[llvm] [AMDGPU] Precommit Tests for 'Fold redundant inf/nan checks into frexp instructions' (PR #214964)

[Shilei Tian via llvm-commits]

================
@@ -0,0 +1,804 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1030 < %s | FileCheck -check-prefix=GFX10 %s
----------------
shiltian wrote:

This is not resolved. The new triple is `-mtriple=amdgpu9.0-amd-amdhsa` and then drop `-mcpu=gfx900`.

https://github.com/llvm/llvm-project/pull/214964