[PATCH] D140100: [SLP]Integrate looking through shuffles logic into ShuffleInstructionBuilder.

[Alexander Kornienko via Phabricator via llvm-commits]

alexfh added a comment.

In D140100#4026269 <https://reviews.llvm.org/D140100#4026269>, @ABataev wrote:

> In D140100#4026248 <https://reviews.llvm.org/D140100#4026248>, @alexfh wrote:
>
>> In D140100#4024152 <https://reviews.llvm.org/D140100#4024152>, @ABataev wrote:
>>
>>> In D140100#4024147 <https://reviews.llvm.org/D140100#4024147>, @alexfh wrote:
>>>
>>>> In D140100#4018269 <https://reviews.llvm.org/D140100#4018269>, @asmok-g wrote:
>>>>
>>>>> Heads-up: This has caused a change in behavior when using `#pragma unroll` in some test using SIMD. In other words, using `#pragma unroll` results in a different output than without it. I'm preparing a reduced test case.
>>>>
>>>> I've got a reduced IR file for that case: F26088275: q.ll <https://reviews.llvm.org/F26088275>
>>>>
>>>>   $ old-clang -O2 q.ll && ./a.out
>>>>   0.0
>>>>   $ new-clang -O2 q.ll && ./a.out
>>>>   5.0
>>>>
>>>> Please fix or revert the patch, if there's no trivial fix.
>>>>
>>>> Thanks!
>>>
>>> Thanks for the reproducer, will investigate it.
>>
>> Alexey, could you revert the commit in the meantime?
>
> It is not so easy, there are several commits on top of it already. I just started looking at it, hope to provide a fix in 1-2hrs, if it will take more time, I'll revert it.

Thanks! Please let me know once you have a resolution or decide to revert this.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D140100/new/

https://reviews.llvm.org/D140100