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");
}
// 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();
}
}
bool
CompositorD3D11::Initialize()
{
bool force = gfxPrefs::LayersAccelerationForceEnabled();
ScopedGfxFeatureReporter reporter("D3D11 Layers", force);
if (!gfxPlatform::CanUseDirect3D11()) {
NS_WARNING("Direct3D 11-accelerated layers are not supported on this system.");
return false;
}
HRESULT hr;
mDevice = gfxWindowsPlatform::GetPlatform()->GetD3D11Device();
if (!mDevice) {
return false;
}
mDevice->GetImmediateContext(byRef(mContext));
if (!mContext) {
return false;
}
mFeatureLevel = mDevice->GetFeatureLevel();
mHwnd = (HWND)mWidget->GetNativeData(NS_NATIVE_WINDOW);
memset(&mVSConstants, 0, sizeof(VertexShaderConstants));
int referenceCount = 0;
UINT size = sizeof(referenceCount);
// If this isn't there yet it'll fail, count will remain 0, which is correct.
mDevice->GetPrivateData(sLayerManagerCount, &size, &referenceCount);
referenceCount++;
mDevice->SetPrivateData(sLayerManagerCount,
sizeof(referenceCount),
&referenceCount);
size = sizeof(DeviceAttachmentsD3D11*);
if (FAILED(mDevice->GetPrivateData(sDeviceAttachmentsD3D11,
&size,
&mAttachments))) {
mAttachments = new DeviceAttachmentsD3D11;
mDevice->SetPrivateData(sDeviceAttachmentsD3D11,
sizeof(mAttachments),
&mAttachments);
D3D11_INPUT_ELEMENT_DESC layout[] =
{
{ "POSITION", 0, DXGI_FORMAT_R32G32_FLOAT, 0, 0, D3D11_INPUT_PER_VERTEX_DATA, 0 },
};
hr = mDevice->CreateInputLayout(layout,
sizeof(layout) / sizeof(D3D11_INPUT_ELEMENT_DESC),
LayerQuadVS,
sizeof(LayerQuadVS),
byRef(mAttachments->mInputLayout));
if (FAILED(hr)) {
return false;
}
Vertex vertices[] = { {{0.0, 0.0}}, {{1.0, 0.0}}, {{0.0, 1.0}}, {{1.0, 1.0}} };
CD3D11_BUFFER_DESC bufferDesc(sizeof(vertices), D3D11_BIND_VERTEX_BUFFER);
D3D11_SUBRESOURCE_DATA data;
data.pSysMem = (void*)vertices;
hr = mDevice->CreateBuffer(&bufferDesc, &data, byRef(mAttachments->mVertexBuffer));
if (FAILED(hr)) {
return false;
}
if (!CreateShaders()) {
return false;
}
CD3D11_BUFFER_DESC cBufferDesc(sizeof(VertexShaderConstants),
D3D11_BIND_CONSTANT_BUFFER,
D3D11_USAGE_DYNAMIC,
D3D11_CPU_ACCESS_WRITE);
hr = mDevice->CreateBuffer(&cBufferDesc, nullptr, byRef(mAttachments->mVSConstantBuffer));
if (FAILED(hr)) {
return false;
}
cBufferDesc.ByteWidth = sizeof(PixelShaderConstants);
hr = mDevice->CreateBuffer(&cBufferDesc, nullptr, byRef(mAttachments->mPSConstantBuffer));
if (FAILED(hr)) {
return false;
}
CD3D11_RASTERIZER_DESC rastDesc(D3D11_DEFAULT);
rastDesc.CullMode = D3D11_CULL_NONE;
rastDesc.ScissorEnable = TRUE;
hr = mDevice->CreateRasterizerState(&rastDesc, byRef(mAttachments->mRasterizerState));
if (FAILED(hr)) {
return false;
}
CD3D11_SAMPLER_DESC samplerDesc(D3D11_DEFAULT);
hr = mDevice->CreateSamplerState(&samplerDesc, byRef(mAttachments->mLinearSamplerState));
if (FAILED(hr)) {
return false;
}
samplerDesc.Filter = D3D11_FILTER_MIN_MAG_MIP_POINT;
hr = mDevice->CreateSamplerState(&samplerDesc, byRef(mAttachments->mPointSamplerState));
if (FAILED(hr)) {
return false;
}
CD3D11_BLEND_DESC blendDesc(D3D11_DEFAULT);
D3D11_RENDER_TARGET_BLEND_DESC rtBlendPremul = {
TRUE,
D3D11_BLEND_ONE, D3D11_BLEND_INV_SRC_ALPHA, D3D11_BLEND_OP_ADD,
D3D11_BLEND_ONE, D3D11_BLEND_INV_SRC_ALPHA, D3D11_BLEND_OP_ADD,
D3D11_COLOR_WRITE_ENABLE_ALL
};
blendDesc.RenderTarget[0] = rtBlendPremul;
hr = mDevice->CreateBlendState(&blendDesc, byRef(mAttachments->mPremulBlendState));
if (FAILED(hr)) {
return false;
}
D3D11_RENDER_TARGET_BLEND_DESC rtBlendNonPremul = {
TRUE,
D3D11_BLEND_SRC_ALPHA, D3D11_BLEND_INV_SRC_ALPHA, D3D11_BLEND_OP_ADD,
D3D11_BLEND_ONE, D3D11_BLEND_INV_SRC_ALPHA, D3D11_BLEND_OP_ADD,
D3D11_COLOR_WRITE_ENABLE_ALL
};
blendDesc.RenderTarget[0] = rtBlendNonPremul;
hr = mDevice->CreateBlendState(&blendDesc, byRef(mAttachments->mNonPremulBlendState));
if (FAILED(hr)) {
return false;
}
if (gfxPrefs::ComponentAlphaEnabled()) {
D3D11_RENDER_TARGET_BLEND_DESC rtBlendComponent = {
TRUE,
D3D11_BLEND_ONE,
D3D11_BLEND_INV_SRC1_COLOR,
D3D11_BLEND_OP_ADD,
D3D11_BLEND_ONE,
D3D11_BLEND_INV_SRC_ALPHA,
D3D11_BLEND_OP_ADD,
D3D11_COLOR_WRITE_ENABLE_ALL
};
blendDesc.RenderTarget[0] = rtBlendComponent;
hr = mDevice->CreateBlendState(&blendDesc, byRef(mAttachments->mComponentBlendState));
if (FAILED(hr)) {
return false;
}
}
D3D11_RENDER_TARGET_BLEND_DESC rtBlendDisabled = {
FALSE,
D3D11_BLEND_SRC_ALPHA, D3D11_BLEND_INV_SRC_ALPHA, D3D11_BLEND_OP_ADD,
D3D11_BLEND_ONE, D3D11_BLEND_INV_SRC_ALPHA, D3D11_BLEND_OP_ADD,
D3D11_COLOR_WRITE_ENABLE_ALL
};
blendDesc.RenderTarget[0] = rtBlendDisabled;
hr = mDevice->CreateBlendState(&blendDesc, byRef(mAttachments->mDisabledBlendState));
if (FAILED(hr)) {
return false;
}
}
nsRefPtr<IDXGIDevice> dxgiDevice;
nsRefPtr<IDXGIAdapter> dxgiAdapter;
mDevice->QueryInterface(dxgiDevice.StartAssignment());
dxgiDevice->GetAdapter(getter_AddRefs(dxgiAdapter));
#ifdef MOZ_METRO
if (IsRunningInWindowsMetro()) {
nsRefPtr<IDXGIFactory2> dxgiFactory;
dxgiAdapter->GetParent(IID_PPV_ARGS(dxgiFactory.StartAssignment()));
nsIntRect rect;
mWidget->GetClientBounds(rect);
DXGI_SWAP_CHAIN_DESC1 swapDesc = { 0 };
// Automatically detect the width and the height from the winrt CoreWindow
swapDesc.Width = rect.width;
swapDesc.Height = rect.height;
// This is the most common swapchain format
swapDesc.Format = DXGI_FORMAT_B8G8R8A8_UNORM;
swapDesc.Stereo = false;
// Don't use multi-sampling
swapDesc.SampleDesc.Count = 1;
swapDesc.SampleDesc.Quality = 0;
swapDesc.BufferUsage = DXGI_USAGE_RENDER_TARGET_OUTPUT;
// Use double buffering to enable flip
swapDesc.BufferCount = 2;
swapDesc.Scaling = DXGI_SCALING_NONE;
// All Metro style apps must use this SwapEffect
swapDesc.SwapEffect = DXGI_SWAP_EFFECT_FLIP_SEQUENTIAL;
swapDesc.Flags = 0;
/**
* Create a swap chain, this swap chain will contain the backbuffer for
* the window we draw to. The front buffer is the full screen front
* buffer.
*/
nsRefPtr<IDXGISwapChain1> swapChain1;
hr = dxgiFactory->CreateSwapChainForCoreWindow(
dxgiDevice, (IUnknown *)mWidget->GetNativeData(NS_NATIVE_ICOREWINDOW),
&swapDesc, nullptr, getter_AddRefs(swapChain1));
if (FAILED(hr)) {
return false;
}
mSwapChain = swapChain1;
} else
#endif
{
nsRefPtr<IDXGIFactory> dxgiFactory;
dxgiAdapter->GetParent(IID_PPV_ARGS(dxgiFactory.StartAssignment()));
DXGI_SWAP_CHAIN_DESC swapDesc;
::ZeroMemory(&swapDesc, sizeof(swapDesc));
swapDesc.BufferDesc.Width = 0;
swapDesc.BufferDesc.Height = 0;
swapDesc.BufferDesc.Format = DXGI_FORMAT_B8G8R8A8_UNORM;
swapDesc.BufferDesc.RefreshRate.Numerator = 60;
swapDesc.BufferDesc.RefreshRate.Denominator = 1;
swapDesc.SampleDesc.Count = 1;
swapDesc.SampleDesc.Quality = 0;
swapDesc.BufferUsage = DXGI_USAGE_RENDER_TARGET_OUTPUT;
swapDesc.BufferCount = 1;
swapDesc.OutputWindow = mHwnd;
swapDesc.Windowed = TRUE;
swapDesc.Flags = 0;
/**
* Create a swap chain, this swap chain will contain the backbuffer for
* the window we draw to. The front buffer is the full screen front
* buffer.
*/
hr = dxgiFactory->CreateSwapChain(dxgiDevice, &swapDesc, byRef(mSwapChain));
if (FAILED(hr)) {
return false;
}
// We need this because we don't want DXGI to respond to Alt+Enter.
dxgiFactory->MakeWindowAssociation(swapDesc.OutputWindow,
DXGI_MWA_NO_WINDOW_CHANGES);
}
reporter.SetSuccessful();
return true;
}
// Load the sample assets.
void D3D12nBodyGravity::LoadAssets()
{
// Create the root signatures.
{
CD3DX12_DESCRIPTOR_RANGE ranges[2];
ranges[0].Init(D3D12_DESCRIPTOR_RANGE_TYPE_SRV, 1, 0);
ranges[1].Init(D3D12_DESCRIPTOR_RANGE_TYPE_UAV, 1, 0);
CD3DX12_ROOT_PARAMETER rootParameters[RootParametersCount];
rootParameters[RootParameterCB].InitAsConstantBufferView(0, 0, D3D12_SHADER_VISIBILITY_ALL);
rootParameters[RootParameterSRV].InitAsDescriptorTable(1, &ranges[0], D3D12_SHADER_VISIBILITY_VERTEX);
rootParameters[RootParameterUAV].InitAsDescriptorTable(1, &ranges[1], D3D12_SHADER_VISIBILITY_ALL);
// The rendering pipeline does not need the UAV parameter.
CD3DX12_ROOT_SIGNATURE_DESC rootSignatureDesc;
rootSignatureDesc.Init(_countof(rootParameters) - 1, 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. Must change visibility for the SRV.
rootParameters[RootParameterSRV].ShaderVisibility = D3D12_SHADER_VISIBILITY_ALL;
CD3DX12_ROOT_SIGNATURE_DESC computeRootSignatureDesc(_countof(rootParameters), rootParameters, 0, nullptr);
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 states, which includes compiling and loading shaders.
{
ComPtr<ID3DBlob> vertexShader;
ComPtr<ID3DBlob> geometryShader;
ComPtr<ID3DBlob> pixelShader;
ComPtr<ID3DBlob> computeShader;
#ifdef _DEBUG
// Enable better shader debugging with the graphics debugging tools.
UINT compileFlags = D3DCOMPILE_DEBUG | D3DCOMPILE_SKIP_OPTIMIZATION;
#else
UINT compileFlags = 0;
#endif
// Load and compile shaders.
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"ParticleDraw.hlsl").c_str(), nullptr, nullptr, "VSParticleDraw", "vs_5_0", compileFlags, 0, &vertexShader, nullptr));
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"ParticleDraw.hlsl").c_str(), nullptr, nullptr, "GSParticleDraw", "gs_5_0", compileFlags, 0, &geometryShader, nullptr));
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"ParticleDraw.hlsl").c_str(), nullptr, nullptr, "PSParticleDraw", "ps_5_0", compileFlags, 0, &pixelShader, nullptr));
ThrowIfFailed(D3DCompileFromFile(GetAssetFullPath(L"NBodyGravityCS.hlsl").c_str(), nullptr, nullptr, "CSMain", "cs_5_0", compileFlags, 0, &computeShader, nullptr));
D3D12_INPUT_ELEMENT_DESC inputElementDescs[] =
{
{ "COLOR", 0, DXGI_FORMAT_R32G32B32A32_FLOAT, 0, 0, D3D12_INPUT_CLASSIFICATION_PER_VERTEX_DATA, 0 },
};
// Describe the blend and depth states.
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_ONE;
blendDesc.RenderTarget[0].SrcBlendAlpha = D3D12_BLEND_ZERO;
blendDesc.RenderTarget[0].DestBlendAlpha = D3D12_BLEND_ZERO;
CD3DX12_DEPTH_STENCIL_DESC depthStencilDesc(D3D12_DEFAULT);
depthStencilDesc.DepthEnable = FALSE;
depthStencilDesc.DepthWriteMask = D3D12_DEPTH_WRITE_MASK_ZERO;
// Describe and create the graphics pipeline state object (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.GS = { reinterpret_cast<UINT8*>(geometryShader->GetBufferPointer()), geometryShader->GetBufferSize() };
psoDesc.PS = { reinterpret_cast<UINT8*>(pixelShader->GetBufferPointer()), pixelShader->GetBufferSize() };
psoDesc.RasterizerState = CD3DX12_RASTERIZER_DESC(D3D12_DEFAULT);
psoDesc.BlendState = blendDesc;
psoDesc.DepthStencilState = depthStencilDesc;
psoDesc.SampleMask = UINT_MAX;
psoDesc.PrimitiveTopologyType = D3D12_PRIMITIVE_TOPOLOGY_TYPE_POINT;
psoDesc.NumRenderTargets = 1;
psoDesc.RTVFormats[0] = DXGI_FORMAT_R8G8B8A8_UNORM;
psoDesc.DSVFormat = DXGI_FORMAT_D24_UNORM_S8_UINT;
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)));
CreateVertexBuffer();
CreateParticleBuffers();
ComPtr<ID3D12Resource> constantBufferCSUpload;
// Create the compute shader's constant buffer.
{
const UINT bufferSize = sizeof(ConstantBufferCS);
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_DEFAULT),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(bufferSize),
D3D12_RESOURCE_STATE_COPY_DEST,
nullptr,
IID_PPV_ARGS(&m_constantBufferCS)));
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(bufferSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&constantBufferCSUpload)));
ConstantBufferCS constantBufferCS = {};
constantBufferCS.param[0] = ParticleCount;
constantBufferCS.param[1] = int(ceil(ParticleCount / 128.0f));
constantBufferCS.paramf[0] = 0.1f;
constantBufferCS.paramf[1] = 1.0f;
D3D12_SUBRESOURCE_DATA computeCBData = {};
computeCBData.pData = reinterpret_cast<UINT8*>(&constantBufferCS);
computeCBData.RowPitch = bufferSize;
computeCBData.SlicePitch = computeCBData.RowPitch;
UpdateSubresources<1>(m_commandList.Get(), m_constantBufferCS.Get(), constantBufferCSUpload.Get(), 0, 0, 1, &computeCBData);
m_commandList->ResourceBarrier(1, &CD3DX12_RESOURCE_BARRIER::Transition(m_constantBufferCS.Get(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_VERTEX_AND_CONSTANT_BUFFER));
}
// Create the geometry shader's constant buffer.
{
const UINT constantBufferGSSize = sizeof(ConstantBufferGS) * FrameCount;
ThrowIfFailed(m_device->CreateCommittedResource(
&CD3DX12_HEAP_PROPERTIES(D3D12_HEAP_TYPE_UPLOAD),
D3D12_HEAP_FLAG_NONE,
&CD3DX12_RESOURCE_DESC::Buffer(constantBufferGSSize),
D3D12_RESOURCE_STATE_GENERIC_READ,
nullptr,
IID_PPV_ARGS(&m_constantBufferGS)
));
ThrowIfFailed(m_constantBufferGS->Map(0, nullptr, reinterpret_cast<void**>(&m_pConstantBufferGSData)));
ZeroMemory(m_pConstantBufferGSData, constantBufferGSSize);
}
// 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);
// Create synchronization objects and wait until assets have been uploaded to the GPU.
{
ThrowIfFailed(m_device->CreateFence(m_renderContextFenceValue, D3D12_FENCE_FLAG_NONE, IID_PPV_ARGS(&m_renderContextFence)));
m_renderContextFenceValue++;
m_renderContextFenceEvent = CreateEventEx(nullptr, FALSE, FALSE, EVENT_ALL_ACCESS);
if (m_renderContextFenceEvent == nullptr)
{
ThrowIfFailed(HRESULT_FROM_WIN32(GetLastError()));
}
WaitForRenderContext();
}
}
