From b915da29dab5d8c6b9cdb1ee6fdc1e0ec6ef39e1 Mon Sep 17 00:00:00 2001 From: Wilco Dijkstra Date: Fri, 28 Aug 2020 17:51:40 +0100 Subject: AArch64: Improve backwards memmove performance On some microarchitectures performance of the backwards memmove improves if the stores use STR with decreasing addresses. So change the memmove loop in memcpy_advsimd.S to use 2x STR rather than STP. Reviewed-by: Adhemerval Zanella (cherry picked from commit bd394d131c10c9ec22c6424197b79410042eed99) --- sysdeps/aarch64/multiarch/memcpy_advsimd.S | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/sysdeps/aarch64/multiarch/memcpy_advsimd.S b/sysdeps/aarch64/multiarch/memcpy_advsimd.S index d4ba747777..48bb6d7ca4 100644 --- a/sysdeps/aarch64/multiarch/memcpy_advsimd.S +++ b/sysdeps/aarch64/multiarch/memcpy_advsimd.S @@ -223,12 +223,13 @@ L(copy_long_backwards): b.ls L(copy64_from_start) L(loop64_backwards): - stp A_q, B_q, [dstend, -32] + str B_q, [dstend, -16] + str A_q, [dstend, -32] ldp A_q, B_q, [srcend, -96] - stp C_q, D_q, [dstend, -64] + str D_q, [dstend, -48] + str C_q, [dstend, -64]! ldp C_q, D_q, [srcend, -128] sub srcend, srcend, 64 - sub dstend, dstend, 64 subs count, count, 64 b.hi L(loop64_backwards) -- cgit 1.4.1