[llvm] [AArch64][GlobalISel] SIMD fpcvt codegen for rounding nodes (PR #165546)

[Matt Arsenault via llvm-commits]

arsenm wrote:

> I am not sure it would make sense to split the patch into non-strict and strict, as single pattern works for both cases, but I can split the testfile as you suggested.

I think you should drop any attempt to handle strictfp from this patch. It's making it a lot harder to review, especially since most of the changes only do anything for the non-strict case. I don't think any of this strictfp stuff actually works as-is. The tests also should not coexist in the same file 

https://github.com/llvm/llvm-project/pull/165546