gh-91404: Use computed gotos and reduce indirection in re (#91495)

python · Apr 15, 2022 · 1b34b56 · 1b34b56
1 parent d104f4d
commit 1b34b56
Show file tree

Hide file tree

Showing 6 changed files with 483 additions and 348 deletions.
diff --git a/Doc/whatsnew/3.11.rst b/Doc/whatsnew/3.11.rst
@@ -520,6 +520,12 @@ Optimizations
   becomes 272 bytes from 352 bytes on 64bit platform.
   (Contributed by Inada Naoki in :issue:`46845`.)
 
+* :mod:`re`'s regular expression matching engine has been partially refactored,
+  and now uses computed gotos (or "threaded code") on supported platforms. As a
+  result, Python 3.11 executes the `pyperformance regular expression benchmarks
+  <https://pyperformance.readthedocs.io/benchmarks.html#regex-dna>`_ up to 10%
+  faster than Python 3.10.
+
 
 Faster CPython
 ==============

diff --git a/Makefile.pre.in b/Makefile.pre.in
@@ -1351,11 +1351,12 @@ regen-stdlib-module-names: build_all Programs/_testembed
 	$(UPDATE_FILE) $(srcdir)/Python/stdlib_module_names.h $(srcdir)/Python/stdlib_module_names.h.new
 
 regen-sre:
-	# Regenerate Modules/_sre/sre_constants.h from Lib/re/_constants.py
-	# using Tools/scripts/generate_sre_constants.py
+	# Regenerate Modules/_sre/sre_constants.h and Modules/_sre/sre_targets.h
+	# from Lib/re/_constants.py using Tools/scripts/generate_sre_constants.py
 	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/scripts/generate_sre_constants.py \
 		$(srcdir)/Lib/re/_constants.py \
-		$(srcdir)/Modules/_sre/sre_constants.h
+		$(srcdir)/Modules/_sre/sre_constants.h \
+		$(srcdir)/Modules/_sre/sre_targets.h
 
 Python/compile.o Python/symtable.o Python/ast_unparse.o Python/ast.o Python/future.o: $(srcdir)/Include/internal/pycore_ast.h
 

diff --git a/Misc/NEWS.d/next/Library/2022-04-12-19-08-13.gh-issue-91404.zjqYHo.rst b/Misc/NEWS.d/next/Library/2022-04-12-19-08-13.gh-issue-91404.zjqYHo.rst
@@ -0,0 +1,3 @@
+Improve the performance of :mod:`re` matching by using computed gotos (or
+"threaded code") on supported platforms and removing expensive pointer
+indirections.