* Re: [PATCH v1] x86: Shrink memcmp-sse4.S code size
[not found] ` <CAFUsyf+DGMa6STkhT1B6O4xRZDuyKP-bbD7PFObyLVFiwjU-yQ@mail.gmail.com>
@ 2022-04-23 1:44 ` Sunil Pandey
0 siblings, 0 replies; only message in thread
From: Sunil Pandey @ 2022-04-23 1:44 UTC (permalink / raw)
To: Noah Goldstein, libc-stable; +Cc: H.J. Lu, GNU C Library
On Wed, Nov 10, 2021 at 6:15 PM Noah Goldstein via Libc-alpha
<libc-alpha@sourceware.org> wrote:
>
> On Wed, Nov 10, 2021 at 8:03 PM H.J. Lu <hjl.tools@gmail.com> wrote:
> >
> > On Wed, Nov 10, 2021 at 4:27 PM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
> > >
> > > No bug.
> > >
> > > This implementation refactors memcmp-sse4.S primarily with minimizing
> > > code size in mind. It does this by removing the lookup table logic and
> > > removing the unrolled check from (256, 512] bytes.
> > >
> > > memcmp-sse4 code size reduction : -3487 bytes
> > > wmemcmp-sse4 code size reduction: -1472 bytes
> > >
> > > The current memcmp-sse4.S implementation has a large code size
> > > cost. This has serious adverse affects on the ICache / ITLB. While
> > > in micro-benchmarks the implementations appears fast, traces of
> > > real-world code have shown that the speed in micro benchmarks does not
> > > translate when the ICache/ITLB are not primed, and that the cost
> > > of the code size has measurable negative affects on overall
> > > application performance.
> > >
> > > See https://research.google/pubs/pub48320/ for more details.
> > > ---
> > > sysdeps/x86_64/multiarch/memcmp-sse4.S | 2267 +++++++-----------------
> > > 1 file changed, 646 insertions(+), 1621 deletions(-)
> > >
> > > diff --git a/sysdeps/x86_64/multiarch/memcmp-sse4.S b/sysdeps/x86_64/multiarch/memcmp-sse4.S
> > > index b82adcd5fa..7686d1aa9e 100644
> > > --- a/sysdeps/x86_64/multiarch/memcmp-sse4.S
> > > +++ b/sysdeps/x86_64/multiarch/memcmp-sse4.S
> > > @@ -24,14 +24,14 @@
> > > # define MEMCMP __memcmp_sse4_1
> > > # endif
> > >
> > > -# define JMPTBL(I, B) (I - B)
> > > +#ifdef USE_AS_WMEMCMP
> > > +# define CMPEQ pcmpeqd
> > > +# define CHAR_SIZE 4
> > > +#else
> > > +# define CMPEQ pcmpeqb
> > > +# define CHAR_SIZE 1
> > > +#endif
> > >
> > > -# define BRANCH_TO_JMPTBL_ENTRY(TABLE, INDEX, SCALE) \
> > > - lea TABLE(%rip), %r11; \
> > > - movslq (%r11, INDEX, SCALE), %rcx; \
> > > - add %r11, %rcx; \
> > > - _CET_NOTRACK jmp *%rcx; \
> > > - ud2
> > >
> > > /* Warning!
> > > wmemcmp has to use SIGNED comparison for elements.
> > > @@ -46,33 +46,253 @@ ENTRY (MEMCMP)
> > > /* Clear the upper 32 bits. */
> > > mov %edx, %edx
> > > # endif
> > > - pxor %xmm0, %xmm0
> > > cmp $79, %RDX_LP
> > > ja L(79bytesormore)
> > > +
> > > + cmp $CHAR_SIZE, %RDX_LP
> > > + jbe L(firstbyte)
> > > +
> > > + /* N in (CHAR_SIZE, 79) bytes. */
> > > + cmpl $32, %edx
> > > + ja L(more_32_bytes)
> > > +
> > > + cmpl $16, %edx
> > > + jae L(16_to_32_bytes)
> > > +
> > > # ifndef USE_AS_WMEMCMP
> > > - cmp $1, %RDX_LP
> > > - je L(firstbyte)
> > > + cmpl $8, %edx
> > > + jae L(8_to_16_bytes)
> > > +
> > > + cmpl $4, %edx
> > > + jb L(2_to_3_bytes)
> > > +
> > > + movl (%rdi), %eax
> > > + movl (%rsi), %ecx
> > > +
> > > + bswap %eax
> > > + bswap %ecx
> > > +
> > > + shlq $32, %rax
> > > + shlq $32, %rcx
> > > +
> > > + movl -4(%rdi, %rdx), %edi
> > > + movl -4(%rsi, %rdx), %esi
> > > +
> > > + bswap %edi
> > > + bswap %esi
> > > +
> > > + orq %rdi, %rax
> > > + orq %rsi, %rcx
> > > + subq %rcx, %rax
> > > + cmovne %edx, %eax
> > > + sbbl %ecx, %ecx
> > > + orl %ecx, %eax
> > > + ret
> > > +
> > > + .p2align 4,, 8
> > > +L(2_to_3_bytes):
> > > + movzwl (%rdi), %eax
> > > + movzwl (%rsi), %ecx
> > > + shll $8, %eax
> > > + shll $8, %ecx
> > > + bswap %eax
> > > + bswap %ecx
> > > + movzbl -1(%rdi, %rdx), %edi
> > > + movzbl -1(%rsi, %rdx), %esi
> > > + orl %edi, %eax
> > > + orl %esi, %ecx
> > > + subl %ecx, %eax
> > > + ret
> > > +
> > > + .p2align 4,, 8
> > > +L(8_to_16_bytes):
> > > + movq (%rdi), %rax
> > > + movq (%rsi), %rcx
> > > +
> > > + bswap %rax
> > > + bswap %rcx
> > > +
> > > + subq %rcx, %rax
> > > + jne L(8_to_16_bytes_done)
> > > +
> > > + movq -8(%rdi, %rdx), %rax
> > > + movq -8(%rsi, %rdx), %rcx
> > > +
> > > + bswap %rax
> > > + bswap %rcx
> > > +
> > > + subq %rcx, %rax
> > > +
> > > +L(8_to_16_bytes_done):
> > > + cmovne %edx, %eax
> > > + sbbl %ecx, %ecx
> > > + orl %ecx, %eax
> > > + ret
> > > +# else
> > > + xorl %eax, %eax
> > > + movl (%rdi), %ecx
> > > + cmpl (%rsi), %ecx
> > > + jne L(8_to_16_bytes_done)
> > > + movl 4(%rdi), %ecx
> > > + cmpl 4(%rsi), %ecx
> > > + jne L(8_to_16_bytes_done)
> > > + movl -4(%rdi, %rdx), %ecx
> > > + cmpl -4(%rsi, %rdx), %ecx
> > > + jne L(8_to_16_bytes_done)
> > > + ret
> > > # endif
> > > - add %rdx, %rsi
> > > - add %rdx, %rdi
> > > - BRANCH_TO_JMPTBL_ENTRY(L(table_64bytes), %rdx, 4)
> > >
> > > -# ifndef USE_AS_WMEMCMP
> > > - .p2align 4
> > > + .p2align 4,, 3
> > > +L(ret_zero):
> > > + xorl %eax, %eax
> > > +L(zero):
> > > + ret
> > > +
> > > + .p2align 4,, 8
> > > L(firstbyte):
> > > + jb L(ret_zero)
> > > +# ifdef USE_AS_WMEMCMP
> > > + xorl %eax, %eax
> > > + movl (%rdi), %ecx
> > > + cmpl (%rsi), %ecx
> > > + je L(zero)
> > > +L(8_to_16_bytes_done):
> > > + setg %al
> > > + leal -1(%rax, %rax), %eax
> > > +# else
> > > movzbl (%rdi), %eax
> > > movzbl (%rsi), %ecx
> > > sub %ecx, %eax
> > > +# endif
> > > ret
> > > +
> > > + .p2align 4
> > > +L(vec_return_begin_48):
> > > + addq $16, %rdi
> > > + addq $16, %rsi
> > > +L(vec_return_begin_32):
> > > + bsfl %eax, %eax
> > > +# ifdef USE_AS_WMEMCMP
> > > + movl 32(%rdi, %rax), %ecx
> > > + xorl %edx, %edx
> > > + cmpl 32(%rsi, %rax), %ecx
> > > + setg %dl
> > > + leal -1(%rdx, %rdx), %eax
> > > +# else
> > > + movzbl 32(%rsi, %rax), %ecx
> > > + movzbl 32(%rdi, %rax), %eax
> > > + subl %ecx, %eax
> > > +# endif
> > > + ret
> > > +
> > > + .p2align 4
> > > +L(vec_return_begin_16):
> > > + addq $16, %rdi
> > > + addq $16, %rsi
> > > +L(vec_return_begin):
> > > + bsfl %eax, %eax
> > > +# ifdef USE_AS_WMEMCMP
> > > + movl (%rdi, %rax), %ecx
> > > + xorl %edx, %edx
> > > + cmpl (%rsi, %rax), %ecx
> > > + setg %dl
> > > + leal -1(%rdx, %rdx), %eax
> > > +# else
> > > + movzbl (%rsi, %rax), %ecx
> > > + movzbl (%rdi, %rax), %eax
> > > + subl %ecx, %eax
> > > +# endif
> > > + ret
> > > +
> > > + .p2align 4
> > > +L(vec_return_end_16):
> > > + subl $16, %edx
> > > +L(vec_return_end):
> > > + bsfl %eax, %eax
> > > + addl %edx, %eax
> > > +# ifdef USE_AS_WMEMCMP
> > > + movl -16(%rdi, %rax), %ecx
> > > + xorl %edx, %edx
> > > + cmpl -16(%rsi, %rax), %ecx
> > > + setg %dl
> > > + leal -1(%rdx, %rdx), %eax
> > > +# else
> > > + movzbl -16(%rsi, %rax), %ecx
> > > + movzbl -16(%rdi, %rax), %eax
> > > + subl %ecx, %eax
> > > # endif
> > > + ret
> > > +
> > > + .p2align 4,, 8
> > > +L(more_32_bytes):
> > > + movdqu (%rdi), %xmm0
> > > + movdqu (%rsi), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin)
> > > +
> > > + movdqu 16(%rdi), %xmm0
> > > + movdqu 16(%rsi), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_16)
> > > +
> > > + cmpl $64, %edx
> > > + jbe L(32_to_64_bytes)
> > > + movdqu 32(%rdi), %xmm0
> > > + movdqu 32(%rsi), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_32)
> > > +
> > > + .p2align 4,, 6
> > > +L(32_to_64_bytes):
> > > + movdqu -32(%rdi, %rdx), %xmm0
> > > + movdqu -32(%rsi, %rdx), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_end_16)
> > > +
> > > + movdqu -16(%rdi, %rdx), %xmm0
> > > + movdqu -16(%rsi, %rdx), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_end)
> > > + ret
> > > +
> > > + .p2align 4
> > > +L(16_to_32_bytes):
> > > + movdqu (%rdi), %xmm0
> > > + movdqu (%rsi), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin)
> > > +
> > > + movdqu -16(%rdi, %rdx), %xmm0
> > > + movdqu -16(%rsi, %rdx), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_end)
> > > + ret
> > > +
> > >
> > > .p2align 4
> > > L(79bytesormore):
> > > + movdqu (%rdi), %xmm0
> > > movdqu (%rsi), %xmm1
> > > - movdqu (%rdi), %xmm2
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(16bytesin256)
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin)
> > > +
> > > +
> > > mov %rsi, %rcx
> > > and $-16, %rsi
> > > add $16, %rsi
> > > @@ -85,1694 +305,499 @@ L(79bytesormore):
> > >
> > > cmp $128, %rdx
> > > ja L(128bytesormore)
> > > -L(less128bytes):
> > > - sub $64, %rdx
> > > -
> > > - movdqu (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(16bytesin256)
> > >
> > > - movdqu 16(%rdi), %xmm2
> > > - pxor 16(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(32bytesin256)
> > > -
> > > - movdqu 32(%rdi), %xmm2
> > > - pxor 32(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(48bytesin256)
> > > -
> > > - movdqu 48(%rdi), %xmm2
> > > - pxor 48(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(64bytesin256)
> > > - cmp $32, %rdx
> > > - jb L(less32bytesin64)
> > > -
> > > - movdqu 64(%rdi), %xmm2
> > > - pxor 64(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(80bytesin256)
> > > -
> > > - movdqu 80(%rdi), %xmm2
> > > - pxor 80(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(96bytesin256)
> > > - sub $32, %rdx
> > > - add $32, %rdi
> > > - add $32, %rsi
> > > -L(less32bytesin64):
> > > - add $64, %rdi
> > > - add $64, %rsi
> > > - add %rdx, %rsi
> > > - add %rdx, %rdi
> > > - BRANCH_TO_JMPTBL_ENTRY(L(table_64bytes), %rdx, 4)
> > > + .p2align 4,, 6
> > > +L(less128bytes):
> > > + movdqu (%rdi), %xmm1
> > > + CMPEQ (%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin)
> > > +
> > > + movdqu 16(%rdi), %xmm1
> > > + CMPEQ 16(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_16)
> > > +
> > > + movdqu 32(%rdi), %xmm1
> > > + CMPEQ 32(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_32)
> > > +
> > > + movdqu 48(%rdi), %xmm1
> > > + CMPEQ 48(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_48)
> > > +
> > > + cmp $96, %rdx
> > > + jb L(32_to_64_bytes)
> > > +
> > > + addq $64, %rdi
> > > + addq $64, %rsi
> > > + subq $64, %rdx
> > > +
> > > + .p2align 4,, 6
> > > +L(last_64_bytes):
> > > + movdqu (%rdi), %xmm1
> > > + CMPEQ (%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin)
> > > +
> > > + movdqu 16(%rdi), %xmm1
> > > + CMPEQ 16(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_16)
> > > +
> > > + movdqu -32(%rdi, %rdx), %xmm0
> > > + movdqu -32(%rsi, %rdx), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_end_16)
> > > +
> > > + movdqu -16(%rdi, %rdx), %xmm0
> > > + movdqu -16(%rsi, %rdx), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_end)
> > > + ret
> > >
> > > + .p2align 4
> > > L(128bytesormore):
> > > - cmp $512, %rdx
> > > - ja L(512bytesormore)
> > > cmp $256, %rdx
> > > - ja L(less512bytes)
> > > + ja L(unaligned_loop)
> > > L(less256bytes):
> > > - sub $128, %rdx
> > > -
> > > - movdqu (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(16bytesin256)
> > > -
> > > - movdqu 16(%rdi), %xmm2
> > > - pxor 16(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(32bytesin256)
> > > -
> > > - movdqu 32(%rdi), %xmm2
> > > - pxor 32(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(48bytesin256)
> > > -
> > > - movdqu 48(%rdi), %xmm2
> > > - pxor 48(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(64bytesin256)
> > > -
> > > - movdqu 64(%rdi), %xmm2
> > > - pxor 64(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(80bytesin256)
> > > -
> > > - movdqu 80(%rdi), %xmm2
> > > - pxor 80(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(96bytesin256)
> > > -
> > > - movdqu 96(%rdi), %xmm2
> > > - pxor 96(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(112bytesin256)
> > > -
> > > - movdqu 112(%rdi), %xmm2
> > > - pxor 112(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(128bytesin256)
> > > -
> > > - add $128, %rsi
> > > - add $128, %rdi
> > > -
> > > - cmp $64, %rdx
> > > - jae L(less128bytes)
> > > -
> > > - cmp $32, %rdx
> > > - jb L(less32bytesin128)
> > > -
> > > - movdqu (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(16bytesin256)
> > > -
> > > - movdqu 16(%rdi), %xmm2
> > > - pxor 16(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(32bytesin256)
> > > - sub $32, %rdx
> > > - add $32, %rdi
> > > - add $32, %rsi
> > > -L(less32bytesin128):
> > > - add %rdx, %rsi
> > > - add %rdx, %rdi
> > > - BRANCH_TO_JMPTBL_ENTRY(L(table_64bytes), %rdx, 4)
> > > -
> > > -L(less512bytes):
> > > - sub $256, %rdx
> > > - movdqu (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(16bytesin256)
> > > -
> > > - movdqu 16(%rdi), %xmm2
> > > - pxor 16(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(32bytesin256)
> > > -
> > > - movdqu 32(%rdi), %xmm2
> > > - pxor 32(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(48bytesin256)
> > > -
> > > - movdqu 48(%rdi), %xmm2
> > > - pxor 48(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(64bytesin256)
> > > -
> > > - movdqu 64(%rdi), %xmm2
> > > - pxor 64(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(80bytesin256)
> > > -
> > > - movdqu 80(%rdi), %xmm2
> > > - pxor 80(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(96bytesin256)
> > > -
> > > - movdqu 96(%rdi), %xmm2
> > > - pxor 96(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(112bytesin256)
> > > -
> > > - movdqu 112(%rdi), %xmm2
> > > - pxor 112(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(128bytesin256)
> > > -
> > > - movdqu 128(%rdi), %xmm2
> > > - pxor 128(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(144bytesin256)
> > > -
> > > - movdqu 144(%rdi), %xmm2
> > > - pxor 144(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(160bytesin256)
> > > -
> > > - movdqu 160(%rdi), %xmm2
> > > - pxor 160(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(176bytesin256)
> > > -
> > > - movdqu 176(%rdi), %xmm2
> > > - pxor 176(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(192bytesin256)
> > > -
> > > - movdqu 192(%rdi), %xmm2
> > > - pxor 192(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(208bytesin256)
> > > -
> > > - movdqu 208(%rdi), %xmm2
> > > - pxor 208(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(224bytesin256)
> > > -
> > > - movdqu 224(%rdi), %xmm2
> > > - pxor 224(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(240bytesin256)
> > > -
> > > - movdqu 240(%rdi), %xmm2
> > > - pxor 240(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(256bytesin256)
> > > -
> > > - add $256, %rsi
> > > - add $256, %rdi
> > > -
> > > - cmp $128, %rdx
> > > - jae L(less256bytes)
> > > + movdqu (%rdi), %xmm1
> > > + CMPEQ (%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin)
> > > +
> > > + movdqu 16(%rdi), %xmm1
> > > + CMPEQ 16(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_16)
> > > +
> > > + movdqu 32(%rdi), %xmm1
> > > + CMPEQ 32(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_32)
> > > +
> > > + movdqu 48(%rdi), %xmm1
> > > + CMPEQ 48(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_48)
> > > +
> > > + addq $64, %rdi
> > > + addq $64, %rsi
> > > +
> > > + movdqu (%rdi), %xmm1
> > > + CMPEQ (%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin)
> > > +
> > > + movdqu 16(%rdi), %xmm1
> > > + CMPEQ 16(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_16)
> > > +
> > > + movdqu 32(%rdi), %xmm1
> > > + CMPEQ 32(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_32)
> > > +
> > > + movdqu 48(%rdi), %xmm1
> > > + CMPEQ 48(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_48)
> > > +
> > > + addq $-128, %rdx
> > > + subq $-64, %rsi
> > > + subq $-64, %rdi
> > >
> > > cmp $64, %rdx
> > > - jae L(less128bytes)
> > > + ja L(less128bytes)
> > >
> > > cmp $32, %rdx
> > > - jb L(less32bytesin256)
> > > -
> > > - movdqu (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(16bytesin256)
> > > -
> > > - movdqu 16(%rdi), %xmm2
> > > - pxor 16(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(32bytesin256)
> > > - sub $32, %rdx
> > > - add $32, %rdi
> > > - add $32, %rsi
> > > -L(less32bytesin256):
> > > - add %rdx, %rsi
> > > - add %rdx, %rdi
> > > - BRANCH_TO_JMPTBL_ENTRY(L(table_64bytes), %rdx, 4)
> > > + ja L(last_64_bytes)
> > > +
> > > + movdqu -32(%rdi, %rdx), %xmm0
> > > + movdqu -32(%rsi, %rdx), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_end_16)
> > > +
> > > + movdqu -16(%rdi, %rdx), %xmm0
> > > + movdqu -16(%rsi, %rdx), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_end)
> > > + ret
> > >
> > > .p2align 4
> > > -L(512bytesormore):
> > > +L(unaligned_loop):
> > > # ifdef DATA_CACHE_SIZE_HALF
> > > mov $DATA_CACHE_SIZE_HALF, %R8_LP
> > > # else
> > > mov __x86_data_cache_size_half(%rip), %R8_LP
> > > # endif
> > > - mov %r8, %r9
> > > - shr $1, %r8
> > > - add %r9, %r8
> > > - cmp %r8, %rdx
> > > - ja L(L2_L3_cache_unaglined)
> > > + movq %r8, %r9
> > > + addq %r8, %r8
> > > + addq %r9, %r8
> > > + cmpq %r8, %rdx
> > > + ja L(L2_L3_cache_unaligned)
> > > sub $64, %rdx
> > > .p2align 4
> > > L(64bytesormore_loop):
> > > - movdqu (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - movdqa %xmm2, %xmm1
> > > + movdqu (%rdi), %xmm0
> > > + movdqu 16(%rdi), %xmm1
> > > + movdqu 32(%rdi), %xmm2
> > > + movdqu 48(%rdi), %xmm3
> > >
> > > - movdqu 16(%rdi), %xmm3
> > > - pxor 16(%rsi), %xmm3
> > > - por %xmm3, %xmm1
> > > + CMPEQ (%rsi), %xmm0
> > > + CMPEQ 16(%rsi), %xmm1
> > > + CMPEQ 32(%rsi), %xmm2
> > > + CMPEQ 48(%rsi), %xmm3
> > >
> > > - movdqu 32(%rdi), %xmm4
> > > - pxor 32(%rsi), %xmm4
> > > - por %xmm4, %xmm1
> > > + pand %xmm0, %xmm1
> > > + pand %xmm2, %xmm3
> > > + pand %xmm1, %xmm3
> > >
> > > - movdqu 48(%rdi), %xmm5
> > > - pxor 48(%rsi), %xmm5
> > > - por %xmm5, %xmm1
> > > + pmovmskb %xmm3, %eax
> > > + incw %ax
> > > + jnz L(64bytesormore_loop_end)
> > >
> > > - ptest %xmm1, %xmm0
> > > - jnc L(64bytesormore_loop_end)
> > > add $64, %rsi
> > > add $64, %rdi
> > > sub $64, %rdx
> > > - jae L(64bytesormore_loop)
> > > + ja L(64bytesormore_loop)
> > >
> > > - add $64, %rdx
> > > - add %rdx, %rsi
> > > - add %rdx, %rdi
> > > - BRANCH_TO_JMPTBL_ENTRY(L(table_64bytes), %rdx, 4)
> > > + .p2align 4,, 6
> > > +L(loop_tail):
> > > + addq %rdx, %rdi
> > > + movdqu (%rdi), %xmm0
> > > + movdqu 16(%rdi), %xmm1
> > > + movdqu 32(%rdi), %xmm2
> > > + movdqu 48(%rdi), %xmm3
> > > +
> > > + addq %rdx, %rsi
> > > + movdqu (%rsi), %xmm4
> > > + movdqu 16(%rsi), %xmm5
> > > + movdqu 32(%rsi), %xmm6
> > > + movdqu 48(%rsi), %xmm7
> > > +
> > > + CMPEQ %xmm4, %xmm0
> > > + CMPEQ %xmm5, %xmm1
> > > + CMPEQ %xmm6, %xmm2
> > > + CMPEQ %xmm7, %xmm3
> > > +
> > > + pand %xmm0, %xmm1
> > > + pand %xmm2, %xmm3
> > > + pand %xmm1, %xmm3
> > > +
> > > + pmovmskb %xmm3, %eax
> > > + incw %ax
> > > + jnz L(64bytesormore_loop_end)
> > > + ret
> > >
> > > -L(L2_L3_cache_unaglined):
> > > - sub $64, %rdx
> > > +L(L2_L3_cache_unaligned):
> > > + subq $64, %rdx
> > > .p2align 4
> > > L(L2_L3_unaligned_128bytes_loop):
> > > prefetchnta 0x1c0(%rdi)
> > > prefetchnta 0x1c0(%rsi)
> > > - movdqu (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - movdqa %xmm2, %xmm1
> > >
> > > - movdqu 16(%rdi), %xmm3
> > > - pxor 16(%rsi), %xmm3
> > > - por %xmm3, %xmm1
> > > + movdqu (%rdi), %xmm0
> > > + movdqu 16(%rdi), %xmm1
> > > + movdqu 32(%rdi), %xmm2
> > > + movdqu 48(%rdi), %xmm3
> > > +
> > > + CMPEQ (%rsi), %xmm0
> > > + CMPEQ 16(%rsi), %xmm1
> > > + CMPEQ 32(%rsi), %xmm2
> > > + CMPEQ 48(%rsi), %xmm3
> > >
> > > - movdqu 32(%rdi), %xmm4
> > > - pxor 32(%rsi), %xmm4
> > > - por %xmm4, %xmm1
> > > + pand %xmm0, %xmm1
> > > + pand %xmm2, %xmm3
> > > + pand %xmm1, %xmm3
> > >
> > > - movdqu 48(%rdi), %xmm5
> > > - pxor 48(%rsi), %xmm5
> > > - por %xmm5, %xmm1
> > > + pmovmskb %xmm3, %eax
> > > + incw %ax
> > > + jnz L(64bytesormore_loop_end)
> > >
> > > - ptest %xmm1, %xmm0
> > > - jnc L(64bytesormore_loop_end)
> > > add $64, %rsi
> > > add $64, %rdi
> > > sub $64, %rdx
> > > - jae L(L2_L3_unaligned_128bytes_loop)
> > > + ja L(L2_L3_unaligned_128bytes_loop)
> > > + jmp L(loop_tail)
> > >
> > > - add $64, %rdx
> > > - add %rdx, %rsi
> > > - add %rdx, %rdi
> > > - BRANCH_TO_JMPTBL_ENTRY(L(table_64bytes), %rdx, 4)
> > >
> > > -/*
> > > - * This case is for machines which are sensitive for unaligned instructions.
> > > - */
> > > + /* This case is for machines which are sensitive for unaligned
> > > + * instructions. */
> > > .p2align 4
> > > L(2aligned):
> > > cmp $128, %rdx
> > > ja L(128bytesormorein2aligned)
> > > L(less128bytesin2aligned):
> > > - sub $64, %rdx
> > > -
> > > - movdqa (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(16bytesin256)
> > > -
> > > - movdqa 16(%rdi), %xmm2
> > > - pxor 16(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(32bytesin256)
> > > -
> > > - movdqa 32(%rdi), %xmm2
> > > - pxor 32(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(48bytesin256)
> > > -
> > > - movdqa 48(%rdi), %xmm2
> > > - pxor 48(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(64bytesin256)
> > > - cmp $32, %rdx
> > > - jb L(less32bytesin64in2alinged)
> > > -
> > > - movdqa 64(%rdi), %xmm2
> > > - pxor 64(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(80bytesin256)
> > > -
> > > - movdqa 80(%rdi), %xmm2
> > > - pxor 80(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(96bytesin256)
> > > - sub $32, %rdx
> > > - add $32, %rdi
> > > - add $32, %rsi
> > > -L(less32bytesin64in2alinged):
> > > - add $64, %rdi
> > > - add $64, %rsi
> > > - add %rdx, %rsi
> > > - add %rdx, %rdi
> > > - BRANCH_TO_JMPTBL_ENTRY(L(table_64bytes), %rdx, 4)
> > > + movdqa (%rdi), %xmm1
> > > + CMPEQ (%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin)
> > > +
> > > + movdqa 16(%rdi), %xmm1
> > > + CMPEQ 16(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_16)
> > > +
> > > + movdqa 32(%rdi), %xmm1
> > > + CMPEQ 32(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_32)
> > > +
> > > + movdqa 48(%rdi), %xmm1
> > > + CMPEQ 48(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_48)
> > > +
> > > + cmp $96, %rdx
> > > + jb L(32_to_64_bytes)
> > > +
> > > + addq $64, %rdi
> > > + addq $64, %rsi
> > > + subq $64, %rdx
> > > +
> > > + .p2align 4,, 6
> > > +L(aligned_last_64_bytes):
> > > + movdqa (%rdi), %xmm1
> > > + CMPEQ (%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin)
> > > +
> > > + movdqa 16(%rdi), %xmm1
> > > + CMPEQ 16(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_16)
> > > +
> > > + movdqu -32(%rdi, %rdx), %xmm0
> > > + movdqu -32(%rsi, %rdx), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_end_16)
> > > +
> > > + movdqu -16(%rdi, %rdx), %xmm0
> > > + movdqu -16(%rsi, %rdx), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_end)
> > > + ret
> > >
> > > .p2align 4
> > > L(128bytesormorein2aligned):
> > > - cmp $512, %rdx
> > > - ja L(512bytesormorein2aligned)
> > > cmp $256, %rdx
> > > - ja L(256bytesormorein2aligned)
> > > + ja L(aligned_loop)
> > > L(less256bytesin2alinged):
> > > - sub $128, %rdx
> > > -
> > > - movdqa (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(16bytesin256)
> > > -
> > > - movdqa 16(%rdi), %xmm2
> > > - pxor 16(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(32bytesin256)
> > > -
> > > - movdqa 32(%rdi), %xmm2
> > > - pxor 32(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(48bytesin256)
> > > -
> > > - movdqa 48(%rdi), %xmm2
> > > - pxor 48(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(64bytesin256)
> > > -
> > > - movdqa 64(%rdi), %xmm2
> > > - pxor 64(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(80bytesin256)
> > > -
> > > - movdqa 80(%rdi), %xmm2
> > > - pxor 80(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(96bytesin256)
> > > -
> > > - movdqa 96(%rdi), %xmm2
> > > - pxor 96(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(112bytesin256)
> > > -
> > > - movdqa 112(%rdi), %xmm2
> > > - pxor 112(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(128bytesin256)
> > > -
> > > - add $128, %rsi
> > > - add $128, %rdi
> > > + movdqa (%rdi), %xmm1
> > > + CMPEQ (%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin)
> > > +
> > > + movdqa 16(%rdi), %xmm1
> > > + CMPEQ 16(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_16)
> > > +
> > > + movdqa 32(%rdi), %xmm1
> > > + CMPEQ 32(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_32)
> > > +
> > > + movdqa 48(%rdi), %xmm1
> > > + CMPEQ 48(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_48)
> > > +
> > > + addq $64, %rdi
> > > + addq $64, %rsi
> > > +
> > > + movdqa (%rdi), %xmm1
> > > + CMPEQ (%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin)
> > > +
> > > + movdqa 16(%rdi), %xmm1
> > > + CMPEQ 16(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_16)
> > > +
> > > + movdqa 32(%rdi), %xmm1
> > > + CMPEQ 32(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_32)
> > > +
> > > + movdqa 48(%rdi), %xmm1
> > > + CMPEQ 48(%rsi), %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_begin_48)
> > > +
> > > + addq $-128, %rdx
> > > + subq $-64, %rsi
> > > + subq $-64, %rdi
> > >
> > > cmp $64, %rdx
> > > - jae L(less128bytesin2aligned)
> > > + ja L(less128bytesin2aligned)
> > >
> > > cmp $32, %rdx
> > > - jb L(less32bytesin128in2aligned)
> > > -
> > > - movdqu (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(16bytesin256)
> > > -
> > > - movdqu 16(%rdi), %xmm2
> > > - pxor 16(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(32bytesin256)
> > > - sub $32, %rdx
> > > - add $32, %rdi
> > > - add $32, %rsi
> > > -L(less32bytesin128in2aligned):
> > > - add %rdx, %rsi
> > > - add %rdx, %rdi
> > > - BRANCH_TO_JMPTBL_ENTRY(L(table_64bytes), %rdx, 4)
> > > -
> > > - .p2align 4
> > > -L(256bytesormorein2aligned):
> > > -
> > > - sub $256, %rdx
> > > - movdqa (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(16bytesin256)
> > > -
> > > - movdqa 16(%rdi), %xmm2
> > > - pxor 16(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(32bytesin256)
> > > -
> > > - movdqa 32(%rdi), %xmm2
> > > - pxor 32(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(48bytesin256)
> > > -
> > > - movdqa 48(%rdi), %xmm2
> > > - pxor 48(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(64bytesin256)
> > > -
> > > - movdqa 64(%rdi), %xmm2
> > > - pxor 64(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(80bytesin256)
> > > -
> > > - movdqa 80(%rdi), %xmm2
> > > - pxor 80(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(96bytesin256)
> > > -
> > > - movdqa 96(%rdi), %xmm2
> > > - pxor 96(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(112bytesin256)
> > > -
> > > - movdqa 112(%rdi), %xmm2
> > > - pxor 112(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(128bytesin256)
> > > -
> > > - movdqa 128(%rdi), %xmm2
> > > - pxor 128(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(144bytesin256)
> > > -
> > > - movdqa 144(%rdi), %xmm2
> > > - pxor 144(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(160bytesin256)
> > > -
> > > - movdqa 160(%rdi), %xmm2
> > > - pxor 160(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(176bytesin256)
> > > -
> > > - movdqa 176(%rdi), %xmm2
> > > - pxor 176(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(192bytesin256)
> > > -
> > > - movdqa 192(%rdi), %xmm2
> > > - pxor 192(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(208bytesin256)
> > > -
> > > - movdqa 208(%rdi), %xmm2
> > > - pxor 208(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(224bytesin256)
> > > -
> > > - movdqa 224(%rdi), %xmm2
> > > - pxor 224(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(240bytesin256)
> > > -
> > > - movdqa 240(%rdi), %xmm2
> > > - pxor 240(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(256bytesin256)
> > > -
> > > - add $256, %rsi
> > > - add $256, %rdi
> > > -
> > > - cmp $128, %rdx
> > > - jae L(less256bytesin2alinged)
> > > -
> > > - cmp $64, %rdx
> > > - jae L(less128bytesin2aligned)
> > > -
> > > - cmp $32, %rdx
> > > - jb L(less32bytesin256in2alinged)
> > > -
> > > - movdqa (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(16bytesin256)
> > > -
> > > - movdqa 16(%rdi), %xmm2
> > > - pxor 16(%rsi), %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(32bytesin256)
> > > - sub $32, %rdx
> > > - add $32, %rdi
> > > - add $32, %rsi
> > > -L(less32bytesin256in2alinged):
> > > - add %rdx, %rsi
> > > - add %rdx, %rdi
> > > - BRANCH_TO_JMPTBL_ENTRY(L(table_64bytes), %rdx, 4)
> > > + ja L(aligned_last_64_bytes)
> > > +
> > > + movdqu -32(%rdi, %rdx), %xmm0
> > > + movdqu -32(%rsi, %rdx), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_end_16)
> > > +
> > > + movdqu -16(%rdi, %rdx), %xmm0
> > > + movdqu -16(%rsi, %rdx), %xmm1
> > > + CMPEQ %xmm0, %xmm1
> > > + pmovmskb %xmm1, %eax
> > > + incw %ax
> > > + jnz L(vec_return_end)
> > > + ret
> > >
> > > .p2align 4
> > > -L(512bytesormorein2aligned):
> > > +L(aligned_loop):
> > > # ifdef DATA_CACHE_SIZE_HALF
> > > mov $DATA_CACHE_SIZE_HALF, %R8_LP
> > > # else
> > > mov __x86_data_cache_size_half(%rip), %R8_LP
> > > # endif
> > > - mov %r8, %r9
> > > - shr $1, %r8
> > > - add %r9, %r8
> > > - cmp %r8, %rdx
> > > - ja L(L2_L3_cache_aglined)
> > > + movq %r8, %r9
> > > + addq %r8, %r8
> > > + addq %r9, %r8
> > > + cmpq %r8, %rdx
> > > + ja L(L2_L3_cache_aligned)
> > >
> > > sub $64, %rdx
> > > .p2align 4
> > > L(64bytesormore_loopin2aligned):
> > > - movdqa (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - movdqa %xmm2, %xmm1
> > > -
> > > - movdqa 16(%rdi), %xmm3
> > > - pxor 16(%rsi), %xmm3
> > > - por %xmm3, %xmm1
> > > + movdqa (%rdi), %xmm0
> > > + movdqa 16(%rdi), %xmm1
> > > + movdqa 32(%rdi), %xmm2
> > > + movdqa 48(%rdi), %xmm3
> > >
> > > - movdqa 32(%rdi), %xmm4
> > > - pxor 32(%rsi), %xmm4
> > > - por %xmm4, %xmm1
> > > + CMPEQ (%rsi), %xmm0
> > > + CMPEQ 16(%rsi), %xmm1
> > > + CMPEQ 32(%rsi), %xmm2
> > > + CMPEQ 48(%rsi), %xmm3
> > >
> > > - movdqa 48(%rdi), %xmm5
> > > - pxor 48(%rsi), %xmm5
> > > - por %xmm5, %xmm1
> > > + pand %xmm0, %xmm1
> > > + pand %xmm2, %xmm3
> > > + pand %xmm1, %xmm3
> > >
> > > - ptest %xmm1, %xmm0
> > > - jnc L(64bytesormore_loop_end)
> > > + pmovmskb %xmm3, %eax
> > > + incw %ax
> > > + jnz L(64bytesormore_loop_end)
> > > add $64, %rsi
> > > add $64, %rdi
> > > sub $64, %rdx
> > > - jae L(64bytesormore_loopin2aligned)
> > > -
> > > - add $64, %rdx
> > > - add %rdx, %rsi
> > > - add %rdx, %rdi
> > > - BRANCH_TO_JMPTBL_ENTRY(L(table_64bytes), %rdx, 4)
> > > -L(L2_L3_cache_aglined):
> > > - sub $64, %rdx
> > > + ja L(64bytesormore_loopin2aligned)
> > > + jmp L(loop_tail)
> > >
> > > +L(L2_L3_cache_aligned):
> > > + subq $64, %rdx
> > > .p2align 4
> > > L(L2_L3_aligned_128bytes_loop):
> > > prefetchnta 0x1c0(%rdi)
> > > prefetchnta 0x1c0(%rsi)
> > > - movdqa (%rdi), %xmm2
> > > - pxor (%rsi), %xmm2
> > > - movdqa %xmm2, %xmm1
> > > -
> > > - movdqa 16(%rdi), %xmm3
> > > - pxor 16(%rsi), %xmm3
> > > - por %xmm3, %xmm1
> > > + movdqa (%rdi), %xmm0
> > > + movdqa 16(%rdi), %xmm1
> > > + movdqa 32(%rdi), %xmm2
> > > + movdqa 48(%rdi), %xmm3
> > >
> > > - movdqa 32(%rdi), %xmm4
> > > - pxor 32(%rsi), %xmm4
> > > - por %xmm4, %xmm1
> > > + CMPEQ (%rsi), %xmm0
> > > + CMPEQ 16(%rsi), %xmm1
> > > + CMPEQ 32(%rsi), %xmm2
> > > + CMPEQ 48(%rsi), %xmm3
> > >
> > > - movdqa 48(%rdi), %xmm5
> > > - pxor 48(%rsi), %xmm5
> > > - por %xmm5, %xmm1
> > > + pand %xmm0, %xmm1
> > > + pand %xmm2, %xmm3
> > > + pand %xmm1, %xmm3
> > >
> > > - ptest %xmm1, %xmm0
> > > - jnc L(64bytesormore_loop_end)
> > > - add $64, %rsi
> > > - add $64, %rdi
> > > - sub $64, %rdx
> > > - jae L(L2_L3_aligned_128bytes_loop)
> > > -
> > > - add $64, %rdx
> > > - add %rdx, %rsi
> > > - add %rdx, %rdi
> > > - BRANCH_TO_JMPTBL_ENTRY(L(table_64bytes), %rdx, 4)
> > > + pmovmskb %xmm3, %eax
> > > + incw %ax
> > > + jnz L(64bytesormore_loop_end)
> > >
> > > + addq $64, %rsi
> > > + addq $64, %rdi
> > > + subq $64, %rdx
> > > + ja L(L2_L3_aligned_128bytes_loop)
> > > + jmp L(loop_tail)
> > >
> > > .p2align 4
> > > L(64bytesormore_loop_end):
> > > - add $16, %rdi
> > > - add $16, %rsi
> > > - ptest %xmm2, %xmm0
> > > - jnc L(16bytes)
> > > -
> > > - add $16, %rdi
> > > - add $16, %rsi
> > > - ptest %xmm3, %xmm0
> > > - jnc L(16bytes)
> > > -
> > > - add $16, %rdi
> > > - add $16, %rsi
> > > - ptest %xmm4, %xmm0
> > > - jnc L(16bytes)
> > > -
> > > - add $16, %rdi
> > > - add $16, %rsi
> > > - jmp L(16bytes)
> > > -
> > > -L(256bytesin256):
> > > - add $256, %rdi
> > > - add $256, %rsi
> > > - jmp L(16bytes)
> > > -L(240bytesin256):
> > > - add $240, %rdi
> > > - add $240, %rsi
> > > - jmp L(16bytes)
> > > -L(224bytesin256):
> > > - add $224, %rdi
> > > - add $224, %rsi
> > > - jmp L(16bytes)
> > > -L(208bytesin256):
> > > - add $208, %rdi
> > > - add $208, %rsi
> > > - jmp L(16bytes)
> > > -L(192bytesin256):
> > > - add $192, %rdi
> > > - add $192, %rsi
> > > - jmp L(16bytes)
> > > -L(176bytesin256):
> > > - add $176, %rdi
> > > - add $176, %rsi
> > > - jmp L(16bytes)
> > > -L(160bytesin256):
> > > - add $160, %rdi
> > > - add $160, %rsi
> > > - jmp L(16bytes)
> > > -L(144bytesin256):
> > > - add $144, %rdi
> > > - add $144, %rsi
> > > - jmp L(16bytes)
> > > -L(128bytesin256):
> > > - add $128, %rdi
> > > - add $128, %rsi
> > > - jmp L(16bytes)
> > > -L(112bytesin256):
> > > - add $112, %rdi
> > > - add $112, %rsi
> > > - jmp L(16bytes)
> > > -L(96bytesin256):
> > > - add $96, %rdi
> > > - add $96, %rsi
> > > - jmp L(16bytes)
> > > -L(80bytesin256):
> > > - add $80, %rdi
> > > - add $80, %rsi
> > > - jmp L(16bytes)
> > > -L(64bytesin256):
> > > - add $64, %rdi
> > > - add $64, %rsi
> > > - jmp L(16bytes)
> > > -L(48bytesin256):
> > > - add $16, %rdi
> > > - add $16, %rsi
> > > -L(32bytesin256):
> > > - add $16, %rdi
> > > - add $16, %rsi
> > > -L(16bytesin256):
> > > - add $16, %rdi
> > > - add $16, %rsi
> > > -L(16bytes):
> > > - mov -16(%rdi), %rax
> > > - mov -16(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > -L(8bytes):
> > > - mov -8(%rdi), %rax
> > > - mov -8(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(12bytes):
> > > - mov -12(%rdi), %rax
> > > - mov -12(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > -L(4bytes):
> > > - mov -4(%rsi), %ecx
> > > -# ifndef USE_AS_WMEMCMP
> > > - mov -4(%rdi), %eax
> > > - cmp %eax, %ecx
> > > -# else
> > > - cmp -4(%rdi), %ecx
> > > -# endif
> > > - jne L(diffin4bytes)
> > > -L(0bytes):
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > -# ifndef USE_AS_WMEMCMP
> > > -/* unreal case for wmemcmp */
> > > - .p2align 4
> > > -L(65bytes):
> > > - movdqu -65(%rdi), %xmm1
> > > - movdqu -65(%rsi), %xmm2
> > > - mov $-65, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(49bytes):
> > > - movdqu -49(%rdi), %xmm1
> > > - movdqu -49(%rsi), %xmm2
> > > - mov $-49, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(33bytes):
> > > - movdqu -33(%rdi), %xmm1
> > > - movdqu -33(%rsi), %xmm2
> > > - mov $-33, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(17bytes):
> > > - mov -17(%rdi), %rax
> > > - mov -17(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > -L(9bytes):
> > > - mov -9(%rdi), %rax
> > > - mov -9(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - movzbl -1(%rdi), %eax
> > > - movzbl -1(%rsi), %edx
> > > - sub %edx, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(13bytes):
> > > - mov -13(%rdi), %rax
> > > - mov -13(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - mov -8(%rdi), %rax
> > > - mov -8(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(5bytes):
> > > - mov -5(%rdi), %eax
> > > - mov -5(%rsi), %ecx
> > > - cmp %eax, %ecx
> > > - jne L(diffin4bytes)
> > > - movzbl -1(%rdi), %eax
> > > - movzbl -1(%rsi), %edx
> > > - sub %edx, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(66bytes):
> > > - movdqu -66(%rdi), %xmm1
> > > - movdqu -66(%rsi), %xmm2
> > > - mov $-66, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(50bytes):
> > > - movdqu -50(%rdi), %xmm1
> > > - movdqu -50(%rsi), %xmm2
> > > - mov $-50, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(34bytes):
> > > - movdqu -34(%rdi), %xmm1
> > > - movdqu -34(%rsi), %xmm2
> > > - mov $-34, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(18bytes):
> > > - mov -18(%rdi), %rax
> > > - mov -18(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > -L(10bytes):
> > > - mov -10(%rdi), %rax
> > > - mov -10(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - movzwl -2(%rdi), %eax
> > > - movzwl -2(%rsi), %ecx
> > > - cmp %cl, %al
> > > - jne L(end)
> > > - and $0xffff, %eax
> > > - and $0xffff, %ecx
> > > - sub %ecx, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(14bytes):
> > > - mov -14(%rdi), %rax
> > > - mov -14(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - mov -8(%rdi), %rax
> > > - mov -8(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(6bytes):
> > > - mov -6(%rdi), %eax
> > > - mov -6(%rsi), %ecx
> > > - cmp %eax, %ecx
> > > - jne L(diffin4bytes)
> > > -L(2bytes):
> > > - movzwl -2(%rsi), %ecx
> > > - movzwl -2(%rdi), %eax
> > > - cmp %cl, %al
> > > - jne L(end)
> > > - and $0xffff, %eax
> > > - and $0xffff, %ecx
> > > - sub %ecx, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(67bytes):
> > > - movdqu -67(%rdi), %xmm2
> > > - movdqu -67(%rsi), %xmm1
> > > - mov $-67, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(51bytes):
> > > - movdqu -51(%rdi), %xmm2
> > > - movdqu -51(%rsi), %xmm1
> > > - mov $-51, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(35bytes):
> > > - movdqu -35(%rsi), %xmm1
> > > - movdqu -35(%rdi), %xmm2
> > > - mov $-35, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(19bytes):
> > > - mov -19(%rdi), %rax
> > > - mov -19(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > -L(11bytes):
> > > - mov -11(%rdi), %rax
> > > - mov -11(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - mov -4(%rdi), %eax
> > > - mov -4(%rsi), %ecx
> > > - cmp %eax, %ecx
> > > - jne L(diffin4bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(15bytes):
> > > - mov -15(%rdi), %rax
> > > - mov -15(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - mov -8(%rdi), %rax
> > > - mov -8(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(7bytes):
> > > - mov -7(%rdi), %eax
> > > - mov -7(%rsi), %ecx
> > > - cmp %eax, %ecx
> > > - jne L(diffin4bytes)
> > > - mov -4(%rdi), %eax
> > > - mov -4(%rsi), %ecx
> > > - cmp %eax, %ecx
> > > - jne L(diffin4bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(3bytes):
> > > - movzwl -3(%rdi), %eax
> > > - movzwl -3(%rsi), %ecx
> > > - cmp %eax, %ecx
> > > - jne L(diffin2bytes)
> > > -L(1bytes):
> > > - movzbl -1(%rdi), %eax
> > > - movzbl -1(%rsi), %ecx
> > > - sub %ecx, %eax
> > > - ret
> > > -# endif
> > > -
> > > - .p2align 4
> > > -L(68bytes):
> > > - movdqu -68(%rdi), %xmm2
> > > - movdqu -68(%rsi), %xmm1
> > > - mov $-68, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(52bytes):
> > > - movdqu -52(%rdi), %xmm2
> > > - movdqu -52(%rsi), %xmm1
> > > - mov $-52, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(36bytes):
> > > - movdqu -36(%rdi), %xmm2
> > > - movdqu -36(%rsi), %xmm1
> > > - mov $-36, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(20bytes):
> > > - movdqu -20(%rdi), %xmm2
> > > - movdqu -20(%rsi), %xmm1
> > > - mov $-20, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > - mov -4(%rsi), %ecx
> > > -
> > > -# ifndef USE_AS_WMEMCMP
> > > - mov -4(%rdi), %eax
> > > - cmp %eax, %ecx
> > > -# else
> > > - cmp -4(%rdi), %ecx
> > > -# endif
> > > - jne L(diffin4bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > -# ifndef USE_AS_WMEMCMP
> > > -/* unreal cases for wmemcmp */
> > > - .p2align 4
> > > -L(69bytes):
> > > - movdqu -69(%rsi), %xmm1
> > > - movdqu -69(%rdi), %xmm2
> > > - mov $-69, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(53bytes):
> > > - movdqu -53(%rsi), %xmm1
> > > - movdqu -53(%rdi), %xmm2
> > > - mov $-53, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(37bytes):
> > > - movdqu -37(%rsi), %xmm1
> > > - movdqu -37(%rdi), %xmm2
> > > - mov $-37, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(21bytes):
> > > - movdqu -21(%rsi), %xmm1
> > > - movdqu -21(%rdi), %xmm2
> > > - mov $-21, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > - mov -8(%rdi), %rax
> > > - mov -8(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(70bytes):
> > > - movdqu -70(%rsi), %xmm1
> > > - movdqu -70(%rdi), %xmm2
> > > - mov $-70, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(54bytes):
> > > - movdqu -54(%rsi), %xmm1
> > > - movdqu -54(%rdi), %xmm2
> > > - mov $-54, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(38bytes):
> > > - movdqu -38(%rsi), %xmm1
> > > - movdqu -38(%rdi), %xmm2
> > > - mov $-38, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(22bytes):
> > > - movdqu -22(%rsi), %xmm1
> > > - movdqu -22(%rdi), %xmm2
> > > - mov $-22, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > - mov -8(%rdi), %rax
> > > - mov -8(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(71bytes):
> > > - movdqu -71(%rsi), %xmm1
> > > - movdqu -71(%rdi), %xmm2
> > > - mov $-71, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(55bytes):
> > > - movdqu -55(%rdi), %xmm2
> > > - movdqu -55(%rsi), %xmm1
> > > - mov $-55, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(39bytes):
> > > - movdqu -39(%rdi), %xmm2
> > > - movdqu -39(%rsi), %xmm1
> > > - mov $-39, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(23bytes):
> > > - movdqu -23(%rdi), %xmm2
> > > - movdqu -23(%rsi), %xmm1
> > > - mov $-23, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > - mov -8(%rdi), %rax
> > > - mov -8(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -# endif
> > > -
> > > - .p2align 4
> > > -L(72bytes):
> > > - movdqu -72(%rsi), %xmm1
> > > - movdqu -72(%rdi), %xmm2
> > > - mov $-72, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(56bytes):
> > > - movdqu -56(%rdi), %xmm2
> > > - movdqu -56(%rsi), %xmm1
> > > - mov $-56, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(40bytes):
> > > - movdqu -40(%rdi), %xmm2
> > > - movdqu -40(%rsi), %xmm1
> > > - mov $-40, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(24bytes):
> > > - movdqu -24(%rdi), %xmm2
> > > - movdqu -24(%rsi), %xmm1
> > > - mov $-24, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -
> > > - mov -8(%rsi), %rcx
> > > - mov -8(%rdi), %rax
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > -# ifndef USE_AS_WMEMCMP
> > > -/* unreal cases for wmemcmp */
> > > - .p2align 4
> > > -L(73bytes):
> > > - movdqu -73(%rsi), %xmm1
> > > - movdqu -73(%rdi), %xmm2
> > > - mov $-73, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(57bytes):
> > > - movdqu -57(%rdi), %xmm2
> > > - movdqu -57(%rsi), %xmm1
> > > - mov $-57, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(41bytes):
> > > - movdqu -41(%rdi), %xmm2
> > > - movdqu -41(%rsi), %xmm1
> > > - mov $-41, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(25bytes):
> > > - movdqu -25(%rdi), %xmm2
> > > - movdqu -25(%rsi), %xmm1
> > > - mov $-25, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > - mov -9(%rdi), %rax
> > > - mov -9(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - movzbl -1(%rdi), %eax
> > > - movzbl -1(%rsi), %ecx
> > > - sub %ecx, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(74bytes):
> > > - movdqu -74(%rsi), %xmm1
> > > - movdqu -74(%rdi), %xmm2
> > > - mov $-74, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(58bytes):
> > > - movdqu -58(%rdi), %xmm2
> > > - movdqu -58(%rsi), %xmm1
> > > - mov $-58, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(42bytes):
> > > - movdqu -42(%rdi), %xmm2
> > > - movdqu -42(%rsi), %xmm1
> > > - mov $-42, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(26bytes):
> > > - movdqu -26(%rdi), %xmm2
> > > - movdqu -26(%rsi), %xmm1
> > > - mov $-26, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > - mov -10(%rdi), %rax
> > > - mov -10(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - movzwl -2(%rdi), %eax
> > > - movzwl -2(%rsi), %ecx
> > > - jmp L(diffin2bytes)
> > > -
> > > - .p2align 4
> > > -L(75bytes):
> > > - movdqu -75(%rsi), %xmm1
> > > - movdqu -75(%rdi), %xmm2
> > > - mov $-75, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(59bytes):
> > > - movdqu -59(%rdi), %xmm2
> > > - movdqu -59(%rsi), %xmm1
> > > - mov $-59, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(43bytes):
> > > - movdqu -43(%rdi), %xmm2
> > > - movdqu -43(%rsi), %xmm1
> > > - mov $-43, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(27bytes):
> > > - movdqu -27(%rdi), %xmm2
> > > - movdqu -27(%rsi), %xmm1
> > > - mov $-27, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > - mov -11(%rdi), %rax
> > > - mov -11(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - mov -4(%rdi), %eax
> > > - mov -4(%rsi), %ecx
> > > - cmp %eax, %ecx
> > > - jne L(diffin4bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -# endif
> > > - .p2align 4
> > > -L(76bytes):
> > > - movdqu -76(%rsi), %xmm1
> > > - movdqu -76(%rdi), %xmm2
> > > - mov $-76, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(60bytes):
> > > - movdqu -60(%rdi), %xmm2
> > > - movdqu -60(%rsi), %xmm1
> > > - mov $-60, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(44bytes):
> > > - movdqu -44(%rdi), %xmm2
> > > - movdqu -44(%rsi), %xmm1
> > > - mov $-44, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(28bytes):
> > > - movdqu -28(%rdi), %xmm2
> > > - movdqu -28(%rsi), %xmm1
> > > - mov $-28, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > - mov -12(%rdi), %rax
> > > - mov -12(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - mov -4(%rsi), %ecx
> > > -# ifndef USE_AS_WMEMCMP
> > > - mov -4(%rdi), %eax
> > > - cmp %eax, %ecx
> > > -# else
> > > - cmp -4(%rdi), %ecx
> > > -# endif
> > > - jne L(diffin4bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > -# ifndef USE_AS_WMEMCMP
> > > -/* unreal cases for wmemcmp */
> > > - .p2align 4
> > > -L(77bytes):
> > > - movdqu -77(%rsi), %xmm1
> > > - movdqu -77(%rdi), %xmm2
> > > - mov $-77, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(61bytes):
> > > - movdqu -61(%rdi), %xmm2
> > > - movdqu -61(%rsi), %xmm1
> > > - mov $-61, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(45bytes):
> > > - movdqu -45(%rdi), %xmm2
> > > - movdqu -45(%rsi), %xmm1
> > > - mov $-45, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(29bytes):
> > > - movdqu -29(%rdi), %xmm2
> > > - movdqu -29(%rsi), %xmm1
> > > - mov $-29, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -
> > > - mov -13(%rdi), %rax
> > > - mov -13(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > -
> > > - mov -8(%rdi), %rax
> > > - mov -8(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(78bytes):
> > > - movdqu -78(%rsi), %xmm1
> > > - movdqu -78(%rdi), %xmm2
> > > - mov $-78, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(62bytes):
> > > - movdqu -62(%rdi), %xmm2
> > > - movdqu -62(%rsi), %xmm1
> > > - mov $-62, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(46bytes):
> > > - movdqu -46(%rdi), %xmm2
> > > - movdqu -46(%rsi), %xmm1
> > > - mov $-46, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(30bytes):
> > > - movdqu -30(%rdi), %xmm2
> > > - movdqu -30(%rsi), %xmm1
> > > - mov $-30, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > - mov -14(%rdi), %rax
> > > - mov -14(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - mov -8(%rdi), %rax
> > > - mov -8(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(79bytes):
> > > - movdqu -79(%rsi), %xmm1
> > > - movdqu -79(%rdi), %xmm2
> > > - mov $-79, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(63bytes):
> > > - movdqu -63(%rdi), %xmm2
> > > - movdqu -63(%rsi), %xmm1
> > > - mov $-63, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(47bytes):
> > > - movdqu -47(%rdi), %xmm2
> > > - movdqu -47(%rsi), %xmm1
> > > - mov $-47, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(31bytes):
> > > - movdqu -31(%rdi), %xmm2
> > > - movdqu -31(%rsi), %xmm1
> > > - mov $-31, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > - mov -15(%rdi), %rax
> > > - mov -15(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - mov -8(%rdi), %rax
> > > - mov -8(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -# endif
> > > - .p2align 4
> > > -L(64bytes):
> > > - movdqu -64(%rdi), %xmm2
> > > - movdqu -64(%rsi), %xmm1
> > > - mov $-64, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(48bytes):
> > > - movdqu -48(%rdi), %xmm2
> > > - movdqu -48(%rsi), %xmm1
> > > - mov $-48, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -L(32bytes):
> > > - movdqu -32(%rdi), %xmm2
> > > - movdqu -32(%rsi), %xmm1
> > > - mov $-32, %dl
> > > - pxor %xmm1, %xmm2
> > > - ptest %xmm2, %xmm0
> > > - jnc L(less16bytes)
> > > -
> > > - mov -16(%rdi), %rax
> > > - mov -16(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > -
> > > - mov -8(%rdi), %rax
> > > - mov -8(%rsi), %rcx
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -
> > > -/*
> > > - * Aligned 8 bytes to avoid 2 branch "taken" in one 16 alinged code block.
> > > - */
> > > - .p2align 3
> > > -L(less16bytes):
> > > - movsbq %dl, %rdx
> > > - mov (%rsi, %rdx), %rcx
> > > - mov (%rdi, %rdx), %rax
> > > - cmp %rax, %rcx
> > > - jne L(diffin8bytes)
> > > - mov 8(%rsi, %rdx), %rcx
> > > - mov 8(%rdi, %rdx), %rax
> > > -L(diffin8bytes):
> > > - cmp %eax, %ecx
> > > - jne L(diffin4bytes)
> > > - shr $32, %rcx
> > > - shr $32, %rax
> > > -
> > > + pmovmskb %xmm0, %ecx
> > > + incw %cx
> > > + jnz L(loop_end_ret)
> > > +
> > > + pmovmskb %xmm1, %ecx
> > > + notw %cx
> > > + sall $16, %ecx
> > > + jnz L(loop_end_ret)
> > > +
> > > + pmovmskb %xmm2, %ecx
> > > + notw %cx
> > > + shlq $32, %rcx
> > > + jnz L(loop_end_ret)
> > > +
> > > + addq $48, %rdi
> > > + addq $48, %rsi
> > > + movq %rax, %rcx
> > > +
> > > + .p2align 4,, 6
> > > +L(loop_end_ret):
> > > + bsfq %rcx, %rcx
> > > # ifdef USE_AS_WMEMCMP
> > > -/* for wmemcmp */
> > > - cmp %eax, %ecx
> > > - jne L(diffin4bytes)
> > > - xor %eax, %eax
> > > - ret
> > > -# endif
> > > -
> > > -L(diffin4bytes):
> > > -# ifndef USE_AS_WMEMCMP
> > > - cmp %cx, %ax
> > > - jne L(diffin2bytes)
> > > - shr $16, %ecx
> > > - shr $16, %eax
> > > -L(diffin2bytes):
> > > - cmp %cl, %al
> > > - jne L(end)
> > > - and $0xffff, %eax
> > > - and $0xffff, %ecx
> > > - sub %ecx, %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(end):
> > > - and $0xff, %eax
> > > - and $0xff, %ecx
> > > - sub %ecx, %eax
> > > - ret
> > > + movl (%rdi, %rcx), %eax
> > > + xorl %edx, %edx
> > > + cmpl (%rsi, %rcx), %eax
> > > + setg %dl
> > > + leal -1(%rdx, %rdx), %eax
> > > # else
> > > -
> > > -/* for wmemcmp */
> > > - mov $1, %eax
> > > - jl L(nequal_bigger)
> > > - neg %eax
> > > - ret
> > > -
> > > - .p2align 4
> > > -L(nequal_bigger):
> > > - ret
> > > -
> > > -L(unreal_case):
> > > - xor %eax, %eax
> > > - ret
> > > + movzbl (%rdi, %rcx), %eax
> > > + movzbl (%rsi, %rcx), %ecx
> > > + subl %ecx, %eax
> > > # endif
> > > -
> > > + ret
> > > END (MEMCMP)
> > > -
> > > - .section .rodata.sse4.1,"a",@progbits
> > > - .p2align 3
> > > -# ifndef USE_AS_WMEMCMP
> > > -L(table_64bytes):
> > > - .int JMPTBL (L(0bytes), L(table_64bytes))
> > > - .int JMPTBL (L(1bytes), L(table_64bytes))
> > > - .int JMPTBL (L(2bytes), L(table_64bytes))
> > > - .int JMPTBL (L(3bytes), L(table_64bytes))
> > > - .int JMPTBL (L(4bytes), L(table_64bytes))
> > > - .int JMPTBL (L(5bytes), L(table_64bytes))
> > > - .int JMPTBL (L(6bytes), L(table_64bytes))
> > > - .int JMPTBL (L(7bytes), L(table_64bytes))
> > > - .int JMPTBL (L(8bytes), L(table_64bytes))
> > > - .int JMPTBL (L(9bytes), L(table_64bytes))
> > > - .int JMPTBL (L(10bytes), L(table_64bytes))
> > > - .int JMPTBL (L(11bytes), L(table_64bytes))
> > > - .int JMPTBL (L(12bytes), L(table_64bytes))
> > > - .int JMPTBL (L(13bytes), L(table_64bytes))
> > > - .int JMPTBL (L(14bytes), L(table_64bytes))
> > > - .int JMPTBL (L(15bytes), L(table_64bytes))
> > > - .int JMPTBL (L(16bytes), L(table_64bytes))
> > > - .int JMPTBL (L(17bytes), L(table_64bytes))
> > > - .int JMPTBL (L(18bytes), L(table_64bytes))
> > > - .int JMPTBL (L(19bytes), L(table_64bytes))
> > > - .int JMPTBL (L(20bytes), L(table_64bytes))
> > > - .int JMPTBL (L(21bytes), L(table_64bytes))
> > > - .int JMPTBL (L(22bytes), L(table_64bytes))
> > > - .int JMPTBL (L(23bytes), L(table_64bytes))
> > > - .int JMPTBL (L(24bytes), L(table_64bytes))
> > > - .int JMPTBL (L(25bytes), L(table_64bytes))
> > > - .int JMPTBL (L(26bytes), L(table_64bytes))
> > > - .int JMPTBL (L(27bytes), L(table_64bytes))
> > > - .int JMPTBL (L(28bytes), L(table_64bytes))
> > > - .int JMPTBL (L(29bytes), L(table_64bytes))
> > > - .int JMPTBL (L(30bytes), L(table_64bytes))
> > > - .int JMPTBL (L(31bytes), L(table_64bytes))
> > > - .int JMPTBL (L(32bytes), L(table_64bytes))
> > > - .int JMPTBL (L(33bytes), L(table_64bytes))
> > > - .int JMPTBL (L(34bytes), L(table_64bytes))
> > > - .int JMPTBL (L(35bytes), L(table_64bytes))
> > > - .int JMPTBL (L(36bytes), L(table_64bytes))
> > > - .int JMPTBL (L(37bytes), L(table_64bytes))
> > > - .int JMPTBL (L(38bytes), L(table_64bytes))
> > > - .int JMPTBL (L(39bytes), L(table_64bytes))
> > > - .int JMPTBL (L(40bytes), L(table_64bytes))
> > > - .int JMPTBL (L(41bytes), L(table_64bytes))
> > > - .int JMPTBL (L(42bytes), L(table_64bytes))
> > > - .int JMPTBL (L(43bytes), L(table_64bytes))
> > > - .int JMPTBL (L(44bytes), L(table_64bytes))
> > > - .int JMPTBL (L(45bytes), L(table_64bytes))
> > > - .int JMPTBL (L(46bytes), L(table_64bytes))
> > > - .int JMPTBL (L(47bytes), L(table_64bytes))
> > > - .int JMPTBL (L(48bytes), L(table_64bytes))
> > > - .int JMPTBL (L(49bytes), L(table_64bytes))
> > > - .int JMPTBL (L(50bytes), L(table_64bytes))
> > > - .int JMPTBL (L(51bytes), L(table_64bytes))
> > > - .int JMPTBL (L(52bytes), L(table_64bytes))
> > > - .int JMPTBL (L(53bytes), L(table_64bytes))
> > > - .int JMPTBL (L(54bytes), L(table_64bytes))
> > > - .int JMPTBL (L(55bytes), L(table_64bytes))
> > > - .int JMPTBL (L(56bytes), L(table_64bytes))
> > > - .int JMPTBL (L(57bytes), L(table_64bytes))
> > > - .int JMPTBL (L(58bytes), L(table_64bytes))
> > > - .int JMPTBL (L(59bytes), L(table_64bytes))
> > > - .int JMPTBL (L(60bytes), L(table_64bytes))
> > > - .int JMPTBL (L(61bytes), L(table_64bytes))
> > > - .int JMPTBL (L(62bytes), L(table_64bytes))
> > > - .int JMPTBL (L(63bytes), L(table_64bytes))
> > > - .int JMPTBL (L(64bytes), L(table_64bytes))
> > > - .int JMPTBL (L(65bytes), L(table_64bytes))
> > > - .int JMPTBL (L(66bytes), L(table_64bytes))
> > > - .int JMPTBL (L(67bytes), L(table_64bytes))
> > > - .int JMPTBL (L(68bytes), L(table_64bytes))
> > > - .int JMPTBL (L(69bytes), L(table_64bytes))
> > > - .int JMPTBL (L(70bytes), L(table_64bytes))
> > > - .int JMPTBL (L(71bytes), L(table_64bytes))
> > > - .int JMPTBL (L(72bytes), L(table_64bytes))
> > > - .int JMPTBL (L(73bytes), L(table_64bytes))
> > > - .int JMPTBL (L(74bytes), L(table_64bytes))
> > > - .int JMPTBL (L(75bytes), L(table_64bytes))
> > > - .int JMPTBL (L(76bytes), L(table_64bytes))
> > > - .int JMPTBL (L(77bytes), L(table_64bytes))
> > > - .int JMPTBL (L(78bytes), L(table_64bytes))
> > > - .int JMPTBL (L(79bytes), L(table_64bytes))
> > > -# else
> > > -L(table_64bytes):
> > > - .int JMPTBL (L(0bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(4bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(8bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(12bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(16bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(20bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(24bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(28bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(32bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(36bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(40bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(44bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(48bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(52bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(56bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(60bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(64bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(68bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(72bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(76bytes), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > - .int JMPTBL (L(unreal_case), L(table_64bytes))
> > > -# endif
> > > #endif
> > > --
> > > 2.25.1
> > >
> >
> > LGTM.
> >
> > Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
> Thanks. Pushed.
> >
> > Thanks.
> >
> > --
> > H.J.
I would like to backport this patch to release branches.
Any comments or objections?
--Sunil
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2022-04-23 1:45 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
[not found] <20211111002714.2527889-1-goldstein.w.n@gmail.com>
[not found] ` <CAMe9rOrssV7DAf3gHwAapLYBcy_1orXt+BtxOixbYM6=pzuLWA@mail.gmail.com>
[not found] ` <CAFUsyf+DGMa6STkhT1B6O4xRZDuyKP-bbD7PFObyLVFiwjU-yQ@mail.gmail.com>
2022-04-23 1:44 ` [PATCH v1] x86: Shrink memcmp-sse4.S code size Sunil Pandey
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).