ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-19 12:30:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

GEMM+Bias+ReLU+Add (#76)

Browse Source 
* tweak conv for odd C

* update script

* clean up elementwise op

* fix build

* clean up

* added example for gemm+bias+relu+add

* added example for gemm+bias+relu

* add profiler for gemm_s_shuffle; re-org files

* add profiler

* fix build

* clean up

* clean up

* clean up

* fix build

[ROCm/composable_kernel commit: 823657ed12]
This commit is contained in:
Chao Liu
2022-02-06 22:32:47 -06:00
committed by GitHub
parent 8890cc207d
commit 8efcb80fa5
77 changed files with 3865 additions and 932 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
script/gemm.sh Executable file
View File

@@ -0,0 +1,20 @@
#!/bin/bash
## GPU visibility
export HIP_VISIBLE_DEVICES=0
make -j $1
DRIVER=example/$1
VERIFY=$2
INIT=$3
REPEAT=$4
######## verify init repeat M___ N___ K___ StrideA StrideB StrideC StrideC1
#$DRIVER $VERIFY $INIT $REPEAT 256 256 256 256 256 256 256
#$DRIVER $VERIFY $INIT $REPEAT 960 1024 1024 1024 1024 1024 1024
#$DRIVER $VERIFY $INIT $REPEAT 1920 2048 2048 2048 2048 2048 2048
$DRIVER $VERIFY $INIT $REPEAT 3840 4096 4096 4096 4096 4096 4096
#$DRIVER $VERIFY $INIT $REPEAT 7680 8192 8192 8192 8192 8192 8192
#$DRIVER $VERIFY $INIT $REPEAT 1024 1024 1024 1024 1024 1024 1024
#$DRIVER $VERIFY $INIT $REPEAT 2048 2048 2048 2048 2048 2048 2048