CUDA Warp Primitives | __shfl_sync | Video Walkthrough (44+ minutes) Posted on March 11, 2019 by admin NVIDIA CUDA / GPU Programming Tags: cuda ballot, cuda c++, cuda code, cuda mask, cuda optimisation, cuda optimization, cuda registers, cuda shuffle sync, cuda warp primitives, cuda warp registers, cuda warp shuffle, cuda _activemask(), cuda __shfl_sync, _shfl, _shfl_sync, __activemask(), __shfl