.section __TEXT,__text,regular,pure_instructions .build_version macos, 10, 14 sdk_version 10, 14 .globl _memcpy_clang ## -- Begin function memcpy_clang .p2align 4, 0x90 _memcpy_clang: ## @memcpy_clang .cfi_startproc ## %bb.0: pushq %rbp .cfi_def_cfa_offset 16 .cfi_offset %rbp, -16 movq %rsp, %rbp .cfi_def_cfa_register %rbp testq %rdx, %rdx je LBB0_12 ## %bb.1: cmpq $32, %rdx jae LBB0_3 ## %bb.2: xorl %eax, %eax jmp LBB0_11 LBB0_3: movq %rdx, %rax andq $-32, %rax leaq -32(%rax), %r9 movq %r9, %r10 shrq $5, %r10 incq %r10 movl %r10d, %r8d andl $3, %r8d cmpq $96, %r9 jae LBB0_5 ## %bb.4: xorl %ecx, %ecx testq %r8, %r8 jne LBB0_8 jmp LBB0_10 LBB0_5: movl $1, %ecx subq %r10, %rcx leaq -1(%r8,%rcx), %r9 xorl %ecx, %ecx .p2align 4, 0x90 LBB0_6: ## =>This Inner Loop Header: Depth=1 movups (%rsi,%rcx), %xmm0 movups 16(%rsi,%rcx), %xmm1 movups %xmm0, (%rdi,%rcx) movups %xmm1, 16(%rdi,%rcx) movups 32(%rsi,%rcx), %xmm0 movups 48(%rsi,%rcx), %xmm1 movups %xmm0, 32(%rdi,%rcx) movups %xmm1, 48(%rdi,%rcx) movups 64(%rsi,%rcx), %xmm0 movups 80(%rsi,%rcx), %xmm1 movups %xmm0, 64(%rdi,%rcx) movups %xmm1, 80(%rdi,%rcx) movups 96(%rsi,%rcx), %xmm0 movups 112(%rsi,%rcx), %xmm1 movups %xmm0, 96(%rdi,%rcx) movups %xmm1, 112(%rdi,%rcx) subq $-128, %rcx addq $4, %r9 jne LBB0_6 ## %bb.7: testq %r8, %r8 je LBB0_10 LBB0_8: addq $16, %rcx negq %r8 .p2align 4, 0x90 LBB0_9: ## =>This Inner Loop Header: Depth=1 movups -16(%rsi,%rcx), %xmm0 movups (%rsi,%rcx), %xmm1 movups %xmm0, -16(%rdi,%rcx) movups %xmm1, (%rdi,%rcx) addq $32, %rcx incq %r8 jne LBB0_9 LBB0_10: cmpq %rdx, %rax je LBB0_12 .p2align 4, 0x90 LBB0_11: ## =>This Inner Loop Header: Depth=1 movzbl (%rsi,%rax), %ecx movb %cl, (%rdi,%rax) incq %rax cmpq %rax, %rdx jne LBB0_11 LBB0_12: popq %rbp retq .cfi_endproc ## -- End function .subsections_via_symbols