From: Ken Jin <kenjin@python.org>
Date: Sun, 11 Jan 2026 18:55:05 +0000 (+0800)
Subject: gh-139038: Update JIT perf figures for 3.14a4 (GH-143705)
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=9633f95b95eb7b14915c39620e83470e3c550015;p=thirdparty%2FPython%2Fcpython.git

gh-139038: Update JIT perf figures for 3.14a4 (GH-143705)
---

diff --git a/Doc/whatsnew/3.15.rst b/Doc/whatsnew/3.15.rst
index 6cb96c074c78..115b7b3c86e0 100644
--- a/Doc/whatsnew/3.15.rst
+++ b/Doc/whatsnew/3.15.rst
@@ -889,14 +889,14 @@ Upgraded JIT compiler
 
 Results from the `pyperformance <https://github.com/python/pyperformance>`__
 benchmark suite report
-`3-4% <https://github.com/facebookexperimental/free-threading-benchmarking/blob/main/results/bm-20251214-3.15.0a2%2B-6cddf04-JIT/bm-20251214-vultr-x86_64-python-6cddf04344a1e8ca9df5-3.15.0a2%2B-6cddf04-vs-base.svg>`__
+`4-5% <https://raw.githubusercontent.com/facebookexperimental/free-threading-benchmarking/refs/heads/main/results/bm-20260110-3.15.0a3%2B-aa8578d-JIT/bm-20260110-vultr-x86_64-python-aa8578dc54df2af9daa3-3.15.0a3%2B-aa8578d-vs-base.svg>`__
 geometric mean performance improvement for the JIT over the standard CPython
 interpreter built with all optimizations enabled on x86-64 Linux. On AArch64
 macOS, the JIT has a
-`7-8% <https://raw.githubusercontent.com/facebookexperimental/free-threading-benchmarking/refs/heads/main/results/bm-20260103-3.15.0a3%2B-9609574-JIT/bm-20260103-macm4pro-arm64-python-9609574e7fd36edfaa8b-3.15.0a3%2B-9609574-vs-base.svg>`__
+`7-8% <https://raw.githubusercontent.com/facebookexperimental/free-threading-benchmarking/refs/heads/main/results/bm-20260110-3.15.0a3%2B-aa8578d-JIT/bm-20260110-macm4pro-arm64-python-aa8578dc54df2af9daa3-3.15.0a3%2B-aa8578d-vs-base.svg>`__
 speedup over the :ref:`tail calling interpreter <whatsnew314-tail-call-interpreter>`
 with all optimizations enabled. The speedups for JIT
-builds versus no JIT builds range from roughly 20% slowdown to over
+builds versus no JIT builds range from roughly 15% slowdown to over
 100% speedup (ignoring the ``unpack_sequence`` microbenchmark) on
 x86-64 Linux and AArch64 macOS systems.