DirectX 11 - 计算着色器:写入输出资源
DirectX 11 - Compute shader: Writing to an output resource
我刚开始使用 DirectX 11 中的计算着色器阶段,在写入计算着色器中的输出资源时遇到了一些不需要的行为。我似乎只得到零作为输出,据我所知,这意味着在计算着色器中执行了越界读取。 (越界写入导致无操作)
创建计算着色器组件
输入资源
首先,我为输入数据创建了一个 ID3D11Buffer*
。在创建用于输入到计算着色器阶段的 SRV 时,它作为资源传递。如果输入数据永远不会改变,那么我们可以在创建 SRV 后释放 ID3D11Buffer*
对象,因为 SRV 将充当资源的句柄。
但是,我想在每一帧更新输入数据,所以我将保留缓冲区供我使用以进行映射。
// Create a buffer to be bound as Compute Shader input (D3D11_BIND_SHADER_RESOURCE).
D3D11_BUFFER_DESC constantDataDesc;
constantDataDesc.Usage = D3D11_USAGE_DYNAMIC;
constantDataDesc.ByteWidth = sizeof(ParticleConstantData) * NUM_PARTICLES;
constantDataDesc.BindFlags = D3D11_BIND_SHADER_RESOURCE;
constantDataDesc.CPUAccessFlags = D3D11_CPU_ACCESS_WRITE;
constantDataDesc.StructureByteStride = sizeof(ParticleConstantData);
constantDataDesc.MiscFlags = D3D11_RESOURCE_MISC_BUFFER_STRUCTURED;
hr = device->CreateBuffer ( &constantDataDesc, 0, &mInputBuffer );
正在使用新创建的缓冲区作为资源创建 SRV
D3D11_SHADER_RESOURCE_VIEW_DESC srvDesc;
srvDesc.Format = DXGI_FORMAT_UNKNOWN;
srvDesc.ViewDimension = D3D11_SRV_DIMENSION_BUFFEREX;
srvDesc.BufferEx.FirstElement = 0;
srvDesc.BufferEx.Flags = 0;
srvDesc.BufferEx.NumElements = NUM_PARTICLES;
hr = device->CreateShaderResourceView( mInputBuffer, &srvDesc, &mInputView );
输出资源
现在我需要创建一个资源供计算着色器写入。我还将创建缓冲区的系统内存版本以供读取。我将使用 ID3D11DeviceContext::CopyResource method 将数据从连接到无人机的计算着色器输出缓冲区复制到系统内存版本以执行映射并将其内容保存回系统内存。
创建计算着色器可以写入的读写缓冲区
(D3D11_BIND_UNORDERED_ACCESS).
D3D11_BUFFER_DESC outputDesc;
outputDesc.Usage = D3D11_USAGE_DEFAULT;
outputDesc.ByteWidth = sizeof(ParticleData) * NUM_PARTICLES;
outputDesc.BindFlags = D3D11_BIND_UNORDERED_ACCESS;
outputDesc.CPUAccessFlags = 0;
outputDesc.StructureByteStride = sizeof(ParticleData);
outputDesc.MiscFlags = D3D11_RESOURCE_MISC_BUFFER_STRUCTURED;
hr = ( device->CreateBuffer( &outputDesc, 0, &mOutputBuffer ) );
创建缓冲区的系统内存版本以从中读取结果
outputDesc.Usage = D3D11_USAGE_STAGING;
outputDesc.BindFlags = 0;
outputDesc.CPUAccessFlags = D3D11_CPU_ACCESS_READ;
hr = ( device->CreateBuffer( &outputDesc, 0, &mOutputResultBuffer ) );
为计算着色器创建无人机以写入结果
D3D11_UNORDERED_ACCESS_VIEW_DESC uavDesc;
uavDesc.Buffer.FirstElement = 0;
uavDesc.Buffer.Flags = 0;
uavDesc.Buffer.NumElements = NUM_PARTICLES;
uavDesc.Format = DXGI_FORMAT_UNKNOWN;
uavDesc.ViewDimension = D3D11_UAV_DIMENSION_BUFFER;
hr = device->CreateUnorderedAccessView( mOutputBuffer, &uavDesc, &mOutputUAV );
正在执行计算着色器(每帧)
C++
mParticleSystem.FillConstantDataBuffer( mDeviceContext, mInputBuffer );
// Enable Compute Shader
mDeviceContext->CSSetShader( mComputeShader, nullptr, 0 );
mDeviceContext->CSSetShaderResources( 0, 1, &mInputView );
mDeviceContext->CSSetUnorderedAccessViews( 0, 1, &mOutputUAV, 0 );
// Dispatch
mDeviceContext->Dispatch( 1, 1, 1 );
// Unbind the input textures from the CS for good housekeeping
ID3D11ShaderResourceView* nullSRV[] = { NULL };
mDeviceContext->CSSetShaderResources( 0, 1, nullSRV );
// Unbind output from compute shader
ID3D11UnorderedAccessView* nullUAV[] = { NULL };
mDeviceContext->CSSetUnorderedAccessViews( 0, 1, nullUAV, 0 );
// Disable Compute Shader
mDeviceContext->CSSetShader( nullptr, nullptr, 0 );
// Copy result
mDeviceContext->CopyResource( mOutputBuffer, mOutputResultBuffer );
// Update particle system data with output from Compute Shader
D3D11_MAPPED_SUBRESOURCE mappedResource;
HRESULT hr = mDeviceContext->Map( mOutputResultBuffer, 0, D3D11_MAP_READ, 0, &mappedResource );
if( SUCCEEDED( hr ) )
{
ParticleData* dataView = reinterpret_cast<ParticleData*>(mappedResource.pData);
// Update particle positions and velocities
mParticleSystem.UpdatePositionAndVelocity( dataView );
mDeviceContext->Unmap( mOutputResultBuffer, 0 );
}
HLSL
struct ConstantParticleData
{
float3 position;
float3 velocity;
float3 initialVelocity;
};
struct ParticleData
{
float3 position;
float3 velocity;
};
StructuredBuffer<ConstantParticleData> inputConstantParticleData : register( t0 );
RWStructuredBuffer<ParticleData> outputParticleData : register( u0 );
[numthreads(32, 1, 1)]
void CS_main( int3 dispatchThreadID : SV_DispatchThreadID )
{
outputParticleData[dispatchThreadID.x].position = inputConstantParticleData[dispatchThreadID.x].position;
}
对于这个问题的内容量,我深表歉意。我精心组织了它,因此您可能会发现它更容易获得概览。
传递给着色器的元素数量是 32。
对我的问题有什么建议吗?谢谢!
您在调用 CopyResource 时将源和目标转错了方向。
我刚开始使用 DirectX 11 中的计算着色器阶段,在写入计算着色器中的输出资源时遇到了一些不需要的行为。我似乎只得到零作为输出,据我所知,这意味着在计算着色器中执行了越界读取。 (越界写入导致无操作)
创建计算着色器组件
输入资源
首先,我为输入数据创建了一个 ID3D11Buffer*
。在创建用于输入到计算着色器阶段的 SRV 时,它作为资源传递。如果输入数据永远不会改变,那么我们可以在创建 SRV 后释放 ID3D11Buffer*
对象,因为 SRV 将充当资源的句柄。
但是,我想在每一帧更新输入数据,所以我将保留缓冲区供我使用以进行映射。
// Create a buffer to be bound as Compute Shader input (D3D11_BIND_SHADER_RESOURCE).
D3D11_BUFFER_DESC constantDataDesc;
constantDataDesc.Usage = D3D11_USAGE_DYNAMIC;
constantDataDesc.ByteWidth = sizeof(ParticleConstantData) * NUM_PARTICLES;
constantDataDesc.BindFlags = D3D11_BIND_SHADER_RESOURCE;
constantDataDesc.CPUAccessFlags = D3D11_CPU_ACCESS_WRITE;
constantDataDesc.StructureByteStride = sizeof(ParticleConstantData);
constantDataDesc.MiscFlags = D3D11_RESOURCE_MISC_BUFFER_STRUCTURED;
hr = device->CreateBuffer ( &constantDataDesc, 0, &mInputBuffer );
正在使用新创建的缓冲区作为资源创建 SRV
D3D11_SHADER_RESOURCE_VIEW_DESC srvDesc;
srvDesc.Format = DXGI_FORMAT_UNKNOWN;
srvDesc.ViewDimension = D3D11_SRV_DIMENSION_BUFFEREX;
srvDesc.BufferEx.FirstElement = 0;
srvDesc.BufferEx.Flags = 0;
srvDesc.BufferEx.NumElements = NUM_PARTICLES;
hr = device->CreateShaderResourceView( mInputBuffer, &srvDesc, &mInputView );
输出资源
现在我需要创建一个资源供计算着色器写入。我还将创建缓冲区的系统内存版本以供读取。我将使用 ID3D11DeviceContext::CopyResource method 将数据从连接到无人机的计算着色器输出缓冲区复制到系统内存版本以执行映射并将其内容保存回系统内存。
创建计算着色器可以写入的读写缓冲区
(D3D11_BIND_UNORDERED_ACCESS).
D3D11_BUFFER_DESC outputDesc;
outputDesc.Usage = D3D11_USAGE_DEFAULT;
outputDesc.ByteWidth = sizeof(ParticleData) * NUM_PARTICLES;
outputDesc.BindFlags = D3D11_BIND_UNORDERED_ACCESS;
outputDesc.CPUAccessFlags = 0;
outputDesc.StructureByteStride = sizeof(ParticleData);
outputDesc.MiscFlags = D3D11_RESOURCE_MISC_BUFFER_STRUCTURED;
hr = ( device->CreateBuffer( &outputDesc, 0, &mOutputBuffer ) );
创建缓冲区的系统内存版本以从中读取结果
outputDesc.Usage = D3D11_USAGE_STAGING;
outputDesc.BindFlags = 0;
outputDesc.CPUAccessFlags = D3D11_CPU_ACCESS_READ;
hr = ( device->CreateBuffer( &outputDesc, 0, &mOutputResultBuffer ) );
为计算着色器创建无人机以写入结果
D3D11_UNORDERED_ACCESS_VIEW_DESC uavDesc;
uavDesc.Buffer.FirstElement = 0;
uavDesc.Buffer.Flags = 0;
uavDesc.Buffer.NumElements = NUM_PARTICLES;
uavDesc.Format = DXGI_FORMAT_UNKNOWN;
uavDesc.ViewDimension = D3D11_UAV_DIMENSION_BUFFER;
hr = device->CreateUnorderedAccessView( mOutputBuffer, &uavDesc, &mOutputUAV );
正在执行计算着色器(每帧)
C++
mParticleSystem.FillConstantDataBuffer( mDeviceContext, mInputBuffer );
// Enable Compute Shader
mDeviceContext->CSSetShader( mComputeShader, nullptr, 0 );
mDeviceContext->CSSetShaderResources( 0, 1, &mInputView );
mDeviceContext->CSSetUnorderedAccessViews( 0, 1, &mOutputUAV, 0 );
// Dispatch
mDeviceContext->Dispatch( 1, 1, 1 );
// Unbind the input textures from the CS for good housekeeping
ID3D11ShaderResourceView* nullSRV[] = { NULL };
mDeviceContext->CSSetShaderResources( 0, 1, nullSRV );
// Unbind output from compute shader
ID3D11UnorderedAccessView* nullUAV[] = { NULL };
mDeviceContext->CSSetUnorderedAccessViews( 0, 1, nullUAV, 0 );
// Disable Compute Shader
mDeviceContext->CSSetShader( nullptr, nullptr, 0 );
// Copy result
mDeviceContext->CopyResource( mOutputBuffer, mOutputResultBuffer );
// Update particle system data with output from Compute Shader
D3D11_MAPPED_SUBRESOURCE mappedResource;
HRESULT hr = mDeviceContext->Map( mOutputResultBuffer, 0, D3D11_MAP_READ, 0, &mappedResource );
if( SUCCEEDED( hr ) )
{
ParticleData* dataView = reinterpret_cast<ParticleData*>(mappedResource.pData);
// Update particle positions and velocities
mParticleSystem.UpdatePositionAndVelocity( dataView );
mDeviceContext->Unmap( mOutputResultBuffer, 0 );
}
HLSL
struct ConstantParticleData
{
float3 position;
float3 velocity;
float3 initialVelocity;
};
struct ParticleData
{
float3 position;
float3 velocity;
};
StructuredBuffer<ConstantParticleData> inputConstantParticleData : register( t0 );
RWStructuredBuffer<ParticleData> outputParticleData : register( u0 );
[numthreads(32, 1, 1)]
void CS_main( int3 dispatchThreadID : SV_DispatchThreadID )
{
outputParticleData[dispatchThreadID.x].position = inputConstantParticleData[dispatchThreadID.x].position;
}
对于这个问题的内容量,我深表歉意。我精心组织了它,因此您可能会发现它更容易获得概览。
传递给着色器的元素数量是 32。
对我的问题有什么建议吗?谢谢!
您在调用 CopyResource 时将源和目标转错了方向。