[PATCH] D150851: [LoopVectorize] Vectorize select-cmp reduction pattern for increasing integer induction variable

[Mel Chen via Phabricator via llvm-commits]

Mel-Chen added a comment.

In D150851#4480526 <https://reviews.llvm.org/D150851#4480526>, @artagnon wrote:

> Yes, I can confirm that there is indeed a bug. Thanks for catching it! I'm thinking about a fix now.

Perhaps Ayal's approach can be helpful. The final `found_func` allows the approach to be more widely applicable. If we only focus on increasing/decreasing induction variables, we may be able to further streamline the process.

In D150851#4467261 <https://reviews.llvm.org/D150851#4467261>, @Ayal wrote:

> Here's a sketch minimizing the size of the indices maintained throughout the loop, so they would avoid wrapping, provide out-of-bound values, and possibly use narrower types depending on trip-count and vl:
>
>   return_type FindLast(return_type unfound_value, vec_predicate_func, found_func) {
>     vec_unsigned_int select_red_part = splat(0); // Zero indicates unfound.
>     vec_unsigned_int step_vec = splat(1); // Count vector iterations starting at 1.
>   
>     for (unsigned int i = 0; i < n; i+=vl, step_vec+=splat(1))
>       select_red_part = (vec_predicate_func(i) ? step_vec : select_red_part;
>   
>     unsigned vec_indices_ored = reduce.or(select_red_part);
>     if (vec_indices_ored == 0)
>       return unfound_value;
>     unsigned inflated_red_part = (select_red_part - splat(1)) * vl + <0,1,...,vl-1>;
>     unsigned last_index = reduce.umax(inflated_red_part);
>     return found_func(last_index);
>   }




Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D150851/new/

https://reviews.llvm.org/D150851