我尝试使用 ExecuteIndirect 来绘制我的实例。
这是我的代码：
struct IndirectCommand
{
D3D12_GPU_VIRTUAL_ADDRESS materialBufferAddress;
D3D12_GPU_VIRTUAL_ADDRESS instanceBufferAddress;
D3D12_DRAW_INDEXED_ARGUMENTS drawArguments;
}; // byte stride: 40
// code for initializing command signature
void InstanceManager::InitIndirectBuffer()
{
D3D12_INDIRECT_ARGUMENT_DESC indirectDescs[3] = {};
indirectDescs[0].Type = D3D12_INDIRECT_ARGUMENT_TYPE_CONSTANT_BUFFER_VIEW;
indirectDescs[0].ConstantBufferView.RootParameterIndex = cMaterialPass;
indirectDescs[1].Type = D3D12_INDIRECT_ARGUMENT_TYPE_SHADER_RESOURCE_VIEW;
indirectDescs[1].ShaderResourceView.RootParameterIndex = cInstancePass;
indirectDescs[2].Type = D3D12_INDIRECT_ARGUMENT_TYPE_DRAW_INDEXED;
D3D12_COMMAND_SIGNATURE_DESC commandSignatureDesc = {};
commandSignatureDesc.pArgumentDescs = indirectDescs;
commandSignatureDesc.NumArgumentDescs = _countof(indirectDescs);
commandSignatureDesc.ByteStride = sizeof(IndirectCommand);
ThrowIfFailed(Engine::GetApp()->GetDevice()->CreateCommandSignature(&commandSignatureDesc, Engine::GetApp()->GetRootSignature(), IID_PPV_ARGS(&mCommandSignature)));
}
附加间接命令缓冲区：
void AppendIndirectCommandBuffer()
{
// wait for gpu
Engine::GetApp()->ResetCommandList();
Engine::GetApp()->ExecuteCommand();
Engine::GetApp()->FlushCommandQueue();
for (int i = 0; i < gNumFrameResources; i++)
{
// alloc upload heap
Engine::GetApp()->GetFrameManager().GetFrameResource(i)->AppendUploadBuffer<IndirectCommand>(mIndirectBufferUpload[i]
, mLastIndirectUploadCount[i]
, mIndirectCount
, false);
// alloc default heap
Engine::GetApp()->GetFrameManager().GetFrameResource(i)->AppendDefaultBuffer<IndirectCommand>(mIndirectBufferDefault[i]
, mLastIndirectDefaultCount[i]
, mIndirectCount++
, false);
}
UpdateIndirectData(_obj);
// code for appending indirect command buffer
}
更新间接命令缓冲区数据：
void UpdateIndirectData(GameObject _obj)
{
UINT matCBByteSize = d3dUtil::CalcConstantBufferByteSize(sizeof(MaterialData));
UINT insCBByteSize = sizeof(InstanceData);
for (int i = 0; i < gNumFrameResources; i++)
{
if (Engine::GetApp()->GetFrameManager().GetFrameResource(i) != NULL)
{
string _matName = _obj->GetComponent<RenderObject>()->GetMaterialName();
string _geoName = _obj->GetComponent<RenderObject>()->GetGeometryName();
Material *mat = Engine::GetApp()->GetMaterialManager().GetMaterial(_matName);
if (mat != nullptr)
{
IndirectCommand data;
data.materialBufferAddress = Engine::GetApp()->GetMaterialManager().GetMaterialBuffer(i)->Resource()->GetGPUVirtualAddress()
+ matCBByteSize*mat->GetMatBufferIndex();
data.instanceBufferAddress = mInstanceBuffer[i]->Resource()->GetGPUVirtualAddress() + mInstanceIndex[_obj->GetID()] * insCBByteSize;
data.drawArguments.BaseVertexLocation = mDrawArgs[_geoName].BaseVertexLocation;
data.drawArguments.IndexCountPerInstance = mDrawArgs[_geoName].IndexCount;
data.drawArguments.StartIndexLocation = mDrawArgs[_geoName].StartIndexLocation;
data.drawArguments.StartInstanceLocation = 0;
data.drawArguments.InstanceCount = 1;
int indirectIndex = mIndirectIndex[_obj->GetID()];
mIndirectCommand[indirectIndex] = data; // an array of indirect command, size is set to 1000 temporarily
// copy to default heap
D3D12_SUBRESOURCE_DATA commandData = {};
commandData.pData = reinterpret_cast<UINT8*>(&mIndirectCommand[0]);
commandData.RowPitch = sizeof(IndirectCommand) * mIndirectCount;
commandData.SlicePitch = commandData.RowPitch;
UpdateSubresources<1U>(Engine::GetApp()->GetCommandList(), mIndirectBufferDefault[i]->Resource(), mIndirectBufferUpload[i]->Resource(), 0, 0, 1, &commandData);
}
}
}
}
最后，间接执行
void DrawIndirectInstance()
{
Engine::GetApp()->GetCommandList()->IASetVertexBuffers(0, 1, &mGeometry->VertexBufferView());
Engine::GetApp()->GetCommandList()->IASetIndexBuffer(&mGeometry->IndexBufferView16());
Engine::GetApp()->GetCommandList()->IASetPrimitiveTopology(D3D_PRIMITIVE_TOPOLOGY_TRIANGLELIST);
// just set a pso for testing, I haven't group my instances by material yet
ID3D12PipelineState *pso = Engine::GetApp()->GetMaterialManager().GetMaterialPSO("test");
Engine::GetApp()->GetCommandList()->SetPipelineState(pso);
int frameIndex = Engine::GetApp()->GetFrameManager().GetCurrFrameIndex();
auto indirectBuffer = mIndirectBufferUpload[frameIndex].get();
auto materialBuffer = Engine::GetApp()->GetMaterialManager().GetMaterialBuffer(frameIndex);
Engine::GetApp()->GetCommandList()->SetGraphicsRootConstantBufferView(cMaterialPass, materialBuffer->Resource()->GetGPUVirtualAddress());
Engine::GetApp()->GetCommandList()->SetGraphicsRootShaderResourceView(cInstancePass, mInstanceBuffer[frameIndex]->Resource()->GetGPUVirtualAddress());
Engine::GetApp()->GetCommandList()->ResourceBarrier(1
, &CD3DX12_RESOURCE_BARRIER::Transition(indirectBuffer->Resource(), D3D12_RESOURCE_STATE_COPY_DEST, D3D12_RESOURCE_STATE_INDIRECT_ARGUMENT));
Engine::GetApp()->GetCommandList()->ExecuteIndirect(mCommandSignature.Get()
, mIndirectCount
, indirectBuffer->Resource()
, 0
, nullptr
, 0);
Engine::GetApp()->GetCommandList()->ResourceBarrier(1
, &CD3DX12_RESOURCE_BARRIER::Transition(indirectBuffer->Resource(), D3D12_RESOURCE_STATE_INDIRECT_ARGUMENT, D3D12_RESOURCE_STATE_COPY_DEST));
}
我使用我的 SceneManager 来加载场景。如果一个游戏对象是一个渲染对象。我的系统将调用 AppendIndirectCommandBuffer() 并将数据复制到间接命令缓冲区中。
如果我在场景初始化后不克隆我的游戏对象，ExecuteIndirect() 会很好用。
我尝试在运行时克隆我的游戏对象（在我的 Update() 中）。
我的系统再次调用 AppendIndirectCommandBuffer() 来调整间接命令缓冲区的大小并将新数据复制到缓冲区。
克隆游戏对象几秒钟后，我的系统开始出现故障并导致我的 R9 380 上出现 TDR。
但在 WARP 和 intel gpu 上都能正常工作。
而且我不知道为什么:(。
如何解决这个问题呢？我真的很想善用间接绘图。
谢谢！
更新
上传堆资源无法传输到 D3D12_RESOURCE_STATE_INDIRECT_ARGUMENT。
我创建了一个默认类型的堆，并使用上传堆将数据复制到它。
我尝试了调试层，没有返回任何错误。我尝试了 GBV，但只有两个错误：
D3D12 ERROR: GPU-BASED VALIDATION: Draw, Uninitialized root argument accessed. Shader Stage: VERTEX, Root Parameter Index: [2], Draw Index: [0], Shader Code: Forward.hlsl(21,2-42), Asm Instruction Range: [0x114-0x13b], Asm Operand Index: [3], Command List: 0x00000134BB3C1EE0:'Unnamed ID3D12GraphicsCommandList Object', SRV/UAV/CBV Descriptor Heap: 0x00000134AE6DD020:'Unnamed ID3D12DescriptorHeap Object', Sampler Descriptor Heap: <not set>, Pipeline State: 0x00000134BB5CB540:'Unnamed ID3D12PipelineState Object', [ EXECUTION ERROR #935: GPU_BASED_VALIDATION_ROOT_ARGUMENT_UNINITIALIZED]
D3D12 ERROR: GPU-BASED VALIDATION: Draw, Uninitialized root argument accessed. Shader Stage: VERTEX, Root Parameter Index: [1], Draw Index: [0], Shader Code: Forward.hlsl(37,2-41), Asm Instruction Range: [0x8c0-0x8e3], Asm Operand Index: [2], Command List: 0x000001D0D7B70860:'Unnamed ID3D12GraphicsCommandList Object', SRV/UAV/CBV Descriptor Heap: 0x000001D0D7AC6C80:'Unnamed ID3D12DescriptorHeap Object', Sampler Descriptor Heap: <not set>, Pipeline State: 0x000001D0D7BBF450:'Unnamed ID3D12PipelineState Object', [ EXECUTION ERROR #935: GPU_BASED_VALIDATION_ROOT_ARGUMENT_UNINITIALIZED]
并发出警告：
D3D12 WARNING: ID3D12CommandList::ExecuteIndirect: GPU-based validation is not supported for ExecuteIndirect that changes root bindings. All further GPU-based validation output may not be reliable. [ EXECUTION WARNING #1000: GPU_BASED_VALIDATION_UNSUPPORTED]
在我调用以下函数后，这两个错误就消失了。
Engine::GetApp()->GetCommandList()->SetGraphicsRootConstantBufferView(cMaterialPass, materialBuffer->Resource()->GetGPUVirtualAddress());
Engine::GetApp()->GetCommandList()->SetGraphicsRootShaderResourceView(cInstancePass, mInstanceBuffer[frameIndex]->Resource()->GetGPUVirtualAddress());
尽管进行了这些修改，它仍然无法正常工作。