cc.sh

/home/prashant/iree/.venv/bin/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-codegen-gpu-native-math-precision=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    punet.mlir   -o old.vmfb

/home/prashant/iree-build/tools/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-codegen-gpu-native-math-precision=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      punet.mlir --iree-hal-dump-executable-sources-to=dump/  -o  new.vmfb -mlir-disable-threading 2> err.txt -mlir-print-debuginfo



iree-run-module \
  --device=hip://0 \
  --device_allocator=caching \
  --module=old.vmfb \
  --parameters=model=checkpoint_pipe_punet_dataset_i8.irpa \
  --function=main \
  --input=1x4x128x128xf16=0.5 \
  --input=1xf16=0.5 \
  --input=2x64x2048xf16=0.5 \
  --input=2x1280xf16=0.5 \
  --input=2x6xf16=0.5 \
  --input=1xf16=0.5 [email protected]

 iree-run-module \
  --device=hip://0 \
  --device_allocator=caching \
  --module=new.vmfb \
  --parameters=model=checkpoint_pipe_punet_dataset_i8.irpa \
  --function=main \
  --input=1x4x128x128xf16=0.5 \
  --input=1xf16=0.5 \
  --input=2x64x2048xf16=0.5 \
  --input=2x1280xf16=0.5 \
  --input=2x6xf16=0.5 \
  --input=1xf16=0.5 [email protected]

 python compare.py