ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-15 10:37:44 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
fbc03c595d7140df7e132dfcba04bd1da736633c
composable_kernel/include/ck/tensor_operation/gpu/grid
History
Qianfeng 573f1de6fa Improve Reduction kernel api (#152) 
* Add ThreadwiseReduction functor as per-thread reduction api

* Using ThreadwiseReduce api and some change in using PartitionedBlockwiseReduction api to simply the kernels

* Add comments and remove useless declarations in the kernels

* Tiny updates

[ROCm/composable_kernel commit: 82c8b9f8ee]
2022-04-04 20:31:44 -05:00
..
gridwise_2d_reduction_blockwise.hpp
Improve Reduction kernel api (#152)
2022-04-04 20:31:44 -05:00
gridwise_2d_reduction_multiblock_atomic_add.hpp
Improve Reduction kernel api (#152)
2022-04-04 20:31:44 -05:00
gridwise_2d_reduction_multiblock_partial_reduce.hpp
Improve Reduction kernel api (#152)
2022-04-04 20:31:44 -05:00
gridwise_2d_reduction_threadwise.hpp
Improve Reduction kernel api (#152)
2022-04-04 20:31:44 -05:00
gridwise_contraction_dlops_v1r2.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00
gridwise_gemm_dlops_v1r2.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00
gridwise_gemm_dlops_v1r3.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00
gridwise_gemm_dlops_v2.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00
gridwise_gemm_dlops_v3.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00
gridwise_gemm_pipeline_v1.hpp
Reorganize files, Part 1 (#119)
2022-03-08 21:46:36 -06:00
gridwise_gemm_reduce_xdl_cshuffle_v1.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00
gridwise_gemm_xdl_cshuffle_v1.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00
gridwise_gemm_xdlops_v2r3.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00
gridwise_gemm_xdlops_v2r4.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00
gridwise_gemm_xdlops_v2r4r2.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00
gridwise_gemm_xdlops_v3r1.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00
gridwise_gemm_xdlops_v3r2.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00
gridwise_gemm_xdlops_v3r3.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00
gridwise_set_buffer_value.hpp
Compile for gfx908 and gfx90a (#130)
2022-03-31 12:33:34 -05:00