database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-30 11:03:19 +03:00
Code Activity

Optimize popcount functions with ARM SVE intrinsics.

Browse Source 
This commit introduces SVE implementations of pg_popcount{32,64}.
Unlike the Neon versions, we need an additional configure-time
check to determine if the compiler supports SVE intrinsics, and we
need a runtime check to determine if the current CPU supports SVE
instructions.  Our testing showed that the SVE implementations are
much faster for larger inputs and are comparable to the status
quo for smaller inputs.

Author: "Devanga.Susmitha@fujitsu.com" <Devanga.Susmitha@fujitsu.com>
Co-authored-by: "Chiranmoy.Bhattacharya@fujitsu.com" <Chiranmoy.Bhattacharya@fujitsu.com>
Co-authored-by: "Malladi, Rama" <ramamalladi@hotmail.com>
Reviewed-by: John Naylor <johncnaylorls@gmail.com>
Reviewed-by: Kirill Reshke <reshkekirill@gmail.com>
Discussion: https://postgr.es/m/010101936e4aaa70-b474ab9e-b9ce-474d-a3ba-a3dc223d295c-000000%40us-west-2.amazonses.com
Discussion: https://postgr.es/m/OSZPR01MB84990A9A02A3515C6E85A65B8B2A2%40OSZPR01MB8499.jpnprd01.prod.outlook.com
This commit is contained in:
Nathan Bossart
2025-03-28 16:20:20 -05:00
parent 3c8e463b0d
commit 519338ace4
7 changed files with 475 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
meson.build
View File

@ -2297,6 +2297,54 @@ int main(void)
endif
###############################################################
# Check for the availability of SVE popcount intrinsics.
###############################################################
if host_cpu == 'aarch64'
prog = '''
#include <arm_sve.h>
char buf[128];
#if defined(__has_attribute) && __has_attribute (target)
__attribute__((target("arch=armv8-a+sve")))
#endif
int main(void)
{
svbool_t pred = svptrue_b64();
svuint8_t vec8;
svuint64_t accum1 = svdup_u64(0),
accum2 = svdup_u64(0),
vec64;
char *p = buf;
uint64_t popcnt,
mask = 0x5555555555555555;
vec64 = svand_n_u64_x(pred, svld1_u64(pred, (const uint64_t *) p), mask);
accum1 = svadd_u64_x(pred, accum1, svcnt_u64_x(pred, vec64));
p += svcntb();
vec64 = svand_n_u64_x(pred, svld1_u64(pred, (const uint64_t *) p), mask);
accum2 = svadd_u64_x(pred, accum2, svcnt_u64_x(pred, vec64));
p += svcntb();
popcnt = svaddv_u64(pred, svadd_u64_x(pred, accum1, accum2));
pred = svwhilelt_b8_s32(0, sizeof(buf));
vec8 = svand_n_u8_x(pred, svld1_u8(pred, (const uint8_t *) p), 0x55);
return (int) (popcnt + svaddv_u8(pred, svcnt_u8_x(pred, vec8)));
}
'''
if cc.links(prog, name: 'SVE popcount', args: test_c_args)
cdata.set('USE_SVE_POPCNT_WITH_RUNTIME_CHECK', 1)
endif
endif
###############################################################
# Select CRC-32C implementation.
#