On Thu, Jun 13, 2013 at 6:55 PM, Chung-Ju Wu <jasonwucj@xxxxxxxxx> wrote:
> 2013/6/13 Chung-Ju Wu <jasonwucj@xxxxxxxxx>:
>> 2013/6/13 Terry Guo <flameroc@xxxxxxxxx>:
>>> Hi there,
>>>
>>> For the below simple case, I think poly1[i] should be hoisted to
>>> outermost loop to avoid loading from innermost loop at each iteration.
>>> But for arm-none-eabi target like cortex-m4, gcc fails to do so. Is
>>> this a normal case or a missing optimization? Please advise.
>>>
>>> void
>>> PolyMul (float *poly1, unsigned int n1,
>>> float *poly2, unsigned int n2,
>>> float *polymul, unsigned int *nmul)
>>> {
>>> unsigned int i, j;
>>>
>>> for (i = 0; i <= n1; i++)
>>> for (j = 0; j <= n2; j++)
>>> polymul[i+j] += poly1[i] * poly2[j];
>>> }
>>>
>>> Thanks.
>>>
>>> BR,
>>> Terry
>>
>> Unless you use 'restrict' qualifier to the pointer type,
>> I don't think compiler can do such optimization due to aliasing issue.
>>
>
> Also I don't think -fstrict-aliasing could help for your case.
> Becase poly1, poly2, and polymul are all 'float *' pointer type.
>
Thanks for your help. You are correct. The 'restrict' qualifier can
give me what I want. With following changes, the poly1[i] can be
hoisted into outermost loop:
void
PolyMul (float *__restrict__ poly1, unsigned int n1,
float *__restrict__ poly2, unsigned int n2,
float *__restrict__ polymul, unsigned int *nmul)
The -fstrict-aliasing doesn't help for either 'int *' or 'float *' pointer type.
BR,
Terry
