diff --git a/mlir/lib/Dialect/Vector/IR/VectorOps.cpp b/mlir/lib/Dialect/Vector/IR/VectorOps.cpp
--- a/mlir/lib/Dialect/Vector/IR/VectorOps.cpp
+++ b/mlir/lib/Dialect/Vector/IR/VectorOps.cpp
@@ -4392,11 +4392,31 @@
   }
 };
 
+// Folds transpose(splat x : src_type) : res_type into splat x : res_type.
+class FoldTransposeSplat final : public OpRewritePattern<TransposeOp> {
+public:
+  using OpRewritePattern<TransposeOp>::OpRewritePattern;
+
+  LogicalResult matchAndRewrite(TransposeOp transposeOp,
+                                PatternRewriter &rewriter) const override {
+    if (auto splatOp =
+            transposeOp.getVector().getDefiningOp<vector::SplatOp>()) {
+      rewriter.replaceOpWithNewOp<vector::SplatOp>(
+          transposeOp, transposeOp.getResultType(), splatOp.getInput());
+      return success();
+    }
+
+    return failure();
+  }
+};
+
 } // namespace
 
 void vector::TransposeOp::getCanonicalizationPatterns(
     RewritePatternSet &results, MLIRContext *context) {
-  results.add<FoldTransposedScalarBroadcast, TransposeFolder>(context);
+  results
+      .add<FoldTransposedScalarBroadcast, TransposeFolder, FoldTransposeSplat>(
+          context);
 }
 
 void vector::TransposeOp::getTransp(SmallVectorImpl<int64_t> &results) {
diff --git a/mlir/test/Dialect/Vector/canonicalize.mlir b/mlir/test/Dialect/Vector/canonicalize.mlir
--- a/mlir/test/Dialect/Vector/canonicalize.mlir
+++ b/mlir/test/Dialect/Vector/canonicalize.mlir
@@ -1472,6 +1472,17 @@
   return %0 : vector<8x4xf32>
 }
 
+// CHECK-LABEL:   func @transpose_splat2(
+// CHECK-SAME:                           %[[VAL_0:.*]]: f32) -> vector<3x4xf32> {
+// CHECK:           %[[VAL_1:.*]] = vector.splat %[[VAL_0]] : vector<3x4xf32>
+// CHECK:           return %[[VAL_1]] : vector<3x4xf32>
+// CHECK:         }
+func @transpose_splat2(%arg : f32) -> vector<3x4xf32> {
+  %splat = vector.splat %arg : vector<4x3xf32>
+  %0 = vector.transpose %splat, [1, 0] : vector<4x3xf32> to vector<3x4xf32>
+  return %0 : vector<3x4xf32>
+}
+
 // -----
 
 // CHECK-LABEL: func @insert_element_fold
diff --git a/mlir/test/Dialect/Vector/vector-transfer-to-vector-load-store.mlir b/mlir/test/Dialect/Vector/vector-transfer-to-vector-load-store.mlir
--- a/mlir/test/Dialect/Vector/vector-transfer-to-vector-load-store.mlir
+++ b/mlir/test/Dialect/Vector/vector-transfer-to-vector-load-store.mlir
@@ -281,22 +281,22 @@
   %cst = arith.constant 0.000000e+00 : f32
   %c0 = arith.constant 0 : index
 
+// CHECK: %[[MASK0:.*]] = vector.splat %{{.*}} : vector<14x7xi1>
   %mask0 = vector.splat %m : vector<7x14xi1>
   %0 = vector.transfer_read %arg1[%c0, %c0, %c0, %c0], %cst, %mask0 {in_bounds = [true, false, true, true], permutation_map = #map0} : memref<?x?x?x?xf32>, vector<7x14x8x16xf32>
-// CHECK: %[[MASK0:.*]] = vector.transpose {{.*}} : vector<7x14xi1> to vector<14x7xi1>
 // CHECK: vector.transfer_read {{.*}} %[[MASK0]] {in_bounds = [false, true, true, true], permutation_map = #[[$MAP0]]} : memref<?x?x?x?xf32>, vector<14x7x8x16xf32>
 // CHECK: vector.transpose %{{.*}}, [1, 0, 2, 3] : vector<14x7x8x16xf32> to vector<7x14x8x16xf32>
 
+// CHECK: %[[MASK1:.*]] = vector.splat %{{.*}} : vector<16x14xi1>
   %mask1 = vector.splat %m : vector<14x16xi1>
   %1 = vector.transfer_read %arg1[%c0, %c0, %c0, %c0], %cst, %mask1 {permutation_map = #map1} : memref<?x?x?x?xf32>, vector<7x14x8x16xf32>
-// CHECK: %[[MASK1:.*]] = vector.transpose {{.*}} : vector<14x16xi1> to vector<16x14xi1>
 // CHECK: vector.transfer_read {{.*}} %[[MASK1]] {permutation_map = #[[$MAP0]]} : memref<?x?x?x?xf32>, vector<16x14x7x8xf32>
 // CHECK: vector.transpose %{{.*}}, [2, 1, 3, 0] : vector<16x14x7x8xf32> to vector<7x14x8x16xf32>
 
+// CHECK: %[[MASK3:.*]] = vector.splat %{{.*}} : vector<14x7xi1>
   %mask2 = vector.splat %m : vector<7x14xi1>
   %2 = vector.transfer_read %arg1[%c0, %c0, %c0, %c0], %cst, %mask2 {in_bounds = [true, false, true, true], permutation_map = #map2} : memref<?x?x?x?xf32>, vector<7x14x8x16xf32>
-// CHECK: %[[MASK2:.*]] = vector.transpose {{.*}} : vector<7x14xi1> to vector<14x7xi1>
-// CHECK: vector.transfer_read {{.*}} %[[MASK2]] {in_bounds = [false, true, true], permutation_map = #[[$MAP1]]} : memref<?x?x?x?xf32>, vector<14x16x7xf32>
+// CHECK: vector.transfer_read {{.*}} %[[MASK3]] {in_bounds = [false, true, true], permutation_map = #[[$MAP1]]} : memref<?x?x?x?xf32>, vector<14x16x7xf32>
 // CHECK: vector.broadcast %{{.*}} : vector<14x16x7xf32> to vector<8x14x16x7xf32>
 // CHECK: vector.transpose %{{.*}}, [3, 1, 0, 2] : vector<8x14x16x7xf32> to vector<7x14x8x16xf32>
 
@@ -328,17 +328,20 @@
 // CHECK-LABEL: func @transfer_write_permutations
 // CHECK-SAME:      %[[ARG0:.*]]: memref<?x?x?x?xf32>
 // CHECK-SAME:      %[[ARG1:.*]]: tensor<?x?x?x?xf32>
+// CHECK-SAME:      %[[ARG2:.*]]: vector<7x14x8x16xf32>
+// CHECK-SAME:      %[[ARG3:.*]]: vector<8x16xf32>
+// CHECK-SAME:      %[[M:.*]]: i1
 func @transfer_write_permutations(
     %arg0 : memref<?x?x?x?xf32>, %arg1 : tensor<?x?x?x?xf32>,
     %v1 : vector<7x14x8x16xf32>, %v2 : vector<8x16xf32>, %m: i1) -> tensor<?x?x?x?xf32> {
   // CHECK-DAG: %[[C0:.*]] = arith.constant 0 : index
   %c0 = arith.constant 0 : index
 
+  // CHECK: %[[MASK:.*]] = vector.splat %[[M]] : vector<8x14x16x7xi1>
   %mask0 = vector.splat %m : vector<7x14x8x16xi1>
   %0 = vector.transfer_write %v1, %arg1[%c0, %c0, %c0, %c0], %mask0 {in_bounds = [true, false, false, true], permutation_map = affine_map<(d0, d1, d2, d3) -> (d2, d1, d3, d0)>} : vector<7x14x8x16xf32>, tensor<?x?x?x?xf32>
-  // CHECK: %[[NEW_MASK0:.*]] = vector.transpose %{{.*}} [2, 1, 3, 0] : vector<7x14x8x16xi1> to vector<8x14x16x7xi1>
   // CHECK: %[[NEW_VEC0:.*]] = vector.transpose %{{.*}} [2, 1, 3, 0] : vector<7x14x8x16xf32> to vector<8x14x16x7xf32>
-  // CHECK: %[[NEW_RES0:.*]] = vector.transfer_write %[[NEW_VEC0]], %[[ARG1]][%c0, %c0, %c0, %c0], %[[NEW_MASK0]] {in_bounds = [false, false, true, true]} : vector<8x14x16x7xf32>, tensor<?x?x?x?xf32>
+  // CHECK: %[[NEW_RES0:.*]] = vector.transfer_write %[[NEW_VEC0]], %[[ARG1]][%c0, %c0, %c0, %c0], %[[MASK]] {in_bounds = [false, false, true, true]} : vector<8x14x16x7xf32>, tensor<?x?x?x?xf32>
 
   vector.transfer_write %v2, %arg0[%c0, %c0, %c0, %c0] {permutation_map = affine_map<(d0, d1, d2, d3) -> (d3, d2)>} : vector<8x16xf32>, memref<?x?x?x?xf32>
   // CHECK: %[[NEW_VEC1:.*]] = vector.transpose %{{.*}} [1, 0] : vector<8x16xf32> to vector<16x8xf32>