From 1d9f99ce1b3788d1897cb53a76d57e973111b8fe Mon Sep 17 00:00:00 2001
From: Naohiro Tamura <naohirot@fujitsu.com>
Date: Fri, 27 Aug 2021 05:03:04 +0000
Subject: [PATCH] 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>
---
 sysdeps/aarch64/multiarch/memset_a64fx.S | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

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
-- 
2.31.1