Restructure the Tile Engine to have faster build time and clear config report (#2747)

* 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>
This commit is contained in:
Thomas Ning
2025-08-30 09:54:18 -04:00
committed by GitHub
parent fcff0043ae
commit 705804d9bf
17 changed files with 3361 additions and 1409 deletions

View File

@@ -25,13 +25,20 @@ if [ $# -ge 1 ]; then
GPU_TARGETS=$1
shift 1
echo "GPU targets provided: $GPU_TARGETS"
REST_ARGS=("$@")
;;
*)
echo "No GPU targets provided, using default targets: $GPU_TARGETS"
echo "No GPU targets provided, using default targets: gfx908;gfx90a;gfx942"
GPU_TARGETS="gfx908;gfx90a;gfx942"
shift 1
REST_ARGS=("$@")
;;
esac
else
echo "No GPU targets provided, using default targets: $GPU_TARGETS"
echo "No GPU targets provided, using default targets: gfx908;gfx90a;gfx942"
GPU_TARGETS="gfx908;gfx90a;gfx942"
shift 1
REST_ARGS=("$@")
fi
cmake \
@@ -43,5 +50,5 @@ cmake
-D GPU_TARGETS=$GPU_TARGETS \
-D CMAKE_VERBOSE_MAKEFILE:BOOL=ON \
-D USE_BITINT_EXTENSION_INT4=OFF \
$@ \
"${REST_ARGS[@]}" \ \
${MY_PROJECT_SOURCE}