On Tue, Apr 29, 2014 at 6:58 PM, H.J. Lu <hjl.to...@gmail.com> wrote:
> On Tue, Apr 29, 2014 at 6:50 AM, Evgeny Stupachenko <evstu...@gmail.com>
> wrote:
>> Hi,
>>
>> The patch adds use of palignr instruction, when we have one operand
>> permutation like:
>> {5 6 7 0 1 2 3 4}:
>>
>> Treating this as {5 6 7 8 9 a b c} on 2 operands, and therefore palignr on 5.
>>
>> Bootstrap and make check passed.
>>
>> Is it ok?
>>
>> Evgeny
>>
>> 2014-04-29 Evgeny Stupachenko <evstu...@gmail.com>
>>
>> * config/i386/i386.c (expand_vec_perm_palignr_one_operand): New.
>> Enables PALIGNR on one operand permutation.
>> * config/i386/i386.c (expand_vec_perm_1): Try PALIGNR on one operand.
>>
>>
>
> I think it is better to include some testcases in this
> patch so that the backend change and its testcases
> are self-contained.
>
I have no idea how to generate permutation for palignr right now, but
I have a patch fixing pr52252 generating such (first part of it is
currently under review with corresponding tests, next part will
generate palignr instructions on the tests).
Initial implementation of palirnr support was committed without tests.
Current patches are extension of this initial implementation.
> Thanks.
>
> --
> H.J.
Thanks,
Evgeny
