1 files changed, 3 insertions, 4 deletions
diff --git a/mlir/lib/Conversion/SPIRVToLLVM/ConvertLaunchFuncToLLVMCalls.cpp b/mlir/lib/Conversion/SPIRVToLLVM/ConvertLaunchFuncToLLVMCalls.cpp
index 0e9eb9799c3e..d7ae9f0e94fe 100644
--- a/mlir/lib/Conversion/SPIRVToLLVM/ConvertLaunchFuncToLLVMCalls.cpp
+++ b/mlir/lib/Conversion/SPIRVToLLVM/ConvertLaunchFuncToLLVMCalls.cpp
@@ -11,8 +11,6 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "mlir/Conversion/SPIRVToLLVM/SPIRVToLLVMPass.h"
-
 #include "mlir/Conversion/ArithToLLVM/ArithToLLVM.h"
 #include "mlir/Conversion/FuncToLLVM/ConvertFuncToLLVM.h"
 #include "mlir/Conversion/LLVMCommon/LoweringOptions.h"
@@ -269,8 +267,9 @@ class GPULaunchLowering : public ConvertOpToLLVMPattern<gpu::LaunchFuncOp> {
       copyInfo.push_back(info);
     }
     // Create a call to the kernel and copy the data back.
-    rewriter.replaceOpWithNewOp<LLVM::CallOp>(op, kernelFunc,
-                                              ArrayRef<Value>());
+    Operation *callOp = rewriter.replaceOpWithNewOp<LLVM::CallOp>(
+        op, kernelFunc, ArrayRef<Value>());
+    rewriter.setInsertionPointAfter(callOp);
     for (CopyInfo info : copyInfo)
       copy(loc, info.src, info.dst, info.size, rewriter);
     return success();