[PATCH v3 3/5] AArch64: Improve A64FX memset

[Wilco Dijkstra]

Simplify handling of remaining bytes. Avoid lots of taken branches and complex
whilelo computations, instead unconditionally write vectors from the end.

---

diff --git a/sysdeps/aarch64/multiarch/memset_a64fx.S b/sysdeps/aarch64/multiarch/memset_a64fx.S
index 608e0e2e2ff5259178e2fdadf1eea8816194d879..fce257fa68120c2b101f29b438c397e10b4c275e 100644
--- a/sysdeps/aarch64/multiarch/memset_a64fx.S
+++ b/sysdeps/aarch64/multiarch/memset_a64fx.S
@@ -130,38 +130,19 @@ L(unroll8):
 	b	1b
 
 L(last):
-	whilelo	p0.b, xzr, rest
-	whilelo	p1.b, vector_length, rest
-	b.last	1f
-	st1b	z0.b, p0, [dst, #0, mul vl]
-	st1b	z0.b, p1, [dst, #1, mul vl]
-	ret
-1:	lsl	tmp1, vector_length, 1	// vector_length * 2
-	whilelo	p2.b, tmp1, rest
-	incb	tmp1
-	whilelo	p3.b, tmp1, rest
-	b.last	1f
-	st1b	z0.b, p0, [dst, #0, mul vl]
-	st1b	z0.b, p1, [dst, #1, mul vl]
-	st1b	z0.b, p2, [dst, #2, mul vl]
-	st1b	z0.b, p3, [dst, #3, mul vl]
-	ret
-1:	lsl	tmp1, vector_length, 2	// vector_length * 4
-	whilelo	p4.b, tmp1, rest
-	incb	tmp1
-	whilelo	p5.b, tmp1, rest
-	incb	tmp1
-	whilelo	p6.b, tmp1, rest
-	incb	tmp1
-	whilelo	p7.b, tmp1, rest
-	st1b	z0.b, p0, [dst, #0, mul vl]
-	st1b	z0.b, p1, [dst, #1, mul vl]
-	st1b	z0.b, p2, [dst, #2, mul vl]
-	st1b	z0.b, p3, [dst, #3, mul vl]
-	st1b	z0.b, p4, [dst, #4, mul vl]
-	st1b	z0.b, p5, [dst, #5, mul vl]
-	st1b	z0.b, p6, [dst, #6, mul vl]
-	st1b	z0.b, p7, [dst, #7, mul vl]
+	cmp	count, vector_length, lsl 1
+	b.ls	2f
+	add	tmp2, vector_length, vector_length, lsl 2
+	cmp	count, tmp2
+	b.ls	5f
+	st1b	z0.b, p0, [dstend, -8, mul vl]
+	st1b	z0.b, p0, [dstend, -7, mul vl]
+	st1b	z0.b, p0, [dstend, -6, mul vl]
+5:	st1b	z0.b, p0, [dstend, -5, mul vl]
+	st1b	z0.b, p0, [dstend, -4, mul vl]
+	st1b	z0.b, p0, [dstend, -3, mul vl]
+2:	st1b	z0.b, p0, [dstend, -2, mul vl]
+	st1b	z0.b, p0, [dstend, -1, mul vl]
 	ret
 
 L(L1_prefetch): // if rest >= L1_SIZE