diff --git a/mlir/include/mlir/Conversion/Passes.td b/mlir/include/mlir/Conversion/Passes.td
--- a/mlir/include/mlir/Conversion/Passes.td
+++ b/mlir/include/mlir/Conversion/Passes.td
@@ -335,7 +335,10 @@
 def GpuToLLVMConversionPass : Pass<"gpu-to-llvm", "ModuleOp"> {
   let summary = "Convert GPU dialect to LLVM dialect with GPU runtime calls";
   let constructor = "mlir::createGpuToLLVMConversionPass()";
-  let dependentDialects = ["LLVM::LLVMDialect"];
+  let dependentDialects = [
+    "LLVM::LLVMDialect",
+    "memref::MemRefDialect",
+  ];
 }
 
 def LowerHostCodeToLLVM : Pass<"lower-host-to-llvm", "ModuleOp"> {
diff --git a/mlir/lib/Conversion/GPUCommon/GPUToLLVMConversion.cpp b/mlir/lib/Conversion/GPUCommon/GPUToLLVMConversion.cpp
--- a/mlir/lib/Conversion/GPUCommon/GPUToLLVMConversion.cpp
+++ b/mlir/lib/Conversion/GPUCommon/GPUToLLVMConversion.cpp
@@ -28,6 +28,7 @@
 #include "mlir/Dialect/GPU/IR/GPUDialect.h"
 #include "mlir/Dialect/GPU/Transforms/Passes.h"
 #include "mlir/Dialect/LLVMIR/LLVMDialect.h"
+#include "mlir/Dialect/MemRef/IR/MemRef.h"
 #include "mlir/IR/Attributes.h"
 #include "mlir/IR/Builders.h"
 #include "mlir/IR/BuiltinOps.h"
diff --git a/mlir/test/Conversion/GPUCommon/transfer_write.mlir b/mlir/test/Conversion/GPUCommon/transfer_write.mlir
new file mode 100644
--- /dev/null
+++ b/mlir/test/Conversion/GPUCommon/transfer_write.mlir
@@ -0,0 +1,13 @@
+// RUN: mlir-opt %s --gpu-to-llvm | FileCheck %s
+
+  func.func @warp_extract(%arg0: index, %arg1: memref<1024x1024xf32>, %arg2: index, %arg3: vector<1xf32>) {
+    %c0 = arith.constant 0 : index
+    vector.warp_execute_on_lane_0(%arg0)[32] {
+      // CHECK:%[[val:[0-9]+]] = llvm.extractelement
+      // CHECK:%[[base:[0-9]+]] = llvm.extractvalue
+      // CHECK:%[[ptr:[0-9]+]] = llvm.getelementptr %[[base]]
+      // CHECK:llvm.store %[[val]], %[[ptr]]
+      vector.transfer_write %arg3, %arg1[%c0, %c0] {in_bounds = [true]} : vector<1xf32>, memref<1024x1024xf32>
+    }
+    return
+  }