|
const Device& device;
|
|
MemoryAllocator& memory_allocator;
|
|
VKScheduler& scheduler;
|
|
StagingBufferPool& staging_pool;
|
|
VKUpdateDescriptorQueue& update_descriptor_queue;
|
|
|
|
vk::Buffer quad_array_lut;
|
|
MemoryCommit quad_array_lut_commit;
|
|
VkIndexType quad_array_lut_index_type{};
|
|
u32 current_num_indices = 0;
|
|
|
|
Uint8Pass uint8_pass;
|
|
QuadIndexedPass quad_index_pass;
|
|
};
|
|
|
|
struct BufferCacheParams {
|
|
using Runtime = Vulkan::BufferCacheRuntime;
|
|
using Buffer = Vulkan::Buffer;
|
|
|
|
static constexpr bool IS_OPENGL = false;
|
|
static constexpr bool HAS_PERSISTENT_UNIFORM_BUFFER_BINDINGS = false;
|
|
static constexpr bool HAS_FULL_INDEX_AND_PRIMITIVE_SUPPORT = false;
|
|
static constexpr bool NEEDS_BIND_UNIFORM_INDEX = false;
|
|
static constexpr bool NEEDS_BIND_STORAGE_INDEX = false;
|
|
static constexpr bool USE_MEMORY_MAPS = true;
|
|
};
|
|
|
|
using BufferCache = VideoCommon::BufferCache<BufferCacheParams>;
|
|
|
|
} // namespace Vulkan
|