diff options
| -rw-r--r-- | sysdeps/x86_64/multiarch/memcpy-sse2-unaligned.S | 47 |
1 files changed, 2 insertions, 45 deletions
diff --git a/sysdeps/x86_64/multiarch/memcpy-sse2-unaligned.S b/sysdeps/x86_64/multiarch/memcpy-sse2-unaligned.S index 19d8aa60ba..335a498a23 100644 --- a/sysdeps/x86_64/multiarch/memcpy-sse2-unaligned.S +++ b/sysdeps/x86_64/multiarch/memcpy-sse2-unaligned.S @@ -25,12 +25,8 @@ ENTRY(__memcpy_sse2_unaligned) movq %rdi, %rax - movq %rsi, %r11 - leaq (%rdx,%rdx), %rcx - subq %rdi, %r11 - subq %rdx, %r11 - cmpq %rcx, %r11 - jb L(overlapping) + testq %rdx, %rdx + je L(return) cmpq $16, %rdx jbe L(less_16) movdqu (%rsi), %xmm8 @@ -89,45 +85,6 @@ L(loop): cmpq %rcx, %rdx jne L(loop) ret -L(overlapping): - testq %rdx, %rdx - .p2align 4,,5 - je L(return) - movq %rdx, %r9 - leaq 16(%rsi), %rcx - leaq 16(%rdi), %r8 - shrq $4, %r9 - movq %r9, %r11 - salq $4, %r11 - cmpq %rcx, %rdi - setae %cl - cmpq %r8, %rsi - setae %r8b - orl %r8d, %ecx - cmpq $15, %rdx - seta %r8b - testb %r8b, %cl - je .L21 - testq %r11, %r11 - je .L21 - xorl %ecx, %ecx - xorl %r8d, %r8d -.L7: - movdqu (%rsi,%rcx), %xmm8 - addq $1, %r8 - movdqu %xmm8, (%rdi,%rcx) - addq $16, %rcx - cmpq %r8, %r9 - ja .L7 - cmpq %r11, %rdx - je L(return) -.L21: - movzbl (%rsi,%r11), %ecx - movb %cl, (%rdi,%r11) - addq $1, %r11 - cmpq %r11, %rdx - ja .L21 - ret L(less_16): testb $24, %dl jne L(between_9_16) |