about summary refs log tree commit diff
diff options
context:
space:
mode:
authorNaohiro Tamura via Libc-alpha <libc-alpha@sourceware.org>2021-08-27 05:03:04 +0000
committerSzabolcs Nagy <szabolcs.nagy@arm.com>2021-09-03 15:59:46 +0100
commit23777232c23f80809613bdfa329f63aadf992922 (patch)
tree02c8d663d92010187a3176126b7dfb6247540f81
parent69623c0db0a540f26ee537bae09446d3dcdf1f80 (diff)
downloadglibc-23777232c23f80809613bdfa329f63aadf992922.tar.gz
glibc-23777232c23f80809613bdfa329f63aadf992922.tar.xz
glibc-23777232c23f80809613bdfa329f63aadf992922.zip
AArch64: Update A64FX memset not to degrade at 16KB
This patch updates unroll8 code so as not to degrade at the peak
performance 16KB for both FX1000 and FX700.

Inserted 2 instructions at the beginning of the unroll8 loop,
cmp and branch, are a workaround that is found heuristically.

Reviewed-by: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
-rw-r--r--sysdeps/aarch64/multiarch/memset_a64fx.S9
1 files changed, 8 insertions, 1 deletions
diff --git a/sysdeps/aarch64/multiarch/memset_a64fx.S b/sysdeps/aarch64/multiarch/memset_a64fx.S
index 7bf759b6a7..f7dfdaace7 100644
--- a/sysdeps/aarch64/multiarch/memset_a64fx.S
+++ b/sysdeps/aarch64/multiarch/memset_a64fx.S
@@ -96,7 +96,14 @@ L(vl_agnostic): // VL Agnostic
 L(unroll8):
 	sub	count, count, tmp1
 	.p2align 4
-1:	st1b_unroll 0, 7
+	// The 2 instructions at the beginning of the following loop,
+	// cmp and branch, are a workaround so as not to degrade at
+	// the peak performance 16KB.
+	// It is found heuristically and the branch condition, b.ne,
+	// is chosen intentionally never to jump.
+1:	cmp	xzr, xzr
+	b.ne	1b
+	st1b_unroll 0, 7
 	add	dst, dst, tmp1
 	subs	count, count, tmp1
 	b.hi	1b