https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110008
Bug ID: 110008
Summary: early returns from functions result in suboptimal code
Product: gcc
Version: 14.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: rtl-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: lh_mouse at 126 dot com
Target Milestone: ---
https://gcc.godbolt.org/z/94Wf3Worq
```
int complex_one(int, int);
int
test(int a, int b, int c)
{
if(__builtin_expect(a, 0) == 0)
return 0;
int r = complex_one(a, b);
r += complex_one(r, c);
return r + a + b;
}
```
GCC:
```
test:
push rdi
push rsi
push rbx
sub rsp, 32
mov ebx, ecx
mov esi, edx
test ecx, ecx
jne .L7
mov eax, ebx
add rsp, 32
pop rbx
pop rsi
pop rdi
ret
.L7:
mov DWORD PTR 80[rsp], r8d
call complex_one
mov edx, DWORD PTR 80[rsp]
mov ecx, eax
mov edi, eax
call complex_one
add edi, eax
add ebx, edi
add ebx, esi
mov eax, ebx
add rsp, 32
pop rbx
pop rsi
pop rdi
ret
```
Clang:
```
test: # @test
xor eax, eax
test edi, edi
jne .LBB0_1
ret
.LBB0_1:
push rbp
push r15
push r14
push rbx
push rax
mov r14d, edx
mov ebx, esi
mov ebp, edi
call complex_one@PLT
mov r15d, eax
mov edi, eax
mov esi, r14d
call complex_one@PLT
add ebx, ebp
add ebx, r15d
add ebx, eax
mov eax, ebx
add rsp, 8
pop rbx
pop r14
pop r15
pop rbp
ret
```
There are two issues in this code: The first one is that GCC uses apparently
more space for temporary variables than Clang. The other is that when `a`
equals zero, Clang skips the normal function prologue which pushes a lot of
registers onto the stack, but GCC performs the check after it, in which case
both the prologue and epilogue get executed for nothing.
