[llvm] [Offload][AMDGPU] accept generic target (PR #118919)

[via llvm-commits]

================
@@ -205,13 +205,16 @@ Expected<std::string> getTargetTripleAndFeatures(hsa_agent_t Agent) {
       return Status;
 
     llvm::StringRef TripleTarget(ISAName.begin(), Length);
-    if (TripleTarget.consume_front("amdgcn-amd-amdhsa"))
-      Target = TripleTarget.ltrim('-').rtrim('\0').str();
-    return HSA_STATUS_INFO_BREAK;
+    if (TripleTarget.consume_front("amdgcn-amd-amdhsa")) {
+      auto Target = TripleTarget.ltrim('-').rtrim('\0').str();
+      if (Target.find("generic") != std::string::npos)
+        Targets.push_back(Target);
+      else
+        Targets[0] = Target;
----------------
hidekisaito wrote:

Expect only one specific ISA. Code is a bit overkill for today's implementation where HSA lists specific ISA upfront and thus we really don't need to IF branch. I just didn't like to blindly assume that ordering.

https://github.com/llvm/llvm-project/pull/118919