https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107051
--- Comment #2 from absoler at smail dot nju.edu.cn ---
(In reply to Richard Biener from comment #1)
> With -O2 I see
>
> func_1:
> .LFB0:
> .cfi_startproc
> movl e(%rip), %eax
> testl %eax, %eax
> je .L2
> .L3:
> jmp .L3
> .p2align 4,,10
> .p2align 3
> .L2:
> movq g_284+8(%rip), %rax
> movq %rax, g_284(%rip)
> ret
>
> note that with -O1 we retain
>
> c = g_284[1];
> c$f0_3 = g_284[1].f0;
> c.f0 = c$f0_3;
> g_284[0] = c;
>
> after GIMPLE optimization which possibly explains this compared to
>
> c = g_284[1];
> g_284[0] = c;
>
> with -O2.
for gcc-13.2.0 -O2, it seems still forget to remove the load for this reduced
case:
```
union U0 {
short f1;
int f2;
};
union U0 g1, g2;
volatile int flag;
void func_1() {
union U0 d[1] = {{.f1 = 1}};
for (; flag;)
;
d[0] = g2;
g1 = d[0];
}
```
```
func_1:
.LFB0:
.cfi_startproc
.p2align 4,,10
.p2align 3
.L2:
movl flag(%rip), %eax
testl %eax, %eax
jne .L2
movl g2(%rip), %eax
movw g2(%rip), %ax
movl %eax, g1(%rip)
ret
.cfi_endproc
```
