From 4325f391987a16484fe273a897530d1089ff1e78 Mon Sep 17 00:00:00 2001 From: Eric Snow Date: Fri, 3 Nov 2023 12:17:54 -0600 Subject: [PATCH] Update the perf regression with the final benchmark results. --- peps/pep-0683.rst | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/peps/pep-0683.rst b/peps/pep-0683.rst index 6abdc1b46c7..939317cc943 100644 --- a/peps/pep-0683.rst +++ b/peps/pep-0683.rst @@ -230,20 +230,17 @@ those described above in `Motivation`_, reflect this improvement. Performance ----------- -A naive implementation shows `a 4% slowdown`_. We have demonstrated -a return to ~performance-neutral~ with a handful of basic mitigations -applied. See the `mitigations`_ section below. +A naive implementation shows `a 2% slowdown`_ (3% with MSVC). +We have demonstrated a return to ~performance-neutral~ with a handful +of basic mitigations applied. See the `mitigations`_ section below. + +.. _a 2% slowdown: https://github.com/python/cpython/pull/19474#issuecomment-1502245844 On the positive side, immortal objects save a significant amount of memory when used `with a pre-fork model `_. Also, immortal objects provide opportunities for specialization in the eval loop that would improve performance. -.. _a 4% slowdown: https://github.com/python/cpython/pull/19474#issuecomment-1032944709 - -TODO: Update the performance impact for the latest branch -(both for GCC and for clang). - Backward Compatibility ----------------------