diff options
-rw-r--r-- | ChangeLog | 5 | ||||
-rw-r--r-- | sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S | 13 |
2 files changed, 18 insertions, 0 deletions
diff --git a/ChangeLog b/ChangeLog index 4b2f408e89..048299a45e 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,5 +1,10 @@ 2016-04-05 H.J. Lu <hongjiu.lu@intel.com> + * sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S: Force + 32-bit displacement to avoid long nop between instructions. + +2016-04-05 H.J. Lu <hongjiu.lu@intel.com> + * sysdeps/x86_64/multiarch/memset-sse2-unaligned-erms.S: Add a comment on VMOVU and VMOVA. 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) |