diff --git a/mlir/lib/Conversion/VectorToSCF/VectorToSCF.cpp b/mlir/lib/Conversion/VectorToSCF/VectorToSCF.cpp
--- a/mlir/lib/Conversion/VectorToSCF/VectorToSCF.cpp
+++ b/mlir/lib/Conversion/VectorToSCF/VectorToSCF.cpp
@@ -16,6 +16,7 @@
 
 #include "../PassDetail.h"
 #include "mlir/Dialect/Affine/EDSC/Intrinsics.h"
+#include "mlir/Dialect/Linalg/Utils/Utils.h"
 #include "mlir/Dialect/SCF/EDSC/Builders.h"
 #include "mlir/Dialect/SCF/EDSC/Intrinsics.h"
 #include "mlir/Dialect/StandardOps/EDSC/Intrinsics.h"
@@ -203,7 +204,10 @@
   Value inBoundsCondition;
   majorIvsPlusOffsets.reserve(majorIvs.size());
   unsigned idx = 0;
-  for (auto it : llvm::zip(majorIvs, majorOffsets, memrefBounds.getUbs())) {
+  SmallVector<Value, 4> bounds =
+      linalg::applyMapToValues(rewriter, xferOp.getLoc(),
+                               xferOp.permutation_map(), memrefBounds.getUbs());
+  for (auto it : llvm::zip(majorIvs, majorOffsets, bounds)) {
     Value iv = std::get<0>(it), off = std::get<1>(it), ub = std::get<2>(it);
     using namespace mlir::edsc::op;
     majorIvsPlusOffsets.push_back(iv + off);
diff --git a/mlir/test/Conversion/VectorToSCF/vector-to-loops.mlir b/mlir/test/Conversion/VectorToSCF/vector-to-loops.mlir
--- a/mlir/test/Conversion/VectorToSCF/vector-to-loops.mlir
+++ b/mlir/test/Conversion/VectorToSCF/vector-to-loops.mlir
@@ -400,3 +400,33 @@
   %0 = vector.transfer_read %A[%c0, %c0], %f0 : memref<2x2xf32>, vector<2x2xf32>
   return %0 : vector<2x2xf32>
 }
+
+func @transfer_read_minor_identity(%A : memref<?x?x?x?xf32>) -> vector<3x3xf32> {
+  %c0 = constant 0 : index
+  %f0 = constant 0.0 : f32
+  %0 = vector.transfer_read %A[%c0, %c0, %c0, %c0], %f0
+    { permutation_map = affine_map<(d0, d1, d2, d3) -> (d2, d3)> }
+      : memref<?x?x?x?xf32>, vector<3x3xf32>
+  return %0 : vector<3x3xf32>
+}
+
+// CHECK-LABEL: transfer_read_minor_identity(
+//  CHECK-SAME:   %[[A:.*]]: memref<?x?x?x?xf32>) -> vector<3x3xf32>
+//  CHECK-NEXT:   %[[c0:.*]] = constant 0 : index
+//  CHECK-NEXT:   %[[cst:.*]] = constant 0.000000e+00 : f32
+//  CHECK-NEXT:   %[[c2:.*]] = constant 2 : index
+//  CHECK-NEXT:   %[[cst0:.*]] = constant dense<0.000000e+00> : vector<3xf32>
+//  CHECK-NEXT:   %[[m:.*]] = alloca() {alignment = 128 : i64} : memref<3xvector<3xf32>>
+//  CHECK-NEXT:   %[[d:.*]] = dim %arg0, %c2 : memref<?x?x?x?xf32>
+//  CHECK-NEXT:   affine.for %[[arg1:.*]] = 0 to 3 {
+//  CHECK-NEXT:      %[[cmp:.*]] = cmpi "slt", %[[arg1]], %[[d]] : index
+//  CHECK-NEXT:      scf.if %[[cmp]] {
+//  CHECK-NEXT:        %[[tr:.*]] = vector.transfer_read %[[A]][%[[c0]], %[[c0]], %[[arg1]], %[[c0]]], %[[cst]] : memref<?x?x?x?xf32>, vector<3xf32>
+//  CHECK-NEXT:        store %[[tr]], %[[m]][%[[arg1]]] : memref<3xvector<3xf32>>
+//  CHECK-NEXT:      } else {
+//  CHECK-NEXT:        store %[[cst0]], %[[m]][%[[arg1]]] : memref<3xvector<3xf32>>
+//  CHECK-NEXT:      }
+//  CHECK-NEXT:    }
+//  CHECK-NEXT:    %[[cast:.*]] = vector.type_cast %[[m]] : memref<3xvector<3xf32>> to memref<vector<3x3xf32>>
+//  CHECK-NEXT:    %[[ret:.*]]  = load %[[cast]][] : memref<vector<3x3xf32>>
+//  CHECK-NEXT:    return %[[ret]] : vector<3x3xf32>