mirror/glibc
2
0
Fork 0
mirror of git://sourceware.org/git/glibc.git synced 2025-01-30 12:31:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

AArch64: Improve SVE memcpy and memmove

Browse Source 
Improve SVE memcpy by copying 2 vectors if the size is small enough.
This improves performance of random memcpy by ~9% on Neoverse V1, and
33-64 byte copies are ~16% faster.

Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
This commit is contained in:
Wilco Dijkstra 2023-02-01 18:45:19 +00:00
parent c980549cc6
commit d2d3f3720c
1 changed files with 16 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
sysdeps/aarch64/multiarch/memcpy_sve.S
View File

@ -67,14 +67,15 @@ ENTRY (__memcpy_sve)
cmp count, 128
b.hi L(copy_long)
cmp count, 32
b.hi L(copy32_128)
whilelo p0.b, xzr, count
cntb vlen
tbnz vlen, 4, L(vlen128)
ld1b z0.b, p0/z, [src]
st1b z0.b, p0, [dstin]
cmp count, vlen, lsl 1
b.hi L(copy32_128)
whilelo p0.b, xzr, count
whilelo p1.b, vlen, count
ld1b z0.b, p0/z, [src, 0, mul vl]
ld1b z1.b, p1/z, [src, 1, mul vl]
st1b z0.b, p0, [dstin, 0, mul vl]
st1b z1.b, p1, [dstin, 1, mul vl]
ret
/* Medium copies: 33..128 bytes. */
@ -102,14 +103,6 @@ L(copy96):
stp C_q, D_q, [dstend, -32]
ret
L(vlen128):
whilelo p1.b, vlen, count
ld1b z0.b, p0/z, [src, 0, mul vl]
ld1b z1.b, p1/z, [src, 1, mul vl]
st1b z0.b, p0, [dstin, 0, mul vl]
st1b z1.b, p1, [dstin, 1, mul vl]
ret
.p2align 4
/* Copy more than 128 bytes. */
L(copy_long):
@ -158,14 +151,15 @@ ENTRY (__memmove_sve)
cmp count, 128
b.hi L(move_long)
cmp count, 32
b.hi L(copy32_128)
whilelo p0.b, xzr, count
cntb vlen
tbnz vlen, 4, L(vlen128)
ld1b z0.b, p0/z, [src]
st1b z0.b, p0, [dstin]
cmp count, vlen, lsl 1
b.hi L(copy32_128)
whilelo p0.b, xzr, count
whilelo p1.b, vlen, count
ld1b z0.b, p0/z, [src, 0, mul vl]
ld1b z1.b, p1/z, [src, 1, mul vl]
st1b z0.b, p0, [dstin, 0, mul vl]
st1b z1.b, p1, [dstin, 1, mul vl]
ret
.p2align 4