| commit | 9781db8906a769507a85280829c42dfe7b02f600 | |
| author | H. Peter Anvin (Intel) <hpa@zytor.com> | |
| Tue, 24 Sep 2019 18:15:04 +0000 (24 11:15 -0700) | ||
| committer | H. Peter Anvin (Intel) <hpa@zytor.com> | |
| Tue, 24 Sep 2019 18:15:04 +0000 (24 11:15 -0700) | ||
| tree | 006bfb344b389854fe4e7c3df484b78368fae7f6 | treesnapshot (tar.gz zip) |
| parent | 01a67a1ba4e4a9b95752e3e97736f15d98fdd1f9 | commitdiff |
| parent | 8571f06061b47471a340e350fdfcd804098637d6 | commitdiff |
Merge branch 'pp-inline'
The inlining of preprocessor tokens has benchmarked about 15% faster in any
realistic scenario than the old code. For an artificial case where
over 50% of symbols are longer than 47 characters there was a slowdown
of about 15%, but that represents an incredibly unlikely scenario in
practice: even if labels are that long (e.g. C++ name mangling) the
majority of tokens should be instructions and registers, which are
uniformly short.
Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
The inlining of preprocessor tokens has benchmarked about 15% faster in any
realistic scenario than the old code. For an artificial case where
over 50% of symbols are longer than 47 characters there was a slowdown
of about 15%, but that represents an incredibly unlikely scenario in
practice: even if labels are that long (e.g. C++ name mangling) the
majority of tokens should be instructions and registers, which are
uniformly short.
Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>