[llvm] [LoopUnroll] Support parallel reductions for minmax (PR #182473)

[Madhur Amilkanthwar via llvm-commits]

================
@@ -1,9 +1,9 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
-; RUN: opt -p loop-unroll -unroll-add-parallel-reductions -S %s | FileCheck %s
+; RUN: opt -p loop-unroll -unroll-parallel-reductions -enable-no-nans-fp-math -enable-no-signed-zeros-fp-math -S %s | FileCheck %s
----------------
madhur13490 wrote:

Thanks. BTW, in case you didn't notice, tests with intrinsics are still chained. Either I can add TODO to handle them or try harder to fix in this patch. (I don't see a clear way in the code to fix this unless I am missing something already there)

https://github.com/llvm/llvm-project/pull/182473