From: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
To: 'GNU C Library' <libc-alpha@sourceware.org>
Cc: Szabolcs Nagy <Szabolcs.Nagy@arm.com>
Subject: [PATCH] AArch64: Improve SVE memcpy and memmove
Date: Fri, 3 Feb 2023 13:05:39 +0000 [thread overview]
Message-ID: <PAWPR08MB898248BE9DB331AC6DBEF4B183D79@PAWPR08MB8982.eurprd08.prod.outlook.com> (raw)
Improve SVE memcpy/memmove by copying 2 vectors if the size is small enough.
This improves performance of random memcpy by ~9% on Neoverse V1, and
memcpy/memmove of 33-64 bytes become ~16% faster.
Passes regress, OK for commit?
---
diff --git a/sysdeps/aarch64/multiarch/memcpy_sve.S b/sysdeps/aarch64/multiarch/memcpy_sve.S
index f4dc214f60bf25e818eb6b8de2d4093ad0c886e1..d11be6a44301af4bfd7fa4900555b769dc58d34d 100644
--- a/sysdeps/aarch64/multiarch/memcpy_sve.S
+++ b/sysdeps/aarch64/multiarch/memcpy_sve.S
@@ -67,14 +67,15 @@ ENTRY (__memcpy_sve)
cmp count, 128
b.hi L(copy_long)
- cmp count, 32
+ cntb vlen
+ cmp count, vlen, lsl 1
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]
+ 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
+ cntb vlen
+ cmp count, vlen, lsl 1
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]
+ 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
next reply other threads:[~2023-02-03 13:05 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-02-03 13:05 Wilco Dijkstra [this message]
2023-02-06 14:29 ` Szabolcs Nagy
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=PAWPR08MB898248BE9DB331AC6DBEF4B183D79@PAWPR08MB8982.eurprd08.prod.outlook.com \
--to=wilco.dijkstra@arm.com \
--cc=Szabolcs.Nagy@arm.com \
--cc=libc-alpha@sourceware.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).