[llvm] [AArch64][GlobalISel] Improve lowering of vector fp16 fptrunc (PR #163398)

[Ryan Cowan via llvm-commits]

================
@@ -536,6 +536,12 @@ G_FPTRUNC
 
 Convert a floating point value to a narrower type.
 
+G_FPTRUNC_ODD
----------------
HolyMolyCowMan wrote:

As per the most recent message here, I have removed the new opcode & instead rely on an AArch64 specific opcode. I have thus moved the lowering to a custom legalizer function.

https://github.com/llvm/llvm-project/pull/163398