fabi/Snappy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Improve the speed of hashing in zippy compression.

Browse Source 
This change replaces the hashing function used during compression with
one that is roughly as good but faster.  This speeds up compression by
two to a few percent on the Intel-, AMD-, and Arm-based machines we
tested.  The amount of compression is roughly unchanged.

PiperOrigin-RevId: 485960303
This commit is contained in:
Snappy Team
2022-11-03 20:36:33 +00:00
committed by Victor Costan
parent a2d219a8a8
commit 8881ba172a
3 changed files with 79 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
cmake/config.h.in
View File

@@ -46,12 +46,19 @@
/* Define to 1 if you target processors with SSSE3+ and have <tmmintrin.h>. */
#cmakedefine01 SNAPPY_HAVE_SSSE3
/* Define to 1 if you target processors with SSE4.2 and have <crc32intrin.h>. */
#cmakedefine01 SNAPPY_HAVE_X86_CRC32
/* Define to 1 if you target processors with BMI2+ and have <bmi2intrin.h>. */
#cmakedefine01 SNAPPY_HAVE_BMI2
/* Define to 1 if you target processors with NEON and have <arm_neon.h>. */
#cmakedefine01 SNAPPY_HAVE_NEON
/* Define to 1 if you have <arm_neon.h> and <arm_acle.h> and want to optimize
compression speed by using __crc32cw from <arm_acle.h>. */
#cmakedefine01 SNAPPY_HAVE_NEON_CRC32
/* Define to 1 if your processor stores words with the most significant byte
first (like Motorola and SPARC, unlike Intel and VAX). */
#cmakedefine01 SNAPPY_IS_BIG_ENDIAN