streamOrderedAllocation cudaDeviceGetDefaultMemPool cudaFreeAsync cudaStreamCreateWithFlags cudaStreamDestroy cudaDeviceGetAttribute cudaMallocAsync cudaSetDevice cudaEventSynchronize cudaEventRecord cudaStreamSynchronize cudaMemPoolSetAttribute cudaEventElapsedTime cudaMemcpyAsync cudaEventCreate whole ./ ../ ../../../Common Performance Strategies true streamOrderedAllocation.cu 1:CUDA Basic Topics 1:Performance Strategies sm60 sm61 sm70 sm72 sm75 sm80 sm86 sm87 sm90 x86_64 linux windows7 arm sbsa ppc64le linux 6.0 exe