[llvm] [AMDGPU][True16][Codegen] true16 codegen for FPtoI1 (PR #125120)

[Ivan Kosarev via llvm-commits]

================
@@ -1,7 +1,6 @@
 # NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
 # RUN: llc -mtriple=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s  | FileCheck -check-prefix=WAVE64 %s
 # RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s  | FileCheck -check-prefix=WAVE32 %s
-# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s  | FileCheck -check-prefix=GFX11 %s
----------------
kosarev wrote:

Makes sense, t16 would use different instructions and fake16 would be easiest to remove if in their own separate files.

https://github.com/llvm/llvm-project/pull/125120