[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <28338f055b3c9afa8b69ff6f05ea20ed@kenip.in>
Date: Fri, 27 Jun 2025 16:09:16 +0530
From: siddhartha@...ip.in
To: linux-mm@...ck.org
Cc: linux-kernel@...r.kernel.org, mgorman@...e.de
Subject: [PATCH] mm: limit THP alignment – performance gain observed in AI inference workloads
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
Powered by blists - more mailing lists