mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-11 17:00:18 +00:00
* add DeviceGemmXdl * update script * fix naming issue * fix comment * output HostTensorDescriptor * rename * padded GEMM for fwd v4r4r4 nhwc * refactor * refactor * refactor * adding ckProfiler * adding ckProfiler * refactor * fix tuning parameter bug * add more gemm instances * add more fp16 GEMM instances * fix profiler driver * fix bug in tuning parameter * add fp32 gemm instances * small fix * refactor * rename * refactor gemm profiler; adding DeviceConv and conv profiler * refactor * fix * add conv profiler * refactor * adding more GEMM and Conv instance * Create README.md Add build instruction for ckProfiler * Create README.md Add Readme for gemm_xdl example * Update README.md Remove build instruction from top most folder * Update README.md * clean up
26 lines
684 B
Bash
Executable File
26 lines
684 B
Bash
Executable File
#!/bin/bash
|
|
|
|
## GPU visibility
|
|
export HIP_VISIBLE_DEVICES=0
|
|
|
|
make -j gemm_driver_offline
|
|
|
|
DRIVER="./host/driver_offline/gemm_driver_offline"
|
|
|
|
LAYOUT=$1
|
|
ALGO=$2
|
|
VERIFY=$3
|
|
INIT=$4
|
|
LOG=$5
|
|
REPEAT=$6
|
|
|
|
M01=$7
|
|
N01=$8
|
|
|
|
######### layout algo verify init log repeat M___ N___ K___ M01_ N01_
|
|
#$DRIVER $LAYOUT $ALGO $VERIFY $INIT $LOG $REPEAT 960 1024 1024 $M01 $N01
|
|
#$DRIVER $LAYOUT $ALGO $VERIFY $INIT $LOG $REPEAT 1024 1024 1024 $M01 $N01
|
|
#$DRIVER $LAYOUT $ALGO $VERIFY $INIT $LOG $REPEAT 1920 2048 2048 $M01 $N01
|
|
$DRIVER $LAYOUT $ALGO $VERIFY $INIT $LOG $REPEAT 3840 4096 4096 $M01 $N01
|
|
#$DRIVER $LAYOUT $ALGO $VERIFY $INIT $LOG $REPEAT 7680 8192 8192 $M01 $N01
|