cdpAdvancedQuicksort -dc -maxrregcount=64 --std=c++14 cudaMemset cudaFree cudaEventRecord cudaEventCreate cudaEventElapsedTime cudaDeviceSynchronize cudaPeekAtLastError cudaMalloc cudaStreamCreateWithFlags cudaGetLastError cudaMemcpyAsync cudaMemcpy cudaGetErrorString cudaGetDeviceProperties ./ ../ ../../../Common Cooperative Groups CUDA Dynamic Parallelism GPGPU CPP14 cudadevrt true cdpAdvancedQuicksort.cu CDP 1:CUDA Advanced Topics sm35 sm37 sm50 sm52 sm53 sm60 sm61 sm70 sm72 sm75 sm80 sm86 sm87 x86_64 linux windows7 x86_64 macosx arm sbsa ppc64le linux 3.5 Advanced Quicksort (CUDA Dynamic Parallelism) exe