Resending this to everyone (sorry for the double send Richard).
On 14/04/2023 09:15, Andre Vieira (lists) wrote:
>
>
> On 14/04/2023 07:55, Richard Biener wrote:
>> On Thu, Apr 13, 2023 at 4:25 PM Andre Vieira (lists)
>> <andre.simoesdiasvie...@arm.com> wrote:
>>>
>>>
>>>
>>> On 13/04/2023 15:00, Richard Biener wrote:
>>>> On Thu, Apr 13, 2023 at 3:00 PM Andre Vieira (lists) via Gcc-patches
>>>> <gcc-patches@gcc.gnu.org> wrote:
>>>>>
>>>>>
>>>>>
>>>
>>> But that's not it, I've been looking at it, and there is code in place
>>> that does what I expected which is defer the choice of vectype for simd
>>> clones until vectorizable_simd_clone_call, unfortunately it has a
>>> mistaken assumption that simdclones don't return :/
>>
>> I think that's not it - when the SIMD clone returns a vector we have to
>> determine the vector type in this function. We cannot defer this.
>
> What's 'this function' here, do you mean we have to determine the
> vectype in 'vect_get_vector_types_for_stmt' &
> 'vect_determine_vf_for_stmt' ? Because at that time we don't yet know
> what clone we will be using, this choice is done inside
> vectorizable_simd_clone_call. In fact, to choose the simd clone, we need
> to know the vf as that has to be a multiple of the chosen clone's
> simdlen. So we simply can't use the simdclone's types (as that depends
> on the simdlen) to choose the vf because the choice of simdlend depends
> on the vf. And there was already code in place to handle this,
> unfortunately that code was wrong and had the wrong assumption that
> simdclones didn't return (probably was true at some point and bitrotted).
>
>>
>>> see vect_get_vector_types_for_stmt:
>>> ...
>>> if (gimple_get_lhs (stmt) == NULL_TREE
>>> /* MASK_STORE has no lhs, but is ok. */
>>> && !gimple_call_internal_p (stmt, IFN_MASK_STORE))
>>> {
>>> if (is_a <gcall *> (stmt))
>>> {
>>> /* Ignore calls with no lhs. These must be calls to
>>> #pragma omp simd functions, and what vectorization
factor
>>> it really needs can't be determined until
>>> vectorizable_simd_clone_call. */
>>> if (dump_enabled_p ())
>>> dump_printf_loc (MSG_NOTE, vect_location,
>>> "defer to SIMD clone analysis.\n");
>>> return opt_result::success ();
>>> }
>>>
>>> return opt_result::failure_at (stmt,
>>> "not vectorized: irregular
>>> stmt.%G", stmt);
>>> }
>>> ...
>>>
>>> I'm working on a patch.
>>>>
>>>>> Kind Regards,
>>>>> Andre
