Related
I'm working on a code to capture the desktop using Desktop duplication and encode the same to h264 using Intel hardwareMFT. The encoder only accepts NV12 format as input. I have got a DXGI_FORMAT_B8G8R8A8_UNORM to NV12 converter(https://github.com/NVIDIA/video-sdk-samples/blob/master/nvEncDXGIOutputDuplicationSample/Preproc.cpp) that works fine, and is based on DirectX VideoProcessor.
The problem is that the VideoProcessor on certain intel graphics hardware supports conversions only from DXGI_FORMAT_B8G8R8A8_UNORM to YUY2 but not NV12, I have confirmed the same by enumerating the supported formats through GetVideoProcessorOutputFormats. Though the VideoProcessor Blt succeeded without any errors, and I could see that the frames in the output video are pixelated a bit, I could notice it if I look at it closely.
I guess, the VideoProcessor has simply failed over to the next supported output format (YUY2) and I'm unknowingly feeding it to the encoder that thinks that the input is in NV12 as configured. There is no failure or major corruption of frames due to the fact that there is little difference like byte order and subsampling between NV12 and YUY2. Also, I don't have pixelating problems on hardware that supports NV12 conversion.
So I decided to do the color conversion using pixel shaders which is based on this code(https://github.com/bavulapati/DXGICaptureDXColorSpaceConversionIntelEncode/blob/master/DXGICaptureDXColorSpaceConversionIntelEncode/DuplicationManager.cpp). I'm able make the pixel shaders work, I have also uploaded my code here(https://codeshare.io/5PJjxP) for reference (simplified it as much as possible).
Now, I'm left with two channels, chroma, and luma respectively
(ID3D11Texture2D textures). And I'm really confused about efficiently
packing the two separate channels into one ID3D11Texture2D texture so
that I may feed the same to the encoder. Is there a way to efficiently
pack the Y and UV channels into a single ID3D11Texture2D in GPU? I'm
really tired of CPU based approaches due to the fact that it's costly,
and doesn't offer the best possible frame rates. In fact, I'm
reluctant to even copy the textures to CPU. I'm thinking of a way to
do it in GPU without any back and forth copies between CPU and GPU.
I have been researching this for quite some time without any progress, any help would be appreciated.
/**
* This method is incomplete. It's just a template of what I want to achieve.
*/
HRESULT CreateNV12TextureFromLumaAndChromaSurface(ID3D11Texture2D** pOutputTexture)
{
HRESULT hr = S_OK;
try
{
//Copying from GPU to CPU. Bad :(
m_pD3D11DeviceContext->CopyResource(m_CPUAccessibleLuminanceSurf, m_LuminanceSurf);
D3D11_MAPPED_SUBRESOURCE resource;
UINT subresource = D3D11CalcSubresource(0, 0, 0);
HRESULT hr = m_pD3D11DeviceContext->Map(m_CPUAccessibleLuminanceSurf, subresource, D3D11_MAP_READ, 0, &resource);
BYTE* sptr = reinterpret_cast<BYTE*>(resource.pData);
BYTE* dptrY = nullptr; // point to the address of Y channel in output surface
//Store Image Pitch
int m_ImagePitch = resource.RowPitch;
int height = GetImageHeight();
int width = GetImageWidth();
for (int i = 0; i < height; i++)
{
memcpy_s(dptrY, m_ImagePitch, sptr, m_ImagePitch);
sptr += m_ImagePitch;
dptrY += m_ImagePitch;
}
m_pD3D11DeviceContext->Unmap(m_CPUAccessibleLuminanceSurf, subresource);
//Copying from GPU to CPU. Bad :(
m_pD3D11DeviceContext->CopyResource(m_CPUAccessibleChrominanceSurf, m_ChrominanceSurf);
hr = m_pD3D11DeviceContext->Map(m_CPUAccessibleChrominanceSurf, subresource, D3D11_MAP_READ, 0, &resource);
sptr = reinterpret_cast<BYTE*>(resource.pData);
BYTE* dptrUV = nullptr; // point to the address of UV channel in output surface
m_ImagePitch = resource.RowPitch;
height /= 2;
width /= 2;
for (int i = 0; i < height; i++)
{
memcpy_s(dptrUV, m_ImagePitch, sptr, m_ImagePitch);
sptr += m_ImagePitch;
dptrUV += m_ImagePitch;
}
m_pD3D11DeviceContext->Unmap(m_CPUAccessibleChrominanceSurf, subresource);
}
catch(HRESULT){}
return hr;
}
Draw NV12:
//
// Draw frame for NV12 texture
//
HRESULT DrawNV12Frame(ID3D11Texture2D* inputTexture)
{
HRESULT hr;
// If window was resized, resize swapchain
if (!m_bIntialized)
{
HRESULT Ret = InitializeNV12Surfaces(inputTexture);
if (!SUCCEEDED(Ret))
{
return Ret;
}
m_bIntialized = true;
}
m_pD3D11DeviceContext->CopyResource(m_ShaderResourceSurf, inputTexture);
D3D11_TEXTURE2D_DESC FrameDesc;
m_ShaderResourceSurf->GetDesc(&FrameDesc);
D3D11_SHADER_RESOURCE_VIEW_DESC ShaderDesc;
ShaderDesc.Format = FrameDesc.Format;
ShaderDesc.ViewDimension = D3D11_SRV_DIMENSION_TEXTURE2D;
ShaderDesc.Texture2D.MostDetailedMip = FrameDesc.MipLevels - 1;
ShaderDesc.Texture2D.MipLevels = FrameDesc.MipLevels;
// Create new shader resource view
ID3D11ShaderResourceView* ShaderResource = nullptr;
hr = m_pD3D11Device->CreateShaderResourceView(m_ShaderResourceSurf, &ShaderDesc, &ShaderResource);
IF_FAILED_THROW(hr);
m_pD3D11DeviceContext->PSSetShaderResources(0, 1, &ShaderResource);
// Set resources
m_pD3D11DeviceContext->OMSetRenderTargets(1, &m_pLumaRT, nullptr);
m_pD3D11DeviceContext->PSSetShader(m_pPixelShaderLuma, nullptr, 0);
m_pD3D11DeviceContext->RSSetViewports(1, &m_VPLuminance);
// Draw textured quad onto render target
m_pD3D11DeviceContext->Draw(NUMVERTICES, 0);
m_pD3D11DeviceContext->OMSetRenderTargets(1, &m_pChromaRT, nullptr);
m_pD3D11DeviceContext->PSSetShader(m_pPixelShaderChroma, nullptr, 0);
m_pD3D11DeviceContext->RSSetViewports(1, &m_VPChrominance);
// Draw textured quad onto render target
m_pD3D11DeviceContext->Draw(NUMVERTICES, 0);
// Release shader resource
ShaderResource->Release();
ShaderResource = nullptr;
return S_OK;
}
Init shaders:
void SetViewPort(D3D11_VIEWPORT* VP, UINT Width, UINT Height)
{
VP->Width = static_cast<FLOAT>(Width);
VP->Height = static_cast<FLOAT>(Height);
VP->MinDepth = 0.0f;
VP->MaxDepth = 1.0f;
VP->TopLeftX = 0;
VP->TopLeftY = 0;
}
HRESULT MakeRTV(ID3D11RenderTargetView** pRTV, ID3D11Texture2D* pSurf)
{
if (*pRTV)
{
(*pRTV)->Release();
*pRTV = nullptr;
}
// Create a render target view
HRESULT hr = m_pD3D11Device->CreateRenderTargetView(pSurf, nullptr, pRTV);
IF_FAILED_THROW(hr);
return S_OK;
}
HRESULT InitializeNV12Surfaces(ID3D11Texture2D* inputTexture)
{
ReleaseSurfaces();
D3D11_TEXTURE2D_DESC lOutputDuplDesc;
inputTexture->GetDesc(&lOutputDuplDesc);
// Create shared texture for all duplication threads to draw into
D3D11_TEXTURE2D_DESC DeskTexD;
RtlZeroMemory(&DeskTexD, sizeof(D3D11_TEXTURE2D_DESC));
DeskTexD.Width = lOutputDuplDesc.Width;
DeskTexD.Height = lOutputDuplDesc.Height;
DeskTexD.MipLevels = 1;
DeskTexD.ArraySize = 1;
DeskTexD.Format = lOutputDuplDesc.Format;
DeskTexD.SampleDesc.Count = 1;
DeskTexD.Usage = D3D11_USAGE_DEFAULT;
DeskTexD.BindFlags = D3D11_BIND_SHADER_RESOURCE;
HRESULT hr = m_pD3D11Device->CreateTexture2D(&DeskTexD, nullptr, &m_ShaderResourceSurf);
IF_FAILED_THROW(hr);
DeskTexD.Format = DXGI_FORMAT_R8_UNORM;
DeskTexD.BindFlags = D3D11_BIND_RENDER_TARGET;
hr = m_pD3D11Device->CreateTexture2D(&DeskTexD, nullptr, &m_LuminanceSurf);
IF_FAILED_THROW(hr);
DeskTexD.CPUAccessFlags = D3D11_CPU_ACCESS_READ;
DeskTexD.Usage = D3D11_USAGE_STAGING;
DeskTexD.BindFlags = 0;
hr = m_pD3D11Device->CreateTexture2D(&DeskTexD, NULL, &m_CPUAccessibleLuminanceSurf);
IF_FAILED_THROW(hr);
SetViewPort(&m_VPLuminance, DeskTexD.Width, DeskTexD.Height);
HRESULT Ret = MakeRTV(&m_pLumaRT, m_LuminanceSurf);
if (!SUCCEEDED(Ret))
return Ret;
DeskTexD.Width = lOutputDuplDesc.Width / 2;
DeskTexD.Height = lOutputDuplDesc.Height / 2;
DeskTexD.Format = DXGI_FORMAT_R8G8_UNORM;
DeskTexD.Usage = D3D11_USAGE_DEFAULT;
DeskTexD.CPUAccessFlags = 0;
DeskTexD.BindFlags = D3D11_BIND_RENDER_TARGET;
hr = m_pD3D11Device->CreateTexture2D(&DeskTexD, nullptr, &m_ChrominanceSurf);
IF_FAILED_THROW(hr);
DeskTexD.CPUAccessFlags = D3D11_CPU_ACCESS_READ;
DeskTexD.Usage = D3D11_USAGE_STAGING;
DeskTexD.BindFlags = 0;
hr = m_pD3D11Device->CreateTexture2D(&DeskTexD, NULL, &m_CPUAccessibleChrominanceSurf);
IF_FAILED_THROW(hr);
SetViewPort(&m_VPChrominance, DeskTexD.Width, DeskTexD.Height);
return MakeRTV(&m_pChromaRT, m_ChrominanceSurf);
}
HRESULT InitVertexShader(ID3D11VertexShader** ppID3D11VertexShader)
{
HRESULT hr = S_OK;
UINT Size = ARRAYSIZE(g_VS);
try
{
IF_FAILED_THROW(m_pD3D11Device->CreateVertexShader(g_VS, Size, NULL, ppID3D11VertexShader));;
m_pD3D11DeviceContext->VSSetShader(m_pVertexShader, nullptr, 0);
// Vertices for drawing whole texture
VERTEX Vertices[NUMVERTICES] =
{
{ XMFLOAT3(-1.0f, -1.0f, 0), XMFLOAT2(0.0f, 1.0f) },
{ XMFLOAT3(-1.0f, 1.0f, 0), XMFLOAT2(0.0f, 0.0f) },
{ XMFLOAT3(1.0f, -1.0f, 0), XMFLOAT2(1.0f, 1.0f) },
{ XMFLOAT3(1.0f, -1.0f, 0), XMFLOAT2(1.0f, 1.0f) },
{ XMFLOAT3(-1.0f, 1.0f, 0), XMFLOAT2(0.0f, 0.0f) },
{ XMFLOAT3(1.0f, 1.0f, 0), XMFLOAT2(1.0f, 0.0f) },
};
UINT Stride = sizeof(VERTEX);
UINT Offset = 0;
D3D11_BUFFER_DESC BufferDesc;
RtlZeroMemory(&BufferDesc, sizeof(BufferDesc));
BufferDesc.Usage = D3D11_USAGE_DEFAULT;
BufferDesc.ByteWidth = sizeof(VERTEX) * NUMVERTICES;
BufferDesc.BindFlags = D3D11_BIND_VERTEX_BUFFER;
BufferDesc.CPUAccessFlags = 0;
D3D11_SUBRESOURCE_DATA InitData;
RtlZeroMemory(&InitData, sizeof(InitData));
InitData.pSysMem = Vertices;
// Create vertex buffer
IF_FAILED_THROW(m_pD3D11Device->CreateBuffer(&BufferDesc, &InitData, &m_VertexBuffer));
m_pD3D11DeviceContext->IASetVertexBuffers(0, 1, &m_VertexBuffer, &Stride, &Offset);
m_pD3D11DeviceContext->IASetPrimitiveTopology(D3D11_PRIMITIVE_TOPOLOGY_TRIANGLELIST);
D3D11_INPUT_ELEMENT_DESC Layout[] =
{
{ "POSITION", 0, DXGI_FORMAT_R32G32B32_FLOAT, 0, 0, D3D11_INPUT_PER_VERTEX_DATA, 0 },
{ "TEXCOORD", 0, DXGI_FORMAT_R32G32_FLOAT, 0, 12, D3D11_INPUT_PER_VERTEX_DATA, 0 }
};
UINT NumElements = ARRAYSIZE(Layout);
hr = m_pD3D11Device->CreateInputLayout(Layout, NumElements, g_VS, Size, &m_pVertexLayout);
m_pD3D11DeviceContext->IASetInputLayout(m_pVertexLayout);
}
catch (HRESULT) {}
return hr;
}
HRESULT InitPixelShaders()
{
HRESULT hr = S_OK;
// Refer https://codeshare.io/5PJjxP for g_PS_Y & g_PS_UV blobs
try
{
UINT Size = ARRAYSIZE(g_PS_Y);
hr = m_pD3D11Device->CreatePixelShader(g_PS_Y, Size, nullptr, &m_pPixelShaderChroma);
IF_FAILED_THROW(hr);
Size = ARRAYSIZE(g_PS_UV);
hr = m_pD3D11Device->CreatePixelShader(g_PS_UV, Size, nullptr, &m_pPixelShaderLuma);
IF_FAILED_THROW(hr);
}
catch (HRESULT) {}
return hr;
}
I am experimenting this RGBA conversion to NV12 in the GPU only, using DirectX11.
This is a good challenge. I'm not familiar with Directx11, so this is my first experimentation.
Check this project for updates : D3D11ShaderNV12
In my current implementation (may not be the last), here is what I do:
Step 1: use a DXGI_FORMAT_B8G8R8A8_UNORM as input texture
Step 2: make a 1st pass shader to get 3 textures (Y:Luma, U:ChromaCb and V:ChromaCr): see YCbCrPS2.hlsl
Step 3: Y is DXGI_FORMAT_R8_UNORM, and is ready for final NV12 texture
Step 4: UV needs to be downsampled in a 2nd pass shader: see ScreenPS2.hlsl (using linear filtering)
Step 5: a third pass shader to sample Y texture
Step 6: a fourth pass shader to sample UV texture using a shift texture (I think other technique could be use)
My final texture is not DXGI_FORMAT_NV12, but a similar DXGI_FORMAT_R8_UNORM texture. My computer is Windows7, so DXGI_FORMAT_NV12 is not handled. I will try later on a another computer.
The process with pictures:
i am learning directx11 these days. and i have been stuck in compute shader section.
so i made four resource and three corresponding view.
immutable input buffer = {1,1,1,1,1} / SRV
immutable input buffer = {2,2,2,2,2} / SRV
output buffer / UAV
staging buffer for reading / No View
and i succeeded to create all things, and dispatch cs function, and copy data from output buffer to staging buffer, and i read/check data.
// INPUT BUFFER1--------------------------------------------------
const int dataSize = 5;
D3D11_BUFFER_DESC vb_dest;
vb_dest.ByteWidth = sizeof(float) * dataSize;
vb_dest.StructureByteStride = sizeof(float);
vb_dest.BindFlags = D3D11_BIND_SHADER_RESOURCE;
vb_dest.Usage = D3D11_USAGE_IMMUTABLE;
vb_dest.CPUAccessFlags = 0;
vb_dest.MiscFlags = 0;
float v1_float[dataSize] = { 1,1,1,1,1 };
D3D11_SUBRESOURCE_DATA v1_data;
v1_data.pSysMem = static_cast<void*>(v1_float);
device->CreateBuffer(
&vb_dest,
&v1_data,
valueBuffer1.GetAddressOf());
D3D11_SHADER_RESOURCE_VIEW_DESC srv_desc;
srv_desc.Format = DXGI_FORMAT_R32_FLOAT;
srv_desc.ViewDimension = D3D11_SRV_DIMENSION_BUFFER;
srv_desc.Buffer.FirstElement = 0;
srv_desc.Buffer.NumElements = dataSize;
srv_desc.Buffer.ElementWidth = sizeof(float);
device->CreateShaderResourceView(
valueBuffer1.Get(),
&srv_desc,
inputSRV1.GetAddressOf());
// INPUT BUFFER2-----------------------------------------------------------
float v2_float[dataSize] = { 2,2,2,2,2 };
D3D11_SUBRESOURCE_DATA v2_data;
v2_data.pSysMem = static_cast<void*>(v2_float);
device->CreateBuffer(
&vb_dest,
&v2_data,
valueBuffer2.GetAddressOf());
device->CreateShaderResourceView(
valueBuffer2.Get(),
&srv_desc,
inputSRV2.GetAddressOf());
// OUTPUT BUFFER-----------------------------------------------------------
D3D11_BUFFER_DESC ov_desc;
ov_desc.ByteWidth = sizeof(float) * dataSize;
ov_desc.StructureByteStride = sizeof(float);
ov_desc.BindFlags = D3D11_BIND_UNORDERED_ACCESS;
ov_desc.Usage = D3D11_USAGE_DEFAULT;
ov_desc.CPUAccessFlags = 0;
ov_desc.MiscFlags = 0;
device->CreateBuffer(
&ov_desc,
nullptr,
outputResource.GetAddressOf());
D3D11_UNORDERED_ACCESS_VIEW_DESC outputUAV_desc;
outputUAV_desc.Format = DXGI_FORMAT_R32_FLOAT;
outputUAV_desc.ViewDimension = D3D11_UAV_DIMENSION_BUFFER;
outputUAV_desc.Buffer.FirstElement = 0;
outputUAV_desc.Buffer.NumElements = dataSize;
outputUAV_desc.Buffer.Flags = 0;
device->CreateUnorderedAccessView(
outputResource.Get(),
&outputUAV_desc,
outputUAV.GetAddressOf());
// BUFFER FOR COPY-----------------------------------------------------------
D3D11_BUFFER_DESC rb_desc;
rb_desc.ByteWidth = sizeof(float) * dataSize;
rb_desc.StructureByteStride = sizeof(float);
rb_desc.Usage = D3D11_USAGE_STAGING;
rb_desc.CPUAccessFlags = D3D11_CPU_ACCESS_READ;
rb_desc.BindFlags = 0;
rb_desc.MiscFlags = 0;
device->CreateBuffer(
&rb_desc,
nullptr,
readResource.GetAddressOf());
// DISPATCH and COPY and GET DATA
dContext->CSSetShaderResources(0, 1, inputSRV1.GetAddressOf());
dContext->CSSetShaderResources(1, 1, inputSRV2.GetAddressOf());
dContext->CSSetUnorderedAccessViews(0, 1, outputUAV.GetAddressOf(), nullptr);
dContext->CSSetShader(cs.Get(), nullptr, 0);
dContext->Dispatch(1, 1, 1);
dContext->CopyResource(readResource.Get(), outputResource.Get());
D3D11_MAPPED_SUBRESOURCE mappedResource2;
ZeroMemory(&mappedResource2, sizeof(D3D11_MAPPED_SUBRESOURCE));
R_CHECK(dContext->Map(readResource.Get(), 0, D3D11_MAP_READ, 0, &mappedResource2));
float* data = static_cast<float*>(mappedResource2.pData);
for (int i = 0; i < 5; ++i)
{
int a = data[i];
}
and this is compute shader code
StructuredBuffer<float> inputA : register(t0);
StructuredBuffer<float> inputB : register(t1);
RWStructuredBuffer<float> output : register(u0);
[numthreads(5, 1, 1)]
void main(int3 id : SV_DispatchThreadID)
{
output[id.x] = inputA[id.x] + inputB[id.x];
}
in CS, it's adding two input buffer data and store into output buffer.
so expected answer would be {3,3,3,3,3}.
but the result is {3,0,0,0,0} only first idx has proper answer.
any advice would be amazing.
dContext->CopyResource(readResource.Get(), outputResource.Get());
D3D11_MAPPED_SUBRESOURCE mappedResource2;
ZeroMemory(&mappedResource2, sizeof(D3D11_MAPPED_SUBRESOURCE));
R_CHECK(dContext->Map(readResource.Get(), 0, D3D11_MAP_READ, 0, &mappedResource2));
float* data = static_cast<float*>(mappedResource2.pData);
for (int i = 0; i < 5; ++i)
{
int a = data[i];
}
this code should be like this.
CopyResource();
Map();
Declare and allocate 'data'
zeromemory(data);
memcopy(data, resource's pointer);
unMap();
for some reason, i have to use the memcopy instead of just reading resource directly with the pointer that i get from mapping.
I' m trying to render two textures one for RGB and another on for the alpha channel, I blend them together with a shader.
The alpha channel texture doesn't overlap properly to the RGB one. It seems to be stretched.
The alpha channel texture changes at every frame and I need to fill starting from an array of uint8_t by the following fuction:
D3DLOCKED_RECT locked_rect;
HRESULT hr = alpha_tex->LockRect(0, &locked_rect, nullptr, 0);
if (!FAILED(hr)) {
ret_code = 0;
BYTE *p_dst = (BYTE *)locked_rect.pBits;
for (uint y = 0; y < height; y++) {
memcpy(p_dst, alpha_array, width);
alpha_array += width;
p_dst += locked_rect.Pitch;
}
alpha_tex->UnlockRect(0);
}
where the alpha_array is a uint8_t array containing the alpha values.
To render the texture i use the following function:
hwctx->d3d9device->Clear(0, 0, D3DCLEAR_TARGET | D3DCLEAR_ZBUFFER, 0xffeeeeee, 1.0f, 0);
hwctx->d3d9device->BeginScene();
ctx->mFX->SetTechnique(ctx->mhTech);
ctx->texRGB->GetSurfaceLevel(0, &ctx->surfRGB);
hwctx->d3d9device->StretchRect((IDirect3DSurface9*)s->vdrFrame->data[3], NULL, ctx->surfRGB, NULL, D3DTEXF_LINEAR);
ctx->mFX->SetTexture(ctx->mhTexRGB, ctx->texRGB);
ctx->mFX->SetTexture(ctx->mhTexAlpha, ctx->texAlpha);
// Enable alpha blending.
hwctx->d3d9device->SetRenderState(D3DRS_ALPHABLENDENABLE, true);
hwctx->d3d9device->SetRenderState(D3DRS_SRCBLEND, D3DBLEND_SRCALPHA);
hwctx->d3d9device->SetRenderState(D3DRS_DESTBLEND, D3DBLEND_INVSRCALPHA);
UINT numPasses = 0;
ctx->mFX->Begin(&numPasses, 0);
for (UINT i = 0; i < numPasses; ++i){
ctx->mFX->BeginPass(i);
hwctx->d3d9device->DrawPrimitive(D3DPT_TRIANGLEFAN, 0, 2);
ctx->mFX->EndPass();
}
ctx->mFX->End();
hwctx->d3d9device->EndScene();
hwctx->d3d9device->Present(0, 0, 0, 0);
// Disable alpha blending.
hwctx->d3d9device->SetRenderState(D3DRS_ALPHABLENDENABLE, false);
I combine the textures by vertex/pixel shader:
uniform extern texture gTexRGB;
uniform extern texture gTexAlpha;
sampler TexRGB = sampler_state{
Texture = <gTexRGB>;
AddressU = WRAP;
AddressV = WRAP;
};
sampler TexAlpha = sampler_state{
Texture = <gTexAlpha>;
AddressU = WRAP;
AddressV = WRAP;
};
struct OutputVS{
float4 posH : POSITION0;
float2 tex0 : TEXCOORD0;
};
OutputVS TextureBlendingVS(float2 tex0: TEXCOORD0){
// Zero out our output.
OutputVS outVS = (OutputVS)0;
// Pass on texture coordinates to be interpolated in rasterization.
outVS.tex0 = tex0;
// Done--return the output.
return outVS;
}
float4 TextureBlendingPS(float2 tex0 : TEXCOORD0) : COLOR{
float3 rgb = tex2D(TexRGB, tex0).rgb;
float alpha = tex2D(TexAlpha, tex0).a;
return float4(rgb, alpha);
}
technique DirLightTexTech{
pass P0 {
// Specify the vertex and pixel shader associated with this pass.
vertexShader = compile vs_2_0 TextureBlendingVS();
pixelShader = compile ps_2_0 TextureBlendingPS();
}
}
The size of the textures is the same but during the rendering something goes wrong.
Please help me. :)
I am trying to read some data from a texture2d in DirectX11 compute shader, however, the 'Load' function of a texture2D object keeps returning 0 even though the texture object is filled with the same float number.
This is a 160 * 120 texture2d with DXGI_FORMAT_R32G32B32A32_FLOAT. The following code is how I created this resource:
HRESULT TestResources(ID3D11Device* pd3dDevice, ID3D11DeviceContext* pImmediateContext) {
float *test = new float[4 * 80 * 60 * 4]; // 80 * 60, 4 channels, 1 big texture contains 4 80 * 60 subimage
for (int i = 0; i < 4 * 80 * 60 * 4; i++) test[i] = 0.7f;
HRESULT hr = S_OK;
D3D11_TEXTURE2D_DESC RTtextureDesc;
ZeroMemory(&RTtextureDesc, sizeof(D3D11_TEXTURE2D_DESC));
RTtextureDesc.Width = 160;
RTtextureDesc.Height = 120;
RTtextureDesc.MipLevels = 1;
RTtextureDesc.ArraySize = 1;
RTtextureDesc.Format = DXGI_FORMAT_R32G32B32A32_FLOAT;
RTtextureDesc.SampleDesc.Count = 1;
RTtextureDesc.SampleDesc.Quality = 0;
RTtextureDesc.Usage = D3D11_USAGE_DYNAMIC;
RTtextureDesc.BindFlags = D3D11_BIND_SHADER_RESOURCE;
RTtextureDesc.CPUAccessFlags = D3D11_CPU_ACCESS_WRITE;
RTtextureDesc.MiscFlags = 0;
D3D11_SUBRESOURCE_DATA InitData;
InitData.pSysMem = test;
InitData.SysMemPitch = sizeof(float) * 4;
V_RETURN(pd3dDevice->CreateTexture2D(&RTtextureDesc, &InitData, &m_pInputTex2Ds));
//V_RETURN(pd3dDevice->CreateTexture2D(&RTtextureDesc, NULL, &m_pInputTex2Ds));
D3D11_SHADER_RESOURCE_VIEW_DESC SRViewDesc;
ZeroMemory(&SRViewDesc, sizeof(SRViewDesc));
SRViewDesc.Format = RTtextureDesc.Format;
SRViewDesc.ViewDimension = D3D11_SRV_DIMENSION_TEXTURE2D;
SRViewDesc.Texture2D.MostDetailedMip = 0;
SRViewDesc.Texture2D.MipLevels = 1;
V_RETURN(pd3dDevice->CreateShaderResourceView(m_pInputTex2Ds, &SRViewDesc, &m_pInputTexSRV));
delete[] test;
return hr;
}
And then I try to run dispatch with X = Y = 2 and Z = 1 like the following:
void ComputeShaderReduction::ExecuteComputeShader(ID3D11DeviceContext* pd3dImmediateContext, UINT uInputNum, ID3D11UnorderedAccessView** ppUAVInputs, UINT X, UINT Y, UINT Z) {
pd3dImmediateContext->CSSetShader(m_pComputeShader, nullptr, 0);
pd3dImmediateContext->CSSetShaderResources(0, 1, &m_pInputTexSRV); // test code
pd3dImmediateContext->CSSetUnorderedAccessViews(0, uInputNum, ppUAVInputs, nullptr);
//pd3dImmediateContext->CSSetUnorderedAccessViews(0, 1, &m_pGPUOutUAVs, nullptr);
pd3dImmediateContext->UpdateSubresource(m_pConstBuf, 0, nullptr, &m_ConstBuf, 0, 0);
pd3dImmediateContext->CSSetConstantBuffers(0, 1, &m_pConstBuf);
pd3dImmediateContext->Dispatch(X, Y, Z);
pd3dImmediateContext->CSSetShader(nullptr, nullptr, 0);
ID3D11UnorderedAccessView* ppUAViewnullptr[1] = { nullptr };
pd3dImmediateContext->CSSetUnorderedAccessViews(0, 1, ppUAViewnullptr, nullptr);
ID3D11ShaderResourceView* ppSRVnullptr[1] = { nullptr };
pd3dImmediateContext->CSSetShaderResources(0, 1, ppSRVnullptr);
ID3D11Buffer* ppCBnullptr[1] = { nullptr };
pd3dImmediateContext->CSSetConstantBuffers(0, 1, ppCBnullptr);
}
And I wrote a very simple CS shader to try to get the data in the texture2d and out it. So, the compute shader looks like this:
#define subimg_dim_x 80
#define subimg_dim_y 60
Texture2D<float4> BufferIn : register(t0);
StructuredBuffer<float> Test: register(t1);
RWStructuredBuffer<float> BufferOut : register(u0);
groupshared float sdata[subimg_dim_x];
[numthreads(subimg_dim_x, 1, 1)]
void CSMain(uint3 DTid : SV_DispatchThreadID,
uint3 threadIdx : SV_GroupThreadID,
uint3 groupIdx : SV_GroupID) {
sdata[threadIdx.x] = 0.0;
GroupMemoryBarrierWithGroupSync();
if (threadIdx.x == 0) {
float4 num = BufferIn.Load(uint3(groupIdx.x, groupIdx.y, 1));
//BufferOut[groupIdx.y * 2 + groupIdx.x] = 2.0; //This one gives me 2.0 as output in the console
BufferOut[groupIdx.y * 2 + groupIdx.x] = num.x; //This one keeps giving me 0.0 and in the texture, r = g = b = a = 0.7 or x = y = z = w = 0.7, so it suppose to print 0.7 in the console.
}
GroupMemoryBarrierWithGroupSync();
}
I think the way I print the CS shader result on CPU end is correct.
void ComputeShaderReduction::CopyToCPUBuffer(ID3D11Device* pdevice, ID3D11DeviceContext* pd3dImmediateContext, ID3D11Buffer* pGPUOutBufs) {
D3D11_BUFFER_DESC desc;
ZeroMemory(&desc, sizeof(desc));
pGPUOutBufs->GetDesc(&desc);
desc.CPUAccessFlags = D3D11_CPU_ACCESS_READ;
desc.Usage = D3D11_USAGE_STAGING;
desc.BindFlags = 0;
desc.MiscFlags = 0;
if (!m_pCPUOutBufs && SUCCEEDED(pdevice->CreateBuffer(&desc, nullptr, &m_pCPUOutBufs))) {
pd3dImmediateContext->CopyResource(m_pCPUOutBufs, pGPUOutBufs);
}
else pd3dImmediateContext->CopyResource(m_pCPUOutBufs, pGPUOutBufs);
D3D11_MAPPED_SUBRESOURCE MappedResource;
float *p;
pd3dImmediateContext->Map(m_pCPUOutBufs, 0, D3D11_MAP_READ, 0, &MappedResource);
p = (float*)MappedResource.pData;
for (int i = 0; i < 4; i++) printf("%d %f\n", i, p[i]);
pd3dImmediateContext->Unmap(m_pCPUOutBufs, 0);
printf("\n");
}
The buffer that bind to UAV has only 4 elements. So, if all the float numbers in my texture2d are 0.7, I should have 4 0.7s get printed in CopyToCPUBuffer function instead of 0.0s.
Is anyone know what could be wrong in my code or can someone provide me an entire example or a tutorial that shows how to read DirectX 11 texture2d's data in compute shader correctly?
Thanks in advance.
The following is wrong for a start. The Pitch of your input data is the number of bytes per row of the texture, not per pixel.
InitData.SysMemPitch = sizeof(float) * 4;
Secondly:
float4 num = BufferIn.Load(uint3(groupIdx.x, groupIdx.y, 1));
You're trying to load data from the 2nd mip of the texture, it only has 1 mip level.
I am trying to use the same image that I successfully shows using the ImageTargets Sample, the thing is my .h doesn't have "indices" or a constant of the type NUM_C_OBJECT_INDEX.
Now, that wouldn't be a problem normally as I would just change this like of code:
glDrawElements(GL_TRIANGLES, numIndices, GL_UNSIGNED_SHORT, indices);
for this one:
glDrawArrays(GL_TRIANGLES, 0, vertex);
where vertex = myObjectVertices. The thing is when I try to do this I get this error:
No matching function for call to 'glDrawArrays'
unless I use:
glDrawArrays(GL_TRIANGLES, 0, myObjectVertices); //so not the variable but the object itself.
the problem here is that since on FrameMarkers I am able to use several renders I need to be able to assign the variable so it delimits to the corresponding image but I can't figure how to get that error fixed aside from using the object itself which isn't useful. Any ideas?
My variables:
const GLvoid* vertices = 0;
const GLvoid* vertex = 0;
const GLvoid* normals = 0;
const GLvoid* indices = 0;
const GLvoid* texCoords = 0;
int numIndices = 0;
example:
case 1:
vertices = &CobjectVertices[0];
normals = &CobjectNormals[0];
indices = &CobjectIndices[0];
texCoords = &CobjectTexCoords[0];
numIndices = NUM_C_OBJECT_INDEX;
break;
case 2:
vertices = &myObjectVerts[0];
vertex = &myObjectVerts;
normals = &myObjectNormals[0];
texCoords = &myObjectTexCoords[0];
break;
Try this:
switch (marker->getMarkerId()) {
case 0:
//vertices = &QobjectVertices[0];
vertices = &1Verts[0];
normals = 0;
// indices = &QobjectIndices[0];
texCoords = &1TexCoords[0];
numIndices = NUM_1_INDEX;
quantVertices= 1NumVerts; //Vertices do Número 1
break;
case 1:
//vertices = &CobjectVertices[0];
vertices = &2Verts[0];
normals = 0;
//indices = &CobjectIndices[0];
texCoords = &2TexCoords[0];
numIndices = NUM_2_INDEX;
quantVertices= 2NumVerts; //Vertices do Número 2
break;
}
glDrawArrays(GL_TRIANGLES, 0,quantVertices);
What you need to do is pass in the vertices using
glVertexPointer( 3, GL_FLOAT, 0, vertex ); // vertex is pointer to vertices array
And then call
glDrawArrays(GL_TRIANGLES, 0, vertexCount); // vertexCount is the number of vertices you have in your array
glDrawArrays third argument must have GLsizei type, so basically it is an integer. In your code vertex variable is a pointer. It will not work. Pass an integer.