[PATCH] mm: limit THP alignment – performance gain observed in AI inference workloads

[siddhartha@kenip.in]

Hi all,

I wanted to share validation data from a Hugging Face-based AI 
inferencing workload,
which was significantly impacted by the THP alignment logic introduced 
in commit efa7df3e3bb5.

Using transformer models with dynamic input lengths on Intel Xeon 
(Cooper Lake),
we observed up to a 3200% throughput improvement after applying the 
patch from Oct 2024:

   mm: limit THP alignment of anonymous mappings to PMD-aligned sizes

Metrics:
- Model: BERT-base
- Inference engine: Transformers + ONNX Runtime
- Kernel: 6.6 vs patched 6.6.8
- Batch size: 8-32, input length: 64-512 tokens
- Metric: inference throughput (samples/sec)

Thanks for the fix -- this change had real impact on a 
production-relevant workload.

Best Regards,
Siddhartha Sharma
ISV @ Kenip
Solution Link: 
https://www.intel.com/content/www/us/en/partner/showcase/offering/a5bHo00000045YUIAY/deadlock-clearance.html