[llvm] [KernelInfo] Implement new LLVM IR pass for GPU code analysis (PR #102944)

[Alex MacLean via llvm-commits]

================
@@ -322,6 +322,32 @@ void Module::eraseNamedMetadata(NamedMDNode *NMD) {
   eraseNamedMDNode(NMD);
 }
 
+SetVector<Function *> Module::getDeviceKernels() {
+  // TODO: Create a more cross-platform way of determining device kernels.
+  NamedMDNode *MD = getNamedMetadata("nvvm.annotations");
----------------
AlexMaclean wrote:

I'm working on deprecating this method of specifying a kernel in favor of the `ptx_kernel` calling convention (see https://github.com/llvm/llvm-project/pull/120806). I think it would be good to check the calling convention of all functions in the module and add them to the set if they have `ptx_kernel` or `amdgpu_kernel` (maybe others too?). 

https://github.com/llvm/llvm-project/pull/102944