From b988f8f3358703fab3a0c050165a13e480b10ccf Mon Sep 17 00:00:00 2001 From: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com> Date: Sun, 27 Sep 2026 11:43:17 +0300 Subject: [PATCH 1/2] Update JIT perf numbers in What's New --- Doc/whatsnew/3.15.rst | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/Doc/whatsnew/3.15.rst b/Doc/whatsnew/3.15.rst index aabc936a24af79c..62b49dd40e103ec 100644 --- a/Doc/whatsnew/3.15.rst +++ b/Doc/whatsnew/3.15.rst @@ -2031,20 +2031,17 @@ Upgraded experimental JIT compiler Results from the `pyperformance `__ benchmark suite report -`8-9% `__ +`7-8% `__ 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 -`12-13% `__ +`11-12% `__ speedup over the :ref:`tail calling interpreter ` with all optimizations enabled. The speedups for JIT 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. -.. attention:: - These results are not yet final. - The major upgrades to the JIT are: * LLVM 21 build-time dependency From 021a846f6e3fd0f263188f514ea510f8ac8dc794 Mon Sep 17 00:00:00 2001 From: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com> Date: Sun, 27 Sep 2026 11:48:55 +0300 Subject: [PATCH 2/2] Add/update articles Co-authored-by: Stan Ulbrych Co-authored-by: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com> --- Doc/whatsnew/3.15.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Doc/whatsnew/3.15.rst b/Doc/whatsnew/3.15.rst index 62b49dd40e103ec..ffd0d64b2297413 100644 --- a/Doc/whatsnew/3.15.rst +++ b/Doc/whatsnew/3.15.rst @@ -2030,11 +2030,11 @@ Upgraded experimental JIT compiler ---------------------------------- Results from the `pyperformance `__ -benchmark suite report +benchmark suite report a `7-8% `__ 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 +macOS, the JIT has an `11-12% `__ speedup over the :ref:`tail calling interpreter ` with all optimizations enabled. The speedups for JIT