diff options
| author | H.J. Lu <hjl.tools@gmail.com> | 2016-04-24 09:55:40 -0700 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2016-04-24 09:55:40 -0700 |
| commit | 8dd19b0b3ca334060eec990f0afa502700939ad3 (patch) | |
| tree | 5c25ea617b71a4234d53386561c474288a209079 | |
| parent | 13fd5ab017a053bbcfc7b73bd18d3b58c9078b8f (diff) | |
| download | glibc-8dd19b0b3ca334060eec990f0afa502700939ad3.tar.gz glibc-8dd19b0b3ca334060eec990f0afa502700939ad3.tar.xz glibc-8dd19b0b3ca334060eec990f0afa502700939ad3.zip | |
Use PREFETCHED_LOAD_SIZE in loop_4x_vec_xxx
| -rw-r--r-- | sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S | 16 |
1 files changed, 8 insertions, 8 deletions
diff --git a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S index b5ffa49539..0a2bf4108f 100644 --- a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S +++ b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S @@ -387,14 +387,14 @@ L(loop_4x_vec_forward): VMOVU VEC_SIZE(%rsi), %VEC(1) VMOVU (VEC_SIZE * 2)(%rsi), %VEC(2) VMOVU (VEC_SIZE * 3)(%rsi), %VEC(3) - addq $(VEC_SIZE * 4), %rsi - subq $(VEC_SIZE * 4), %rdx + addq $(PREFETCHED_LOAD_SIZE), %rsi + subq $(PREFETCHED_LOAD_SIZE), %rdx VMOVA %VEC(0), (%rdi) VMOVA %VEC(1), VEC_SIZE(%rdi) VMOVA %VEC(2), (VEC_SIZE * 2)(%rdi) VMOVA %VEC(3), (VEC_SIZE * 3)(%rdi) - addq $(VEC_SIZE * 4), %rdi - cmpq $(VEC_SIZE * 4), %rdx + addq $(PREFETCHED_LOAD_SIZE), %rdi + cmpq $(PREFETCHED_LOAD_SIZE), %rdx ja L(loop_4x_vec_forward) /* Store the last 4 * VEC. */ VMOVU %VEC(5), (%rcx) @@ -439,14 +439,14 @@ L(loop_4x_vec_backward): VMOVU -VEC_SIZE(%rcx), %VEC(1) VMOVU -(VEC_SIZE * 2)(%rcx), %VEC(2) VMOVU -(VEC_SIZE * 3)(%rcx), %VEC(3) - subq $(VEC_SIZE * 4), %rcx - subq $(VEC_SIZE * 4), %rdx + subq $(PREFETCHED_LOAD_SIZE), %rcx + subq $(PREFETCHED_LOAD_SIZE), %rdx VMOVA %VEC(0), (%r9) VMOVA %VEC(1), -VEC_SIZE(%r9) VMOVA %VEC(2), -(VEC_SIZE * 2)(%r9) VMOVA %VEC(3), -(VEC_SIZE * 3)(%r9) - subq $(VEC_SIZE * 4), %r9 - cmpq $(VEC_SIZE * 4), %rdx + subq $(PREFETCHED_LOAD_SIZE), %r9 + cmpq $(PREFETCHED_LOAD_SIZE), %rdx ja L(loop_4x_vec_backward) /* Store the first 4 * VEC. */ VMOVU %VEC(4), (%rdi) |