[committed] Force 32-bit displacement in memset-vec-unaligned-erms.S
Commit Message
* sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S: Force
32-bit displacement to avoid long nop between instructions.
---
sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S | 13 +++++++++++++
1 file changed, 13 insertions(+)
@@ -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)