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

[Lorenzo Stoakes <lorenzo.stoakes@oracle.com>]

+cc Vlata

On Fri, Jun 27, 2025 at 04:09:16PM +0530, siddhartha@kenip.in wrote:
> 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

All congratulations are owed to Vlastimil Babka for doing this, cc'd :)

I gather he enjoys novelty beer mugs as tokens of thanks ;)

>
> 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
>