为什么添加内联程序集注释会导致 GCC 生成的代码发生如此根本的变化？

所以，我有这样的代码：

constexpr unsigned N = 1000;
void f1(char* sum, char* a, char* b) {
for(int i = 0; i < N; ++i) {
sum[i] = a[i] + b[i];
}
}
void f2(char* sum, char* a, char* b) {
char* end = sum + N;
while(sum != end) {
*sum++ = *a++ + *b++;
}
}

我想看看GCC 4.7.2将生成的代码。所以我运行了g++ -march=native -O3 -masm=intel -S a.c++ -std=c++11，得到了以下输出：

.file   "a.c++"
.intel_syntax noprefix
.text
.p2align 4,,15
.globl  _Z2f1PcS_S_
.type   _Z2f1PcS_S_, @function
_Z2f1PcS_S_:
.LFB0:
.cfi_startproc
lea     rcx, [rdx+16]
lea     rax, [rdi+16]
cmp     rdi, rcx
setae   r8b
cmp     rdx, rax
setae   cl
or      cl, r8b
je      .L5
lea     rcx, [rsi+16]
cmp     rdi, rcx
setae   cl
cmp     rsi, rax
setae   al
or      cl, al
je      .L5
xor     eax, eax
.p2align 4,,10
.p2align 3
.L3:
movdqu  xmm0, XMMWORD PTR [rdx+rax]
movdqu  xmm1, XMMWORD PTR [rsi+rax]
paddb   xmm0, xmm1
movdqu  XMMWORD PTR [rdi+rax], xmm0
add     rax, 16
cmp     rax, 992
jne     .L3
mov     ax, 8
mov     r9d, 992
.L2:
sub     eax, 1
lea     rcx, [rdx+r9]
add     rdi, r9
lea     r8, [rax+1]
add     rsi, r9
xor     eax, eax
.p2align 4,,10
.p2align 3
.L4:
movzx   edx, BYTE PTR [rcx+rax]
add     dl, BYTE PTR [rsi+rax]
mov     BYTE PTR [rdi+rax], dl
add     rax, 1
cmp     rax, r8
jne     .L4
rep
ret
.L5:
mov     eax, 1000
xor     r9d, r9d
jmp     .L2
.cfi_endproc
.LFE0:
.size   _Z2f1PcS_S_, .-_Z2f1PcS_S_
.p2align 4,,15
.globl  _Z2f2PcS_S_
.type   _Z2f2PcS_S_, @function
_Z2f2PcS_S_:
.LFB1:
.cfi_startproc
lea     rcx, [rdx+16]
lea     rax, [rdi+16]
cmp     rdi, rcx
setae   r8b
cmp     rdx, rax
setae   cl
or      cl, r8b
je      .L19
lea     rcx, [rsi+16]
cmp     rdi, rcx
setae   cl
cmp     rsi, rax
setae   al
or      cl, al
je      .L19
xor     eax, eax
.p2align 4,,10
.p2align 3
.L17:
movdqu  xmm0, XMMWORD PTR [rdx+rax]
movdqu  xmm1, XMMWORD PTR [rsi+rax]
paddb   xmm0, xmm1
movdqu  XMMWORD PTR [rdi+rax], xmm0
add     rax, 16
cmp     rax, 992
jne     .L17
add     rdi, 992
add     rsi, 992
add     rdx, 992
mov     r8d, 8
.L16:
xor     eax, eax
.p2align 4,,10
.p2align 3
.L18:
movzx   ecx, BYTE PTR [rdx+rax]
add     cl, BYTE PTR [rsi+rax]
mov     BYTE PTR [rdi+rax], cl
add     rax, 1
cmp     rax, r8
jne     .L18
rep
ret
.L19:
mov     r8d, 1000
jmp     .L16
.cfi_endproc
.LFE1:
.size   _Z2f2PcS_S_, .-_Z2f2PcS_S_
.ident  "GCC: (GNU) 4.7.2"
.section        .note.GNU-stack,"",@progbits

我不太擅长阅读汇编，所以我决定添加一些标记来知道循环的主体去了哪里：

constexpr unsigned N = 1000;
void f1(char* sum, char* a, char* b) {
for(int i = 0; i < N; ++i) {
asm("# im in ur loop");
sum[i] = a[i] + b[i];
}
}
void f2(char* sum, char* a, char* b) {
char* end = sum + N;
while(sum != end) {
asm("# im in ur loop");
*sum++ = *a++ + *b++;
}
}

GCC吐出了这个：

.file   "a.c++"
.intel_syntax noprefix
.text
.p2align 4,,15
.globl  _Z2f1PcS_S_
.type   _Z2f1PcS_S_, @function
_Z2f1PcS_S_:
.LFB0:
.cfi_startproc
xor eax, eax
.p2align 4,,10
.p2align 3
.L2:
#APP
# 4 "a.c++" 1
# im in ur loop
# 0 "" 2
#NO_APP
movzx   ecx, BYTE PTR [rdx+rax]
add cl, BYTE PTR [rsi+rax]
mov BYTE PTR [rdi+rax], cl
add rax, 1
cmp rax, 1000
jne .L2
rep
ret
.cfi_endproc
.LFE0:
.size   _Z2f1PcS_S_, .-_Z2f1PcS_S_
.p2align 4,,15
.globl  _Z2f2PcS_S_
.type   _Z2f2PcS_S_, @function
_Z2f2PcS_S_:
.LFB1:
.cfi_startproc
xor eax, eax
.p2align 4,,10
.p2align 3
.L6:
#APP
# 12 "a.c++" 1
# im in ur loop
# 0 "" 2
#NO_APP
movzx   ecx, BYTE PTR [rdx+rax]
add cl, BYTE PTR [rsi+rax]
mov BYTE PTR [rdi+rax], cl
add rax, 1
cmp rax, 1000
jne .L6
rep
ret
.cfi_endproc
.LFE1:
.size   _Z2f2PcS_S_, .-_Z2f2PcS_S_
.ident  "GCC: (GNU) 4.7.2"
.section    .note.GNU-stack,"",@progbits

这要短得多，并且有一些显著的区别，比如缺少SIMD指令。我期待着同样的输出，中间有一些评论。我是不是在做一些错误的假设？GCC的优化器是否受到asm注释的阻碍？