[clang] [CIR][AMDGPU] Add support for AMDGCN cos builtins (PR #197806)

[Ayokunle Amodu via cfe-commits]

================
@@ -0,0 +1,26 @@
+#include "../CodeGenCUDA/Inputs/cuda.h"
----------------
ayokunle321 wrote:

@arsenm I can't seem to find where the BF16 tests are kept. I don't see any in clang/test/CodeGenHIP, but I do see BF16 builtin tests in the OpenCL directory:

https://github.com/llvm/llvm-project/blob/e44d060dfd617e8a5e37b61adcb38ed4ac5d782d/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx1250.cl#L288

That's probably why the incubator referenced the OpenCL ones. @skc7 could you please comment on this? 

https://github.com/llvm/llvm-project/pull/197806