composable_kernel

mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 10:09:41 +00:00

Files

Shaojie WANG cd3fbda406 example for convnd bwd weight bf16 splitk (#265 )

* add GetWorkSpaceSize to base arg and make an example on convnd_bwd_weight

* add bwd weight for bf16: init

* remove redundant compute

* use datatype and split k to check whether a workspace is used

* remove unused computation for work space size

* add some code for bfp16

* add device/grid unary op

* add unary type convert to bwd-weight example

* support bf16 splitk kernel for convnd bwd weight

* 1. remove comments. 2. add checkvalidity. 3. add gridsize computation

* add workspace size check

* fix format

* change function name

[ROCm/composable_kernel commit: 561ec12f4a]

2022-06-16 14:16:01 -05:00

host_utility

Navi21 gemm (#197 )

2022-05-24 12:19:27 -05:00

problem_transform

Unified implementation of 1d/2d/3d conv bwd-data. fp32/fp16/bfp16/int8 (#134 )

2022-03-29 10:52:25 -05:00

tensor

Compile for gfx908 and gfx90a (#130 )

2022-03-31 12:33:34 -05:00

tensor_description

Resolution of issue #153 : Add compiler warning on comparing int and size_t (#212 )