Vector shuffling

On Mon, Oct 3, 2011 at 6:12 PM, Richard Henderson <rth@redhat.com> wrote:
> On 10/03/2011 09:43 AM, Artem Shinkarov wrote:
>> Hi, Richard
>>
>> There is a problem with the testcases of the patch you have committed
>> for me. The code in every test-case is doubled. Could you please,
>> apply the following patch, otherwise it would fail all the tests from
>> the vector-shuffle-patch would fail.
>
> Huh.  Dunno what happened there.  Fixed.
>
>> Also, if it is possible, could you change my name from in the
>> ChangeLog from "Artem Shinkarov" to "Artjoms Sinkarovs". The last
>> version is the way I am spelled in the passport, and the name I use in
>> the ChangeLog.
>
> Fixed.
>
>
> r~
>

Richard, there was a problem causing segfault in ix86_expand_vshuffle
which I have fixed with the patch attached.

Another thing I cannot figure out is the following case:
#define vector(elcount, type)  \
__attribute__((vector_size((elcount)*sizeof(type)))) type

vector (8, short) __attribute__ ((noinline))
f (vector (8, short) x, vector (8, short) y, vector (8, short) mask) {
    return  __builtin_shuffle (x, y, mask);
}

int main (int argc, char *argv[]) {
    vector (8, short) v0 = {argc, 1,2,3,4,5,6,7};
    vector (8, short) v1 = {argc, 1,argc,3,4,5,argc,7};
    vector (8, short) mask0 = {0,2,3,1,4,5,6,7};
    vector (8, short) v2;
    int i;

    v2 = f (v0, v1,  mask0);
    /* v2 =  __builtin_shuffle (v0, v1, mask0); */
    for (i = 0; i < 8; i ++)
      __builtin_printf ("%i, ", v2[i]);

    return 0;
}

I am compiling with support of ssse3, in my case it is ./xgcc -B. b.c
-O3 -mtune=core2 -march=core2

And I get 1, 1, 1, 3, 4, 5, 1, 7, on the output, which is wrong.

But if I will call __builtin_shuffle directly, then the answer is correct.

Any ideas?


Thanks,
Artem.

Ping.

Richard, the patch in the attachment should be submitted asap. The
other problem could wait for a while.

Thanks,
Artem.

On Tue, Oct 4, 2011 at 12:04 AM, Artem Shinkarov
<artyom.shinkaroff@gmail.com> wrote:
> On Mon, Oct 3, 2011 at 6:12 PM, Richard Henderson <rth@redhat.com> wrote:
>> On 10/03/2011 09:43 AM, Artem Shinkarov wrote:
>>> Hi, Richard
>>>
>>> There is a problem with the testcases of the patch you have committed
>>> for me. The code in every test-case is doubled. Could you please,
>>> apply the following patch, otherwise it would fail all the tests from
>>> the vector-shuffle-patch would fail.
>>
>> Huh.  Dunno what happened there.  Fixed.
>>
>>> Also, if it is possible, could you change my name from in the
>>> ChangeLog from "Artem Shinkarov" to "Artjoms Sinkarovs". The last
>>> version is the way I am spelled in the passport, and the name I use in
>>> the ChangeLog.
>>
>> Fixed.
>>
>>
>> r~
>>
>
> Richard, there was a problem causing segfault in ix86_expand_vshuffle
> which I have fixed with the patch attached.
>
> Another thing I cannot figure out is the following case:
> #define vector(elcount, type)  \
> __attribute__((vector_size((elcount)*sizeof(type)))) type
>
> vector (8, short) __attribute__ ((noinline))
> f (vector (8, short) x, vector (8, short) y, vector (8, short) mask) {
>    return  __builtin_shuffle (x, y, mask);
> }
>
> int main (int argc, char *argv[]) {
>    vector (8, short) v0 = {argc, 1,2,3,4,5,6,7};
>    vector (8, short) v1 = {argc, 1,argc,3,4,5,argc,7};
>    vector (8, short) mask0 = {0,2,3,1,4,5,6,7};
>    vector (8, short) v2;
>    int i;
>
>    v2 = f (v0, v1,  mask0);
>    /* v2 =  __builtin_shuffle (v0, v1, mask0); */
>    for (i = 0; i < 8; i ++)
>      __builtin_printf ("%i, ", v2[i]);
>
>    return 0;
> }
>
> I am compiling with support of ssse3, in my case it is ./xgcc -B. b.c
> -O3 -mtune=core2 -march=core2
>
> And I get 1, 1, 1, 3, 4, 5, 1, 7, on the output, which is wrong.
>
> But if I will call __builtin_shuffle directly, then the answer is correct.
>
> Any ideas?
>
>
> Thanks,
> Artem.
>

On 10/04/2011 08:18 AM, Artem Shinkarov wrote:
> Ping.
> 
> Richard, the patch in the attachment should be submitted asap. The
> other problem could wait for a while.

The patch in the attachment is wrong too.  I've re-written the x86
backend support, adding TARGET_XOP in the process.  I've also re-written
the test cases so that they actually test what we wanted.

Patch to follow once testing is complete.


r~