diff options
| author | Heikki Linnakangas <heikki.linnakangas@iki.fi> | 2015-04-14 23:58:16 +0300 |
|---|---|---|
| committer | Heikki Linnakangas <heikki.linnakangas@iki.fi> | 2015-04-14 23:58:16 +0300 |
| commit | 936546dcbc24ad1f2b3d33e73aa5c5fde4d2be84 (patch) | |
| tree | b6d29aa4308a156d363a08bf4f7ebf89f4047e85 /config/c-compiler.m4 | |
| parent | b73e7a0716264e5159947b1a755b9ab864142489 (diff) | |
| download | postgresql-936546dcbc24ad1f2b3d33e73aa5c5fde4d2be84.tar.gz | |
Optimize pg_comp_crc32c_sse42 routine slightly, and also use it on x86.
Eliminate the separate 'len' variable from the loops, and also use the 4
byte instruction. This shaves off a few more cycles. Even though this
routine that uses the special SSE 4.2 instructions is much faster than a
generic routine, it's still a hot spot, so let's make it as fast as
possible.
Change the configure test to not test _mm_crc32_u64. That variant is only
available in the 64-bit x86-64 architecture, not in 32-bit x86. Modify
pg_comp_crc32c_sse42 so that it only uses _mm_crc32_u64 on x86-64. With
these changes, the SSE accelerated CRC-32C implementation can also be used
on 32-bit x86 systems.
This also fixes the 32-bit MSVC build.
Diffstat (limited to 'config/c-compiler.m4')
| -rw-r--r-- | config/c-compiler.m4 | 10 |
1 files changed, 7 insertions, 3 deletions
diff --git a/config/c-compiler.m4 b/config/c-compiler.m4 index f81e7d6139..4ef0de65a8 100644 --- a/config/c-compiler.m4 +++ b/config/c-compiler.m4 @@ -476,12 +476,16 @@ fi])# PGAC_HAVE_GCC__ATOMIC_INT64_CAS # PGAC_SSE42_CRC32_INTRINSICS # ----------------------- -# Check if the compiler supports _mm_crc32_u8 and _mm_crc32_u64 intrinsics. +# Check if the compiler supports the x86 CRC instructions added in SSE 4.2, +# using the _mm_crc32_u8 and _mm_crc32_u32 intrinsic functions. (We don't +# test the 8-byte variant, _mm_crc32_u64, but it is assumed to be present if +# the other ones are, on x86-64 platforms) +# # An optional compiler flag can be passed as argument (e.g. -msse4.2). If the # intrinsics are supported, sets pgac_sse42_crc32_intrinsics, and CFLAGS_SSE42. AC_DEFUN([PGAC_SSE42_CRC32_INTRINSICS], [define([Ac_cachevar], [AS_TR_SH([pgac_cv_sse42_crc32_intrinsics_$1])])dnl -AC_CACHE_CHECK([for _mm_crc32_u8 and _mm_crc32_u64 with CFLAGS=$1], [Ac_cachevar], +AC_CACHE_CHECK([for _mm_crc32_u8 and _mm_crc32_u32 with CFLAGS=$1], [Ac_cachevar], [pgac_save_CFLAGS=$CFLAGS CFLAGS="$pgac_save_CFLAGS $1" ac_save_c_werror_flag=$ac_c_werror_flag @@ -489,7 +493,7 @@ ac_c_werror_flag=yes AC_TRY_LINK([#include <nmmintrin.h>], [unsigned int crc = 0; crc = _mm_crc32_u8(crc, 0); - crc = (unsigned int) _mm_crc32_u64(crc, 0);], + crc = _mm_crc32_u32(crc, 0);], [Ac_cachevar=yes], [Ac_cachevar=no]) ac_c_werror_flag=$ac_save_c_werror_flag |