cc.sh

echo "compiling the old vmfb"
iree-compile --iree-hal-target-backends=rocm --iree-hip-target=gfx942 --iree-vm-bytecode-module-output-format=flatbuffer-binary --iree-preprocessing-pass-pipeline="builtin.module(util.func(iree-global-opt-raise-special-ops, iree-flow-canonicalize), iree-preprocessing-transpose-convolution-pipeline, iree-preprocessing-pad-to-intrinsics, util.func(iree-preprocessing-generalize-linalg-matmul-experimental))" --iree-hal-dump-executable-files-to=dump/ --iree-dispatch-creation-enable-aggressive-fusion --iree-dispatch-creation-enable-fuse-horizontal-contractions=false --iree-opt-aggressively-propagate-transposes=true --iree-codegen-llvmgpu-use-vector-distribution=true --iree-opt-data-tiling=false --iree-vm-target-truncate-unsupported-floats --iree-opt-outer-dim-concat=true  --iree-hal-indirect-command-buffers=true --iree-stream-resource-memory-model=discrete --iree-hal-memoization=true --iree-opt-strip-assertions --iree-global-opt-propagate-transposes=true --iree-opt-const-eval=false --iree-llvmgpu-enable-prefetch=true --iree-execution-model=async-external     test.mlir   -o old.vmfb -mlir-print-ir-after-all 2> warp.txt


echo "compiling the new vmfb"
iree-compile --iree-hal-target-backends=rocm --iree-hip-target=gfx942 --iree-vm-bytecode-module-output-format=flatbuffer-binary --iree-preprocessing-pass-pipeline="builtin.module(util.func(iree-global-opt-raise-special-ops, iree-flow-canonicalize), iree-preprocessing-transpose-convolution-pipeline, iree-preprocessing-pad-to-intrinsics, util.func(iree-preprocessing-generalize-linalg-matmul-experimental))" --iree-hal-dump-executable-files-to=dump/ --iree-dispatch-creation-enable-aggressive-fusion --iree-dispatch-creation-enable-fuse-horizontal-contractions=false --iree-opt-aggressively-propagate-transposes=true --iree-codegen-llvmgpu-use-vector-distribution=true --iree-opt-data-tiling=false --iree-vm-target-truncate-unsupported-floats --iree-opt-outer-dim-concat=true  --iree-hal-indirect-command-buffers=true --iree-stream-resource-memory-model=discrete --iree-hal-memoization=true --iree-opt-strip-assertions --iree-global-opt-propagate-transposes=true --iree-opt-const-eval=false --iree-llvmgpu-enable-prefetch=true --iree-execution-model=async-external  -iree-codegen-llvmgpu-test-vector-distribution-on-reduction   test.mlir   -o  new.vmfb -mlir-disable-threading -mlir-print-ir-after-all 2> vecd.txt



echo "running the old vmfb"
iree-run-module \
--device=hip://0 \
--device_allocator=caching \
--module=old.vmfb \
--parameters=model=checkpoint_pipe_punet_dataset_i8.irpa \
--function=faulty \
[email protected] \
[email protected]  [email protected]

echo "running the new vmfb"
iree-run-module \
--device=hip://0 \
--device_allocator=caching \
--module=new.vmfb \
--parameters=model=checkpoint_pipe_punet_dataset_i8.irpa \
--function=faulty \
[email protected] \
[email protected]  [email protected]


python compare.py