void Model::CreatePipelineState()
{
Microsoft::WRL::ComPtr<ID3DBlob> VertexShader;
Microsoft::WRL::ComPtr<ID3DBlob> PixelShader;
LoadAndCompileShader(VertexShader, PixelShader);
std::array<D3D12_INPUT_ELEMENT_DESC, 2> InputElementDesc
{ {
{ "POSITION", 0, DXGI_FORMAT_R32G32B32_FLOAT, 0, 0, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
{ "COLOR", 0, DXGI_FORMAT_R32G32B32A32_FLOAT, 0, 12, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 }
} };
D3D12_GRAPHICS_PIPELINE_STATE_DESC PipelineStateDesc = {};
PipelineStateDesc.InputLayout = { InputElementDesc.data(), static_cast<UINT>(InputElementDesc.size()) };
PipelineStateDesc.pRootSignature = RootSignature.Get();
PipelineStateDesc.VS = CD3DX12_SHADER_BYTECODE(VertexShader.Get());
PipelineStateDesc.PS = CD3DX12_SHADER_BYTECODE(PixelShader.Get());
PipelineStateDesc.RasterizerState = CD3DX12_RASTERIZER_DESC(D3D12_DEFAULT);
PipelineStateDesc.BlendState = CD3DX12_BLEND_DESC(D3D12_DEFAULT);
PipelineStateDesc.DepthStencilState = CD3DX12_DEPTH_STENCIL_DESC(D3D12_DEFAULT);
PipelineStateDesc.SampleMask = UINT_MAX;
PipelineStateDesc.SampleDesc.Count = 1;
PipelineStateDesc.NumRenderTargets = 1;
PipelineStateDesc.RTVFormats[0] = DXGI_FORMAT_R8G8B8A8_UNORM;
PipelineStateDesc.DSVFormat = DXGI_FORMAT_D32_FLOAT;
PipelineStateDesc.PrimitiveTopologyType = D3D12_PRIMITIVE_TOPOLOGY_TYPE_TRIANGLE;
Utility::ThrowOnFail(DeviceContext.GetDevice()->CreateGraphicsPipelineState(&PipelineStateDesc, IID_PPV_ARGS(&PipelineState)));
}
void WorldObjectEffect::createRootSigAndPSO(ComPtr<ID3D12RootSignature> &sig, ComPtr<ID3D12PipelineState> &pso)
{
// Define the vertex input layout.
D3D12_INPUT_ELEMENT_DESC inputElementDescs[] =
{
{ "POSITION", 0, DXGI_FORMAT_R32G32B32_FLOAT, 0, D3D12_APPEND_ALIGNED_ELEMENT, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
{ "NORMAL", 0, DXGI_FORMAT_R32G32B32_FLOAT, 0, D3D12_APPEND_ALIGNED_ELEMENT, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
{ "TEXCOORD", 0, DXGI_FORMAT_R32G32_FLOAT, 0, D3D12_APPEND_ALIGNED_ELEMENT, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 }
//{ "POSITION", 0, DXGI_FORMAT_R32G32B32A32_FLOAT, 0, D3D12_APPEND_ALIGNED_ELEMENT, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
//{ "NORMAL", 0, DXGI_FORMAT_R32G32B32A32_FLOAT, 0, D3D12_APPEND_ALIGNED_ELEMENT, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
//{ "TEXCOORD", 0, DXGI_FORMAT_R32G32_FLOAT, 0, D3D12_APPEND_ALIGNED_ELEMENT, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 }
};
// Describe and create the graphics pipeline state object (PSO).
CD3DX12_BLEND_DESC blendDesc(D3D12_DEFAULT);
blendDesc.RenderTarget[0].BlendEnable = TRUE;
blendDesc.RenderTarget[0].SrcBlend = D3D12_BLEND_SRC_ALPHA;
blendDesc.RenderTarget[0].DestBlend = D3D12_BLEND_INV_SRC_ALPHA;//D3D12_BLEND_ONE;
blendDesc.RenderTarget[0].SrcBlendAlpha = D3D12_BLEND_ZERO;
blendDesc.RenderTarget[0].DestBlendAlpha = D3D12_BLEND_ZERO;
D3D12_GRAPHICS_PIPELINE_STATE_DESC psoDesc = {};
psoDesc.InputLayout = { inputElementDescs, _countof(inputElementDescs) };
psoDesc.RasterizerState = CD3DX12_RASTERIZER_DESC(D3D12_DEFAULT);
psoDesc.BlendState = blendDesc;
psoDesc.DepthStencilState = CD3DX12_DEPTH_STENCIL_DESC(D3D12_DEFAULT);
psoDesc.SampleMask = UINT_MAX;
psoDesc.PrimitiveTopologyType = D3D12_PRIMITIVE_TOPOLOGY_TYPE_TRIANGLE;
psoDesc.NumRenderTargets = 1;
psoDesc.RTVFormats[0] = DXGI_FORMAT_R8G8B8A8_UNORM;
psoDesc.DSVFormat = DXGI_FORMAT_D32_FLOAT;
psoDesc.SampleDesc.Count = 1;
psoDesc.VS = { binShader_ObjectVS, sizeof(binShader_ObjectVS) };
psoDesc.PS = { binShader_ObjectPS, sizeof(binShader_ObjectPS) };
ThrowIfFailed(xapp().device->CreateRootSignature(0, binShader_ObjectVS, sizeof(binShader_ObjectVS), IID_PPV_ARGS(&sig)));
sig.Get()->SetName(L"Object_root_signature");
psoDesc.pRootSignature = sig.Get();
ThrowIfFailed(xapp().device->CreateGraphicsPipelineState(&psoDesc, IID_PPV_ARGS(&pso)));
pso.Get()->SetName(L"state_objecteffect_init");
}
void SkyDome::OnCreate(ID3D12Device* pDevice, UploadHeapDX12* pUploadHeap, DXGI_FORMAT outFormat, ResourceViewHeapsDX12 *pResourceViewHeaps, StaticBufferPoolDX12 *pStaticBufferPool, DynamicBufferRingDX12 *pDynamicBufferRing, UINT sampleDescCount, void *pluginManager, void *msghandler)
{
m_pDynamicBufferRing = pDynamicBufferRing;
char buff[512];
GetCurrentDirectoryA(512, buff);
if (m_CubeDiffuseTexture.InitFromFile(pDevice, pUploadHeap, L"./plugins/media/envmap/diffuse.dds", pluginManager, msghandler) != 0)
return;
if (m_CubeSpecularTexture.InitFromFile(pDevice, pUploadHeap, L"./plugins/media/envmap/specular.dds", pluginManager, msghandler) != 0)
return;
pResourceViewHeaps->AllocCBV_SRV_UAVDescriptor(1, &m_CubeSpecularTextureSRV);
m_CubeSpecularTexture.CreateCubeSRV(0, &m_CubeSpecularTextureSRV);
D3D12_DEPTH_STENCIL_DESC DepthStencilDesc = CD3DX12_DEPTH_STENCIL_DESC(D3D12_DEFAULT);
DepthStencilDesc.DepthFunc = D3D12_COMPARISON_FUNC_LESS_EQUAL;
m_skydome.OnCreate(pDevice, pUploadHeap->GetNode(), "./plugins/shaders/", "SkyDome.hlsl", outFormat, pResourceViewHeaps, pStaticBufferPool, 1, NULL, NULL, sampleDescCount);
m_initok = true;
}
// Load the sample assets.
void D3D12HeterogeneousMultiadapter::LoadAssets()
{
// Create the root signatures.
{
CD3DX12_ROOT_PARAMETER rootParameters[2];
rootParameters[0].InitAsConstantBufferView(0, 0, D3D12_SHADER_VISIBILITY_VERTEX);
rootParameters[1].InitAsConstantBufferView(1, 0, D3D12_SHADER_VISIBILITY_PIXEL);
CD3DX12_ROOT_SIGNATURE_DESC rootSignatureDesc;
rootSignatureDesc.Init(_countof(rootParameters), rootParameters, 0, nullptr, D3D12_ROOT_SIGNATURE_FLAG_ALLOW_INPUT_ASSEMBLER_INPUT_LAYOUT);
ComPtr<ID3DBlob> signature;
ComPtr<ID3DBlob> error;
ThrowIfFailed(D3D12SerializeRootSignature(&rootSignatureDesc, D3D_ROOT_SIGNATURE_VERSION_1, &signature, &error));
ThrowIfFailed(m_devices[Primary]->CreateRootSignature(0, signature->GetBufferPointer(), signature->GetBufferSize(), IID_PPV_ARGS(&m_rootSignature)));
CD3DX12_DESCRIPTOR_RANGE ranges[1];
ranges[0].Init(D3D12_DESCRIPTOR_RANGE_TYPE_SRV, 1, 0);
CD3DX12_ROOT_PARAMETER blurRootParameters[3];
blurRootParameters[0].InitAsConstantBufferView(0, 0, D3D12_SHADER_VISIBILITY_PIXEL);
blurRootParameters[1].InitAsDescriptorTable(_countof(ranges), ranges, D3D12_SHADER_VISIBILITY_PIXEL);
blurRootParameters[2].InitAsConstantBufferView(1, 0, D3D12_SHADER_VISIBILITY_PIXEL);
CD3DX12_STATIC_SAMPLER_DESC staticPointSampler(0);
staticPointSampler.Filter = D3D12_FILTER_MIN_MAG_MIP_POINT;
staticPointSampler.ShaderVisibility = D3D12_SHADER_VISIBILITY_PIXEL;
CD3DX12_STATIC_SAMPLER_DESC staticLinearSampler(1);
staticLinearSampler.Filter = D3D12_FILTER_MIN_MAG_MIP_LINEAR;
staticLinearSampler.ShaderVisibility = D3D12_SHADER_VISIBILITY_PIXEL;
D3D12_STATIC_SAMPLER_DESC staticSamplers[] = { staticPointSampler, staticLinearSampler };
rootSignatureDesc.Init(_countof(blurRootParameters), blurRootParameters, _countof(staticSamplers), staticSamplers, D3D12_ROOT_SIGNATURE_FLAG_ALLOW_INPUT_ASSEMBLER_INPUT_LAYOUT);
ThrowIfFailed(D3D12SerializeRootSignature(&rootSignatureDesc, D3D_ROOT_SIGNATURE_VERSION_1, &signature, &error));
ThrowIfFailed(m_devices[Secondary]->CreateRootSignature(0, signature->GetBufferPointer(), signature->GetBufferSize(), IID_PPV_ARGS(&m_blurRootSignature)));
}
// Create the pipeline states, which includes compiling and loading shaders.
{
ComPtr<ID3DBlob> vertexShader;
ComPtr<ID3DBlob> pixelShader;
ComPtr<ID3DBlob> vertexShaderBlur;
ComPtr<ID3DBlob> pixelShaderBlurU;
ComPtr<ID3DBlob> pixelShaderBlurV;
ComPtr<ID3DBlob> error;
#if defined(_DEBUG)
// Enable better shader debugging with the graphics debugging tools.
UINT compileFlags = D3DCOMPILE_DEBUG | D3DCOMPILE_SKIP_OPTIMIZATION;
#else
UINT compileFlags = 0;
#endif
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"shaders.hlsl").c_str(), nullptr, nullptr, "VShader", "vs_5_0", compileFlags, 0, &vertexShader, &error));
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"shaders.hlsl").c_str(), nullptr, nullptr, "PShader", "ps_5_0", compileFlags, 0, &pixelShader, &error));
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"blurShaders.hlsl").c_str(), nullptr, nullptr, "VSSimpleBlur", "vs_5_0", compileFlags, 0, &vertexShaderBlur, &error));
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"blurShaders.hlsl").c_str(), nullptr, nullptr, "PSSimpleBlurU", "ps_5_0", compileFlags, 0, &pixelShaderBlurU, &error));
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"blurShaders.hlsl").c_str(), nullptr, nullptr, "PSSimpleBlurV", "ps_5_0", compileFlags, 0, &pixelShaderBlurV, &error));
// Define the vertex input layouts.
const D3D12_INPUT_ELEMENT_DESC inputElementDescs[] =
{
{ "POSITION", 0, DXGI_FORMAT_R32G32B32_FLOAT, 0, 0, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
};
const D3D12_INPUT_ELEMENT_DESC blurInputElementDescs[] =
{
{ "POSITION", 0, DXGI_FORMAT_R32G32B32A32_FLOAT, 0, 0, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
{ "TEXCOORD", 0, DXGI_FORMAT_R32G32_FLOAT, 0, D3D12_APPEND_ALIGNED_ELEMENT, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
};
// Describe and create the graphics pipeline state objects (PSOs).
D3D12_GRAPHICS_PIPELINE_STATE_DESC psoDesc = {};
psoDesc.InputLayout = { inputElementDescs, _countof(inputElementDescs) };
psoDesc.pRootSignature = m_rootSignature.Get();
psoDesc.VS = CD3DX12_SHADER_BYTECODE(vertexShader.Get());
psoDesc.PS = CD3DX12_SHADER_BYTECODE(pixelShader.Get());
psoDesc.RasterizerState = CD3DX12_RASTERIZER_DESC(D3D12_DEFAULT);
psoDesc.BlendState = CD3DX12_BLEND_DESC(D3D12_DEFAULT);
psoDesc.DepthStencilState = CD3DX12_DEPTH_STENCIL_DESC(D3D12_DEFAULT);
psoDesc.SampleMask = UINT_MAX;
psoDesc.PrimitiveTopologyType = D3D12_PRIMITIVE_TOPOLOGY_TYPE_TRIANGLE;
psoDesc.NumRenderTargets = 1;
psoDesc.RTVFormats[0] = DXGI_FORMAT_R8G8B8A8_UNORM;
psoDesc.DSVFormat = DXGI_FORMAT_D32_FLOAT;
psoDesc.SampleDesc.Count = 1;
ThrowIfFailed(m_devices[Primary]->CreateGraphicsPipelineState(&psoDesc, IID_PPV_ARGS(&m_pipelineState)));
psoDesc.InputLayout = { blurInputElementDescs, _countof(blurInputElementDescs) };
psoDesc.pRootSignature = m_blurRootSignature.Get();
psoDesc.VS = CD3DX12_SHADER_BYTECODE(vertexShaderBlur.Get());
psoDesc.PS = CD3DX12_SHADER_BYTECODE(pixelShaderBlurU.Get());
psoDesc.DepthStencilState.DepthEnable = false;
psoDesc.DSVFormat = DXGI_FORMAT_UNKNOWN;
ThrowIfFailed(m_devices[Secondary]->CreateGraphicsPipelineState(&psoDesc, IID_PPV_ARGS(&m_blurPipelineStates[0])));
psoDesc.PS = CD3DX12_SHADER_BYTECODE(pixelShaderBlurV.Get());
ThrowIfFailed(m_devices[Secondary]->CreateGraphicsPipelineState(&psoDesc, IID_PPV_ARGS(&m_blurPipelineStates[1])));
}
// Create the command lists.
ThrowIfFailed(m_devices[Primary]->CreateCommandList(0, D3D12_COMMAND_LIST_TYPE_DIRECT, m_directCommandAllocators[Primary][m_frameIndex].Get(), m_pipelineState.Get(), IID_PPV_ARGS(&m_directCommandLists[Primary])));
ThrowIfFailed(m_devices[Primary]->CreateCommandList(0, D3D12_COMMAND_LIST_TYPE_COPY, m_copyCommandAllocators[m_frameIndex].Get(), m_pipelineState.Get(), IID_PPV_ARGS(&m_copyCommandList)));
ThrowIfFailed(m_copyCommandList->Close());
ThrowIfFailed(m_devices[Secondary]->CreateCommandList(0, D3D12_COMMAND_LIST_TYPE_DIRECT, m_directCommandAllocators[Secondary][m_frameIndex].Get(), m_blurPipelineStates[0].Get(), IID_PPV_ARGS(&m_directCommandLists[Secondary])));
// Note: ComPtr's are CPU objects but these resources need to stay in scope until
// the command list that references them has finished executing on the GPU.
// We will flush the GPU at the end of this method to ensure the resources are not
// prematurely destroyed.
ComPtr<ID3D12Resource> vertexBufferUpload;
ComPtr<ID3D12Resource> fullscreenQuadVertexBufferUpload;
// Create the vertex buffer for the primary adapter.
{
// Define the geometry for a triangle.
Vertex triangleVertices[] =
{
{ { 0.0f, TriangleHalfWidth, TriangleDepth } },
{ { TriangleHalfWidth, -TriangleHalfWidth, TriangleDepth } },
{ { -TriangleHalfWidth, -TriangleHalfWidth, TriangleDepth } }
};
const UINT vertexBufferSize = sizeof(triangleVertices);
ThrowIfFailed(m_devices[Primary]->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(vertexBufferSize),
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_vertexBuffer)));
ThrowIfFailed(m_devices[Primary]->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(vertexBufferSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&vertexBufferUpload)));
// Copy data to the intermediate upload heap and then schedule a copy
// from the upload heap to the vertex buffer.
D3D12_SUBRESOURCE_DATA vertexData = {};
vertexData.pData = reinterpret_cast<UINT8*>(triangleVertices);
vertexData.RowPitch = vertexBufferSize;
vertexData.SlicePitch = vertexData.RowPitch;
UpdateSubresources<1>(m_directCommandLists[Primary].Get(), m_vertexBuffer.Get(), vertexBufferUpload.Get(), 0, 0, 1, &vertexData);
m_directCommandLists[Primary]->ResourceBarrier(1, &CD3DX12_RESOURCE_BARRIER::Transition(m_vertexBuffer.Get(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_VERTEX_AND_CONSTANT_BUFFER));
// Initialize the vertex buffer view.
m_vertexBufferView.BufferLocation = m_vertexBuffer->GetGPUVirtualAddress();
m_vertexBufferView.StrideInBytes = sizeof(Vertex);
m_vertexBufferView.SizeInBytes = sizeof(triangleVertices);
}
// Create the vertex buffer for the secondary adapter.
{
// Define the geometry for a fullscreen triangle.
VertexPositionUV quadVertices[] =
{
{ { -1.0f, -1.0f, 0.0f, 1.0f }, { 0.0f, 0.0f } }, // Bottom left.
{ { -1.0f, 1.0f, 0.0f, 1.0f }, { 0.0f, 1.0f } }, // Top left.
{ { 1.0f, -1.0f, 0.0f, 1.0f }, { 1.0f, 0.0f } }, // Bottom right.
{ { 1.0f, 1.0f, 0.0f, 1.0f }, { 1.0f, 1.0f } }, // Top right.
};
const UINT vertexBufferSize = sizeof(quadVertices);
ThrowIfFailed(m_devices[Secondary]->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(vertexBufferSize),
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_fullscreenQuadVertexBuffer)));
ThrowIfFailed(m_devices[Secondary]->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(vertexBufferSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&fullscreenQuadVertexBufferUpload)));
// Copy data to the intermediate upload heap and then schedule a copy
// from the upload heap to the vertex buffer.
D3D12_SUBRESOURCE_DATA vertexData = {};
vertexData.pData = reinterpret_cast<UINT8*>(quadVertices);
vertexData.RowPitch = vertexBufferSize;
vertexData.SlicePitch = vertexData.RowPitch;
UpdateSubresources<1>(m_directCommandLists[Secondary].Get(), m_fullscreenQuadVertexBuffer.Get(), fullscreenQuadVertexBufferUpload.Get(), 0, 0, 1, &vertexData);
m_directCommandLists[Secondary]->ResourceBarrier(1, &CD3DX12_RESOURCE_BARRIER::Transition(m_fullscreenQuadVertexBuffer.Get(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_VERTEX_AND_CONSTANT_BUFFER));
// Initialize the vertex buffer view.
m_fullscreenQuadVertexBufferView.BufferLocation = m_fullscreenQuadVertexBuffer->GetGPUVirtualAddress();
m_fullscreenQuadVertexBufferView.StrideInBytes = sizeof(VertexPositionUV);
m_fullscreenQuadVertexBufferView.SizeInBytes = sizeof(quadVertices);
}
// Create the depth stencil view.
{
D3D12_DEPTH_STENCIL_VIEW_DESC depthStencilDesc = {};
depthStencilDesc.Format = DXGI_FORMAT_D32_FLOAT;
depthStencilDesc.ViewDimension = D3D12_DSV_DIMENSION_TEXTURE2D;
depthStencilDesc.Flags = D3D12_DSV_FLAG_NONE;
const CD3DX12_CLEAR_VALUE clearValue(DXGI_FORMAT_D32_FLOAT, 1.0f, 0);
ThrowIfFailed(m_devices[Primary]->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Tex2D(DXGI_FORMAT_D32_FLOAT, m_width, m_height, 1, 0, 1, 0, D3D12_RESOURCE_FLAG_ALLOW_DEPTH_STENCIL),
D3D12_RESOURCE_STATE_DEPTH_WRITE,
&clearValue,
IID_PPV_ARGS(&m_depthStencil)
));
m_devices[Primary]->CreateDepthStencilView(m_depthStencil.Get(), &depthStencilDesc, m_dsvHeap->GetCPUDescriptorHandleForHeapStart());
}
// Create the constant buffers.
{
{
const UINT64 constantBufferSize = sizeof(ConstantBufferData) * MaxTriangleCount * FrameCount;
ThrowIfFailed(m_devices[Primary]->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(constantBufferSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&m_constantBuffer)));
// Setup constant buffer data.
for (UINT n = 0; n < MaxTriangleCount; n++)
{
m_constantBufferData[n].velocity = XMFLOAT4(GetRandomFloat(0.01f, 0.02f), 0.0f, 0.0f, 0.0f);
m_constantBufferData[n].offset = XMFLOAT4(GetRandomFloat(-5.0f, -1.5f), GetRandomFloat(-1.0f, 1.0f), GetRandomFloat(0.0f, 2.0f), 0.0f);
m_constantBufferData[n].color = XMFLOAT4(GetRandomFloat(0.5f, 1.0f), GetRandomFloat(0.5f, 1.0f), GetRandomFloat(0.5f, 1.0f), 1.0f);
XMStoreFloat4x4(&m_constantBufferData[n].projection, XMMatrixTranspose(XMMatrixPerspectiveFovLH(XM_PIDIV4, m_aspectRatio, 0.01f, 20.0f)));
}
// Map the constant buffer. We don't unmap this until the app closes.
// Keeping things mapped for the lifetime of the resource is okay.
CD3DX12_RANGE readRange(0, 0); // We do not intend to read from this resource on the CPU.
ThrowIfFailed(m_constantBuffer->Map(0, &readRange, reinterpret_cast<void**>(&m_pCbvDataBegin)));
memcpy(m_pCbvDataBegin, &m_constantBufferData[0], constantBufferSize / FrameCount);
}
{
const UINT64 workloadConstantBufferSize = sizeof(WorkloadConstantBufferData) * FrameCount;
ThrowIfFailed(m_devices[Primary]->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(workloadConstantBufferSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&m_workloadConstantBuffer)));
// Setup constant buffer data.
m_workloadConstantBufferData.loopCount = m_psLoopCount;
// Map the constant buffer. We don't unmap this until the app closes.
// Keeping things mapped for the lifetime of the resource is okay.
CD3DX12_RANGE readRange(0, 0); // We do not intend to read from this resource on the CPU.
ThrowIfFailed(m_workloadConstantBuffer->Map(0, &readRange, reinterpret_cast<void**>(&m_pWorkloadCbvDataBegin)));
memcpy(m_pWorkloadCbvDataBegin, &m_workloadConstantBufferData, workloadConstantBufferSize / FrameCount);
}
{
const UINT64 blurWorkloadConstantBufferSize = sizeof(WorkloadConstantBufferData) * FrameCount;
ThrowIfFailed(m_devices[Secondary]->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(blurWorkloadConstantBufferSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&m_blurWorkloadConstantBuffer)));
// Setup constant buffer data.
m_blurWorkloadConstantBufferData.loopCount = m_blurPSLoopCount;
// Map the constant buffer. We don't unmap this until the app closes.
// Keeping things mapped for the lifetime of the resource is okay.
CD3DX12_RANGE readRange(0, 0); // We do not intend to read from this resource on the CPU.
ThrowIfFailed(m_blurWorkloadConstantBuffer->Map(0, &readRange, reinterpret_cast<void**>(&m_pBlurWorkloadCbvDataBegin)));
memcpy(m_pBlurWorkloadCbvDataBegin, &m_blurWorkloadConstantBufferData, blurWorkloadConstantBufferSize / FrameCount);
}
{
ThrowIfFailed(m_devices[Secondary]->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(sizeof(BlurConstantBufferData)),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&m_blurConstantBuffer)));
// Map the constant buffer.
CD3DX12_RANGE readRange(0, 0); // We do not intend to read from this resource on the CPU.
ThrowIfFailed(m_blurConstantBuffer->Map(0, &readRange, reinterpret_cast<void**>(&m_pBlurCbvDataBegin)));
// Setup constant buffer data.
m_pBlurCbvDataBegin[0].offset = 0.5f;
m_pBlurCbvDataBegin[0].textureDimensions.x = static_cast<float>(m_width);
m_pBlurCbvDataBegin[0].textureDimensions.y = static_cast<float>(m_height);
// Unmap the constant buffer because we don't update this again.
// If we ever do, it should be buffered by the number of frames like other constant buffers.
const CD3DX12_RANGE emptyRange(0, 0);
m_blurConstantBuffer->Unmap(0, &emptyRange);
m_pBlurCbvDataBegin = nullptr;
}
}
// Close the command lists and execute them to begin the vertex buffer copies into the default heaps.
for (UINT i = 0; i < GraphicsAdaptersCount; i++)
{
ThrowIfFailed(m_directCommandLists[i]->Close());
ID3D12CommandList* ppCommandLists[] = { m_directCommandLists[i].Get() };
m_directCommandQueues[i]->ExecuteCommandLists(_countof(ppCommandLists), ppCommandLists);
}
// Create synchronization objects and wait until assets have been uploaded to the GPU.
// We use a cross-adapter fence for handling Signals and Waits between adapters.
// We use regular fences for things that don't need to be cross adapter because they don't need the additional overhead associated with being cross-adapter.
{
// Fence used to control CPU pacing.
ThrowIfFailed(m_devices[Secondary]->CreateFence(0, D3D12_FENCE_FLAG_NONE, IID_PPV_ARGS(&m_frameFence)));
// Fence used by the primary adapter to signal its copy queue that it has completed rendering.
// When this is signaled, the primary adapter's copy queue can begin copying to the cross-adapter shared resource.
ThrowIfFailed(m_devices[Primary]->CreateFence(0, D3D12_FENCE_FLAG_NONE, IID_PPV_ARGS(&m_renderFence)));
// Cross-adapter shared fence used by both adapters.
// Used by the primary adapter to signal the secondary adapter that it has completed copying to the cross-adapter shared resource.
// When this is signaled, the secondary adapter can begin its work.
ThrowIfFailed(m_devices[Primary]->CreateFence(0, D3D12_FENCE_FLAG_SHARED | D3D12_FENCE_FLAG_SHARED_CROSS_ADAPTER, IID_PPV_ARGS(&m_crossAdapterFences[Primary])));
// For now, require GENERIC_ALL access.
HANDLE fenceHandle = nullptr;
ThrowIfFailed(m_devices[Primary]->CreateSharedHandle(
m_crossAdapterFences[Primary].Get(),
nullptr,
GENERIC_ALL,
nullptr,
&fenceHandle));
HRESULT openSharedHandleResult = m_devices[Secondary]->OpenSharedHandle(fenceHandle, IID_PPV_ARGS(&m_crossAdapterFences[Secondary]));
// We can close the handle after opening the cross-adapter shared fence.
CloseHandle(fenceHandle);
ThrowIfFailed(openSharedHandleResult);
for (UINT i = 0; i < GraphicsAdaptersCount; i++)
{
// Create an event handle to use for frame synchronization.
m_fenceEvents[i] = CreateEventEx(nullptr, FALSE, FALSE, EVENT_ALL_ACCESS);
if (m_fenceEvents == nullptr)
{
ThrowIfFailed(HRESULT_FROM_WIN32(GetLastError()));
}
// Wait for the command list to execute; we are reusing the same command
// list in our main loop but for now, we just want to wait for setup to
// complete before continuing.
WaitForGpu(static_cast<GraphicsAdapter>(i));
}
}
}
// Load the sample assets.
void D3D12DynamicIndexing::LoadAssets()
{
// Note: ComPtr's are CPU objects but these resources need to stay in scope until
// the command list that references them has finished executing on the GPU.
// We will flush the GPU at the end of this method to ensure the resources are not
// prematurely destroyed.
ComPtr<ID3D12Resource> vertexBufferUploadHeap;
ComPtr<ID3D12Resource> indexBufferUploadHeap;
ComPtr<ID3D12Resource> textureUploadHeap;
ComPtr<ID3D12Resource> materialsUploadHeap;
// Create the root signature.
{
CD3DX12_DESCRIPTOR_RANGE ranges[3];
ranges[0].Init(D3D12_DESCRIPTOR_RANGE_TYPE_SRV, 1 + CityMaterialCount, 0); // Diffuse texture + array of materials.
ranges[1].Init(D3D12_DESCRIPTOR_RANGE_TYPE_SAMPLER, 1, 0);
ranges[2].Init(D3D12_DESCRIPTOR_RANGE_TYPE_CBV, 1, 0);
CD3DX12_ROOT_PARAMETER rootParameters[4];
rootParameters[0].InitAsDescriptorTable(1, &ranges[0], D3D12_SHADER_VISIBILITY_PIXEL);
rootParameters[1].InitAsDescriptorTable(1, &ranges[1], D3D12_SHADER_VISIBILITY_PIXEL);
rootParameters[2].InitAsDescriptorTable(1, &ranges[2], D3D12_SHADER_VISIBILITY_VERTEX);
rootParameters[3].InitAsConstants(1, 0, 0, D3D12_SHADER_VISIBILITY_PIXEL);
CD3DX12_ROOT_SIGNATURE_DESC rootSignatureDesc;
rootSignatureDesc.Init(_countof(rootParameters), rootParameters, 0, nullptr, D3D12_ROOT_SIGNATURE_FLAG_ALLOW_INPUT_ASSEMBLER_INPUT_LAYOUT);
ComPtr<ID3DBlob> signature;
ComPtr<ID3DBlob> error;
ThrowIfFailed(D3D12SerializeRootSignature(&rootSignatureDesc, D3D_ROOT_SIGNATURE_VERSION_1, &signature, &error));
ThrowIfFailed(m_device->CreateRootSignature(0, signature->GetBufferPointer(), signature->GetBufferSize(), IID_PPV_ARGS(&m_rootSignature)));
NAME_D3D12_OBJECT(m_rootSignature);
}
// Create the pipeline state, which includes loading shaders.
{
UINT8* pVertexShaderData;
UINT8* pPixelShaderData;
UINT vertexShaderDataLength;
UINT pixelShaderDataLength;
ThrowIfFailed(ReadDataFromFile(GetAssetFullPath(L"shader_mesh_simple_vert.cso").c_str(), &pVertexShaderData, &vertexShaderDataLength));
ThrowIfFailed(ReadDataFromFile(GetAssetFullPath(L"shader_mesh_dynamic_indexing_pixel.cso").c_str(), &pPixelShaderData, &pixelShaderDataLength));
CD3DX12_RASTERIZER_DESC rasterizerStateDesc(D3D12_DEFAULT);
rasterizerStateDesc.CullMode = D3D12_CULL_MODE_NONE;
// Describe and create the graphics pipeline state object (PSO).
D3D12_GRAPHICS_PIPELINE_STATE_DESC psoDesc = {};
psoDesc.InputLayout = { SampleAssets::StandardVertexDescription, SampleAssets::StandardVertexDescriptionNumElements };
psoDesc.pRootSignature = m_rootSignature.Get();
psoDesc.VS = CD3DX12_SHADER_BYTECODE(pVertexShaderData, vertexShaderDataLength);
psoDesc.PS = CD3DX12_SHADER_BYTECODE(pPixelShaderData, pixelShaderDataLength);
psoDesc.RasterizerState = rasterizerStateDesc;
psoDesc.BlendState = CD3DX12_BLEND_DESC(D3D12_DEFAULT);
psoDesc.DepthStencilState = CD3DX12_DEPTH_STENCIL_DESC(D3D12_DEFAULT);
psoDesc.SampleMask = UINT_MAX;
psoDesc.PrimitiveTopologyType = D3D12_PRIMITIVE_TOPOLOGY_TYPE_TRIANGLE;
psoDesc.NumRenderTargets = 1;
psoDesc.RTVFormats[0] = DXGI_FORMAT_R8G8B8A8_UNORM;
psoDesc.DSVFormat = DXGI_FORMAT_D32_FLOAT;
psoDesc.SampleDesc.Count = 1;
ThrowIfFailed(m_device->CreateGraphicsPipelineState(&psoDesc, IID_PPV_ARGS(&m_pipelineState)));
NAME_D3D12_OBJECT(m_pipelineState);
delete pVertexShaderData;
delete pPixelShaderData;
}
ThrowIfFailed(m_device->CreateCommandList(0, D3D12_COMMAND_LIST_TYPE_DIRECT, m_commandAllocator.Get(), nullptr, IID_PPV_ARGS(&m_commandList)));
NAME_D3D12_OBJECT(m_commandList);
// Create render target views (RTVs).
CD3DX12_CPU_DESCRIPTOR_HANDLE rtvHandle(m_rtvHeap->GetCPUDescriptorHandleForHeapStart());
for (UINT i = 0; i < FrameCount; i++)
{
ThrowIfFailed(m_swapChain->GetBuffer(i, IID_PPV_ARGS(&m_renderTargets[i])));
m_device->CreateRenderTargetView(m_renderTargets[i].Get(), nullptr, rtvHandle);
rtvHandle.Offset(1, m_rtvDescriptorSize);
NAME_D3D12_OBJECT_INDEXED(m_renderTargets, i);
}
// Read in mesh data for vertex/index buffers.
UINT8* pMeshData;
UINT meshDataLength;
ThrowIfFailed(ReadDataFromFile(GetAssetFullPath(SampleAssets::DataFileName).c_str(), &pMeshData, &meshDataLength));
// Create the vertex buffer.
{
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(SampleAssets::VertexDataSize),
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_vertexBuffer)));
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(SampleAssets::VertexDataSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&vertexBufferUploadHeap)));
NAME_D3D12_OBJECT(m_vertexBuffer);
// Copy data to the intermediate upload heap and then schedule a copy
// from the upload heap to the vertex buffer.
D3D12_SUBRESOURCE_DATA vertexData = {};
vertexData.pData = pMeshData + SampleAssets::VertexDataOffset;
vertexData.RowPitch = SampleAssets::VertexDataSize;
vertexData.SlicePitch = vertexData.RowPitch;
UpdateSubresources<1>(m_commandList.Get(), m_vertexBuffer.Get(), vertexBufferUploadHeap.Get(), 0, 0, 1, &vertexData);
m_commandList->ResourceBarrier(1, &CD3DX12_RESOURCE_BARRIER::Transition(m_vertexBuffer.Get(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_VERTEX_AND_CONSTANT_BUFFER));
// Initialize the vertex buffer view.
m_vertexBufferView.BufferLocation = m_vertexBuffer->GetGPUVirtualAddress();
m_vertexBufferView.StrideInBytes = SampleAssets::StandardVertexStride;
m_vertexBufferView.SizeInBytes = SampleAssets::VertexDataSize;
}
// Create the index buffer.
{
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(SampleAssets::IndexDataSize),
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_indexBuffer)));
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(SampleAssets::IndexDataSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&indexBufferUploadHeap)));
NAME_D3D12_OBJECT(m_indexBuffer);
// Copy data to the intermediate upload heap and then schedule a copy
// from the upload heap to the index buffer.
D3D12_SUBRESOURCE_DATA indexData = {};
indexData.pData = pMeshData + SampleAssets::IndexDataOffset;
indexData.RowPitch = SampleAssets::IndexDataSize;
indexData.SlicePitch = indexData.RowPitch;
UpdateSubresources<1>(m_commandList.Get(), m_indexBuffer.Get(), indexBufferUploadHeap.Get(), 0, 0, 1, &indexData);
m_commandList->ResourceBarrier(1, &CD3DX12_RESOURCE_BARRIER::Transition(m_indexBuffer.Get(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_INDEX_BUFFER));
// Describe the index buffer view.
m_indexBufferView.BufferLocation = m_indexBuffer->GetGPUVirtualAddress();
m_indexBufferView.Format = SampleAssets::StandardIndexFormat;
m_indexBufferView.SizeInBytes = SampleAssets::IndexDataSize;
m_numIndices = SampleAssets::IndexDataSize / 4; // R32_UINT (SampleAssets::StandardIndexFormat) = 4 bytes each.
}
// Create the textures and sampler.
{
// Procedurally generate an array of textures to use as city materials.
{
// All of these materials use the same texture desc.
D3D12_RESOURCE_DESC textureDesc = {};
textureDesc.MipLevels = 1;
textureDesc.Format = DXGI_FORMAT_R8G8B8A8_UNORM;
textureDesc.Width = CityMaterialTextureWidth;
textureDesc.Height = CityMaterialTextureHeight;
textureDesc.Flags = D3D12_RESOURCE_FLAG_NONE;
textureDesc.DepthOrArraySize = 1;
textureDesc.SampleDesc.Count = 1;
textureDesc.SampleDesc.Quality = 0;
textureDesc.Dimension = D3D12_RESOURCE_DIMENSION_TEXTURE2D;
// The textures evenly span the color rainbow so that each city gets
// a different material.
float materialGradStep = (1.0f / static_cast<float>(CityMaterialCount));
// Generate texture data.
std::vector<std::vector<unsigned char>> cityTextureData;
cityTextureData.resize(CityMaterialCount);
for (UINT i = 0; i < CityMaterialCount; ++i)
{
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&textureDesc,
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_cityMaterialTextures[i])));
NAME_D3D12_OBJECT_INDEXED(m_cityMaterialTextures, i);
// Fill the texture.
float t = i * materialGradStep;
cityTextureData[i].resize(CityMaterialTextureWidth * CityMaterialTextureHeight * CityMaterialTextureChannelCount);
for (int x = 0; x < CityMaterialTextureWidth; ++x)
{
for (int y = 0; y < CityMaterialTextureHeight; ++y)
{
// Compute the appropriate index into the buffer based on the x/y coordinates.
int pixelIndex = (y * CityMaterialTextureChannelCount * CityMaterialTextureWidth) + (x * CityMaterialTextureChannelCount);
// Determine this row's position along the rainbow gradient.
float tPrime = t + ((static_cast<float>(y) / static_cast<float>(CityMaterialTextureHeight)) * materialGradStep);
// Compute the RGB value for this position along the rainbow
// and pack the pixel value.
XMVECTOR hsl = XMVectorSet(tPrime, 0.5f, 0.5f, 1.0f);
XMVECTOR rgb = XMColorHSLToRGB(hsl);
cityTextureData[i][pixelIndex + 0] = static_cast<unsigned char>((255 * XMVectorGetX(rgb)));
cityTextureData[i][pixelIndex + 1] = static_cast<unsigned char>((255 * XMVectorGetY(rgb)));
cityTextureData[i][pixelIndex + 2] = static_cast<unsigned char>((255 * XMVectorGetZ(rgb)));
cityTextureData[i][pixelIndex + 3] = 255;
}
}
}
// Upload texture data to the default heap resources.
{
const UINT subresourceCount = textureDesc.DepthOrArraySize * textureDesc.MipLevels;
const UINT64 uploadBufferStep = GetRequiredIntermediateSize(m_cityMaterialTextures[0].Get(), 0, subresourceCount); // All of our textures are the same size in this case.
const UINT64 uploadBufferSize = uploadBufferStep * CityMaterialCount;
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(uploadBufferSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&materialsUploadHeap)));
for (int i = 0; i < CityMaterialCount; ++i)
{
// Copy data to the intermediate upload heap and then schedule
// a copy from the upload heap to the appropriate texture.
D3D12_SUBRESOURCE_DATA textureData = {};
textureData.pData = &cityTextureData[i][0];
textureData.RowPitch = static_cast<LONG_PTR>((CityMaterialTextureChannelCount * textureDesc.Width));
textureData.SlicePitch = textureData.RowPitch * textureDesc.Height;
UpdateSubresources(m_commandList.Get(), m_cityMaterialTextures[i].Get(), materialsUploadHeap.Get(), i * uploadBufferStep, 0, subresourceCount, &textureData);
m_commandList->ResourceBarrier(1, &CD3DX12_RESOURCE_BARRIER::Transition(m_cityMaterialTextures[i].Get(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_PIXEL_SHADER_RESOURCE));
}
}
}
// Load the occcity diffuse texture with baked-in ambient lighting.
// This texture will be blended with a texture from the materials
// array in the pixel shader.
{
D3D12_RESOURCE_DESC textureDesc = {};
textureDesc.MipLevels = SampleAssets::Textures[0].MipLevels;
textureDesc.Format = SampleAssets::Textures[0].Format;
textureDesc.Width = SampleAssets::Textures[0].Width;
textureDesc.Height = SampleAssets::Textures[0].Height;
textureDesc.Flags = D3D12_RESOURCE_FLAG_NONE;
textureDesc.DepthOrArraySize = 1;
textureDesc.SampleDesc.Count = 1;
textureDesc.SampleDesc.Quality = 0;
textureDesc.Dimension = D3D12_RESOURCE_DIMENSION_TEXTURE2D;
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&textureDesc,
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_cityDiffuseTexture)));
const UINT subresourceCount = textureDesc.DepthOrArraySize * textureDesc.MipLevels;
const UINT64 uploadBufferSize = GetRequiredIntermediateSize(m_cityDiffuseTexture.Get(), 0, subresourceCount);
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(uploadBufferSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&textureUploadHeap)));
NAME_D3D12_OBJECT(m_cityDiffuseTexture);
// Copy data to the intermediate upload heap and then schedule
// a copy from the upload heap to the diffuse texture.
D3D12_SUBRESOURCE_DATA textureData = {};
textureData.pData = pMeshData + SampleAssets::Textures[0].Data[0].Offset;
textureData.RowPitch = SampleAssets::Textures[0].Data[0].Pitch;
textureData.SlicePitch = SampleAssets::Textures[0].Data[0].Size;
UpdateSubresources(m_commandList.Get(), m_cityDiffuseTexture.Get(), textureUploadHeap.Get(), 0, 0, subresourceCount, &textureData);
m_commandList->ResourceBarrier(1, &CD3DX12_RESOURCE_BARRIER::Transition(m_cityDiffuseTexture.Get(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_PIXEL_SHADER_RESOURCE));
}
// Describe and create a sampler.
D3D12_SAMPLER_DESC samplerDesc = {};
samplerDesc.Filter = D3D12_FILTER_MIN_MAG_MIP_LINEAR;
samplerDesc.AddressU = D3D12_TEXTURE_ADDRESS_MODE_WRAP;
samplerDesc.AddressV = D3D12_TEXTURE_ADDRESS_MODE_WRAP;
samplerDesc.AddressW = D3D12_TEXTURE_ADDRESS_MODE_WRAP;
samplerDesc.MinLOD = 0;
samplerDesc.MaxLOD = D3D12_FLOAT32_MAX;
samplerDesc.MipLODBias = 0.0f;
samplerDesc.MaxAnisotropy = 1;
samplerDesc.ComparisonFunc = D3D12_COMPARISON_FUNC_ALWAYS;
m_device->CreateSampler(&samplerDesc, m_samplerHeap->GetCPUDescriptorHandleForHeapStart());
// Create SRV for the city's diffuse texture.
CD3DX12_CPU_DESCRIPTOR_HANDLE srvHandle(m_cbvSrvHeap->GetCPUDescriptorHandleForHeapStart(), 0, m_cbvSrvDescriptorSize);
D3D12_SHADER_RESOURCE_VIEW_DESC diffuseSrvDesc = {};
diffuseSrvDesc.Shader4ComponentMapping = D3D12_DEFAULT_SHADER_4_COMPONENT_MAPPING;
diffuseSrvDesc.Format = SampleAssets::Textures->Format;
diffuseSrvDesc.ViewDimension = D3D12_SRV_DIMENSION_TEXTURE2D;
diffuseSrvDesc.Texture2D.MipLevels = 1;
m_device->CreateShaderResourceView(m_cityDiffuseTexture.Get(), &diffuseSrvDesc, srvHandle);
srvHandle.Offset(m_cbvSrvDescriptorSize);
// Create SRVs for each city material.
for (int i = 0; i < CityMaterialCount; ++i)
{
D3D12_SHADER_RESOURCE_VIEW_DESC materialSrvDesc = {};
materialSrvDesc.Shader4ComponentMapping = D3D12_DEFAULT_SHADER_4_COMPONENT_MAPPING;
materialSrvDesc.Format = DXGI_FORMAT_R8G8B8A8_UNORM;
materialSrvDesc.ViewDimension = D3D12_SRV_DIMENSION_TEXTURE2D;
materialSrvDesc.Texture2D.MipLevels = 1;
m_device->CreateShaderResourceView(m_cityMaterialTextures[i].Get(), &materialSrvDesc, srvHandle);
srvHandle.Offset(m_cbvSrvDescriptorSize);
}
}
delete pMeshData;
// Create the depth stencil view.
{
D3D12_DEPTH_STENCIL_VIEW_DESC depthStencilDesc = {};
depthStencilDesc.Format = DXGI_FORMAT_D32_FLOAT;
depthStencilDesc.ViewDimension = D3D12_DSV_DIMENSION_TEXTURE2D;
depthStencilDesc.Flags = D3D12_DSV_FLAG_NONE;
D3D12_CLEAR_VALUE depthOptimizedClearValue = {};
depthOptimizedClearValue.Format = DXGI_FORMAT_D32_FLOAT;
depthOptimizedClearValue.DepthStencil.Depth = 1.0f;
depthOptimizedClearValue.DepthStencil.Stencil = 0;
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Tex2D(DXGI_FORMAT_D32_FLOAT, m_width, m_height, 1, 0, 1, 0, D3D12_RESOURCE_FLAG_ALLOW_DEPTH_STENCIL),
D3D12_RESOURCE_STATE_DEPTH_WRITE,
&depthOptimizedClearValue,
IID_PPV_ARGS(&m_depthStencil)
));
NAME_D3D12_OBJECT(m_depthStencil);
m_device->CreateDepthStencilView(m_depthStencil.Get(), &depthStencilDesc, m_dsvHeap->GetCPUDescriptorHandleForHeapStart());
}
// Close the command list and execute it to begin the initial GPU setup.
ThrowIfFailed(m_commandList->Close());
ID3D12CommandList* ppCommandLists[] = { m_commandList.Get() };
m_commandQueue->ExecuteCommandLists(_countof(ppCommandLists), ppCommandLists);
CreateFrameResources();
// Create synchronization objects and wait until assets have been uploaded to the GPU.
{
ThrowIfFailed(m_device->CreateFence(m_fenceValue, D3D12_FENCE_FLAG_NONE, IID_PPV_ARGS(&m_fence)));
m_fenceValue++;
// Create an event handle to use for frame synchronization.
m_fenceEvent = CreateEvent(nullptr, FALSE, FALSE, nullptr);
if (m_fenceEvent == nullptr)
{
ThrowIfFailed(HRESULT_FROM_WIN32(GetLastError()));
}
// Wait for the command list to execute; we are reusing the same command
// list in our main loop but for now, we just want to wait for setup to
// complete before continuing.
// Signal and increment the fence value.
const UINT64 fenceToWaitFor = m_fenceValue;
ThrowIfFailed(m_commandQueue->Signal(m_fence.Get(), fenceToWaitFor));
m_fenceValue++;
// Wait until the fence is completed.
ThrowIfFailed(m_fence->SetEventOnCompletion(fenceToWaitFor, m_fenceEvent));
WaitForSingleObject(m_fenceEvent, INFINITE);
}
}
// Load the sample assets.
void D3D12PredicationQueries::LoadAssets()
{
// Create a root signature consisting of a single CBV parameter.
{
D3D12_FEATURE_DATA_ROOT_SIGNATURE featureData = {};
// This is the highest version the sample supports. If CheckFeatureSupport succeeds, the HighestVersion returned will not be greater than this.
featureData.HighestVersion = D3D_ROOT_SIGNATURE_VERSION_1_1;
if (FAILED(m_device->CheckFeatureSupport(D3D12_FEATURE_ROOT_SIGNATURE, &featureData, sizeof(featureData))))
{
featureData.HighestVersion = D3D_ROOT_SIGNATURE_VERSION_1_0;
}
CD3DX12_DESCRIPTOR_RANGE1 ranges[1];
CD3DX12_ROOT_PARAMETER1 rootParameters[1];
ranges[0].Init(D3D12_DESCRIPTOR_RANGE_TYPE_CBV, 1, 0, 0, D3D12_DESCRIPTOR_RANGE_FLAG_DATA_STATIC);
rootParameters[0].InitAsDescriptorTable(1, &ranges[0], D3D12_SHADER_VISIBILITY_VERTEX);
// Allow input layout and deny uneccessary access to certain pipeline stages.
D3D12_ROOT_SIGNATURE_FLAGS rootSignatureFlags =
D3D12_ROOT_SIGNATURE_FLAG_ALLOW_INPUT_ASSEMBLER_INPUT_LAYOUT |
D3D12_ROOT_SIGNATURE_FLAG_DENY_HULL_SHADER_ROOT_ACCESS |
D3D12_ROOT_SIGNATURE_FLAG_DENY_DOMAIN_SHADER_ROOT_ACCESS |
D3D12_ROOT_SIGNATURE_FLAG_DENY_GEOMETRY_SHADER_ROOT_ACCESS |
D3D12_ROOT_SIGNATURE_FLAG_DENY_PIXEL_SHADER_ROOT_ACCESS;
CD3DX12_VERSIONED_ROOT_SIGNATURE_DESC rootSignatureDesc;
rootSignatureDesc.Init_1_1(_countof(rootParameters), rootParameters, 0, nullptr, rootSignatureFlags);
ComPtr<ID3DBlob> signature;
ComPtr<ID3DBlob> error;
ThrowIfFailed(D3DX12SerializeVersionedRootSignature(&rootSignatureDesc, featureData.HighestVersion, &signature, &error));
ThrowIfFailed(m_device->CreateRootSignature(0, signature->GetBufferPointer(), signature->GetBufferSize(), IID_PPV_ARGS(&m_rootSignature)));
NAME_D3D12_OBJECT(m_rootSignature);
}
// Create the pipeline state, which includes compiling and loading shaders.
{
ComPtr<ID3DBlob> vertexShader;
ComPtr<ID3DBlob> pixelShader;
#if defined(_DEBUG)
// Enable better shader debugging with the graphics debugging tools.
UINT compileFlags = D3DCOMPILE_DEBUG | D3DCOMPILE_SKIP_OPTIMIZATION;
#else
UINT compileFlags = 0;
#endif
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"shaders.hlsl").c_str(), nullptr, nullptr, "VSMain", "vs_5_0", compileFlags, 0, &vertexShader, nullptr));
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"shaders.hlsl").c_str(), nullptr, nullptr, "PSMain", "ps_5_0", compileFlags, 0, &pixelShader, nullptr));
// Define the vertex input layout.
D3D12_INPUT_ELEMENT_DESC inputElementDescs[] =
{
{ "POSITION", 0, DXGI_FORMAT_R32G32B32_FLOAT, 0, 0, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
{ "COLOR", 0, DXGI_FORMAT_R32G32B32A32_FLOAT, 0, 12, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 }
};
// Enable alpha blending so we can visualize the occlusion query results.
CD3DX12_BLEND_DESC blendDesc(D3D12_DEFAULT);
blendDesc.RenderTarget[0] =
{
TRUE, FALSE,
D3D12_BLEND_SRC_ALPHA, D3D12_BLEND_INV_SRC_ALPHA, D3D12_BLEND_OP_ADD,
D3D12_BLEND_ONE, D3D12_BLEND_ZERO, D3D12_BLEND_OP_ADD,
D3D12_LOGIC_OP_NOOP,
D3D12_COLOR_WRITE_ENABLE_ALL,
};
// Describe and create the graphics pipeline state objects (PSO).
D3D12_GRAPHICS_PIPELINE_STATE_DESC psoDesc = {};
psoDesc.InputLayout = { inputElementDescs, _countof(inputElementDescs) };
psoDesc.pRootSignature = m_rootSignature.Get();
psoDesc.VS = CD3DX12_SHADER_BYTECODE(vertexShader.Get());
psoDesc.PS = CD3DX12_SHADER_BYTECODE(pixelShader.Get());
psoDesc.RasterizerState = CD3DX12_RASTERIZER_DESC(D3D12_DEFAULT);
psoDesc.BlendState = blendDesc;
psoDesc.DepthStencilState = CD3DX12_DEPTH_STENCIL_DESC(D3D12_DEFAULT);
psoDesc.SampleMask = UINT_MAX;
psoDesc.PrimitiveTopologyType = D3D12_PRIMITIVE_TOPOLOGY_TYPE_TRIANGLE;
psoDesc.NumRenderTargets = 1;
psoDesc.RTVFormats[0] = DXGI_FORMAT_R8G8B8A8_UNORM;
psoDesc.DSVFormat = DXGI_FORMAT_D32_FLOAT;
psoDesc.SampleDesc.Count = 1;
ThrowIfFailed(m_device->CreateGraphicsPipelineState(&psoDesc, IID_PPV_ARGS(&m_pipelineState)));
NAME_D3D12_OBJECT(m_pipelineState);
// Disable color writes and depth writes for the occlusion query's state.
psoDesc.BlendState.RenderTarget[0].RenderTargetWriteMask = 0;
psoDesc.DepthStencilState.DepthWriteMask = D3D12_DEPTH_WRITE_MASK_ZERO;
ThrowIfFailed(m_device->CreateGraphicsPipelineState(&psoDesc, IID_PPV_ARGS(&m_queryState)));
NAME_D3D12_OBJECT(m_queryState);
}
// Create the command list.
ThrowIfFailed(m_device->CreateCommandList(0, D3D12_COMMAND_LIST_TYPE_DIRECT, m_commandAllocators[m_frameIndex].Get(), m_pipelineState.Get(), IID_PPV_ARGS(&m_commandList)));
NAME_D3D12_OBJECT(m_commandList);
// Note: ComPtr's are CPU objects but this resource needs to stay in scope until
// the command list that references it has finished executing on the GPU.
// We will flush the GPU at the end of this method to ensure the resource is not
// prematurely destroyed.
ComPtr<ID3D12Resource> vertexBufferUpload;
// Create the vertex buffer.
{
// Create geometry for two quads and a bounding box for the occlusion query.
// Geometry will be rendered back-to-front to support transparency in the scene.
Vertex quadVertices[] =
{
// Far quad - in practice this would be a complex geometry.
{ { -0.25f, -0.25f * m_aspectRatio, 0.5f }, { 1.0f, 1.0f, 1.0f, 1.0f } },
{ { -0.25f, 0.25f * m_aspectRatio, 0.5f }, { 1.0f, 1.0f, 1.0f, 1.0f } },
{ { 0.25f, -0.25f * m_aspectRatio, 0.5f }, { 1.0f, 1.0f, 1.0f, 1.0f } },
{ { 0.25f, 0.25f * m_aspectRatio, 0.5f }, { 1.0f, 1.0f, 1.0f, 1.0f } },
// Near quad.
{ { -0.5f, -0.35f * m_aspectRatio, 0.0f }, { 1.0f, 0.0f, 0.0f, 0.65f } },
{ { -0.5f, 0.35f * m_aspectRatio, 0.0f }, { 1.0f, 0.0f, 0.0f, 0.65f } },
{ { 0.5f, -0.35f * m_aspectRatio, 0.0f }, { 1.0f, 1.0f, 0.0f, 0.65f } },
{ { 0.5f, 0.35f * m_aspectRatio, 0.0f }, { 1.0f, 1.0f, 0.0f, 0.65f } },
// Far quad bounding box used for occlusion query (offset slightly to avoid z-fighting).
{ { -0.25f, -0.25f * m_aspectRatio, 0.4999f }, { 0.0f, 0.0f, 0.0f, 1.0f } },
{ { -0.25f, 0.25f * m_aspectRatio, 0.4999f }, { 0.0f, 0.0f, 0.0f, 1.0f } },
{ { 0.25f, -0.25f * m_aspectRatio, 0.4999f }, { 0.0f, 0.0f, 0.0f, 1.0f } },
{ { 0.25f, 0.25f * m_aspectRatio, 0.4999f }, { 0.0f, 0.0f, 0.0f, 1.0f } },
};
const UINT vertexBufferSize = sizeof(quadVertices);
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(vertexBufferSize),
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_vertexBuffer)));
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(vertexBufferSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&vertexBufferUpload)));
NAME_D3D12_OBJECT(m_vertexBuffer);
// Copy data to the intermediate upload heap and then schedule a copy
// from the upload heap to the vertex buffer.
D3D12_SUBRESOURCE_DATA vertexData = {};
vertexData.pData = reinterpret_cast<UINT8*>(quadVertices);
vertexData.RowPitch = vertexBufferSize;
vertexData.SlicePitch = vertexData.RowPitch;
UpdateSubresources<1>(m_commandList.Get(), m_vertexBuffer.Get(), vertexBufferUpload.Get(), 0, 0, 1, &vertexData);
m_commandList->ResourceBarrier(1, &CD3DX12_RESOURCE_BARRIER::Transition(m_vertexBuffer.Get(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_VERTEX_AND_CONSTANT_BUFFER));
// Initialize the vertex buffer view.
m_vertexBufferView.BufferLocation = m_vertexBuffer->GetGPUVirtualAddress();
m_vertexBufferView.StrideInBytes = sizeof(Vertex);
m_vertexBufferView.SizeInBytes = sizeof(quadVertices);
}
// Create the constant buffers.
{
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(FrameCount * sizeof(m_constantBufferData)),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&m_constantBuffer)));
NAME_D3D12_OBJECT(m_constantBuffer);
// Map and initialize the constant buffer. We don't unmap this until the
// app closes. Keeping things mapped for the lifetime of the resource is okay.
CD3DX12_RANGE readRange(0, 0); // We do not intend to read from this resource on the CPU.
ThrowIfFailed(m_constantBuffer->Map(0, &readRange, reinterpret_cast<void**>(&m_pCbvDataBegin)));
ZeroMemory(m_pCbvDataBegin, FrameCount * sizeof(m_constantBufferData));
// Create constant buffer views to access the upload buffer.
CD3DX12_CPU_DESCRIPTOR_HANDLE cpuHandle(m_cbvHeap->GetCPUDescriptorHandleForHeapStart());
D3D12_GPU_VIRTUAL_ADDRESS gpuAddress = m_constantBuffer->GetGPUVirtualAddress();
D3D12_CONSTANT_BUFFER_VIEW_DESC cbvDesc = {};
cbvDesc.SizeInBytes = sizeof(SceneConstantBuffer);
for (UINT n = 0; n < FrameCount; n++)
{
cbvDesc.BufferLocation = gpuAddress;
m_device->CreateConstantBufferView(&cbvDesc, cpuHandle);
cpuHandle.Offset(m_cbvSrvDescriptorSize);
gpuAddress += cbvDesc.SizeInBytes;
cbvDesc.BufferLocation = gpuAddress;
m_device->CreateConstantBufferView(&cbvDesc, cpuHandle);
cpuHandle.Offset(m_cbvSrvDescriptorSize);
gpuAddress += cbvDesc.SizeInBytes;
}
}
// Create the depth stencil view.
{
D3D12_DEPTH_STENCIL_VIEW_DESC depthStencilDesc = {};
depthStencilDesc.Format = DXGI_FORMAT_D32_FLOAT;
depthStencilDesc.ViewDimension = D3D12_DSV_DIMENSION_TEXTURE2D;
depthStencilDesc.Flags = D3D12_DSV_FLAG_NONE;
D3D12_CLEAR_VALUE depthOptimizedClearValue = {};
depthOptimizedClearValue.Format = DXGI_FORMAT_D32_FLOAT;
depthOptimizedClearValue.DepthStencil.Depth = 1.0f;
depthOptimizedClearValue.DepthStencil.Stencil = 0;
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Tex2D(DXGI_FORMAT_D32_FLOAT, m_width, m_height, 1, 0, 1, 0, D3D12_RESOURCE_FLAG_ALLOW_DEPTH_STENCIL),
D3D12_RESOURCE_STATE_DEPTH_WRITE,
&depthOptimizedClearValue,
IID_PPV_ARGS(&m_depthStencil)
));
NAME_D3D12_OBJECT(m_depthStencil);
m_device->CreateDepthStencilView(m_depthStencil.Get(), &depthStencilDesc, m_dsvHeap->GetCPUDescriptorHandleForHeapStart());
}
// Create the query result buffer.
{
D3D12_RESOURCE_DESC queryResultDesc = CD3DX12_RESOURCE_DESC::Buffer(8);
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&queryResultDesc,
D3D12_RESOURCE_STATE_PREDICATION,
nullptr,
IID_PPV_ARGS(&m_queryResult)
));
NAME_D3D12_OBJECT(m_queryResult);
}
// Close the command list and execute it to begin the vertex buffer copy into
// the default heap.
ThrowIfFailed(m_commandList->Close());
ID3D12CommandList* ppCommandLists[] = { m_commandList.Get() };
m_commandQueue->ExecuteCommandLists(_countof(ppCommandLists), ppCommandLists);
// Create synchronization objects and wait until assets have been uploaded to the GPU.
{
ThrowIfFailed(m_device->CreateFence(m_fenceValues[m_frameIndex], D3D12_FENCE_FLAG_NONE, IID_PPV_ARGS(&m_fence)));
m_fenceValues[m_frameIndex]++;
// Create an event handle to use for frame synchronization.
m_fenceEvent = CreateEvent(nullptr, FALSE, FALSE, nullptr);
if (m_fenceEvent == nullptr)
{
ThrowIfFailed(HRESULT_FROM_WIN32(GetLastError()));
}
// Wait for the command list to execute; we are reusing the same command
// list in our main loop but for now, we just want to wait for setup to
// complete before continuing.
WaitForGpu();
}
}
void GltfPbr::CreatePipeline(ID3D12Device* pDevice, UINT node, std::vector<std::string> semanticNames, std::vector<D3D12_INPUT_ELEMENT_DESC> layout, PBRPrimitives *pPrimitive)
{
//=================================================================================================
// let vertex shader know what buffers are present
// The Shader Code glTF20_EX.hlsl has if defs that are enable using these attributes when compiled
// and ref by the D3D12_GRAPHICS_PIPELINE_STATE_DESC
//=================================================================================================
bool Has_Normals = false;
std::map<std::string, std::string> attributeDefines;
for (unsigned int i = 0; i < layout.size(); i++)
{
layout[i].SemanticName = semanticNames[i].c_str();
attributeDefines[std::string("HAS_") + layout[i].SemanticName] = "1";
if (semanticNames[i].compare("NORMAL") == 0) Has_Normals = true;
}
// Compile shaders
//
ID3DBlob *pBlobShaderVert, *pBlobShaderPixel;
{
// build macro structure
//
std::vector<D3D_SHADER_MACRO> macros;
CompileMacros(&attributeDefines, ¯os);
CompileMacros(&pPrimitive->m_pMaterial->m_defines, ¯os);
macros.push_back(D3D_SHADER_MACRO{ NULL, NULL });
ID3DBlob *pError;
D3DCompileFromFile(L"./plugins/shaders/glTF20_EX.hlsl", macros.data(), nullptr, "mainVS", "vs_5_0", 0, 0, &pBlobShaderVert, &pError);
D3DCompileFromFile(L"./plugins/shaders/glTF20_EX.hlsl", macros.data(), nullptr, "mainPS", "ps_5_0", 0, 0, &pBlobShaderPixel, &pError);
if (pError != NULL)
{
char *msg = (char *)pError->GetBufferPointer();
MessageBoxA(0, msg, "", 0);
}
}
// Create root signature
//
{
CD3DX12_DESCRIPTOR_RANGE DescRange[4];
DescRange[0].Init(D3D12_DESCRIPTOR_RANGE_TYPE_CBV, 1, 0); // b0 <- per frame
DescRange[1].Init(D3D12_DESCRIPTOR_RANGE_TYPE_SRV, pPrimitive->m_pMaterial->m_textureCount, 0); // t0 <- per material
DescRange[2].Init(D3D12_DESCRIPTOR_RANGE_TYPE_CBV, 1, 1); // b1 <- per material parameters
DescRange[3].Init(D3D12_DESCRIPTOR_RANGE_TYPE_SAMPLER, 5, 0); // s0 <- samplers
CD3DX12_ROOT_PARAMETER RTSlot[4];
RTSlot[0].InitAsDescriptorTable(1, &DescRange[0], D3D12_SHADER_VISIBILITY_ALL);
RTSlot[1].InitAsDescriptorTable(1, &DescRange[1], D3D12_SHADER_VISIBILITY_PIXEL);
RTSlot[2].InitAsDescriptorTable(1, &DescRange[2], D3D12_SHADER_VISIBILITY_ALL);
RTSlot[3].InitAsDescriptorTable(1, &DescRange[3], D3D12_SHADER_VISIBILITY_PIXEL);
// the root signature contains 3 slots to be used
CD3DX12_ROOT_SIGNATURE_DESC descRootSignature = CD3DX12_ROOT_SIGNATURE_DESC();
descRootSignature.NumParameters = 4;
descRootSignature.pParameters = RTSlot;
descRootSignature.NumStaticSamplers = 0;
descRootSignature.pStaticSamplers = NULL;
// deny uneccessary access to certain pipeline stages
descRootSignature.Flags = D3D12_ROOT_SIGNATURE_FLAG_NONE
| D3D12_ROOT_SIGNATURE_FLAG_ALLOW_INPUT_ASSEMBLER_INPUT_LAYOUT
//| D3D12_ROOT_SIGNATURE_FLAG_DENY_VERTEX_SHADER_ROOT_ACCESS
| D3D12_ROOT_SIGNATURE_FLAG_DENY_HULL_SHADER_ROOT_ACCESS
| D3D12_ROOT_SIGNATURE_FLAG_DENY_DOMAIN_SHADER_ROOT_ACCESS
| D3D12_ROOT_SIGNATURE_FLAG_DENY_GEOMETRY_SHADER_ROOT_ACCESS;
//| D3D12_ROOT_SIGNATURE_FLAG_DENY_PIXEL_SHADER_ROOT_ACCESS;
ID3DBlob *pOutBlob, *pErrorBlob = NULL;
ThrowIfFailed(D3D12SerializeRootSignature(&descRootSignature, D3D_ROOT_SIGNATURE_VERSION_1, &pOutBlob, &pErrorBlob));
ThrowIfFailed(
pDevice->CreateRootSignature(
node,
pOutBlob->GetBufferPointer(),
pOutBlob->GetBufferSize(),
IID_PPV_ARGS(&pPrimitive->m_RootSignature))
);
pPrimitive->m_RootSignature->SetName(L"OnCreatePrimitiveColorPass");
pOutBlob->Release();
if (pErrorBlob)
pErrorBlob->Release();
}
D3D12_RENDER_TARGET_BLEND_DESC blendingOpaque = D3D12_RENDER_TARGET_BLEND_DESC
{
FALSE,FALSE,
D3D12_BLEND_ONE, D3D12_BLEND_ZERO, D3D12_BLEND_OP_ADD,
D3D12_BLEND_ONE, D3D12_BLEND_ZERO, D3D12_BLEND_OP_ADD,
D3D12_LOGIC_OP_NOOP,
D3D12_COLOR_WRITE_ENABLE_ALL,
};
D3D12_RENDER_TARGET_BLEND_DESC blendingBlend = D3D12_RENDER_TARGET_BLEND_DESC
{
TRUE,FALSE,
D3D12_BLEND_SRC_ALPHA, D3D12_BLEND_INV_SRC_ALPHA, D3D12_BLEND_OP_ADD,
D3D12_BLEND_ONE, D3D12_BLEND_ZERO, D3D12_BLEND_OP_ADD,
D3D12_LOGIC_OP_NOOP,
D3D12_COLOR_WRITE_ENABLE_ALL,
};
// Create a PSO description
//
if (!pBlobShaderVert || !pBlobShaderPixel)
{
throw 1;
}
D3D12_GRAPHICS_PIPELINE_STATE_DESC descPso = {};
descPso.InputLayout = { layout.data(), (UINT)layout.size() };
descPso.pRootSignature = pPrimitive->m_RootSignature.Get();
descPso.VS = { reinterpret_cast<BYTE*>(pBlobShaderVert->GetBufferPointer()), pBlobShaderVert->GetBufferSize() };
descPso.PS = { reinterpret_cast<BYTE*>(pBlobShaderPixel->GetBufferPointer()), pBlobShaderPixel->GetBufferSize() };
descPso.RasterizerState = CD3DX12_RASTERIZER_DESC(D3D12_DEFAULT);
descPso.RasterizerState.CullMode = D3D12_CULL_MODE_FRONT;
// Decide on default view based on attributes available
if (m_pGLTFData)
{
if(m_pGLTFData->isBinFile)
descPso.RasterizerState.FillMode = D3D12_FILL_MODE_WIREFRAME;
else {
if (Has_Normals)
{
descPso.RasterizerState.FillMode = D3D12_FILL_MODE_SOLID;
}
else
descPso.RasterizerState.FillMode = D3D12_FILL_MODE_WIREFRAME;
}
}
else
{
if (Has_Normals)
{
descPso.RasterizerState.FillMode = D3D12_FILL_MODE_SOLID;
}
else
descPso.RasterizerState.FillMode = D3D12_FILL_MODE_WIREFRAME;
}
descPso.BlendState = CD3DX12_BLEND_DESC(D3D12_DEFAULT);
descPso.BlendState.IndependentBlendEnable = TRUE;
descPso.BlendState.RenderTarget[0] = blendingBlend;
descPso.DepthStencilState = CD3DX12_DEPTH_STENCIL_DESC(D3D12_DEFAULT);
descPso.DepthStencilState.DepthFunc = D3D12_COMPARISON_FUNC_LESS;
descPso.SampleMask = UINT_MAX;
descPso.PrimitiveTopologyType = D3D12_PRIMITIVE_TOPOLOGY_TYPE_TRIANGLE;
descPso.NumRenderTargets = 1;
descPso.RTVFormats[0] = DXGI_FORMAT_R16G16B16A16_UNORM;
descPso.DSVFormat = DXGI_FORMAT_D32_FLOAT;
descPso.SampleDesc.Count = 4;
descPso.NodeMask = node;
descPso.Flags = D3D12_PIPELINE_STATE_FLAG_NONE;
ThrowIfFailed(
pDevice->CreateGraphicsPipelineState(&descPso, IID_PPV_ARGS(&pPrimitive->m_PipelineRender))
);
// create samplers if not initialized (this should happen once)
if (m_sampler.GetSize()==0)
{
m_pResourceViewHeaps->AllocSamplerDescriptor(5, &m_sampler);
//for pbr materials
D3D12_SAMPLER_DESC SamplerDesc;
ZeroMemory(&SamplerDesc, sizeof(SamplerDesc));
SamplerDesc.Filter = D3D12_FILTER_MIN_MAG_LINEAR_MIP_POINT;
SamplerDesc.AddressU = D3D12_TEXTURE_ADDRESS_MODE_WRAP;
SamplerDesc.AddressV = D3D12_TEXTURE_ADDRESS_MODE_WRAP;
SamplerDesc.AddressW = D3D12_TEXTURE_ADDRESS_MODE_WRAP;
SamplerDesc.BorderColor[0] = 0.0f;
SamplerDesc.BorderColor[1] = 0.0f;
SamplerDesc.BorderColor[2] = 0.0f;
SamplerDesc.BorderColor[3] = 0.0f;
SamplerDesc.MinLOD = 0.0f;
SamplerDesc.MaxLOD = D3D12_FLOAT32_MAX;
SamplerDesc.MipLODBias = 0;
SamplerDesc.ComparisonFunc = D3D12_COMPARISON_FUNC_ALWAYS;
SamplerDesc.MaxAnisotropy = 1;
pDevice->CreateSampler(&SamplerDesc, m_sampler.GetCPU(0));
// diffuse env map sampler
ZeroMemory(&SamplerDesc, sizeof(SamplerDesc));
SamplerDesc.Filter = D3D12_FILTER_MIN_MAG_LINEAR_MIP_POINT;
SamplerDesc.AddressU = D3D12_TEXTURE_ADDRESS_MODE_CLAMP;
SamplerDesc.AddressV = D3D12_TEXTURE_ADDRESS_MODE_CLAMP;
SamplerDesc.AddressW = D3D12_TEXTURE_ADDRESS_MODE_WRAP;
SamplerDesc.BorderColor[0] = 0.0f;
SamplerDesc.BorderColor[1] = 0.0f;
SamplerDesc.BorderColor[2] = 0.0f;
SamplerDesc.BorderColor[3] = 0.0f;
SamplerDesc.MinLOD = 0.0f;
SamplerDesc.MaxLOD = D3D12_FLOAT32_MAX;
SamplerDesc.MipLODBias = 0;
SamplerDesc.ComparisonFunc = D3D12_COMPARISON_FUNC_ALWAYS;
SamplerDesc.MaxAnisotropy = 1;
pDevice->CreateSampler(&SamplerDesc, m_sampler.GetCPU(1));
// specular env map sampler
ZeroMemory(&SamplerDesc, sizeof(SamplerDesc));
SamplerDesc.Filter = D3D12_FILTER_MIN_MAG_MIP_LINEAR;
SamplerDesc.AddressU = D3D12_TEXTURE_ADDRESS_MODE_CLAMP;
SamplerDesc.AddressV = D3D12_TEXTURE_ADDRESS_MODE_CLAMP;
SamplerDesc.AddressW = D3D12_TEXTURE_ADDRESS_MODE_WRAP;
SamplerDesc.BorderColor[0] = 0.0f;
SamplerDesc.BorderColor[1] = 0.0f;
SamplerDesc.BorderColor[2] = 0.0f;
SamplerDesc.BorderColor[3] = 0.0f;
SamplerDesc.MinLOD = 0.0f;
SamplerDesc.MaxLOD = D3D12_FLOAT32_MAX;
SamplerDesc.MipLODBias = 0;
SamplerDesc.ComparisonFunc = D3D12_COMPARISON_FUNC_ALWAYS;
SamplerDesc.MaxAnisotropy = 1;
pDevice->CreateSampler(&SamplerDesc, m_sampler.GetCPU(2));
// specular BRDF lut sampler
ZeroMemory(&SamplerDesc, sizeof(SamplerDesc));
SamplerDesc.Filter = D3D12_FILTER_MIN_MAG_LINEAR_MIP_POINT;
SamplerDesc.AddressU = D3D12_TEXTURE_ADDRESS_MODE_CLAMP;
SamplerDesc.AddressV = D3D12_TEXTURE_ADDRESS_MODE_CLAMP;
SamplerDesc.AddressW = D3D12_TEXTURE_ADDRESS_MODE_WRAP;
SamplerDesc.BorderColor[0] = 0.0f;
SamplerDesc.BorderColor[1] = 0.0f;
SamplerDesc.BorderColor[2] = 0.0f;
SamplerDesc.BorderColor[3] = 0.0f;
SamplerDesc.MinLOD = 0.0f;
SamplerDesc.MaxLOD = D3D12_FLOAT32_MAX;
SamplerDesc.MipLODBias = 0;
SamplerDesc.ComparisonFunc = D3D12_COMPARISON_FUNC_ALWAYS;
SamplerDesc.MaxAnisotropy = 1;
pDevice->CreateSampler(&SamplerDesc, m_sampler.GetCPU(3));
// specular BRDF lut sampler
D3D12_SAMPLER_DESC samplerShadow = {
D3D12_FILTER_COMPARISON_MIN_MAG_LINEAR_MIP_POINT,
D3D12_TEXTURE_ADDRESS_MODE_CLAMP,
D3D12_TEXTURE_ADDRESS_MODE_CLAMP,
D3D12_TEXTURE_ADDRESS_MODE_CLAMP,
0.0f,
1u,
D3D12_COMPARISON_FUNC_LESS_EQUAL,
{ 0.0f, 0.0f, 0.0f, 0.0f },
0.0f,
D3D12_FLOAT32_MAX
};
pDevice->CreateSampler(&samplerShadow, m_sampler.GetCPU(4));
}
pPrimitive->m_sampler = &m_sampler;
}
void CrossNodeResources::LoadAssets()
{
// Create the root signatures.
// Root signatures may be shared across GPU nodes.
{
D3D12_FEATURE_DATA_ROOT_SIGNATURE featureData = {};
// This is the highest version the sample supports. If CheckFeatureSupport succeeds, the HighestVersion returned will not be greater than this.
featureData.HighestVersion = D3D_ROOT_SIGNATURE_VERSION_1_1;
if (FAILED(m_device->CheckFeatureSupport(D3D12_FEATURE_ROOT_SIGNATURE, &featureData, sizeof(featureData))))
{
featureData.HighestVersion = D3D_ROOT_SIGNATURE_VERSION_1_0;
}
// Create a root signature for rendering the triangle scene.
{
CD3DX12_DESCRIPTOR_RANGE1 sceneRanges[1];
sceneRanges[0].Init(D3D12_DESCRIPTOR_RANGE_TYPE_CBV, 1, 0, 0, D3D12_DESCRIPTOR_RANGE_FLAG_DATA_STATIC);
CD3DX12_ROOT_PARAMETER1 sceneRootParameters[2];
sceneRootParameters[0].InitAsDescriptorTable(1, &sceneRanges[0], D3D12_SHADER_VISIBILITY_VERTEX);
sceneRootParameters[1].InitAsConstants(1, 1, 0, D3D12_SHADER_VISIBILITY_VERTEX);
CD3DX12_VERSIONED_ROOT_SIGNATURE_DESC sceneRootSignatureDesc;
sceneRootSignatureDesc.Init_1_1(_countof(sceneRootParameters), sceneRootParameters, 0, nullptr, D3D12_ROOT_SIGNATURE_FLAG_ALLOW_INPUT_ASSEMBLER_INPUT_LAYOUT);
ComPtr<ID3DBlob> signature;
ComPtr<ID3DBlob> error;
ThrowIfFailed(D3DX12SerializeVersionedRootSignature(&sceneRootSignatureDesc, featureData.HighestVersion, &signature, &error));
ThrowIfFailed(m_device->CreateRootSignature(Settings::SharedNodeMask, signature->GetBufferPointer(), signature->GetBufferSize(), IID_PPV_ARGS(&m_sceneRootSignature)));
}
// Create a root signature for the post-process pass.
{
CD3DX12_DESCRIPTOR_RANGE1 postRanges[2];
postRanges[0].Init(D3D12_DESCRIPTOR_RANGE_TYPE_SRV, Settings::SceneHistoryCount, 0, 0, D3D12_DESCRIPTOR_RANGE_FLAG_DATA_STATIC_WHILE_SET_AT_EXECUTE);
postRanges[1].Init(D3D12_DESCRIPTOR_RANGE_TYPE_SAMPLER, 1, 0);
CD3DX12_ROOT_PARAMETER1 postRootParameters[3];
postRootParameters[0].InitAsDescriptorTable(1, &postRanges[0], D3D12_SHADER_VISIBILITY_PIXEL);
postRootParameters[1].InitAsDescriptorTable(1, &postRanges[1], D3D12_SHADER_VISIBILITY_PIXEL);
postRootParameters[2].InitAsConstants(2, 0, 0, D3D12_SHADER_VISIBILITY_PIXEL);
CD3DX12_VERSIONED_ROOT_SIGNATURE_DESC postRootSignatureDesc;
postRootSignatureDesc.Init_1_1(_countof(postRootParameters), postRootParameters, 0, nullptr, D3D12_ROOT_SIGNATURE_FLAG_ALLOW_INPUT_ASSEMBLER_INPUT_LAYOUT);
ComPtr<ID3DBlob> signature;
ComPtr<ID3DBlob> error;
ThrowIfFailed(D3DX12SerializeVersionedRootSignature(&postRootSignatureDesc, featureData.HighestVersion, &signature, &error));
ThrowIfFailed(m_device->CreateRootSignature(Settings::SharedNodeMask, signature->GetBufferPointer(), signature->GetBufferSize(), IID_PPV_ARGS(&m_postRootSignature)));
}
}
// Create the pipeline state, which includes compiling and loading shaders.
// Pipeline states may be shared across GPU nodes.
{
// Define the vertex input layout for the triangle scene.
D3D12_INPUT_ELEMENT_DESC inputElementDescs[] =
{
{ "POSITION", 0, DXGI_FORMAT_R32G32B32_FLOAT, 0, 0, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
};
// Describe and create the graphics pipeline state objects (PSO).
D3D12_GRAPHICS_PIPELINE_STATE_DESC psoDesc = {};
psoDesc.InputLayout = { inputElementDescs, _countof(inputElementDescs) };
psoDesc.pRootSignature = m_sceneRootSignature.Get();
psoDesc.VS = { g_SceneVS, sizeof(g_SceneVS) };
psoDesc.PS = { g_ScenePS, sizeof(g_ScenePS) };
psoDesc.RasterizerState = CD3DX12_RASTERIZER_DESC(D3D12_DEFAULT);
psoDesc.BlendState = CD3DX12_BLEND_DESC(D3D12_DEFAULT);
psoDesc.DepthStencilState = CD3DX12_DEPTH_STENCIL_DESC(D3D12_DEFAULT);
psoDesc.SampleMask = UINT_MAX;
psoDesc.PrimitiveTopologyType = D3D12_PRIMITIVE_TOPOLOGY_TYPE_TRIANGLE;
psoDesc.NumRenderTargets = 1;
psoDesc.RTVFormats[0] = DXGI_FORMAT_R8G8B8A8_UNORM;
psoDesc.DSVFormat = DXGI_FORMAT_D32_FLOAT;
psoDesc.SampleDesc.Count = 1;
psoDesc.NodeMask = Settings::SharedNodeMask;
ThrowIfFailed(m_device->CreateGraphicsPipelineState(&psoDesc, IID_PPV_ARGS(&m_scenePipelineState)));
// Define the vertex input layout for the post-process fullscreen quad.
D3D12_INPUT_ELEMENT_DESC postInputElementDescs[] =
{
{ "POSITION", 0, DXGI_FORMAT_R32G32B32_FLOAT, 0, 0, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
{ "TEXCOORD", 0, DXGI_FORMAT_R32G32_FLOAT, 0, D3D12_APPEND_ALIGNED_ELEMENT, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
};
// Describe and create the PSO for the post-process pass.
D3D12_GRAPHICS_PIPELINE_STATE_DESC postPsoDesc = {};
postPsoDesc.InputLayout = { postInputElementDescs, _countof(postInputElementDescs) };
postPsoDesc.pRootSignature = m_postRootSignature.Get();
postPsoDesc.VS = { g_PostVS, sizeof(g_PostVS) };
postPsoDesc.PS = { g_PostPS, sizeof(g_PostPS) };
postPsoDesc.RasterizerState = CD3DX12_RASTERIZER_DESC(D3D12_DEFAULT);
postPsoDesc.BlendState = CD3DX12_BLEND_DESC(D3D12_DEFAULT);
postPsoDesc.DepthStencilState.DepthEnable = FALSE;
postPsoDesc.DepthStencilState.StencilEnable = FALSE;
postPsoDesc.SampleMask = UINT_MAX;
postPsoDesc.PrimitiveTopologyType = D3D12_PRIMITIVE_TOPOLOGY_TYPE_TRIANGLE;
postPsoDesc.NumRenderTargets = 1;
postPsoDesc.RTVFormats[0] = DXGI_FORMAT_R8G8B8A8_UNORM;
postPsoDesc.SampleDesc.Count = 1;
postPsoDesc.NodeMask = Settings::SharedNodeMask;
ThrowIfFailed(m_device->CreateGraphicsPipelineState(&postPsoDesc, IID_PPV_ARGS(&m_postPipelineState)));
}
// Create and map the constant buffers.
// Upload heaps live in system memory and can be made visible to all GPU nodes.
{
const UINT constantBufferDataSize = Settings::TriangleCount * Settings::SceneConstantBufferFrames * sizeof(SceneConstantBuffer);
D3D12_HEAP_PROPERTIES uploadHeapProps = CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD);
uploadHeapProps.VisibleNodeMask = Settings::SharedNodeMask;
ThrowIfFailed(m_device->CreateCommittedResource(
&uploadHeapProps,
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(constantBufferDataSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&m_sceneConstantBuffer)));
// Map the constant buffers. We don't unmap this until the app closes.
// Keeping things mapped for the lifetime of the resource is okay.
ThrowIfFailed(m_sceneConstantBuffer->Map(0, nullptr, reinterpret_cast<void**>(&m_mappedConstantBuffer)));
ZeroMemory(m_mappedConstantBuffer, constantBufferDataSize);
}
}
// Load the sample assets.
void D3D12Bundles::LoadAssets()
{
// These upload heaps are only needed during loading.
ComPtr<ID3D12Resource> vertexBufferUploadHeap;
ComPtr<ID3D12Resource> indexBufferUploadHeap;
ComPtr<ID3D12Resource> textureUploadHeap;
// Create the root signature.
{
CD3DX12_DESCRIPTOR_RANGE ranges[3];
ranges[0].Init(D3D12_DESCRIPTOR_RANGE_TYPE_SRV, 1, 0);
ranges[1].Init(D3D12_DESCRIPTOR_RANGE_TYPE_SAMPLER, 1, 0);
ranges[2].Init(D3D12_DESCRIPTOR_RANGE_TYPE_CBV, 1, 0);
CD3DX12_ROOT_PARAMETER rootParameters[3];
rootParameters[0].InitAsDescriptorTable(1, &ranges[0], D3D12_SHADER_VISIBILITY_PIXEL);
rootParameters[1].InitAsDescriptorTable(1, &ranges[1], D3D12_SHADER_VISIBILITY_PIXEL);
rootParameters[2].InitAsDescriptorTable(1, &ranges[2], D3D12_SHADER_VISIBILITY_ALL);
CD3DX12_ROOT_SIGNATURE_DESC rootSignatureDesc;
rootSignatureDesc.Init(_countof(rootParameters), rootParameters, 0, nullptr, D3D12_ROOT_SIGNATURE_FLAG_ALLOW_INPUT_ASSEMBLER_INPUT_LAYOUT);
ComPtr<ID3DBlob> signature;
ComPtr<ID3DBlob> error;
ThrowIfFailed(D3D12SerializeRootSignature(&rootSignatureDesc, D3D_ROOT_SIGNATURE_VERSION_1, &signature, &error));
ThrowIfFailed(m_device->CreateRootSignature(0, signature->GetBufferPointer(), signature->GetBufferSize(), IID_PPV_ARGS(&m_rootSignature)));
}
// Create the pipeline state, which includes loading shaders.
{
UINT8* pVertexShaderData;
UINT8* pPixelShaderData1;
UINT8* pPixelShaderData2;
UINT vertexShaderDataLength;
UINT pixelShaderDataLength1;
UINT pixelShaderDataLength2;
// Load pre-compiled shaders.
ThrowIfFailed(ReadDataFromFile(GetAssetFullPath(L"shader_mesh_simple_vert.cso").c_str(), &pVertexShaderData, &vertexShaderDataLength));
ThrowIfFailed(ReadDataFromFile(GetAssetFullPath(L"shader_mesh_simple_pixel.cso").c_str(), &pPixelShaderData1, &pixelShaderDataLength1));
ThrowIfFailed(ReadDataFromFile(GetAssetFullPath(L"shader_mesh_alt_pixel.cso").c_str(), &pPixelShaderData2, &pixelShaderDataLength2));
CD3DX12_RASTERIZER_DESC rasterizerStateDesc(D3D12_DEFAULT);
rasterizerStateDesc.CullMode = D3D12_CULL_MODE_NONE;
// Describe and create the graphics pipeline state objects (PSO).
D3D12_GRAPHICS_PIPELINE_STATE_DESC psoDesc = {};
psoDesc.InputLayout = { SampleAssets::StandardVertexDescription, SampleAssets::StandardVertexDescriptionNumElements };
psoDesc.pRootSignature = m_rootSignature.Get();
psoDesc.VS = { pVertexShaderData, vertexShaderDataLength };
psoDesc.PS = { pPixelShaderData1, pixelShaderDataLength1 };
psoDesc.RasterizerState = rasterizerStateDesc;
psoDesc.BlendState = CD3DX12_BLEND_DESC(D3D12_DEFAULT);
psoDesc.DepthStencilState = CD3DX12_DEPTH_STENCIL_DESC(D3D12_DEFAULT);
psoDesc.SampleMask = UINT_MAX;
psoDesc.PrimitiveTopologyType = D3D12_PRIMITIVE_TOPOLOGY_TYPE_TRIANGLE;
psoDesc.NumRenderTargets = 1;
psoDesc.RTVFormats[0] = DXGI_FORMAT_R8G8B8A8_UNORM;
psoDesc.DSVFormat = DXGI_FORMAT_D32_FLOAT;
psoDesc.SampleDesc.Count = 1;
ThrowIfFailed(m_device->CreateGraphicsPipelineState(&psoDesc, IID_PPV_ARGS(&m_pipelineState1)));
// Modify the description to use an alternate pixel shader and create
// a second PSO.
psoDesc.PS = { pPixelShaderData2, pixelShaderDataLength2 };
ThrowIfFailed(m_device->CreateGraphicsPipelineState(&psoDesc, IID_PPV_ARGS(&m_pipelineState2)));
delete pVertexShaderData;
delete pPixelShaderData1;
delete pPixelShaderData2;
}
ThrowIfFailed(m_device->CreateCommandList(0, D3D12_COMMAND_LIST_TYPE_DIRECT, m_commandAllocator.Get(), nullptr, IID_PPV_ARGS(&m_commandList)));
// Create render target views (RTVs).
CD3DX12_CPU_DESCRIPTOR_HANDLE rtvHandle(m_rtvHeap->GetCPUDescriptorHandleForHeapStart());
for (UINT i = 0; i < FrameCount; i++)
{
ThrowIfFailed(m_swapChain->GetBuffer(i, IID_PPV_ARGS(&m_renderTargets[i])));
m_device->CreateRenderTargetView(m_renderTargets[i].Get(), nullptr, rtvHandle);
rtvHandle.Offset(1, m_rtvDescriptorSize);
}
// Read in mesh data for vertex/index buffers.
UINT8* pMeshData;
UINT meshDataLength;
ThrowIfFailed(ReadDataFromFile(GetAssetFullPath(SampleAssets::DataFileName).c_str(), &pMeshData, &meshDataLength));
// Create the vertex buffer.
{
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(SampleAssets::VertexDataSize),
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_vertexBuffer)));
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(SampleAssets::VertexDataSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&vertexBufferUploadHeap)));
// Copy data to the intermediate upload heap and then schedule a copy
// from the upload heap to the vertex buffer.
D3D12_SUBRESOURCE_DATA vertexData = {};
vertexData.pData = pMeshData + SampleAssets::VertexDataOffset;
vertexData.RowPitch = SampleAssets::VertexDataSize;
vertexData.SlicePitch = vertexData.RowPitch;
UpdateSubresources<1>(m_commandList.Get(), m_vertexBuffer.Get(), vertexBufferUploadHeap.Get(), 0, 0, 1, &vertexData);
m_commandList->ResourceBarrier(1, &CD3DX12_RESOURCE_BARRIER::Transition(m_vertexBuffer.Get(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_VERTEX_AND_CONSTANT_BUFFER));
// Initialize the vertex buffer view.
m_vertexBufferView.BufferLocation = m_vertexBuffer->GetGPUVirtualAddress();
m_vertexBufferView.StrideInBytes = SampleAssets::StandardVertexStride;
m_vertexBufferView.SizeInBytes = SampleAssets::VertexDataSize;
}
// Create the index buffer.
{
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(SampleAssets::IndexDataSize),
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_indexBuffer)));
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(SampleAssets::IndexDataSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&indexBufferUploadHeap)));
// Copy data to the intermediate upload heap and then schedule a copy
// from the upload heap to the index buffer.
D3D12_SUBRESOURCE_DATA indexData = {};
indexData.pData = pMeshData + SampleAssets::IndexDataOffset;
indexData.RowPitch = SampleAssets::IndexDataSize;
indexData.SlicePitch = indexData.RowPitch;
UpdateSubresources<1>(m_commandList.Get(), m_indexBuffer.Get(), indexBufferUploadHeap.Get(), 0, 0, 1, &indexData);
m_commandList->ResourceBarrier(1, &CD3DX12_RESOURCE_BARRIER::Transition(m_indexBuffer.Get(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_INDEX_BUFFER));
// Describe the index buffer view.
m_indexBufferView.BufferLocation = m_indexBuffer->GetGPUVirtualAddress();
m_indexBufferView.Format = SampleAssets::StandardIndexFormat;
m_indexBufferView.SizeInBytes = SampleAssets::IndexDataSize;
m_numIndices = SampleAssets::IndexDataSize / 4; // R32_UINT (SampleAssets::StandardIndexFormat) = 4 bytes each.
}
// Create the texture and sampler.
{
// Describe and create a Texture2D.
D3D12_RESOURCE_DESC textureDesc = {};
textureDesc.MipLevels = SampleAssets::Textures[0].MipLevels;
textureDesc.Format = SampleAssets::Textures[0].Format;
textureDesc.Width = SampleAssets::Textures[0].Width;
textureDesc.Height = SampleAssets::Textures[0].Height;
textureDesc.Flags = D3D12_RESOURCE_FLAG_NONE;
textureDesc.DepthOrArraySize = 1;
textureDesc.SampleDesc.Count = 1;
textureDesc.SampleDesc.Quality = 0;
textureDesc.Dimension = D3D12_RESOURCE_DIMENSION_TEXTURE2D;
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&textureDesc,
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_texture)));
const UINT subresourceCount = textureDesc.DepthOrArraySize * textureDesc.MipLevels;
const UINT64 uploadBufferSize = GetRequiredIntermediateSize(m_texture.Get(), 0, subresourceCount);
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(uploadBufferSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&textureUploadHeap)));
// Copy data to the intermediate upload heap and then schedule a copy
// from the upload heap to the Texture2D.
D3D12_SUBRESOURCE_DATA textureData = {};
textureData.pData = pMeshData + SampleAssets::Textures[0].Data[0].Offset;
textureData.RowPitch = SampleAssets::Textures[0].Data[0].Pitch;
textureData.SlicePitch = SampleAssets::Textures[0].Data[0].Size;
UpdateSubresources(m_commandList.Get(), m_texture.Get(), textureUploadHeap.Get(), 0, 0, subresourceCount, &textureData);
m_commandList->ResourceBarrier(1, &CD3DX12_RESOURCE_BARRIER::Transition(m_texture.Get(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_PIXEL_SHADER_RESOURCE));
// Describe and create a sampler.
D3D12_SAMPLER_DESC samplerDesc = {};
samplerDesc.Filter = D3D12_FILTER_MIN_MAG_MIP_LINEAR;
samplerDesc.AddressU = D3D12_TEXTURE_ADDRESS_MODE_WRAP;
samplerDesc.AddressV = D3D12_TEXTURE_ADDRESS_MODE_WRAP;
samplerDesc.AddressW = D3D12_TEXTURE_ADDRESS_MODE_WRAP;
samplerDesc.MinLOD = 0;
samplerDesc.MaxLOD = D3D12_FLOAT32_MAX;
samplerDesc.MipLODBias = 0.0f;
samplerDesc.MaxAnisotropy = 1;
samplerDesc.ComparisonFunc = D3D12_COMPARISON_FUNC_ALWAYS;
m_device->CreateSampler(&samplerDesc, m_samplerHeap->GetCPUDescriptorHandleForHeapStart());
// Describe and create a SRV for the texture.
D3D12_SHADER_RESOURCE_VIEW_DESC srvDesc = {};
srvDesc.Shader4ComponentMapping = D3D12_DEFAULT_SHADER_4_COMPONENT_MAPPING;
srvDesc.Format = SampleAssets::Textures->Format;
srvDesc.ViewDimension = D3D12_SRV_DIMENSION_TEXTURE2D;
srvDesc.Texture2D.MipLevels = 1;
m_device->CreateShaderResourceView(m_texture.Get(), &srvDesc, m_cbvSrvHeap->GetCPUDescriptorHandleForHeapStart());
}
delete pMeshData;
// Create the depth stencil view.
{
D3D12_DEPTH_STENCIL_VIEW_DESC depthStencilDesc = {};
depthStencilDesc.Format = DXGI_FORMAT_D32_FLOAT;
depthStencilDesc.ViewDimension = D3D12_DSV_DIMENSION_TEXTURE2D;
depthStencilDesc.Flags = D3D12_DSV_FLAG_NONE;
D3D12_CLEAR_VALUE depthOptimizedClearValue = {};
depthOptimizedClearValue.Format = DXGI_FORMAT_D32_FLOAT;
depthOptimizedClearValue.DepthStencil.Depth = 1.0f;
depthOptimizedClearValue.DepthStencil.Stencil = 0;
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Tex2D(DXGI_FORMAT_D32_FLOAT, m_width, m_height, 1, 0, 1, 0, D3D12_RESOURCE_FLAG_ALLOW_DEPTH_STENCIL),
D3D12_RESOURCE_STATE_DEPTH_WRITE,
&depthOptimizedClearValue,
IID_PPV_ARGS(&m_depthStencil)
));
m_device->CreateDepthStencilView(m_depthStencil.Get(), &depthStencilDesc, m_dsvHeap->GetCPUDescriptorHandleForHeapStart());
}
// Close the command list and execute it to begin the initial GPU setup.
ThrowIfFailed(m_commandList->Close());
ID3D12CommandList* ppCommandLists[] = { m_commandList.Get() };
m_commandQueue->ExecuteCommandLists(_countof(ppCommandLists), ppCommandLists);
CreateFrameResources();
// Create synchronization objects and wait until assets have been uploaded to the GPU.
{
ThrowIfFailed(m_device->CreateFence(m_fenceValue, D3D12_FENCE_FLAG_NONE, IID_PPV_ARGS(&m_fence)));
m_fenceValue++;
// Create an event handle to use for frame synchronization.
m_fenceEvent = CreateEvent(nullptr, FALSE, FALSE, nullptr);
if (m_fenceEvent == nullptr)
{
ThrowIfFailed(HRESULT_FROM_WIN32(GetLastError()));
}
// Wait for the command list to execute; we are reusing the same command
// list in our main loop but for now, we just want to wait for setup to
// complete before continuing.
// Signal and increment the fence value.
const UINT64 fenceToWaitFor = m_fenceValue;
ThrowIfFailed(m_commandQueue->Signal(m_fence.Get(), fenceToWaitFor));
m_fenceValue++;
// Wait until the fence is completed.
ThrowIfFailed(m_fence->SetEventOnCompletion(fenceToWaitFor, m_fenceEvent));
WaitForSingleObject(m_fenceEvent, INFINITE);
}
}
// Load the sample assets.
void D3D12ExecuteIndirect::LoadAssets()
{
// Create the root signatures.
{
CD3DX12_ROOT_PARAMETER rootParameters[GraphicsRootParametersCount];
rootParameters[Cbv].InitAsConstantBufferView(0, 0, D3D12_SHADER_VISIBILITY_VERTEX);
CD3DX12_ROOT_SIGNATURE_DESC rootSignatureDesc;
rootSignatureDesc.Init(_countof(rootParameters), rootParameters, 0, nullptr, D3D12_ROOT_SIGNATURE_FLAG_ALLOW_INPUT_ASSEMBLER_INPUT_LAYOUT);
ComPtr<ID3DBlob> signature;
ComPtr<ID3DBlob> error;
ThrowIfFailed(D3D12SerializeRootSignature(&rootSignatureDesc, D3D_ROOT_SIGNATURE_VERSION_1, &signature, &error));
ThrowIfFailed(m_device->CreateRootSignature(0, signature->GetBufferPointer(), signature->GetBufferSize(), IID_PPV_ARGS(&m_rootSignature)));
// Create compute signature.
CD3DX12_DESCRIPTOR_RANGE ranges[2];
ranges[0].Init(D3D12_DESCRIPTOR_RANGE_TYPE_SRV, 2, 0);
ranges[1].Init(D3D12_DESCRIPTOR_RANGE_TYPE_UAV, 1, 0);
CD3DX12_ROOT_PARAMETER computeRootParameters[ComputeRootParametersCount];
computeRootParameters[SrvUavTable].InitAsDescriptorTable(2, ranges);
computeRootParameters[RootConstants].InitAsConstants(4, 0);
CD3DX12_ROOT_SIGNATURE_DESC computeRootSignatureDesc;
computeRootSignatureDesc.Init(_countof(computeRootParameters), computeRootParameters);
ThrowIfFailed(D3D12SerializeRootSignature(&computeRootSignatureDesc, D3D_ROOT_SIGNATURE_VERSION_1, &signature, &error));
ThrowIfFailed(m_device->CreateRootSignature(0, signature->GetBufferPointer(), signature->GetBufferSize(), IID_PPV_ARGS(&m_computeRootSignature)));
}
// Create the pipeline state, which includes compiling and loading shaders.
{
ComPtr<ID3DBlob> vertexShader;
ComPtr<ID3DBlob> pixelShader;
ComPtr<ID3DBlob> computeShader;
ComPtr<ID3DBlob> error;
#if defined(_DEBUG)
// Enable better shader debugging with the graphics debugging tools.
UINT compileFlags = D3DCOMPILE_DEBUG | D3DCOMPILE_SKIP_OPTIMIZATION;
#else
UINT compileFlags = 0;
#endif
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"shaders.hlsl").c_str(), nullptr, nullptr, "VSMain", "vs_5_0", compileFlags, 0, &vertexShader, &error));
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"shaders.hlsl").c_str(), nullptr, nullptr, "PSMain", "ps_5_0", compileFlags, 0, &pixelShader, &error));
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"compute.hlsl").c_str(), nullptr, nullptr, "CSMain", "cs_5_0", compileFlags, 0, &computeShader, &error));
// Define the vertex input layout.
D3D12_INPUT_ELEMENT_DESC inputElementDescs[] =
{
{ "POSITION", 0, DXGI_FORMAT_R32G32B32_FLOAT, 0, 0, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
};
// Describe and create the graphics pipeline state objects (PSO).
D3D12_GRAPHICS_PIPELINE_STATE_DESC psoDesc = {};
psoDesc.InputLayout = { inputElementDescs, _countof(inputElementDescs) };
psoDesc.pRootSignature = m_rootSignature.Get();
psoDesc.VS = { reinterpret_cast<UINT8*>(vertexShader->GetBufferPointer()), vertexShader->GetBufferSize() };
psoDesc.PS = { reinterpret_cast<UINT8*>(pixelShader->GetBufferPointer()), pixelShader->GetBufferSize() };
psoDesc.RasterizerState = CD3DX12_RASTERIZER_DESC(D3D12_DEFAULT);
psoDesc.BlendState = CD3DX12_BLEND_DESC(D3D12_DEFAULT);
psoDesc.DepthStencilState = CD3DX12_DEPTH_STENCIL_DESC(D3D12_DEFAULT);
psoDesc.SampleMask = UINT_MAX;
psoDesc.PrimitiveTopologyType = D3D12_PRIMITIVE_TOPOLOGY_TYPE_TRIANGLE;
psoDesc.NumRenderTargets = 1;
psoDesc.RTVFormats[0] = DXGI_FORMAT_R8G8B8A8_UNORM;
psoDesc.DSVFormat = DXGI_FORMAT_D32_FLOAT;
psoDesc.SampleDesc.Count = 1;
ThrowIfFailed(m_device->CreateGraphicsPipelineState(&psoDesc, IID_PPV_ARGS(&m_pipelineState)));
// Describe and create the compute pipeline state object (PSO).
D3D12_COMPUTE_PIPELINE_STATE_DESC computePsoDesc = {};
computePsoDesc.pRootSignature = m_computeRootSignature.Get();
computePsoDesc.CS = { reinterpret_cast<UINT8*>(computeShader->GetBufferPointer()), computeShader->GetBufferSize() };
ThrowIfFailed(m_device->CreateComputePipelineState(&computePsoDesc, IID_PPV_ARGS(&m_computeState)));
}
// Create the command list.
ThrowIfFailed(m_device->CreateCommandList(0, D3D12_COMMAND_LIST_TYPE_DIRECT, m_commandAllocators[m_frameIndex].Get(), m_pipelineState.Get(), IID_PPV_ARGS(&m_commandList)));
ThrowIfFailed(m_device->CreateCommandList(0, D3D12_COMMAND_LIST_TYPE_COMPUTE, m_computeCommandAllocators[m_frameIndex].Get(), m_computeState.Get(), IID_PPV_ARGS(&m_computeCommandList)));
ThrowIfFailed(m_computeCommandList->Close());
// Note: ComPtr's are CPU objects but these resources need to stay in scope until
// the command list that references them has finished executing on the GPU.
// We will flush the GPU at the end of this method to ensure the resources are not
// prematurely destroyed.
ComPtr<ID3D12Resource> vertexBufferUpload;
ComPtr<ID3D12Resource> commandBufferUpload;
// Create the vertex buffer.
{
// Define the geometry for a triangle.
Vertex triangleVertices[] =
{
{ { 0.0f, TriangleHalfWidth, TriangleDepth } },
{ { TriangleHalfWidth, -TriangleHalfWidth, TriangleDepth } },
{ { -TriangleHalfWidth, -TriangleHalfWidth, TriangleDepth } }
};
const UINT vertexBufferSize = sizeof(triangleVertices);
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(vertexBufferSize),
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_vertexBuffer)));
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(vertexBufferSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&vertexBufferUpload)));
// Copy data to the intermediate upload heap and then schedule a copy
// from the upload heap to the vertex buffer.
D3D12_SUBRESOURCE_DATA vertexData = {};
vertexData.pData = reinterpret_cast<UINT8*>(triangleVertices);
vertexData.RowPitch = vertexBufferSize;
vertexData.SlicePitch = vertexData.RowPitch;
UpdateSubresources<1>(m_commandList.Get(), m_vertexBuffer.Get(), vertexBufferUpload.Get(), 0, 0, 1, &vertexData);
m_commandList->ResourceBarrier(1, &CD3DX12_RESOURCE_BARRIER::Transition(m_vertexBuffer.Get(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_VERTEX_AND_CONSTANT_BUFFER));
// Initialize the vertex buffer view.
m_vertexBufferView.BufferLocation = m_vertexBuffer->GetGPUVirtualAddress();
m_vertexBufferView.StrideInBytes = sizeof(Vertex);
m_vertexBufferView.SizeInBytes = sizeof(triangleVertices);
}
// Create the depth stencil view.
{
D3D12_DEPTH_STENCIL_VIEW_DESC depthStencilDesc = {};
depthStencilDesc.Format = DXGI_FORMAT_D32_FLOAT;
depthStencilDesc.ViewDimension = D3D12_DSV_DIMENSION_TEXTURE2D;
depthStencilDesc.Flags = D3D12_DSV_FLAG_NONE;
D3D12_CLEAR_VALUE depthOptimizedClearValue = {};
depthOptimizedClearValue.Format = DXGI_FORMAT_D32_FLOAT;
depthOptimizedClearValue.DepthStencil.Depth = 1.0f;
depthOptimizedClearValue.DepthStencil.Stencil = 0;
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Tex2D(DXGI_FORMAT_D32_FLOAT, m_width, m_height, 1, 0, 1, 0, D3D12_RESOURCE_FLAG_ALLOW_DEPTH_STENCIL),
D3D12_RESOURCE_STATE_DEPTH_WRITE,
&depthOptimizedClearValue,
IID_PPV_ARGS(&m_depthStencil)
));
m_device->CreateDepthStencilView(m_depthStencil.Get(), &depthStencilDesc, m_dsvHeap->GetCPUDescriptorHandleForHeapStart());
}
// Create the constant buffers.
{
const UINT constantBufferDataSize = TriangleResourceCount * sizeof(ConstantBufferData);
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(constantBufferDataSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&m_constantBuffer)));
D3D12_CONSTANT_BUFFER_VIEW_DESC cbvDesc = {};
cbvDesc.SizeInBytes = sizeof(ConstantBufferData);
// Create constant buffer views to access the upload buffer.
for (UINT n = 0; n < TriangleCount; n++)
{
m_constantBufferData[n].velocity = XMFLOAT4(GetRandomFloat(0.01f, 0.02f), 0.0f, 0.0f, 0.0f);
m_constantBufferData[n].offset = XMFLOAT4(GetRandomFloat(-5.0f, -1.5f), GetRandomFloat(-1.0f, 1.0f), GetRandomFloat(0.0f, 2.0f), 0.0f);
m_constantBufferData[n].color = XMFLOAT4(GetRandomFloat(0.5f, 1.0f), GetRandomFloat(0.5f, 1.0f), GetRandomFloat(0.5f, 1.0f), 1.0f);
XMStoreFloat4x4(&m_constantBufferData[n].projection, XMMatrixTranspose(XMMatrixPerspectiveFovLH(XM_PIDIV4, m_aspectRatio, 0.01f, 20.0f)));
}
// Map the constant buffers. We don't unmap this until the app closes.
// Keeping things mapped for the lifetime of the resource is okay.
CD3DX12_RANGE readRange(0, 0); // We do not intend to read from this resource on the CPU.
ThrowIfFailed(m_constantBuffer->Map(0, &readRange, reinterpret_cast<void**>(&m_pCbvDataBegin)));
memcpy(m_pCbvDataBegin, &m_constantBufferData[0], TriangleCount * sizeof(ConstantBufferData));
// Create shader resource views (SRV) of the constant buffers for the
// compute shader to read from.
D3D12_SHADER_RESOURCE_VIEW_DESC srvDesc = {};
srvDesc.Format = DXGI_FORMAT_UNKNOWN;
srvDesc.ViewDimension = D3D12_SRV_DIMENSION_BUFFER;
srvDesc.Shader4ComponentMapping = D3D12_DEFAULT_SHADER_4_COMPONENT_MAPPING;
srvDesc.Buffer.NumElements = TriangleCount;
srvDesc.Buffer.StructureByteStride = sizeof(ConstantBufferData);
srvDesc.Buffer.Flags = D3D12_BUFFER_SRV_FLAG_NONE;
CD3DX12_CPU_DESCRIPTOR_HANDLE cbvSrvHandle(m_cbvSrvUavHeap->GetCPUDescriptorHandleForHeapStart(), CbvSrvOffset, m_cbvSrvUavDescriptorSize);
for (UINT frame = 0; frame < FrameCount; frame++)
{
srvDesc.Buffer.FirstElement = frame * TriangleCount;
m_device->CreateShaderResourceView(m_constantBuffer.Get(), &srvDesc, cbvSrvHandle);
cbvSrvHandle.Offset(CbvSrvUavDescriptorCountPerFrame, m_cbvSrvUavDescriptorSize);
}
}
// Create the command signature used for indirect drawing.
{
// Each command consists of a CBV update and a DrawInstanced call.
D3D12_INDIRECT_ARGUMENT_DESC argumentDescs[2] = {};
argumentDescs[0].Type = D3D12_INDIRECT_ARGUMENT_TYPE_CONSTANT_BUFFER_VIEW;
argumentDescs[0].ConstantBufferView.RootParameterIndex = Cbv;
argumentDescs[1].Type = D3D12_INDIRECT_ARGUMENT_TYPE_DRAW;
D3D12_COMMAND_SIGNATURE_DESC commandSignatureDesc = {};
commandSignatureDesc.pArgumentDescs = argumentDescs;
commandSignatureDesc.NumArgumentDescs = _countof(argumentDescs);
commandSignatureDesc.ByteStride = sizeof(IndirectCommand);
ThrowIfFailed(m_device->CreateCommandSignature(&commandSignatureDesc, m_rootSignature.Get(), IID_PPV_ARGS(&m_commandSignature)));
}
// Create the command buffers and UAVs to store the results of the compute work.
{
std::vector<IndirectCommand> commands;
commands.resize(TriangleResourceCount);
const UINT commandBufferSize = CommandBufferSizePerFrame * FrameCount;
D3D12_RESOURCE_DESC commandBufferDesc = CD3DX12_RESOURCE_DESC::Buffer(commandBufferSize);
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&commandBufferDesc,
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_commandBuffer)));
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(commandBufferSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&commandBufferUpload)));
D3D12_GPU_VIRTUAL_ADDRESS gpuAddress = m_constantBuffer->GetGPUVirtualAddress();
UINT commandIndex = 0;
for (UINT frame = 0; frame < FrameCount; frame++)
{
for (UINT n = 0; n < TriangleCount; n++)
{
commands[commandIndex].cbv = gpuAddress;
commands[commandIndex].drawArguments.VertexCountPerInstance = 3;
commands[commandIndex].drawArguments.InstanceCount = 1;
commands[commandIndex].drawArguments.StartVertexLocation = 0;
commands[commandIndex].drawArguments.StartInstanceLocation = 0;
commandIndex++;
gpuAddress += sizeof(ConstantBufferData);
}
}
// Copy data to the intermediate upload heap and then schedule a copy
// from the upload heap to the command buffer.
D3D12_SUBRESOURCE_DATA commandData = {};
commandData.pData = reinterpret_cast<UINT8*>(&commands[0]);
commandData.RowPitch = commandBufferSize;
commandData.SlicePitch = commandData.RowPitch;
UpdateSubresources<1>(m_commandList.Get(), m_commandBuffer.Get(), commandBufferUpload.Get(), 0, 0, 1, &commandData);
m_commandList->ResourceBarrier(1, &CD3DX12_RESOURCE_BARRIER::Transition(m_commandBuffer.Get(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_NON_PIXEL_SHADER_RESOURCE));
// Create SRVs for the command buffers.
D3D12_SHADER_RESOURCE_VIEW_DESC srvDesc = {};
srvDesc.Format = DXGI_FORMAT_UNKNOWN;
srvDesc.ViewDimension = D3D12_SRV_DIMENSION_BUFFER;
srvDesc.Shader4ComponentMapping = D3D12_DEFAULT_SHADER_4_COMPONENT_MAPPING;
srvDesc.Buffer.NumElements = TriangleCount;
srvDesc.Buffer.StructureByteStride = sizeof(IndirectCommand);
srvDesc.Buffer.Flags = D3D12_BUFFER_SRV_FLAG_NONE;
CD3DX12_CPU_DESCRIPTOR_HANDLE commandsHandle(m_cbvSrvUavHeap->GetCPUDescriptorHandleForHeapStart(), CommandsOffset, m_cbvSrvUavDescriptorSize);
for (UINT frame = 0; frame < FrameCount; frame++)
{
srvDesc.Buffer.FirstElement = frame * TriangleCount;
m_device->CreateShaderResourceView(m_commandBuffer.Get(), &srvDesc, commandsHandle);
commandsHandle.Offset(CbvSrvUavDescriptorCountPerFrame, m_cbvSrvUavDescriptorSize);
}
// Create the unordered access views (UAVs) that store the results of the compute work.
CD3DX12_CPU_DESCRIPTOR_HANDLE processedCommandsHandle(m_cbvSrvUavHeap->GetCPUDescriptorHandleForHeapStart(), ProcessedCommandsOffset, m_cbvSrvUavDescriptorSize);
for (UINT frame = 0; frame < FrameCount; frame++)
{
// Allocate a buffer large enough to hold all of the indirect commands
// for a single frame as well as a UAV counter.
commandBufferDesc = CD3DX12_RESOURCE_DESC::Buffer(CommandBufferSizePerFrame + sizeof(UINT), D3D12_RESOURCE_FLAG_ALLOW_UNORDERED_ACCESS);
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&commandBufferDesc,
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_processedCommandBuffers[frame])));
D3D12_UNORDERED_ACCESS_VIEW_DESC uavDesc = {};
uavDesc.Format = DXGI_FORMAT_UNKNOWN;
uavDesc.ViewDimension = D3D12_UAV_DIMENSION_BUFFER;
uavDesc.Buffer.FirstElement = 0;
uavDesc.Buffer.NumElements = TriangleCount;
uavDesc.Buffer.StructureByteStride = sizeof(IndirectCommand);
uavDesc.Buffer.CounterOffsetInBytes = CommandBufferSizePerFrame;
uavDesc.Buffer.Flags = D3D12_BUFFER_UAV_FLAG_NONE;
m_device->CreateUnorderedAccessView(
m_processedCommandBuffers[frame].Get(),
m_processedCommandBuffers[frame].Get(),
&uavDesc,
processedCommandsHandle);
processedCommandsHandle.Offset(CbvSrvUavDescriptorCountPerFrame, m_cbvSrvUavDescriptorSize);
}
// Allocate a buffer that can be used to reset the UAV counters and initialize
// it to 0.
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(sizeof(UINT)),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&m_processedCommandBufferCounterReset)));
UINT8* pMappedCounterReset = nullptr;
CD3DX12_RANGE readRange(0, 0); // We do not intend to read from this resource on the CPU.
ThrowIfFailed(m_processedCommandBufferCounterReset->Map(0, &readRange, reinterpret_cast<void**>(&pMappedCounterReset)));
ZeroMemory(pMappedCounterReset, sizeof(UINT));
m_processedCommandBufferCounterReset->Unmap(0, nullptr);
}
// Close the command list and execute it to begin the vertex buffer copy into
// the default heap.
ThrowIfFailed(m_commandList->Close());
ID3D12CommandList* ppCommandLists[] = { m_commandList.Get() };
m_commandQueue->ExecuteCommandLists(_countof(ppCommandLists), ppCommandLists);
// Create synchronization objects and wait until assets have been uploaded to the GPU.
{
ThrowIfFailed(m_device->CreateFence(m_fenceValues[m_frameIndex], D3D12_FENCE_FLAG_NONE, IID_PPV_ARGS(&m_fence)));
ThrowIfFailed(m_device->CreateFence(m_fenceValues[m_frameIndex], D3D12_FENCE_FLAG_NONE, IID_PPV_ARGS(&m_computeFence)));
m_fenceValues[m_frameIndex]++;
// Create an event handle to use for frame synchronization.
m_fenceEvent = CreateEvent(nullptr, FALSE, FALSE, nullptr);
if (m_fenceEvent == nullptr)
{
ThrowIfFailed(HRESULT_FROM_WIN32(GetLastError()));
}
// Wait for the command list to execute; we are reusing the same command
// list in our main loop but for now, we just want to wait for setup to
// complete before continuing.
WaitForGpu();
}
}
void Material::Finalise(std::vector<D3D12_INPUT_ELEMENT_DESC> inputLayout, bool alpha, bool deferred)
{
_pPipelineState = GetPSO(_pVertexShader->GetBufferPointer(), _pPixelShader->GetBufferPointer(), alpha);
// Create the pipeline state, which includes compiling and loading shaders.
if (_pPipelineState == nullptr)
{
CD3DX12_BLEND_DESC blendState = CD3DX12_BLEND_DESC(D3D12_DEFAULT);
if (alpha)
{
blendState.RenderTarget[0].BlendEnable = true;
blendState.RenderTarget[0].SrcBlend = D3D12_BLEND_SRC_ALPHA;
blendState.RenderTarget[0].DestBlend = D3D12_BLEND_INV_SRC_ALPHA;
blendState.RenderTarget[0].BlendOp = D3D12_BLEND_OP_ADD;
blendState.RenderTarget[0].SrcBlendAlpha = D3D12_BLEND_ONE;
blendState.RenderTarget[0].DestBlendAlpha = D3D12_BLEND_ZERO;
blendState.RenderTarget[0].BlendOpAlpha = D3D12_BLEND_OP_ADD;
}
// Describe and create the graphics pipeline state object (PSO).
D3D12_GRAPHICS_PIPELINE_STATE_DESC psoDesc = {};
psoDesc.InputLayout = {&inputLayout[0], UINT(inputLayout.size())};
psoDesc.pRootSignature = _pRootSignature;
psoDesc.VS = {reinterpret_cast<UINT8*>(_pVertexShader->GetBufferPointer()), _pVertexShader->GetBufferSize()};
psoDesc.PS = {reinterpret_cast<UINT8*>(_pPixelShader->GetBufferPointer()), _pPixelShader->GetBufferSize()};
psoDesc.RasterizerState = CD3DX12_RASTERIZER_DESC(D3D12_DEFAULT);
psoDesc.DSVFormat = DXGI_FORMAT_D32_FLOAT;
psoDesc.BlendState = blendState;
psoDesc.SampleMask = UINT_MAX;
psoDesc.SampleDesc.Count = 1;
psoDesc.PrimitiveTopologyType = D3D12_PRIMITIVE_TOPOLOGY_TYPE_TRIANGLE;
if (deferred)
{
psoDesc.DepthStencilState = CD3DX12_DEPTH_STENCIL_DESC(D3D12_DEFAULT);
psoDesc.DepthStencilState.DepthFunc = _depthCheck;
psoDesc.DepthStencilState.DepthEnable = TRUE;
psoDesc.DepthStencilState.StencilEnable = FALSE;
psoDesc.DepthStencilState.DepthWriteMask = _depthWrite;
psoDesc.NumRenderTargets = GBuffer::GBUFFER_NUM_BUFFERS;
for (size_t i = 0; i < GBuffer::GBUFFER_NUM_BUFFERS; ++i)
{
psoDesc.RTVFormats[i] = GBuffer::Buffers[i].Format;
}
}
else
{
psoDesc.NumRenderTargets = 1;
psoDesc.DepthStencilState.DepthEnable = false;
psoDesc.RTVFormats[0] = DXGI_FORMAT_R8G8B8A8_UNORM;
}
LOGFAILEDCOM(_pDevice->CreateGraphicsPipelineState(&psoDesc, IID_PPV_ARGS(&_pPipelineState)));
PSOCacheItem cacheItem;
cacheItem.PipelineState = _pPipelineState;
cacheItem.VertexShader = _pVertexShader;
cacheItem.VertexByteCode = _pVertexShader->GetBufferPointer();
cacheItem.PixelShader = _pPixelShader;
cacheItem.PixelByteCode = _pPixelShader->GetBufferPointer();
_psoCache.push_back(cacheItem);
}
}
