diff options
author | H.J. Lu <hjl.tools@gmail.com> | 2016-04-05 05:21:07 -0700 |
---|---|---|
committer | H.J. Lu <hjl.tools@gmail.com> | 2016-04-05 11:00:37 -0700 |
commit | c2d3bdd6aec639fd66fceb3e2c145420c25d409b (patch) | |
tree | 923088f32773b44eff3a29a06217519fe4f910fe | |
parent | 070a5e77d66f5520c1bbbc24dc1843a0a1c161ee (diff) | |
download | glibc-c2d3bdd6aec639fd66fceb3e2c145420c25d409b.tar.gz |
Force 32-bit displacement in memset-vec-unaligned-erms.S
* sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S: Force
32-bit displacement to avoid long nop between instructions.
(cherry picked from commit ec0cac9a1f4094bd0db6f77c1b329e7a40eecc10)
-rw-r--r-- | sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S | 13 |
1 files changed, 13 insertions, 0 deletions
diff --git a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S index 9383517536..fe0f74516d 100644 --- a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S +++ b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S @@ -159,10 +159,23 @@ L(return): .p2align 4 L(loop_start): leaq (VEC_SIZE * 4)(%rdi), %rcx +# if VEC_SIZE == 32 || VEC_SIZE == 64 + /* Force 32-bit displacement to avoid long nop between + instructions. */ + VMOVU.d32 %VEC(0), (%rdi) +# else VMOVU %VEC(0), (%rdi) +# endif andq $-(VEC_SIZE * 4), %rcx +# if VEC_SIZE == 32 + /* Force 32-bit displacement to avoid long nop between + instructions. */ + VMOVU.d32 %VEC(0), -VEC_SIZE(%rdi,%rdx) + VMOVU.d32 %VEC(0), VEC_SIZE(%rdi) +# else VMOVU %VEC(0), -VEC_SIZE(%rdi,%rdx) VMOVU %VEC(0), VEC_SIZE(%rdi) +# endif VMOVU %VEC(0), -(VEC_SIZE * 2)(%rdi,%rdx) VMOVU %VEC(0), (VEC_SIZE * 2)(%rdi) VMOVU %VEC(0), -(VEC_SIZE * 3)(%rdi,%rdx) |