1
0
mirror of https://github.com/postgres/postgres.git synced 2025-07-27 12:41:57 +03:00

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.
This commit is contained in:
Heikki Linnakangas
2015-04-14 23:58:16 +03:00
parent b73e7a0716
commit 936546dcbc
3 changed files with 43 additions and 24 deletions

12
configure vendored
View File

@ -14172,8 +14172,8 @@ fi
# First check if the _mm_crc32_u8 and _mm_crc32_u64 intrinsics can be used
# with the default compiler flags. If not, check if adding the -msse4.2
# flag helps. CFLAGS_SSE42 is set to -msse4.2 if that's required.
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm_crc32_u8 and _mm_crc32_u64 with CFLAGS=" >&5
$as_echo_n "checking for _mm_crc32_u8 and _mm_crc32_u64 with CFLAGS=... " >&6; }
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm_crc32_u8 and _mm_crc32_u32 with CFLAGS=" >&5
$as_echo_n "checking for _mm_crc32_u8 and _mm_crc32_u32 with CFLAGS=... " >&6; }
if ${pgac_cv_sse42_crc32_intrinsics_+:} false; then :
$as_echo_n "(cached) " >&6
else
@ -14189,7 +14189,7 @@ main ()
{
unsigned int crc = 0;
crc = _mm_crc32_u8(crc, 0);
crc = (unsigned int) _mm_crc32_u64(crc, 0);
crc = _mm_crc32_u32(crc, 0);
;
return 0;
}
@ -14212,8 +14212,8 @@ if test x"$pgac_cv_sse42_crc32_intrinsics_" = x"yes"; then
fi
if test x"$pgac_sse42_crc32_intrinsics" != x"yes"; then
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm_crc32_u8 and _mm_crc32_u64 with CFLAGS=-msse4.2" >&5
$as_echo_n "checking for _mm_crc32_u8 and _mm_crc32_u64 with CFLAGS=-msse4.2... " >&6; }
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm_crc32_u8 and _mm_crc32_u32 with CFLAGS=-msse4.2" >&5
$as_echo_n "checking for _mm_crc32_u8 and _mm_crc32_u32 with CFLAGS=-msse4.2... " >&6; }
if ${pgac_cv_sse42_crc32_intrinsics__msse4_2+:} false; then :
$as_echo_n "(cached) " >&6
else
@ -14229,7 +14229,7 @@ main ()
{
unsigned int crc = 0;
crc = _mm_crc32_u8(crc, 0);
crc = (unsigned int) _mm_crc32_u64(crc, 0);
crc = _mm_crc32_u32(crc, 0);
;
return 0;
}