[llvm] [X86] Baseline test for "invalid operand order for fp16 vector comparison" issue (PR #159786)

[Simon Pilgrim via llvm-commits]

================
@@ -0,0 +1,131 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512fp16 -mattr=+avx512vl -O2| FileCheck %s
----------------
RKSimon wrote:

`-mattr=+avx512fp16 -mattr=+avx512vl` -> `-mattr=+avx512fp16,+avx512vl`

and drop -O2 (unnecessary)

https://github.com/llvm/llvm-project/pull/159786