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

[Aniket Lal via cfe-commits]

================
@@ -1582,6 +1582,26 @@ void CodeGenFunction::GenerateCode(GlobalDecl GD, llvm::Function *Fn,
     // Implicit copy-assignment gets the same special treatment as implicit
     // copy-constructors.
     emitImplicitAssignmentOperatorBody(Args);
+  } else if (FD->hasAttr<OpenCLKernelAttr>() &&
+             GD.getKernelReferenceKind() == KernelReferenceKind::Kernel) {
+    CallArgList CallArgs;
+    for (unsigned i = 0; i < Args.size(); ++i) {
+      Address ArgAddr = GetAddrOfLocalVar(Args[i]);
+      QualType ArgQualType = Args[i]->getType();
+      RValue ArgRValue = convertTempToRValue(ArgAddr, ArgQualType, Loc);
----------------
lalaniket8 wrote:

> > Although we don't see the callsite in this littest since it gets inlined away.
> 
> We shouldn't be running these optimizations in a frontend test

If we want to stop inlining for this test, we can add `-disable-llvm-passes` to it's runlines 

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