[llvm] [ARM]: codegen `llvm.roundeven.v*` (PR #141786)

[David Green via llvm-commits]

================
@@ -0,0 +1,78 @@
+; RUN: llc -mtriple=armv8 -mattr=+neon %s -o - | FileCheck %s
+
+; The llvm.arm.neon.frintn intrinsic should be auto-upgraded to the
+; target-independent roundeven intrinsic.
----------------
davemgreen wrote:

This isn't true yet, but wasn't done for the other vector intrinsics too. They currently get unrolled.

https://github.com/llvm/llvm-project/pull/141786