taichi_benchmark
taichi_benchmark copied to clipboard
Published
20 hours ago •
taichi-dev
taichi-dev
Results
3
taichi_benchmark issues
Sort by
recently updated
recently updated
newest added
Moved the MAC benchmark code from houkensjtu's repo. More work needs to be done to refine the code and explanations.
Currently we support warp-based parallel [scan](https://github.com/taichi-dev/taichi_benchmark/blob/main/prefix_scan/taichi/scan.py) for Vulkan and CUDA. Lets use this issue to track some performance data: ENV: RTX3080 with Driver 510. CUDA 11.6. | Number of elements...
