diff options
| author | H.J. Lu <hjl.tools@gmail.com> | 2017-06-23 12:45:57 -0700 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2017-06-23 12:46:12 -0700 |
| commit | 049816c3be14e47e5fe10f8cd5a38bb611d34ce5 (patch) | |
| tree | ad7c9e5f7277c4e8dd9dcaf4fa2cc0bbf78ac1cc | |
| parent | 52a8e5cb43a937d5224d271537093a1f92d78e94 (diff) | |
| download | glibc-049816c3be14e47e5fe10f8cd5a38bb611d34ce5.tar glibc-049816c3be14e47e5fe10f8cd5a38bb611d34ce5.tar.gz glibc-049816c3be14e47e5fe10f8cd5a38bb611d34ce5.tar.bz2 glibc-049816c3be14e47e5fe10f8cd5a38bb611d34ce5.zip | |
x86-64: Optimize L(between_2_3) in memcmp-avx2-movbe.S
Turn
movzbl -1(%rdi, %rdx), %edi
movzbl -1(%rsi, %rdx), %esi
orl %edi, %eax
orl %esi, %ecx
into
movb -1(%rdi, %rdx), %al
movb -1(%rsi, %rdx), %cl
* sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S (between_2_3):
Replace movzbl and orl with movb.
| -rw-r--r-- | ChangeLog | 5 | ||||
| -rw-r--r-- | sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S | 6 |
2 files changed, 7 insertions, 4 deletions
@@ -1,3 +1,8 @@ +2017-06-23 H.J. Lu <hongjiu.lu@intel.com> + + * sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S (between_2_3): + Replace movzbl and orl with movb. + 2017-06-23 Gabriel F. T. Gomes <gftg@linux.vnet.ibm.com> * manual/arith.texi (Infinity and NaN): Document SNANFN and SNANFNx. diff --git a/sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S b/sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S index 2cd2f71b85..abcc61c381 100644 --- a/sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S +++ b/sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S @@ -144,10 +144,8 @@ L(between_2_3): shll $8, %ecx bswap %eax bswap %ecx - movzbl -1(%rdi, %rdx), %edi - movzbl -1(%rsi, %rdx), %esi - orl %edi, %eax - orl %esi, %ecx + movb -1(%rdi, %rdx), %al + movb -1(%rsi, %rdx), %cl /* Subtraction is okay because the upper 8 bits are zero. */ subl %ecx, %eax ret |