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

[Wilco Dijkstra via Libc-alpha <libc-alpha@sourceware.org>]

Simplify the code for memsets smaller than L1. Improve the unroll8 and L1_prefetch loops.

---
diff --git a/sysdeps/aarch64/multiarch/memset_a64fx.S b/sysdeps/aarch64/multiarch/memset_a64fx.S
index 8665c272431b46dadea53c63ab74829c3aa99312..36628e101db33a9a8ff5234b98dd5a3a5c9ed73c 100644
--- a/sysdeps/aarch64/multiarch/memset_a64fx.S
+++ b/sysdeps/aarch64/multiarch/memset_a64fx.S
@@ -30,7 +30,6 @@
 #define L2_SIZE         (8*1024*1024)	// L2 8MB - 1MB
 #define CACHE_LINE_SIZE	256
 #define PF_DIST_L1	(CACHE_LINE_SIZE * 16)	// Prefetch distance L1
-#define rest		x2
 #define vector_length	x9
 
 #if HAVE_AARCH64_SVE_ASM
@@ -89,29 +88,19 @@ ENTRY (MEMSET)
 
 	.p2align 4
 L(vl_agnostic): // VL Agnostic
-	mov	rest, count
 	mov	dst, dstin
-	add	dstend, dstin, count
-	// if rest >= L2_SIZE && vector_length == 64 then L(L2)
-	mov	tmp1, 64
-	cmp	rest, L2_SIZE
-	ccmp	vector_length, tmp1, 0, cs
-	b.eq	L(L2)
-	// if rest >= L1_SIZE && vector_length == 64 then L(L1_prefetch)
-	cmp	rest, L1_SIZE
-	ccmp	vector_length, tmp1, 0, cs
-	b.eq	L(L1_prefetch)
-
+	cmp	count, L1_SIZE
+	b.hi	L(L1_prefetch)
 
+	// count >= 8 * vector_length
 L(unroll8):
-	lsl	tmp1, vector_length, 3
-	.p2align 3
-1:	cmp	rest, tmp1
-	b.cc	L(last)
-	st1b_unroll
+	sub	count, count, tmp1
+	.p2align 4
+1:	subs	count, count, tmp1
+	st1b_unroll 0, 7
 	add	dst, dst, tmp1
-	sub	rest, rest, tmp1
-	b	1b
+	b.hi	1b
+	add	count, count, tmp1
 
 L(last):
 	cmp	count, vector_length, lsl 1
@@ -129,18 +118,22 @@ L(last):
 	st1b	z0.b, p0, [dstend, -1, mul vl]
 	ret
 
-L(L1_prefetch): // if rest >= L1_SIZE
+	// count >= L1_SIZE
 	.p2align 3
+L(L1_prefetch):
+	cmp	count, L2_SIZE
+	b.hs	L(L2)
+	cmp	vector_length, 64
+	b.ne	L(unroll8)
 1:	st1b_unroll 0, 3
 	prfm	pstl1keep, [dst, PF_DIST_L1]
 	st1b_unroll 4, 7
 	prfm	pstl1keep, [dst, PF_DIST_L1 + CACHE_LINE_SIZE]
 	add	dst, dst, CACHE_LINE_SIZE * 2
-	sub	rest, rest, CACHE_LINE_SIZE * 2
-	cmp	rest, L1_SIZE
-	b.ge	1b
-	cbnz	rest, L(unroll8)
-	ret
+	sub	count, count, CACHE_LINE_SIZE * 2
+	cmp	count, PF_DIST_L1
+	b.hs	1b
+	b	L(unroll8)
 
 	// count >= L2_SIZE
 L(L2):