[llvm] [AArch64][GlobalISel] Improve lowering of vector fp16 fpext (PR #165554)

[Ryan Cowan via llvm-commits]

================
@@ -4852,6 +4852,7 @@ LegalizerHelper::lower(MachineInstr &MI, unsigned TypeIdx, LLT LowerHintTy) {
     return lowerMemcpyInline(MI);
   case G_ZEXT:
   case G_SEXT:
+  case G_FPEXT:
----------------
HolyMolyCowMan wrote:

That is my understanding too. I realise now that we don't quite want the functionality that this lower provides so I have opted to instead use legalizer mutations for this.

https://github.com/llvm/llvm-project/pull/165554