Top Answers

1. __activemask() vs __ballot_sync()
   23 votes
2. CUDA How Does Kernel Fusion Improve Performance on Memory Bound Applications on the GPU?
   18 votes
3. How can I get the number of CUDA cores in my GPU using Python and Numba?
   14 votes
4. How to generalize fast matrix multiplication on GPU using numba
   12 votes
5. CUDA 9 shfl vs. shfl_sync
   12 votes