On Tue, Apr 10, 2018 at 12:40 PM, Richard Sandiford
wrote:
> Jakub Jelinek writes:
>> On Mon, Apr 09, 2018 at 06:47:45PM +0100, Richard Sandiford wrote:
>>> In this PR we used WIDEN_SUM_EXPR to vectorise:
>>>
>>> short i, y;
>>> int sum;
>>>
Jakub Jelinek writes:
> On Mon, Apr 09, 2018 at 06:47:45PM +0100, Richard Sandiford wrote:
>> In this PR we used WIDEN_SUM_EXPR to vectorise:
>>
>> short i, y;
>> int sum;
>> [...]
>> for (i = x; i > 0; i--)
>> sum += y;
>>
>> with 4 ints and 8 shorts per vector.
On Mon, Apr 9, 2018 at 7:47 PM, Richard Sandiford
wrote:
> In this PR we used WIDEN_SUM_EXPR to vectorise:
>
> short i, y;
> int sum;
> [...]
> for (i = x; i > 0; i--)
> sum += y;
>
> with 4 ints and 8 shorts per vector. The problem was that we set
> the
On Mon, Apr 09, 2018 at 06:47:45PM +0100, Richard Sandiford wrote:
> In this PR we used WIDEN_SUM_EXPR to vectorise:
>
> short i, y;
> int sum;
> [...]
> for (i = x; i > 0; i--)
> sum += y;
>
> with 4 ints and 8 shorts per vector. The problem was that we set
> the VF based only on
In this PR we used WIDEN_SUM_EXPR to vectorise:
short i, y;
int sum;
[...]
for (i = x; i > 0; i--)
sum += y;
with 4 ints and 8 shorts per vector. The problem was that we set
the VF based only on the ints, then calculated the number of vector
copies based on the shorts, giving 4/8.