mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 10:09:41 +00:00
06fad18aaf
* Making edits to identify individual compilation issues.
* Minor fix for blob txt files not being created.
* Fixing compilation issues.
* Fixing ordering bug.
* Adding python profiling functionality.
* Setting individual build as default.
* Setting gpu target filtering for tile engine to gfx90a, gfx942 and gfx950.
* update the default running parameters and settings
* Fixing bug with benchmarking, shifting file generation to build instead of config.
* Updating fixes.
* Fixing json output and parsing.
* Disable ccache for tile engine gemm ops because we dont need it.
* Removing duplicate type definition.
* Improving json printing.
* Add the flexibility of different layout and more warp tile support
* Fix extra flag in name of individual kernels.
* Fixing bug with booleans.
* Solve the first patch of the post merge conflict
* Compilation fixes, and cosmetic improvements.
* Yet again compilation fixes after latest changes from develop.
* Fixing python benchmarking script.
---------
Co-authored-by: Vidyasagar Ananthan <vidyasagar.ananthan@amd.com>
Co-authored-by: Vidyasagar Ananthan <vanantha@amd.com>
[ROCm/composable_kernel commit: 705804d9bf]
55 lines
2.2 KiB
Bash
Executable File
55 lines
2.2 KiB
Bash
Executable File
#!/bin/bash
|
|
# exit when a command exits with non-zero status; also when an unbound variable is referenced
|
|
set -eu
|
|
# pipefail is supported by many shells, not supported by sh and dash
|
|
set -o pipefail 2>/dev/null | true
|
|
# when treating a string as a sequence, do not split on spaces
|
|
IFS=$(printf '\n\t')
|
|
|
|
# clean the build system files
|
|
find . -name CMakeFiles -type d -exec rm -rfv {} +
|
|
find . -name CMakeCache.txt -type f -exec rm -rv {} +
|
|
|
|
if [ $# -ge 1 ]; then
|
|
MY_PROJECT_SOURCE="$1"
|
|
shift 1
|
|
else
|
|
MY_PROJECT_SOURCE=".."
|
|
fi
|
|
|
|
GPU_TARGETS="gfx908;gfx90a;gfx942"
|
|
|
|
if [ $# -ge 1 ]; then
|
|
case "$1" in
|
|
gfx*)
|
|
GPU_TARGETS=$1
|
|
shift 1
|
|
echo "GPU targets provided: $GPU_TARGETS"
|
|
REST_ARGS=("$@")
|
|
;;
|
|
*)
|
|
echo "No GPU targets provided, using default targets: gfx908;gfx90a;gfx942"
|
|
GPU_TARGETS="gfx908;gfx90a;gfx942"
|
|
shift 1
|
|
REST_ARGS=("$@")
|
|
;;
|
|
esac
|
|
else
|
|
echo "No GPU targets provided, using default targets: gfx908;gfx90a;gfx942"
|
|
GPU_TARGETS="gfx908;gfx90a;gfx942"
|
|
shift 1
|
|
REST_ARGS=("$@")
|
|
fi
|
|
|
|
cmake \
|
|
-D CMAKE_PREFIX_PATH=/opt/rocm/ \
|
|
-D CMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/clang++ \
|
|
-D CMAKE_CXX_FLAGS="-ftemplate-backtrace-limit=0 -fPIE -Wno-gnu-line-marker" \
|
|
-D CMAKE_BUILD_TYPE=Release \
|
|
-D BUILD_DEV=ON \
|
|
-D GPU_TARGETS=$GPU_TARGETS \
|
|
-D CMAKE_VERBOSE_MAKEFILE:BOOL=ON \
|
|
-D USE_BITINT_EXTENSION_INT4=OFF \
|
|
"${REST_ARGS[@]}" \ \
|
|
${MY_PROJECT_SOURCE}
|