This adds code to lower f16 to f32 fp_exts's using an MVE VCVT instructions, similar to D81139. Again it goes through the lowering of a BUILD_VECTOR, but is slightly simpler only having to deal with interleaved indices. It adds a VCVTL node to lower to, similar to VCVTN.
Details
Details
Diff Detail
Diff Detail
- Repository
- rG LLVM Github Monorepo
Event Timeline
Comment Actions
Do you have a testcase that shows what happens for a plain fpext <8 x half> %strided.vec to <8 x float> without any surrounding shuffles?
llvm/test/CodeGen/Thumb2/mve-vcvt16.ll | ||
---|---|---|
38 |
Like this one? |
Like this one?