[PATCH] D147996: [X86] combineConcatVectorOps - remove FADD/FSUB/FMUL handling (2-1)

Mon Apr 17 17:48:51 PDT 2023

xiangzhangllvm added a comment.

In D147996#4273856 <https://reviews.llvm.org/D147996#4273856>, @LuoYuanke wrote:

> In D147996#4273314 <https://reviews.llvm.org/D147996#4273314>, @RKSimon wrote:
>
>> LGTM if its causing regressions, but I'd appreciate any time you can spend on PR60441
>
> It seems there is ScalarizerPass that can scalarize the vector, but it is not enabled. We can scalarize the small vector before the vectorization and let vectorizer re-vectorize them. I did a rough experiment with below patch and it seems the code of https://godbolt.org/z/sojxs9EGK can be vectorized with command `clang -g0 -O3 -march=x86-64-v4 -ffast-math -mllvm -scalarize-load-store t.cpp -S`
> ...

That is a very good experiment for re-vectorization, I think we should do more test for other tests, maybe a big improvement for vectorization optimization.

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D147996/new/

https://reviews.llvm.org/D147996