conjugateGradientMultiDeviceCG -ewp -maxrregcount=64 --std=c++11 cudaHostAlloc cudaMemPrefetchAsync cudaFree cudaLaunchCooperativeKernel cudaMallocManaged cudaSetDevice cudaGetDeviceCount cudaGetDeviceProperties cudaFreeHost cudaMemset cudaStreamCreate cudaStreamSynchronize cudaDeviceEnablePeerAccess cudaMemAdvise cudaOccupancyMaxActiveBlocksPerMultiprocessor cudaDeviceCanAccessPeer whole ./ ../ ../../../Common Unified Memory Linear Algebra Cooperative Groups MultiDevice Cooperative Groups CUBLAS Library CUSPARSE Library CUDA Sparse Matrix Unified Memory Multi-GPU CPP11 cudadevrt true conjugateGradientMultiDeviceCG.cu UVM MDCG CPP11 1:CUDA Advanced Topics 3:Linear Algebra sm60 sm61 sm70 sm72 sm75 sm80 sm86 sm87 sm90 x86_64 linux ppc64le linux windows aarch64 sbsa 6.0 exe