search

TiledTensor / TiledCUDA

TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.
MIT License
157 stars 10 forks source link

refactor(copy): refine the implementation of shared to register copy. #68

Closed haruhi55 closed 4 months ago

haruhi55 commented 4 months ago

resolve https://github.com/TiledTensor/TiledCUDA/issues/65 resolve https://github.com/TiledTensor/TiledCUDA/issues/63