diff --git a/mlir/include/mlir/Dialect/Linalg/Passes.h b/mlir/include/mlir/Dialect/Linalg/Passes.h
--- a/mlir/include/mlir/Dialect/Linalg/Passes.h
+++ b/mlir/include/mlir/Dialect/Linalg/Passes.h
@@ -13,9 +13,11 @@
 #ifndef MLIR_DIALECT_LINALG_PASSES_H_
 #define MLIR_DIALECT_LINALG_PASSES_H_
 
+#include "mlir/Dialect/Linalg/Utils/Utils.h"
 #include "mlir/Pass/Pass.h"
 
 namespace mlir {
+
 std::unique_ptr<OperationPass<FuncOp>> createConvertElementwiseToLinalgPass();
 
 std::unique_ptr<OperationPass<FuncOp>> createLinalgFoldUnitExtentDimsPass();
@@ -23,15 +25,10 @@
 std::unique_ptr<Pass> createLinalgElementwiseOpFusionPass();
 std::unique_ptr<Pass> createFoldReshapeOpsByLinearizationPass();
 
-std::unique_ptr<OperationPass<FuncOp>>
-createLinalgTilingPass(ArrayRef<int64_t> tileSizes = {});
-
-std::unique_ptr<OperationPass<FuncOp>>
-createLinalgTilingToParallelLoopsPass(ArrayRef<int64_t> tileSizes = {});
-
-std::unique_ptr<OperationPass<FuncOp>>
-createLinalgTilingToTiledLoopPass(ArrayRef<int64_t> tileSizes = {},
-                                  ArrayRef<StringRef> distributionTypes = {});
+std::unique_ptr<OperationPass<FuncOp>> createLinalgTilingPass(
+    ArrayRef<int64_t> tileSizes = {},
+    linalg::LinalgTilingLoopType loopType = linalg::LinalgTilingLoopType::Loops,
+    ArrayRef<StringRef> distributionTypes = {});
 
 std::unique_ptr<OperationPass<FuncOp>>
 createLinalgPromotionPass(bool dynamicBuffers, bool useAlloca);
diff --git a/mlir/include/mlir/Dialect/Linalg/Passes.td b/mlir/include/mlir/Dialect/Linalg/Passes.td
--- a/mlir/include/mlir/Dialect/Linalg/Passes.td
+++ b/mlir/include/mlir/Dialect/Linalg/Passes.td
@@ -169,43 +169,15 @@
     "scf::SCFDialect"
   ];
   let options = [
-    ListOption<"tileSizes", "linalg-tile-sizes", "int64_t", "Tile sizes",
-               "llvm::cl::ZeroOrMore, llvm::cl::MiscFlags::CommaSeparated">
-  ];
-}
-
-def LinalgTilingToParallelLoops
-    : FunctionPass<"linalg-tile-to-parallel-loops"> {
-  let summary = "Tile operations in the linalg dialect to parallel loops";
-  let constructor = "mlir::createLinalgTilingToParallelLoopsPass()";
-  let options = [
-    ListOption<"tileSizes", "linalg-tile-sizes", "int64_t", "Tile sizes",
-               "llvm::cl::ZeroOrMore, llvm::cl::MiscFlags::CommaSeparated">
-  ];
-  let dependentDialects = [
-    "AffineDialect",
-    "linalg::LinalgDialect",
-    "memref::MemRefDialect",
-    "scf::SCFDialect"
-  ];
-}
-
-def LinalgTilingToTiledLoops
-    : FunctionPass<"linalg-tile-to-tiled-loop"> {
-  let summary = "Tile operations in the linalg dialect to linalg.tiled_loop";
-  let constructor = "mlir::createLinalgTilingToTiledLoopPass()";
-  let options = [
-    ListOption<"tileSizes", "linalg-tile-sizes", "int64_t", "Tile sizes",
+    ListOption<"tileSizes", "tile-sizes", "int64_t", "Tile sizes",
                "llvm::cl::ZeroOrMore, llvm::cl::MiscFlags::CommaSeparated">,
-    ListOption<"distributionTypes", "linalg-distribution-types", "std::string",
-               "DistributionTypes",
+    Option<"loopType", "loop-type", "std::string", /*default=*/"\"for\"",
+           "Specify the type of loops to generate: for, parallel or "
+           "tiled_loop">,
+    ListOption<"distributionTypes", "distribution-types", "std::string",
+               "DistributionTypes (if loop-type=tiled_loop)",
                "llvm::cl::ZeroOrMore, llvm::cl::MiscFlags::CommaSeparated">
-  ];
-  let dependentDialects = [
-    "AffineDialect",
-    "linalg::LinalgDialect",
-    "memref::MemRefDialect",
-    "scf::SCFDialect"
+
   ];
 }
 
diff --git a/mlir/include/mlir/Dialect/Linalg/Transforms/Transforms.h b/mlir/include/mlir/Dialect/Linalg/Transforms/Transforms.h
--- a/mlir/include/mlir/Dialect/Linalg/Transforms/Transforms.h
+++ b/mlir/include/mlir/Dialect/Linalg/Transforms/Transforms.h
@@ -435,19 +435,6 @@
   Optional<Identifier> replacement;
 };
 
-///
-/// Linalg tiling patterns.
-///
-/// Apply the `tileLinalgOp` transformation as a pattern.
-/// `filter` controls LinalgTransformMarker matching and update when specified.
-/// See `tileLinalgOp` for more details.
-enum class LinalgTilingLoopType {
-  Loops = 0,
-  AffineLoops = 1,
-  ParallelLoops = 2,
-  TiledLoops = 3,
-};
-
 using TileSizeComputationFunction =
     std::function<SmallVector<Value, 4>(OpBuilder &, Operation *)>;
 
diff --git a/mlir/include/mlir/Dialect/Linalg/Utils/Utils.h b/mlir/include/mlir/Dialect/Linalg/Utils/Utils.h
--- a/mlir/include/mlir/Dialect/Linalg/Utils/Utils.h
+++ b/mlir/include/mlir/Dialect/Linalg/Utils/Utils.h
@@ -76,9 +76,17 @@
     ArrayRef<OpFoldResult> sizes, ArrayRef<OpFoldResult> strides);
 
 //===----------------------------------------------------------------------===//
-// Fusion utilities
+// Fusion / Tiling utilities
 //===----------------------------------------------------------------------===//
 
+/// The type of loops to be generated during tiling.
+enum class LinalgTilingLoopType {
+  Loops = 0,
+  AffineLoops = 1,
+  ParallelLoops = 2,
+  TiledLoops = 3,
+};
+
 /// Checks whether the specific `producer` is the last write to exactly the
 /// whole `consumedView`. This checks structural dominance, that the dependence
 /// is a RAW without any interleaved write to any piece of `consumedView`.
diff --git a/mlir/lib/Dialect/Linalg/Transforms/Tiling.cpp b/mlir/lib/Dialect/Linalg/Transforms/Tiling.cpp
--- a/mlir/lib/Dialect/Linalg/Transforms/Tiling.cpp
+++ b/mlir/lib/Dialect/Linalg/Transforms/Tiling.cpp
@@ -508,89 +508,59 @@
       funcOp, getLinalgTilingCanonicalizationPatterns(ctx));
 }
 
-static void
-applyTilingToLoopPatterns(LinalgTilingLoopType loopType, FuncOp funcOp,
-                          ArrayRef<int64_t> tileSizes,
-                          ArrayRef<StringRef> distributionTypes = {}) {
-  auto options = LinalgTilingOptions()
-                     .setTileSizes(tileSizes)
-                     .setLoopType(loopType)
-                     .setDistributionTypes(distributionTypes);
-  MLIRContext *ctx = funcOp.getContext();
-  RewritePatternSet patterns(ctx);
-  insertTilingPatterns(patterns, options);
-  scf::populateSCFForLoopCanonicalizationPatterns(patterns);
-  (void)applyPatternsAndFoldGreedily(funcOp, std::move(patterns));
-  (void)applyPatternsAndFoldGreedily(
-      funcOp, getLinalgTilingCanonicalizationPatterns(ctx));
-  // Drop the marker.
-  funcOp.walk([](LinalgOp op) {
-    op->removeAttr(LinalgTransforms::kLinalgTransformMarker);
-  });
-
-  // Apply swap pattern after generating loop nest and running
-  // canonicalizations.
-  applyExtractSliceOfPadTensorSwapPattern(funcOp);
-}
-
 namespace {
 struct LinalgTilingPass : public LinalgTilingBase<LinalgTilingPass> {
   LinalgTilingPass() = default;
-  LinalgTilingPass(ArrayRef<int64_t> sizes) { tileSizes = sizes; }
-
-  void runOnFunction() override {
-    applyTilingToLoopPatterns(LinalgTilingLoopType::Loops, getFunction(),
-                              tileSizes);
-  }
-};
-
-struct LinalgTilingToParallelLoopsPass
-    : public LinalgTilingToParallelLoopsBase<LinalgTilingToParallelLoopsPass> {
-  LinalgTilingToParallelLoopsPass() = default;
-  LinalgTilingToParallelLoopsPass(ArrayRef<int64_t> sizes) {
-    tileSizes = sizes;
+  LinalgTilingPass(ArrayRef<int64_t> tileSizes, LinalgTilingLoopType loopType,
+                   ArrayRef<StringRef> distributionTypes) {
+    this->tileSizes = tileSizes;
+    this->loopType = "";
+    this->loopTypeEnum = loopType;
+    this->distributionTypes = llvm::to_vector<2>(llvm::map_range(
+        distributionTypes, [](StringRef ref) { return ref.str(); }));
   }
 
   void runOnFunction() override {
-    applyTilingToLoopPatterns(LinalgTilingLoopType::ParallelLoops,
-                              getFunction(), tileSizes);
-  }
-};
-
-struct LinalgTilingToTiledLoopsPass
-    : public LinalgTilingToTiledLoopsBase<LinalgTilingToTiledLoopsPass> {
-  LinalgTilingToTiledLoopsPass() = default;
-  LinalgTilingToTiledLoopsPass(ArrayRef<int64_t> sizes,
-                               ArrayRef<StringRef> types) {
-    tileSizes = sizes;
-    distributionTypes = llvm::to_vector<2>(
-        llvm::map_range(types, [](StringRef ref) { return ref.str(); }));
+    FuncOp funcOp = getFunction();
+    LinalgTilingLoopType type =
+        llvm::StringSwitch<LinalgTilingLoopType>(loopType)
+            .Case("for", LinalgTilingLoopType::Loops)
+            .Case("affine", LinalgTilingLoopType::AffineLoops)
+            .Case("parallel", LinalgTilingLoopType::ParallelLoops)
+            .Case("tiled_loop", LinalgTilingLoopType::TiledLoops)
+            .Default(loopTypeEnum);
+    auto distTypes = llvm::to_vector<2>(llvm::map_range(
+        distributionTypes, [](std::string &str) { return StringRef(str); }));
+    auto options = LinalgTilingOptions()
+                       .setTileSizes(tileSizes)
+                       .setLoopType(type)
+                       .setDistributionTypes(distTypes);
+    MLIRContext *ctx = funcOp.getContext();
+    RewritePatternSet patterns(ctx);
+    insertTilingPatterns(patterns, options);
+    scf::populateSCFForLoopCanonicalizationPatterns(patterns);
+    (void)applyPatternsAndFoldGreedily(funcOp, std::move(patterns));
+    (void)applyPatternsAndFoldGreedily(
+        funcOp, getLinalgTilingCanonicalizationPatterns(ctx));
+    // Drop the marker.
+    funcOp.walk([](LinalgOp op) {
+      op->removeAttr(LinalgTransforms::kLinalgTransformMarker);
+    });
+
+    // Apply swap pattern after generating loop nest and running
+    // canonicalizations.
+    applyExtractSliceOfPadTensorSwapPattern(funcOp);
   }
 
-  void runOnFunction() override {
-    applyTilingToLoopPatterns(
-        LinalgTilingLoopType::TiledLoops, getFunction(), tileSizes,
-        llvm::to_vector<2>(
-            llvm::map_range(distributionTypes,
-                            [](std::string &str) { return StringRef(str); })));
-  }
+  LinalgTilingLoopType loopTypeEnum;
 };
 
 } // namespace
 
 std::unique_ptr<OperationPass<FuncOp>>
-mlir::createLinalgTilingPass(ArrayRef<int64_t> tileSizes) {
-  return std::make_unique<LinalgTilingPass>(tileSizes);
-}
-
-std::unique_ptr<OperationPass<FuncOp>>
-mlir::createLinalgTilingToParallelLoopsPass(ArrayRef<int64_t> tileSizes) {
-  return std::make_unique<LinalgTilingToParallelLoopsPass>(tileSizes);
-}
-
-std::unique_ptr<OperationPass<FuncOp>>
-mlir::createLinalgTilingToTiledLoopPass(ArrayRef<int64_t> tileSizes,
-                                        ArrayRef<StringRef> distributionTypes) {
-  return std::make_unique<LinalgTilingToTiledLoopsPass>(tileSizes,
-                                                        distributionTypes);
+mlir::createLinalgTilingPass(ArrayRef<int64_t> tileSizes,
+                             linalg::LinalgTilingLoopType loopType,
+                             ArrayRef<StringRef> distributionTypes) {
+  return std::make_unique<LinalgTilingPass>(tileSizes, loopType,
+                                            distributionTypes);
 }
diff --git a/mlir/test/Dialect/Linalg/tile-conv-padding.mlir b/mlir/test/Dialect/Linalg/tile-conv-padding.mlir
--- a/mlir/test/Dialect/Linalg/tile-conv-padding.mlir
+++ b/mlir/test/Dialect/Linalg/tile-conv-padding.mlir
@@ -1,5 +1,5 @@
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,3,0,0,4" | FileCheck %s -check-prefix=TILE-23004
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2" | FileCheck %s -check-prefix=TILE-20000
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3,0,0,4" | FileCheck %s -check-prefix=TILE-23004
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2" | FileCheck %s -check-prefix=TILE-20000
 
 // TILE-23004-DAG: #[[$strided4D:.*]] = affine_map<(d0, d1, d2, d3)[s0, s1, s2, s3] -> (d0 * s1 + s0 + d1 * s2 + d2 * s3 + d3)>
 // TILE-20000-DAG: #[[$strided4D:.*]] = affine_map<(d0, d1, d2, d3)[s0, s1, s2, s3] -> (d0 * s1 + s0 + d1 * s2 + d2 * s3 + d3)>
diff --git a/mlir/test/Dialect/Linalg/tile-conv.mlir b/mlir/test/Dialect/Linalg/tile-conv.mlir
--- a/mlir/test/Dialect/Linalg/tile-conv.mlir
+++ b/mlir/test/Dialect/Linalg/tile-conv.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,3,0,0,4" | FileCheck %s -check-prefix=TILE-23004
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3,0,0,4" | FileCheck %s -check-prefix=TILE-23004
 
 // TILE-23004-DAG: #[[$D0x30pS0x10:.*]] = affine_map<(d0) -> (d0 * 30)>
 // TILE-23004-DAG: #[[$S0x10p90D0x30pS1:.*]] = affine_map<(d0)[s0, s1] -> (s0 * 10 + 51, d0 * -30 + s0 * 10 + s1 * 30)>
diff --git a/mlir/test/Dialect/Linalg/tile-indexed.mlir b/mlir/test/Dialect/Linalg/tile-indexed.mlir
--- a/mlir/test/Dialect/Linalg/tile-indexed.mlir
+++ b/mlir/test/Dialect/Linalg/tile-indexed.mlir
@@ -1,6 +1,6 @@
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=10,25" -split-input-file | FileCheck %s -check-prefix=TILE-10n25
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=25,0" -split-input-file | FileCheck %s -check-prefix=TILE-25n0
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=0,25" -split-input-file | FileCheck %s -check-prefix=TILE-0n25
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=10,25" -split-input-file | FileCheck %s -check-prefix=TILE-10n25
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=25,0" -split-input-file | FileCheck %s -check-prefix=TILE-25n0
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=0,25" -split-input-file | FileCheck %s -check-prefix=TILE-0n25
 
 func @indexed_vector(%arg0: memref<50xindex>) {
   linalg.generic {indexing_maps = [affine_map<(i) -> (i)>],
diff --git a/mlir/test/Dialect/Linalg/tile-pad-tensor-op.mlir b/mlir/test/Dialect/Linalg/tile-pad-tensor-op.mlir
--- a/mlir/test/Dialect/Linalg/tile-pad-tensor-op.mlir
+++ b/mlir/test/Dialect/Linalg/tile-pad-tensor-op.mlir
@@ -1,6 +1,6 @@
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,3" -cse -split-input-file | \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3" -cse -split-input-file | \
 // RUN: FileCheck %s -check-prefix=TILE2
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=0,3" -resolve-shaped-type-result-dims -cse -split-input-file | \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=0,3" -resolve-shaped-type-result-dims -cse -split-input-file | \
 // RUN: FileCheck %s -check-prefix=TILE1
 
 //  TILE2-DAG:  #[[MAP0:.*]] = affine_map<()[s0] -> (s0 + 8)>
diff --git a/mlir/test/Dialect/Linalg/tile-parallel-reduce.mlir b/mlir/test/Dialect/Linalg/tile-parallel-reduce.mlir
--- a/mlir/test/Dialect/Linalg/tile-parallel-reduce.mlir
+++ b/mlir/test/Dialect/Linalg/tile-parallel-reduce.mlir
@@ -1,6 +1,6 @@
-// RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=2,4,8" -split-input-file | FileCheck %s
-// RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=2" -split-input-file | FileCheck %s -check-prefix=TILE1
-// RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=2,4" -split-input-file | FileCheck %s -check-prefix=TILE2
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,4,8 loop-type=parallel" -split-input-file | FileCheck %s
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2 loop-type=parallel" -split-input-file | FileCheck %s -check-prefix=TILE1
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,4 loop-type=parallel" -split-input-file | FileCheck %s -check-prefix=TILE2
 
 func @gemm(%arg0 : memref<?x?xf32>,
            %arg1 : memref<?x?xf32>,
diff --git a/mlir/test/Dialect/Linalg/tile-parallel.mlir b/mlir/test/Dialect/Linalg/tile-parallel.mlir
--- a/mlir/test/Dialect/Linalg/tile-parallel.mlir
+++ b/mlir/test/Dialect/Linalg/tile-parallel.mlir
@@ -1,7 +1,7 @@
-// RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=2" | FileCheck %s -check-prefix=TILE-2
-// RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=0,2" | FileCheck %s -check-prefix=TILE-02
-// RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=0,0,2" | FileCheck %s -check-prefix=TILE-002
-// RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=2,3,4" | FileCheck %s -check-prefix=TILE-234
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2 loop-type=parallel" | FileCheck %s -check-prefix=TILE-2
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=0,2 loop-type=parallel" | FileCheck %s -check-prefix=TILE-02
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=0,0,2 loop-type=parallel" | FileCheck %s -check-prefix=TILE-002
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3,4 loop-type=parallel" | FileCheck %s -check-prefix=TILE-234
 
 #id_2d = affine_map<(i, j) -> (i, j)>
 #pointwise_2d_trait = {
diff --git a/mlir/test/Dialect/Linalg/tile-simple-conv.mlir b/mlir/test/Dialect/Linalg/tile-simple-conv.mlir
--- a/mlir/test/Dialect/Linalg/tile-simple-conv.mlir
+++ b/mlir/test/Dialect/Linalg/tile-simple-conv.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,3,4" | FileCheck %s
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3,4" | FileCheck %s
 
 //  CHECK-DAG: #[[MAP0:.*]] = affine_map<(d0)[s0] -> (2, -d0 + s0)>
 //  CHECK-DAG: #[[MAP1:.*]] = affine_map<(d0)[s0, s1] -> (s0 + 2, -d0 + s0 + s1)>
diff --git a/mlir/test/Dialect/Linalg/tile-tensors.mlir b/mlir/test/Dialect/Linalg/tile-tensors.mlir
--- a/mlir/test/Dialect/Linalg/tile-tensors.mlir
+++ b/mlir/test/Dialect/Linalg/tile-tensors.mlir
@@ -1,5 +1,5 @@
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,3,4" -split-input-file | FileCheck %s
-// RUN: mlir-opt %s -linalg-tile-to-tiled-loop="linalg-tile-sizes=2,3,4 linalg-distribution-types=block_x,block_y,none" -split-input-file | FileCheck %s -check-prefix=TLOOP
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3,4" -split-input-file | FileCheck %s
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3,4 loop-type=tiled_loop distribution-types=block_x,block_y,none" -split-input-file | FileCheck %s -check-prefix=TLOOP
 
 // CHECK-LABEL: func @matmul_tensors(
 // CHECK-SAME:    %[[TA:[0-9a-z]+]]: tensor<?x?xf32>
diff --git a/mlir/test/Dialect/Linalg/tile.mlir b/mlir/test/Dialect/Linalg/tile.mlir
--- a/mlir/test/Dialect/Linalg/tile.mlir
+++ b/mlir/test/Dialect/Linalg/tile.mlir
@@ -1,7 +1,7 @@
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2" -mlir-disable-threading=true | FileCheck %s -check-prefix=TILE-2
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=0,2" -mlir-disable-threading=true | FileCheck %s -check-prefix=TILE-02
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=0,0,2" -mlir-disable-threading=true | FileCheck %s -check-prefix=TILE-002
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,3,4" -mlir-disable-threading=true | FileCheck %s -check-prefix=TILE-234
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2" -mlir-disable-threading=true | FileCheck %s -check-prefix=TILE-2
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=0,2" -mlir-disable-threading=true | FileCheck %s -check-prefix=TILE-02
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=0,0,2" -mlir-disable-threading=true | FileCheck %s -check-prefix=TILE-002
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3,4" -mlir-disable-threading=true | FileCheck %s -check-prefix=TILE-234
 
 //   TILE-2-DAG: #[[$strided1D:.*]] = affine_map<(d0)[s0] -> (d0 + s0)>
 //  TILE-02-DAG: #[[$strided1D:.*]] = affine_map<(d0)[s0] -> (d0 + s0)>
diff --git a/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-1d-call.mlir b/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-1d-call.mlir
--- a/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-1d-call.mlir
+++ b/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-1d-call.mlir
@@ -3,7 +3,7 @@
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=4" -convert-linalg-to-loops -convert-scf-to-std \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=4" -convert-linalg-to-loops -convert-scf-to-std \
 // RUN:   -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
@@ -14,7 +14,7 @@
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=4" \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=4" \
 // RUN:   -test-conv-vectorization="tile-sizes=1,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
diff --git a/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-1d-nwc-wcf-call.mlir b/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-1d-nwc-wcf-call.mlir
--- a/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-1d-nwc-wcf-call.mlir
+++ b/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-1d-nwc-wcf-call.mlir
@@ -3,7 +3,7 @@
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,4" -convert-linalg-to-loops -convert-scf-to-std \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,4" -convert-linalg-to-loops -convert-scf-to-std \
 // RUN:   -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
@@ -14,7 +14,7 @@
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,4" \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,4" \
 // RUN:   -test-conv-vectorization="tile-sizes=1,1,1,3,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
diff --git a/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-2d-call.mlir b/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-2d-call.mlir
--- a/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-2d-call.mlir
+++ b/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-2d-call.mlir
@@ -3,7 +3,7 @@
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,2" -convert-linalg-to-loops -convert-scf-to-std \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,2" -convert-linalg-to-loops -convert-scf-to-std \
 // RUN:   -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
@@ -14,7 +14,7 @@
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,2" \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,2" \
 // RUN:   -test-conv-vectorization="tile-sizes=1,1,3,3"  -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
diff --git a/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-2d-nhwc-hwcf-call.mlir b/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-2d-nhwc-hwcf-call.mlir
--- a/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-2d-nhwc-hwcf-call.mlir
+++ b/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-2d-nhwc-hwcf-call.mlir
@@ -3,7 +3,7 @@
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,3,3,2" -convert-linalg-to-loops -convert-scf-to-std \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3,3,2" -convert-linalg-to-loops -convert-scf-to-std \
 // RUN:   -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
@@ -14,7 +14,7 @@
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,3,3,2" \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3,3,2" \
 // RUN:   -test-conv-vectorization="tile-sizes=1,1,1,1,3,3,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
diff --git a/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-3d-call.mlir b/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-3d-call.mlir
--- a/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-3d-call.mlir
+++ b/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-3d-call.mlir
@@ -3,7 +3,7 @@
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,2,2" -convert-linalg-to-loops -convert-scf-to-std \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,2,2" -convert-linalg-to-loops -convert-scf-to-std \
 // RUN:   -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
@@ -14,7 +14,7 @@
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,2,2" \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,2,2" \
 // RUN:   -test-conv-vectorization="tile-sizes=1,1,1,3,3,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
diff --git a/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-3d-ndhwc-dhwcf-call.mlir b/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-3d-ndhwc-dhwcf-call.mlir
--- a/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-3d-ndhwc-dhwcf-call.mlir
+++ b/mlir/test/Integration/Dialect/Linalg/CPU/test-conv-3d-ndhwc-dhwcf-call.mlir
@@ -3,7 +3,7 @@
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=0,5,5,5" -convert-linalg-to-loops -convert-scf-to-std \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=0,5,5,5" -convert-linalg-to-loops -convert-scf-to-std \
 // RUN:   -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
@@ -14,7 +14,7 @@
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=0,5,5,5" \
+// RUN: mlir-opt %s -linalg-tile="tile-sizes=0,5,5,5" \
 // RUN:   -test-conv-vectorization="tile-sizes=1,1,1,1,1,3,3,3,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
diff --git a/mlir/test/Integration/Dialect/Linalg/CPU/test-tensor-matmul.mlir b/mlir/test/Integration/Dialect/Linalg/CPU/test-tensor-matmul.mlir
--- a/mlir/test/Integration/Dialect/Linalg/CPU/test-tensor-matmul.mlir
+++ b/mlir/test/Integration/Dialect/Linalg/CPU/test-tensor-matmul.mlir
@@ -5,7 +5,7 @@
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s  -linalg-tile="linalg-tile-sizes=1,2,3" -linalg-bufferize \
+// RUN: mlir-opt %s  -linalg-tile="tile-sizes=1,2,3" -linalg-bufferize \
 // RUN: -scf-bufferize -std-bufferize -tensor-constant-bufferize -tensor-bufferize \
 // RUN: -func-bufferize \
 // RUN: -finalizing-bufferize -convert-linalg-to-loops -convert-scf-to-std -convert-scf-to-std \