[llvm] [NVPTX] Add support for atomic add for f16 type (PR #84295)

[Justin Fargnoli via llvm-commits]

================
@@ -0,0 +1,28 @@
+; RUN: llc < %s -march=nvptx -mcpu=sm_70 -mattr=+ptx63 | FileCheck %s
----------------
justinfargnoli wrote:

The ordering of the `ld.param.*`s relative to the `atom.*` instructions isn't relevant to this test, correct? If so, we may not want to include those `CHECK-NEXT:`s in the test. 

https://github.com/llvm/llvm-project/pull/84295