Skip to content

Commit fc53ffe

Browse files
committed
Add comment linking to the likely culprit in GCC.
1 parent 087f134 commit fc53ffe

File tree

1 file changed

+2
-1
lines changed

1 file changed

+2
-1
lines changed

Python/ceval.c

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -951,7 +951,8 @@ _PyObjectArray_Free(PyObject **array, PyObject **scratch)
951951
#if (defined(__GNUC__) && __GNUC__ >= 10 && !defined(__clang__)) && defined(__x86_64__)
952952
/*
953953
* gh-129987: The SLP autovectorizer can cause poor code generation for
954-
* opcode dispatch in some GCC versions (observed in GCCs 12 through 15),
954+
* opcode dispatch in some GCC versions (observed in GCCs 12 through 15,
955+
* probably caused by https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115777),
955956
* negating any benefit we get from vectorization elsewhere in the
956957
* interpreter loop. Disabling it significantly affected older GCC versions
957958
* (prior to GCC 9, 40% performance drop), so we have to selectively disable

0 commit comments

Comments
 (0)