Index: mlir/lib/Conversion/GPUCommon/ConvertLaunchFuncToRuntimeCalls.cpp
===================================================================
--- mlir/lib/Conversion/GPUCommon/ConvertLaunchFuncToRuntimeCalls.cpp
+++ 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/GPU/GPUDialect.h"
 #include "mlir/Dialect/LLVMIR/LLVMDialect.h"
 #include "mlir/IR/Attributes.h"
@@ -296,6 +297,7 @@
   OwningRewritePatternList patterns;
   LLVMConversionTarget target(getContext());
 
+  populateVectorToLLVMConversionPatterns(converter, patterns);
   populateStdToLLVMConversionPatterns(converter, patterns);
   populateAsyncStructuralTypeConversionsAndLegality(&getContext(), converter,
                                                     patterns, target);
Index: mlir/test/mlir-cuda-runner/gpu-to-cubin.mlir
===================================================================
--- mlir/test/mlir-cuda-runner/gpu-to-cubin.mlir
+++ mlir/test/mlir-cuda-runner/gpu-to-cubin.mlir
@@ -17,7 +17,10 @@
 }
 
 // CHECK: [1, 1, 1, 1, 1]
+// CHECK: ( 1, 1 )
 func @main() {
+  %v0 = constant 0.0 : f32
+  %c0 = constant 0: index
   %arg0 = alloc() : memref<5xf32>
   %21 = constant 5 : i32
   %22 = memref_cast %arg0 : memref<5xf32> to memref<?xf32>
@@ -27,6 +30,8 @@
   %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<2xf32>, vector<5xf32>
+  vector.print %val1: vector<2xf32>
   return
 }
 
Index: mlir/tools/mlir-cuda-runner/mlir-cuda-runner.cpp
===================================================================
--- mlir/tools/mlir-cuda-runner/mlir-cuda-runner.cpp
+++ mlir/tools/mlir-cuda-runner/mlir-cuda-runner.cpp
@@ -26,6 +26,7 @@
 #include "mlir/Dialect/LLVMIR/LLVMDialect.h"
 #include "mlir/Dialect/LLVMIR/NVVMDialect.h"
 #include "mlir/Dialect/StandardOps/IR/Ops.h"
+#include "mlir/Dialect/Vector/VectorOps.h"
 #include "mlir/ExecutionEngine/JitRunner.h"
 #include "mlir/ExecutionEngine/OptUtils.h"
 #include "mlir/IR/BuiltinOps.h"
@@ -156,7 +157,7 @@
   mlir::DialectRegistry registry;
   registry.insert<mlir::LLVM::LLVMDialect, mlir::NVVM::NVVMDialect,
                   mlir::async::AsyncDialect, mlir::gpu::GPUDialect,
-                  mlir::StandardOpsDialect>();
+                  mlir::vector::VectorDialect, mlir::StandardOpsDialect>();
   registry.addDialectInterface<NVVM::NVVMDialect,
                                NVVMDialectLLVMIRTranslationInterface>();
   mlir::registerLLVMDialectTranslation(registry);