[clang] [llvm] [SPIRV] GPU intrinsics (PR #131190)

[Matt Arsenault via llvm-commits]

================
@@ -0,0 +1,427 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-attributes
+; RUN: opt -S -mtriple=amdgcn-- -passes=lower-gpu-intrinsic < %s | FileCheck %s --check-prefix=AMDGCN
----------------
arsenm wrote:

Should not be testing amdgpu handling in test/CodeGen/SPIRV. Duplicate the test.

Also this is just an IR->IR test, should go in test/Transforms/LowerGPUIntrinsics

https://github.com/llvm/llvm-project/pull/131190