From tree dump we can see that there are two assignments from x, one
to unsigned and one to signed. I guess that's the reason. Apparently
there is room to improve though.
int prephitmp.8;
int * D.2027;
unsigned int D.2026;
unsigned int x.1;
int x.0;
# BLOCK 2 freq:10000
# PRED: ENTRY [100.0%] (fallthru,exec)
x.0_1 = x;
x.1_2 = (unsigned int) x.0_1; // unsigned move
D.2026_3 = x.1_2 * 4;
D.2027_5 = a_4(D) + D.2026_3;
*D.2027_5 = 1;
prephitmp.8_6 = x; // signed move
On Mon, Nov 14, 2011 at 4:01 PM, Jiangning Liu <jiangning....@arm.com> wrote:
> Hi,
>
> For this test case,
>
> int x;
> extern void f(void);
>
> void g(int *a)
> {
> a[x] = 1;
> if (x == 100)
> f();
> a[x] = 2;
> }
>
> For trunk, the x86 assembly code is like below,
>
> movl x, %eax
> movl 16(%esp), %ebx
> movl $1, (%ebx,%eax,4)
> movl x, %eax // Is this a redundant one?
> cmpl $100, %eax
> je .L4
> movl $2, (%ebx,%eax,4)
> addl $8, %esp
> .cfi_remember_state
> .cfi_def_cfa_offset 8
> popl %ebx
> .cfi_restore 3
> .cfi_def_cfa_offset 4
> ret
> .p2align 4,,7
> .p2align 3
> .L4:
> .cfi_restore_state
> call f
> movl x, %eax
> movl $2, (%ebx,%eax,4)
> addl $8, %esp
> .cfi_def_cfa_offset 8
> popl %ebx
> .cfi_restore 3
> .cfi_def_cfa_offset 4
> Ret
>
> Is the 2nd "movl x, %eax" is a redundant one for single thread programming
> model? If yes, can this be optimized away?
>
> Thanks,
> -Jiangning
>
>
>
>
