1.29. SIMD
je .L25
movzx eax, BYTE PTR [rsi+11]
cmp rcx, 12
mov BYTE PTR [rdi+11], al
je .L26
movzx eax, BYTE PTR [rsi+12]
cmp rcx, 13
mov BYTE PTR [rdi+12], al
je .L27
movzx eax, BYTE PTR [rsi+13]
cmp rcx, 15
mov BYTE PTR [rdi+13], al
jne .L28
movzx eax, BYTE PTR [rsi+14]
mov BYTE PTR [rdi+14], al
mov eax, 15
.L4:
mov r10, rdx
lea r9, [rdx-1]
sub r10, rcx
lea r8, [r10-16]
sub r9, rcx
shr r8, 4
add r8, 1
mov r11, r8
sal r11, 4
cmp r9, 14
jbe .L6
lea rbp, [rsi+rcx]
xor r9d, r9d
add rcx, rdi
xor ebx, ebx
.L7:
movdqa xmm0, XMMWORD PTR [rbp+0+r9]
add rbx, 1
movups XMMWORD PTR [rcx+r9], xmm0
add r9, 16
cmp rbx, r8
jb .L7
add rax, r11
cmp r10, r11
je .L1
.L6:
movzx ecx, BYTE PTR [rsi+rax]
mov BYTE PTR [rdi+rax], cl
lea rcx, [rax+1]
cmp rdx, rcx
jbe .L1
movzx ecx, BYTE PTR [rsi+1+rax]
mov BYTE PTR [rdi+1+rax], cl
lea rcx, [rax+2]
cmp rdx, rcx
jbe .L1
movzx ecx, BYTE PTR [rsi+2+rax]
mov BYTE PTR [rdi+2+rax], cl
lea rcx, [rax+3]
cmp rdx, rcx
jbe .L1
movzx ecx, BYTE PTR [rsi+3+rax]
mov BYTE PTR [rdi+3+rax], cl
lea rcx, [rax+4]
cmp rdx, rcx
jbe .L1
movzx ecx, BYTE PTR [rsi+4+rax]
mov BYTE PTR [rdi+4+rax], cl
lea rcx, [rax+5]
cmp rdx, rcx
jbe .L1
movzx ecx, BYTE PTR [rsi+5+rax]
mov BYTE PTR [rdi+5+rax], cl