fabi/Xenia-Canary
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #61 from chrisps/canary_experimental

Browse Source 
performance improvements, kernel fixes, cpu accuracy improvements
This commit is contained in:
Radosław Gliński
2022-08-21 09:31:09 +02:00
committed by GitHub
parent 010b59e81c d85bfc1894
commit 0b013fdc6b
70 changed files with 1744 additions and 541 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/xenia/gpu/vulkan/vulkan_command_processor.cc
View File

@@ -1157,7 +1157,14 @@ void VulkanCommandProcessor::WriteRegister(uint32_t index, uint32_t value) {
}
}
}
void VulkanCommandProcessor::WriteRegistersFromMem(uint32_t start_index,
uint32_t* base,
uint32_t num_registers) {
for (uint32_t i = 0; i < num_registers; ++i) {
uint32_t data = xe::load_and_swap<uint32_t>(base + i);
VulkanCommandProcessor::WriteRegister(start_index + i, data);
}
}
void VulkanCommandProcessor::SparseBindBuffer(
VkBuffer buffer, uint32_t bind_count, const VkSparseMemoryBind* binds,
VkPipelineStageFlags wait_stage_mask) {

7
src/xenia/gpu/vulkan/vulkan_command_processor.h
View File

@@ -45,7 +45,7 @@ namespace xe {
namespace gpu {
namespace vulkan {
class VulkanCommandProcessor : public CommandProcessor {
class VulkanCommandProcessor final : public CommandProcessor {
public:
// Single-descriptor layouts for use within a single frame.
enum class SingleTransientDescriptorLayout {
@@ -259,8 +259,11 @@ class VulkanCommandProcessor : public CommandProcessor {
protected:
bool SetupContext() override;
void ShutdownContext() override;
XE_FORCEINLINE
void WriteRegister(uint32_t index, uint32_t value) override;
XE_FORCEINLINE
virtual void WriteRegistersFromMem(uint32_t start_index, uint32_t* base,
uint32_t num_registers) override;
void OnGammaRamp256EntryTableValueWritten() override;
void OnGammaRampPWLValueWritten() override;

25
src/xenia/gpu/vulkan/vulkan_shared_memory.cc
View File

@@ -376,18 +376,21 @@ bool VulkanSharedMemory::AllocateSparseHostGpuMemoryRange(
}
bool VulkanSharedMemory::UploadRanges(
const std::vector<std::pair<uint32_t, uint32_t>>& upload_page_ranges) {
if (upload_page_ranges.empty()) {
const std::pair<uint32_t, uint32_t>* upload_page_ranges,
unsigned num_upload_ranges) {
if (!num_upload_ranges) {
return true;
}
auto& range_front = upload_page_ranges[0];
auto& range_back = upload_page_ranges[num_upload_ranges - 1];
// upload_page_ranges are sorted, use them to determine the range for the
// ordering barrier.
Use(Usage::kTransferDestination,
std::make_pair(
upload_page_ranges.front().first << page_size_log2(),
(upload_page_ranges.back().first + upload_page_ranges.back().second -
upload_page_ranges.front().first)
<< page_size_log2()));
std::make_pair(range_front.first << page_size_log2(),
(range_back.first + range_back.second - range_front.first)
<< page_size_log2()));
command_processor_.SubmitBarriers(true);
DeferredCommandBuffer& command_buffer =
command_processor_.deferred_command_buffer();
@@ -395,9 +398,11 @@ bool VulkanSharedMemory::UploadRanges(
bool successful = true;
upload_regions_.clear();
VkBuffer upload_buffer_previous = VK_NULL_HANDLE;
for (auto upload_range : upload_page_ranges) {
uint32_t upload_range_start = upload_range.first;
uint32_t upload_range_length = upload_range.second;
// for (auto upload_range : upload_page_ranges) {
for (unsigned int i = 0; i < num_upload_ranges; ++i) {
uint32_t upload_range_start = upload_page_ranges[i].first;
uint32_t upload_range_length = upload_page_ranges[i].second;
trace_writer_.WriteMemoryRead(upload_range_start << page_size_log2(),
upload_range_length << page_size_log2());
while (upload_range_length) {

4
src/xenia/gpu/vulkan/vulkan_shared_memory.h
View File

@@ -62,8 +62,8 @@ class VulkanSharedMemory : public SharedMemory {
bool AllocateSparseHostGpuMemoryRange(uint32_t offset_allocations,
uint32_t length_allocations) override;
bool UploadRanges(const std::vector<std::pair<uint32_t, uint32_t>>&
upload_page_ranges) override;
bool UploadRanges(const std::pair<uint32_t, uint32_t>*
upload_page_ranges, unsigned num_ranges) override;
private:
void GetUsageMasks(Usage usage, VkPipelineStageFlags& stage_mask,