commit | ddbbeb05cb3f0a4c27e7a5d5d0305462db373677 | [log] [tgz] |
---|---|---|
author | Adenilson Cavalcanti <[email protected]> | Tue Aug 07 16:08:59 2018 |
committer | Commit Bot <[email protected]> | Tue Aug 07 16:08:59 2018 |
tree | 23f122953a2b885cb670fe8810ed3ff028c02dfb | |
parent | a61bf9be1eacd91434dcacbe5b40c686bf006519 [diff] [blame] |
Neon-Optimized hash chain This should help with compression of data, using NEON instructions (therefore useful for ARMv7/ARMv8). Average gains were around 4% to 5% in data compression, depending on the data entropy. Re-write of a patch contributed to Fedora Core, for reference: https://src.fedoraproject.org/rpms/zlib/c/25e9802713484882c27c1f979a6610a42414ee13?branch=master Bug: 863257 Change-Id: I76573d75843d6a63de75d8a9536da98515314543 Reviewed-on: https://chromium-review.googlesource.com/1136940 Reviewed-by: Mike Klein <[email protected]> Reviewed-by: Chris Blume <[email protected]> Commit-Queue: Adenilson Cavalcanti <[email protected]> Cr-Commit-Position: refs/heads/master@{#581241}
diff --git a/third_party/zlib/BUILD.gn b/third_party/zlib/BUILD.gn index 902e287..69b49ba 100644 --- a/third_party/zlib/BUILD.gn +++ b/third_party/zlib/BUILD.gn
@@ -283,6 +283,7 @@ deps += [ ":zlib_inflate_chunk_simd" ] sources -= [ "inflate.c" ] + sources += [ "contrib/optimizations/slide_hash_neon.h" ] } }