1 files changed, 13 insertions, 4 deletions
diff --git a/clang/lib/CodeGen/CGHLSLRuntime.cpp b/clang/lib/CodeGen/CGHLSLRuntime.cpp
index 2c293523fca8..c354e58e15f4 100644
--- a/clang/lib/CodeGen/CGHLSLRuntime.cpp
+++ b/clang/lib/CodeGen/CGHLSLRuntime.cpp
@@ -389,6 +389,11 @@ llvm::Value *CGHLSLRuntime::emitInputSemantic(IRBuilder<> &B,
         CGM.getIntrinsic(getThreadIdIntrinsic());
     return buildVectorInput(B, ThreadIDIntrinsic, Ty);
   }
+  if (D.hasAttr<HLSLSV_GroupThreadIDAttr>()) {
+    llvm::Function *GroupThreadIDIntrinsic =
+        CGM.getIntrinsic(getGroupThreadIdIntrinsic());
+    return buildVectorInput(B, GroupThreadIDIntrinsic, Ty);
+  }
   if (D.hasAttr<HLSLSV_GroupIDAttr>()) {
     llvm::Function *GroupIDIntrinsic = CGM.getIntrinsic(Intrinsic::dx_group_id);
     return buildVectorInput(B, GroupIDIntrinsic, Ty);
@@ -507,13 +512,17 @@ void CGHLSLRuntime::generateGlobalCtorDtorCalls() {
       IP = Token->getNextNode();
     }
     IRBuilder<> B(IP);
-    for (auto *Fn : CtorFns)
-      B.CreateCall(FunctionCallee(Fn), {}, OB);
+    for (auto *Fn : CtorFns) {
+      auto CI = B.CreateCall(FunctionCallee(Fn), {}, OB);
+      CI->setCallingConv(Fn->getCallingConv());
+    }
 
     // Insert global dtors before the terminator of the last instruction
     B.SetInsertPoint(F.back().getTerminator());
-    for (auto *Fn : DtorFns)
-      B.CreateCall(FunctionCallee(Fn), {}, OB);
+    for (auto *Fn : DtorFns) {
+      auto CI = B.CreateCall(FunctionCallee(Fn), {}, OB);
+      CI->setCallingConv(Fn->getCallingConv());
+    }
   }
 
   // No need to keep global ctors/dtors for non-lib profile after call to