[llvm] [LoongArch] Optimize extracting f32/f64 from 256-bit vector by using XVPICKVE. (PR #151914)

via llvm-commits llvm-commits at lists.llvm.org
Mon Aug 4 03:18:45 PDT 2025


zhaoqi5 wrote:

> Yes, but we don't need an extra pattern for `f32/f64 extractelement+insertelement` now. As you can see in the tests. Integer types could be considered.

Great.

https://github.com/llvm/llvm-project/pull/151914


More information about the llvm-commits mailing list