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

[Dmitry Sidorov via cfe-commits]

MrSidims wrote:

@lalaniket8 @arsenm I don't have a strong opinion, but shouldn't this transformation be done during 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, so during such lowering the translator moves kernel's body to impl function (just like this patch does). Together it results in quite odd behavior: https://github.com/KhronosGroup/SPIRV-LLVM-Translator/issues/3115

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