From d80db600664bec381230be85955b54884f21a619 Mon Sep 17 00:00:00 2001 From: Wilco Dijkstra Date: Tue, 6 Nov 2018 14:42:10 +0000 Subject: [PATCH] Adjust writeback in non-zero memset This fixes an ineffiency in the non-zero memset. Delaying the writeback until the end of the loop is slightly faster on some cores - this shows ~5% performance gain on Cortex-A53 when doing large non-zero memsets. Tested against the GLIBC testsuite. --- newlib/libc/machine/aarch64/memset.S | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/newlib/libc/machine/aarch64/memset.S b/newlib/libc/machine/aarch64/memset.S index 799e7b787..7c8fe583b 100644 --- a/newlib/libc/machine/aarch64/memset.S +++ b/newlib/libc/machine/aarch64/memset.S @@ -142,10 +142,10 @@ L(set_long): b.eq L(try_zva) L(no_zva): sub count, dstend, dst /* Count is 16 too large. */ - add dst, dst, 16 + sub dst, dst, 16 /* Dst is biased by -32. */ sub count, count, 64 + 16 /* Adjust count and bias for loop. */ -1: stp q0, q0, [dst], 64 - stp q0, q0, [dst, -32] +1: stp q0, q0, [dst, 32] + stp q0, q0, [dst, 64]! L(tail64): subs count, count, 64 b.hi 1b