ShuriZma
/
xenia
mirror of https://github.com/xenia-project/xenia.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[D3D12] Remove SRV[unbounded] and UAV overlap in bindless root sig

This commit is contained in:
Triang3l 2020-10-18 22:09:08 +03:00
parent fd18a97f3a
commit 9081046e7b
2 changed files with 71 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

94
src/xenia/gpu/d3d12/d3d12_command_processor.cc
View File

@ -950,6 +950,10 @@ bool D3D12CommandProcessor::SetupContext() {
if (bindless_resources_used_) {
// Global bindless resource root signatures.
// No CBV or UAV descriptor ranges with any descriptors to be allocated
// dynamically (via RequestPersistentViewBindlessDescriptor or
// RequestOneUseSingleViewDescriptors) should be here, because they would
// overlap the unbounded SRV range, which is not allowed on Nvidia Fermi!
D3D12_ROOT_SIGNATURE_DESC root_signature_bindless_desc;
D3D12_ROOT_PARAMETER
root_parameters_bindless[kRootParameter_Bindless_Count];
@ -1056,45 +1060,6 @@ bool D3D12CommandProcessor::SetupContext() {
parameter.DescriptorTable.NumDescriptorRanges = 0;
parameter.DescriptorTable.pDescriptorRanges = root_bindless_view_ranges;
parameter.ShaderVisibility = D3D12_SHADER_VISIBILITY_ALL;
// 2D array textures.
{
assert_true(parameter.DescriptorTable.NumDescriptorRanges <
xe::countof(root_bindless_view_ranges));
auto& range = root_bindless_view_ranges[parameter.DescriptorTable
.NumDescriptorRanges++];
range.RangeType = D3D12_DESCRIPTOR_RANGE_TYPE_SRV;
range.NumDescriptors = UINT_MAX;
range.BaseShaderRegister = 0;
range.RegisterSpace =
UINT(DxbcShaderTranslator::SRVSpace::kBindlessTextures2DArray);
range.OffsetInDescriptorsFromTableStart = 0;
}
// 3D textures.
{
assert_true(parameter.DescriptorTable.NumDescriptorRanges <
xe::countof(root_bindless_view_ranges));
auto& range = root_bindless_view_ranges[parameter.DescriptorTable
.NumDescriptorRanges++];
range.RangeType = D3D12_DESCRIPTOR_RANGE_TYPE_SRV;
range.NumDescriptors = UINT_MAX;
range.BaseShaderRegister = 0;
range.RegisterSpace =
UINT(DxbcShaderTranslator::SRVSpace::kBindlessTextures3D);
range.OffsetInDescriptorsFromTableStart = 0;
}
// Cube textures.
{
assert_true(parameter.DescriptorTable.NumDescriptorRanges <
xe::countof(root_bindless_view_ranges));
auto& range = root_bindless_view_ranges[parameter.DescriptorTable
.NumDescriptorRanges++];
range.RangeType = D3D12_DESCRIPTOR_RANGE_TYPE_SRV;
range.NumDescriptors = UINT_MAX;
range.BaseShaderRegister = 0;
range.RegisterSpace =
UINT(DxbcShaderTranslator::SRVSpace::kBindlessTexturesCube);
range.OffsetInDescriptorsFromTableStart = 0;
}
// Shared memory SRV.
{
assert_true(parameter.DescriptorTable.NumDescriptorRanges <
@ -1137,6 +1102,51 @@ bool D3D12CommandProcessor::SetupContext() {
range.OffsetInDescriptorsFromTableStart =
UINT(SystemBindlessView::kEdramR32UintUAV);
}
// Used UAV and SRV ranges must not overlap on Nvidia Fermi, so textures
// have OffsetInDescriptorsFromTableStart after all static descriptors of
// other types.
// 2D array textures.
{
assert_true(parameter.DescriptorTable.NumDescriptorRanges <
xe::countof(root_bindless_view_ranges));
auto& range = root_bindless_view_ranges[parameter.DescriptorTable
.NumDescriptorRanges++];
range.RangeType = D3D12_DESCRIPTOR_RANGE_TYPE_SRV;
range.NumDescriptors = UINT_MAX;
range.BaseShaderRegister = 0;
range.RegisterSpace =
UINT(DxbcShaderTranslator::SRVSpace::kBindlessTextures2DArray);
range.OffsetInDescriptorsFromTableStart =
UINT(SystemBindlessView::kUnboundedSRVsStart);
}
// 3D textures.
{
assert_true(parameter.DescriptorTable.NumDescriptorRanges <
xe::countof(root_bindless_view_ranges));
auto& range = root_bindless_view_ranges[parameter.DescriptorTable
.NumDescriptorRanges++];
range.RangeType = D3D12_DESCRIPTOR_RANGE_TYPE_SRV;
range.NumDescriptors = UINT_MAX;
range.BaseShaderRegister = 0;
range.RegisterSpace =
UINT(DxbcShaderTranslator::SRVSpace::kBindlessTextures3D);
range.OffsetInDescriptorsFromTableStart =
UINT(SystemBindlessView::kUnboundedSRVsStart);
}
// Cube textures.
{
assert_true(parameter.DescriptorTable.NumDescriptorRanges <
xe::countof(root_bindless_view_ranges));
auto& range = root_bindless_view_ranges[parameter.DescriptorTable
.NumDescriptorRanges++];
range.RangeType = D3D12_DESCRIPTOR_RANGE_TYPE_SRV;
range.NumDescriptors = UINT_MAX;
range.BaseShaderRegister = 0;
range.RegisterSpace =
UINT(DxbcShaderTranslator::SRVSpace::kBindlessTexturesCube);
range.OffsetInDescriptorsFromTableStart =
UINT(SystemBindlessView::kUnboundedSRVsStart);
}
}
root_signature_bindless_vs_ = ui::d3d12::util::CreateRootSignature(
provider, root_signature_bindless_desc);
@ -3938,7 +3948,8 @@ bool D3D12CommandProcessor::UpdateBindings(
for (uint32_t i = 0; i < texture_count_vertex; ++i) {
const D3D12Shader::TextureBinding& texture = textures_vertex[i];
descriptor_indices[texture.bindless_descriptor_index] =
texture_cache_->GetActiveTextureBindlessSRVIndex(texture);
texture_cache_->GetActiveTextureBindlessSRVIndex(texture) -
uint32_t(SystemBindlessView::kUnboundedSRVsStart);
}
current_texture_layout_uid_vertex_ = texture_layout_uid_vertex;
if (texture_count_vertex) {
@ -3973,7 +3984,8 @@ bool D3D12CommandProcessor::UpdateBindings(
for (uint32_t i = 0; i < texture_count_pixel; ++i) {
const D3D12Shader::TextureBinding& texture = textures_pixel[i];
descriptor_indices[texture.bindless_descriptor_index] =
texture_cache_->GetActiveTextureBindlessSRVIndex(texture);
texture_cache_->GetActiveTextureBindlessSRVIndex(texture) -
uint32_t(SystemBindlessView::kUnboundedSRVsStart);
}
current_texture_layout_uid_pixel_ = texture_layout_uid_pixel;
if (texture_count_pixel) {

25
src/xenia/gpu/d3d12/d3d12_command_processor.h
View File

@ -114,20 +114,23 @@ class D3D12CommandProcessor : public CommandProcessor {
assert_true(bindless_resources_used_);
return view_bindless_heap_gpu_start_;
}
// Returns UINT32_MAX if no free descriptors.
// Returns UINT32_MAX if no free descriptors. If the unbounded SRV range for
// bindless resources is also used in the root signature of the draw /
// dispatch referencing this descriptor, this must only be used to allocate
// SRVs, otherwise it won't work on Nvidia Fermi (root signature creation will
// fail)!
uint32_t RequestPersistentViewBindlessDescriptor();
void ReleaseViewBindlessDescriptorImmediately(uint32_t descriptor_index);
// Request non-contiguous SRV/UAV descriptors for use only within the next
// Request non-contiguous CBV/SRV/UAV descriptors for use only within the next
// draw or dispatch command done for internal purposes. May change the current
// descriptor heap.
// descriptor heap. If the unbounded SRV range for bindless resources is also
// used in the root signature of the draw / dispatch referencing these
// descriptors, this must only be used to allocate SRVs, otherwise it won't
// work on Nvidia Fermi (root signature creation will fail)!
bool RequestOneUseSingleViewDescriptors(
uint32_t count, ui::d3d12::util::DescriptorCPUGPUHandlePair* handles_out);
// These are needed often, so they are always allocated.
enum class SystemBindlessView : uint32_t {
kNullTexture2DArray,
kNullTexture3D,
kNullTextureCube,
kSharedMemoryRawSRV,
kSharedMemoryR32UintSRV,
kSharedMemoryR32G32UintSRV,
@ -148,6 +151,14 @@ class D3D12CommandProcessor : public CommandProcessor {
kGammaRampNormalSRV,
kGammaRampPWLSRV,
// Beyond this point, SRVs are accessible to shaders through an unbounded
// range - no descriptors of other types bound to shaders alongside
// unbounded ranges - must be located beyond this point.
kUnboundedSRVsStart,
kNullTexture2DArray = kUnboundedSRVsStart,
kNullTexture3D,
kNullTextureCube,
kCount,
};
ui::d3d12::util::DescriptorCPUGPUHandlePair GetSystemBindlessViewHandlePair(