diff options
| -rw-r--r-- | sysdeps/aarch64/multiarch/memset_a64fx.S | 9 |
1 files changed, 8 insertions, 1 deletions
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 |