[llvm] [AMDGPU] Add regbankselect rules for G_ICMP/G_FCMP (PR #172048)

[Matt Arsenault via llvm-commits]

================
@@ -0,0 +1,84 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -global-isel -new-reg-bank-select < %s | FileCheck %s
+
+define i1 @fcmp_f16_uniform(half inreg %a, half inreg %b) {
----------------
arsenm wrote:

But this is a VGPR use, so would these benefit from testing with vcc and SGPR uses too (I thought all of this was covered in existing tests?) 

https://github.com/llvm/llvm-project/pull/172048