cdpAdvancedQuicksort -dc -maxrregcount=64 --std=c++14 cudaStreamCreateWithFlags cudaMemcpy cudaMemcpyAsync cudaFree cudaGetErrorString cudaGetLastError cudaPeekAtLastError cudaDeviceSynchronize cudaEventRecord cudaMemset cudaMalloc cudaEventElapsedTime cudaGetDeviceProperties cudaEventCreate ./ ../ ../../../Common Cooperative Groups CUDA Dynamic Parallelism GPGPU CPP14 cudadevrt true cdpAdvancedQuicksort.cu CDP 1:CUDA Advanced Topics x86_64 linux windows7 x86_64 macosx arm sbsa ppc64le linux 3.5 Advanced Quicksort (CUDA Dynamic Parallelism) exe