[clang] [Clang][OpenCL][AMDGPU] Allow a kernel to call another kernel (PR #115821)

[Matt Arsenault via cfe-commits]

arsenm wrote:

> @lalaniket8 @arsenm I don't have a strong opinion, but shouldn't this transformation be done during lowering to the target? 

This is the lowering to the target. 


> Current version of the patch brings odd behavior for LLVM IR to SPIR-V lowering for OpenCL kernels. SPIR-V don't allow one EntryPoint to refer another EntryPoint, 

Yes, that's the entire point of this change. We've avoided introducing the invalid situation of an entry calling another entry, which requires 2 IR function bodies with different calling conventions. The calling convention is getting set incorrectly on the implementation function if you see an entry calling another entry 


https://github.com/llvm/llvm-project/pull/115821