Author: Thibault Monnier Date: 2026-02-26T19:56:47+01:00 New Revision: f6917fa6c90a9d55d3bfd9d8aa4583834771565d
URL: https://github.com/llvm/llvm-project/commit/f6917fa6c90a9d55d3bfd9d8aa4583834771565d DIFF: https://github.com/llvm/llvm-project/commit/f6917fa6c90a9d55d3bfd9d8aa4583834771565d.diff LOG: [Clang][Lexer][Performance] Optimize Lexer whitespace skipping logic (#180819) ... by extracting the check for space character and marking it as `LLVM_LIKELY`. This increases performance because the space is by far the most common horizontal character, so in most cases, this change allows to replace a lookup table check with a simple comparison, reducing latency and helping the cache. This does not reduce instruction count, as a lookup table and a comparison are both a single instruction. However, it _does_ reduce cycles in a consistent manner, around `0.2` - `0.3`%: [benchmark](https://llvm-compile-time-tracker.com/compare.php?from=3192fe2c7b08912cc72c86471a593165b615dc28&to=faa899a6ce518c1176f2bf59f199eb42e59d840e&stat=cycles). I tested this locally and am able to confirm this is not noise (at least not entirely, it does feel weird that this impacts `O3` more than `O0`...), as I achieved almost `2`% faster PP speed in my tests. Added: Modified: clang/lib/Lex/Lexer.cpp Removed: ################################################################################ diff --git a/clang/lib/Lex/Lexer.cpp b/clang/lib/Lex/Lexer.cpp index 92c3046a6fd19..b100fc29fcd69 100644 --- a/clang/lib/Lex/Lexer.cpp +++ b/clang/lib/Lex/Lexer.cpp @@ -2533,8 +2533,8 @@ bool Lexer::SkipWhitespace(Token &Result, const char *CurPtr) { // Skip consecutive spaces efficiently. while (true) { - // Skip horizontal whitespace very aggressively. - while (isHorizontalWhitespace(Char)) + // Skip horizontal whitespace, especially space, very aggressively. + while (Char == ' ' || isHorizontalWhitespace(Char)) Char = *++CurPtr; // Otherwise if we have something other than whitespace, we're done. @@ -3757,10 +3757,12 @@ bool Lexer::LexTokenInternal(Token &Result) { const char *CurPtr = BufferPtr; // Small amounts of horizontal whitespace is very common between tokens. - if (isHorizontalWhitespace(*CurPtr)) { + // Check for space character separately to skip the expensive + // isHorizontalWhitespace() check + if (*CurPtr == ' ' || isHorizontalWhitespace(*CurPtr)) { do { ++CurPtr; - } while (isHorizontalWhitespace(*CurPtr)); + } while (*CurPtr == ' ' || isHorizontalWhitespace(*CurPtr)); // If we are keeping whitespace and other tokens, just return what we just // skipped. The next lexer invocation will return the token after the _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
