[llvm] [AMDGPU] Handle negated f16 and fp conversion DAG combines (PR #213202)

[Matt Arsenault via llvm-commits]

================
@@ -0,0 +1,117 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc -mtriple=amdgpu9.0a-amd-amdhsa < %s | FileCheck %s
----------------
arsenm wrote:

```suggestion
; RUN: llc -mtriple=amdgpu7-amd-amdhsa < %s | FileCheck %s
```

This is still testing a target with legal f16, which won't use these nodes. Please recommit the test so we can see the diff from the patch in the second commit 

https://github.com/llvm/llvm-project/pull/213202