x86: Improve memmove-vec-unaligned-erms.S

This patch changes the condition for copy 4x VEC so that if length is
exactly equal to 4 * VEC_SIZE it will use the 4x VEC case instead of
8x VEC case.

Results For Skylake memcpy-avx2-erms
size, al1 , al2 , Cur T   , New T   , Win , New / Cur
128 , 0   , 0   , 9.137   , 6.873   , New , 75.22
128 , 7   , 0   , 12.933  , 7.732   , New , 59.79
128 , 0   , 7   , 11.852  , 6.76    , New , 57.04
128 , 7   , 7   , 12.587  , 6.808   , New , 54.09

Results For Icelake memcpy-evex-erms
size, al1 , al2 , Cur T   , New T   , Win , New / Cur
128 , 0   , 0   , 9.963   , 5.416   , New , 54.36
128 , 7   , 0   , 16.467  , 8.061   , New , 48.95
128 , 0   , 7   , 14.388  , 7.644   , New , 53.13
128 , 7   , 7   , 14.546  , 7.642   , New , 52.54

Results For Tigerlake memcpy-evex-erms
size, al1 , al2 , Cur T   , New T   , Win , New / Cur
128 , 0   , 0   , 8.979   , 4.95    , New , 55.13
128 , 7   , 0   , 14.245  , 7.122   , New , 50.0
128 , 0   , 7   , 12.668  , 6.675   , New , 52.69
128 , 7   , 7   , 13.042  , 6.802   , New , 52.15

Results For Skylake memmove-avx2-erms
size, al1 , al2 , Cur T   , New T   , Win , New / Cur
128 , 0   , 32  , 6.181   , 5.691   , New , 92.07
128 , 32  , 0   , 6.165   , 5.752   , New , 93.3
128 , 0   , 7   , 13.923  , 9.37    , New , 67.3
128 , 7   , 0   , 12.049  , 10.182  , New , 84.5

Results For Icelake memmove-evex-erms
size, al1 , al2 , Cur T   , New T   , Win , New / Cur
128 , 0   , 32  , 5.479   , 4.889   , New , 89.23
128 , 32  , 0   , 5.127   , 4.911   , New , 95.79
128 , 0   , 7   , 18.885  , 13.547  , New , 71.73
128 , 7   , 0   , 15.565  , 14.436  , New , 92.75

Results For Tigerlake memmove-evex-erms
size, al1 , al2 , Cur T   , New T   , Win , New / Cur
128 , 0   , 32  , 5.275   , 4.815   , New , 91.28
128 , 32  , 0   , 5.376   , 4.565   , New , 84.91
128 , 0   , 7   , 19.426  , 14.273  , New , 73.47
128 , 7   , 0   , 15.924  , 14.951  , New , 93.89

Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
This commit is contained in:
Noah Goldstein 2021-05-23 19:43:24 -04:00
parent fc335a0ded
commit 1b992204f6

View File

@ -420,8 +420,8 @@ L(more_2x_vec):
cmpq $(VEC_SIZE * 8), %rdx
ja L(more_8x_vec)
cmpq $(VEC_SIZE * 4), %rdx
jb L(last_4x_vec)
/* Copy from 4 * VEC to 8 * VEC, inclusively. */
jbe L(last_4x_vec)
/* Copy from 4 * VEC + 1 to 8 * VEC, inclusively. */
VMOVU (%rsi), %VEC(0)
VMOVU VEC_SIZE(%rsi), %VEC(1)
VMOVU (VEC_SIZE * 2)(%rsi), %VEC(2)
@ -440,7 +440,7 @@ L(more_2x_vec):
VMOVU %VEC(7), -(VEC_SIZE * 4)(%rdi,%rdx)
VZEROUPPER_RETURN
L(last_4x_vec):
/* Copy from 2 * VEC to 4 * VEC. */
/* Copy from 2 * VEC + 1 to 4 * VEC, inclusively. */
VMOVU (%rsi), %VEC(0)
VMOVU VEC_SIZE(%rsi), %VEC(1)
VMOVU -VEC_SIZE(%rsi,%rdx), %VEC(2)