Copy Directx12 to cuda memory

Accelerated Computing CUDA CUDA Programming and Performance
,
1

Hello,

I’m trying to copy a directx12 texture (content of a backbuffer) to cuda memory.
So I 've followed the cuda sample and it works, but my algorithm can be more efficient

void* pData = nullptr;
	cudaExternalMemoryBufferDesc buffDesc{};
	memset(&buffDesc, 0, sizeof(buffDesc));

	buffDesc.offset = 0;
	buffDesc.size = d3d12Texture.memSize;

	cudaExternalMemoryGetMappedBuffer(&pData, m_externalMemory, &buffDesc);
	auto format = cv::directx::getTypeFromDXGI_FORMAT(31);//D3DFMT_A2B10G10R10 is the same as DXGI_FORMAT_R10G10B10A2_UNORM

	cv::cuda::GpuMat(static_cast<int>(d3d12Texture.resource->GetDesc().Height),
		static_cast<int>(d3d12Texture.resource->GetDesc().Width),
		format, pData).copyTo(mat);
		
	cudaFree(pData);

The code is called at each new frame. Does the memory pData can be mapped without freeing at every call ?
thanks.