refactor(cell): Refactor GEMM according to the changes in the RegTile definition.

TiledTensor / TiledCUDA

TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.

MIT License

158 stars 10 forks source link

Closed haruhi55 closed 4 months ago

haruhi55 commented 4 months ago

Refactor the wrapper for the WMMA PTX instruction based on the updated RegTile definition.