diff --git a/mlir/lib/Conversion/GPUCommon/ConvertLaunchFuncToRuntimeCalls.cpp b/mlir/lib/Conversion/GPUCommon/ConvertLaunchFuncToRuntimeCalls.cpp
--- a/mlir/lib/Conversion/GPUCommon/ConvertLaunchFuncToRuntimeCalls.cpp
+++ b/mlir/lib/Conversion/GPUCommon/ConvertLaunchFuncToRuntimeCalls.cpp
@@ -18,6 +18,7 @@
 #include "../PassDetail.h"
 #include "mlir/Conversion/AsyncToLLVM/AsyncToLLVM.h"
 #include "mlir/Conversion/StandardToLLVM/ConvertStandardToLLVM.h"
+#include "mlir/Conversion/VectorToLLVM/ConvertVectorToLLVM.h"
 #include "mlir/Dialect/Async/IR/Async.h"
 #include "mlir/Dialect/GPU/GPUDialect.h"
 #include "mlir/Dialect/GPU/Passes.h"
@@ -313,6 +314,7 @@
   OwningRewritePatternList patterns;
   LLVMConversionTarget target(getContext());
 
+  populateVectorToLLVMConversionPatterns(converter, patterns);
   populateStdToLLVMConversionPatterns(converter, patterns);
   populateAsyncStructuralTypeConversionsAndLegality(&getContext(), converter,
                                                     patterns, target);
diff --git a/mlir/test/Integration/GPU/CUDA/gpu-to-cubin.mlir b/mlir/test/Integration/GPU/CUDA/gpu-to-cubin.mlir
--- a/mlir/test/Integration/GPU/CUDA/gpu-to-cubin.mlir
+++ b/mlir/test/Integration/GPU/CUDA/gpu-to-cubin.mlir
@@ -21,7 +21,10 @@
 }
 
 // CHECK: [1, 1, 1, 1, 1]
+// CHECK: ( 1, 1 )
 func @main() {
+  %v0 = constant 0.0 : f32
+  %c0 = constant 0: index
   %arg0 = memref.alloc() : memref<5xf32>
   %21 = constant 5 : i32
   %22 = memref.cast %arg0 : memref<5xf32> to memref<?xf32>
@@ -31,6 +34,8 @@
   %24 = constant 1.0 : f32
   call @other_func(%24, %22) : (f32, memref<?xf32>) -> ()
   call @print_memref_f32(%23) : (memref<*xf32>) -> ()
+  %val1 = vector.transfer_read %arg0[%c0], %v0: memref<5xf32>, vector<2xf32>
+  vector.print %val1: vector<2xf32>
   return
 }