Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update Custom OPs broken references #739

Merged
merged 1 commit into from
Dec 24, 2024
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions tests/cpu/bench/custom_op_bench/README.md
Original file line number Diff line number Diff line change
@@ -1,14 +1,14 @@
# Running benchmarks for Intel Extension for PyTorch Custom OPs
Evaluate performance for custom operator with [launcher](../../../../tutorials/intro_launch.md).
Evaluate performance for custom operator with [launcher](../../../../docs/tutorials/performance_tuning/launch_script.md).
## Prepare envrioment
Follow [performance_tuning_guide](../../../../tutorials/Performance_Tuning.md) to install Memory_Allocator(you can choose Tcmalloc or Jemalloc).
Follow [performance_tuning_guide](../../../../docs/tutorials/performance_tuning/tuning_guide.md) to install Memory_Allocator(you can choose Tcmalloc or Jemalloc).
Install intel-openmp:

```
pip install intel-openmp=2024.1.2
```

## Evaluate [Interaction](../../../../intel_extension_for_pytorch/nn/functional/interaction.py)
## Evaluate [Interaction](../../../../intel_extension_for_pytorch/cpu/nn/interaction.py)

1.Inference: 1 instance per core in real world scenario

Expand All @@ -34,7 +34,7 @@ python -m intel_extension_for_pytorch.cpu.launch --node-id 0 optimizer.py --opti
python -m intel_extension_for_pytorch.cpu.launch --node-id 0 optimizer.py --optimizer adam # for adam
```

## Evaluate IPEX [MergedEmbeddingBag](../../../../intel_extension_for_pytorch/nn/module/merged_embeddingbag.py)
## Evaluate IPEX [MergedEmbeddingBag](../../../../intel_extension_for_pytorch/nn/modules/merged_embeddingbag.py)
```
export CORES=`lscpu | grep Core | awk '{print $4}'`
export BATCHSIZE=$((128*CORES))
Expand Down