diff --git a/mlir/lib/Conversion/LoopsToGPU/LoopsToGPUPass.cpp b/mlir/lib/Conversion/LoopsToGPU/LoopsToGPUPass.cpp
--- a/mlir/lib/Conversion/LoopsToGPU/LoopsToGPUPass.cpp
+++ b/mlir/lib/Conversion/LoopsToGPU/LoopsToGPUPass.cpp
@@ -24,36 +24,17 @@
 using namespace mlir;
 using namespace mlir::loop;
 
-static llvm::cl::OptionCategory clOptionsCategory(PASS_NAME " options");
-static llvm::cl::opt<unsigned>
-    clNumBlockDims("gpu-block-dims",
-                   llvm::cl::desc("Number of GPU block dimensions for mapping"),
-                   llvm::cl::cat(clOptionsCategory), llvm::cl::init(1u));
-static llvm::cl::opt<unsigned> clNumThreadDims(
-    "gpu-thread-dims",
-    llvm::cl::desc("Number of GPU thread dimensions for mapping"),
-    llvm::cl::cat(clOptionsCategory), llvm::cl::init(1u));
-
-static llvm::cl::OptionCategory clLoopOpToGPUCategory(LOOPOP_TO_GPU_PASS_NAME
-                                                      " options");
-static llvm::cl::list<unsigned>
-    clNumWorkGroups("gpu-num-workgroups",
-                    llvm::cl::desc("Num workgroups in the GPU launch"),
-                    llvm::cl::ZeroOrMore, llvm::cl::MiscFlags::CommaSeparated,
-                    llvm::cl::cat(clLoopOpToGPUCategory));
-static llvm::cl::list<unsigned>
-    clWorkGroupSize("gpu-workgroup-size",
-                    llvm::cl::desc("Workgroup Size in the GPU launch"),
-                    llvm::cl::ZeroOrMore, llvm::cl::MiscFlags::CommaSeparated,
-                    llvm::cl::cat(clLoopOpToGPUCategory));
-
 namespace {
 // A pass that traverses top-level loops in the function and converts them to
 // GPU launch operations.  Nested launches are not allowed, so this does not
 // walk the function recursively to avoid considering nested loops.
 struct ForLoopMapper : public FunctionPass<ForLoopMapper> {
-  ForLoopMapper(unsigned numBlockDims, unsigned numThreadDims)
-      : numBlockDims(numBlockDims), numThreadDims(numThreadDims) {}
+  ForLoopMapper() = default;
+  ForLoopMapper(const ForLoopMapper &) {}
+  ForLoopMapper(unsigned numBlockDims, unsigned numThreadDims) {
+    this->numBlockDims = numBlockDims;
+    this->numThreadDims = numThreadDims;
+  }
 
   void runOnFunction() override {
     for (Block &block : getFunction())
@@ -70,8 +51,14 @@
       }
   }
 
-  unsigned numBlockDims;
-  unsigned numThreadDims;
+  Option<unsigned> numBlockDims{
+      *this, "gpu-block-dims",
+      llvm::cl::desc("Number of GPU block dimensions for mapping"),
+      llvm::cl::init(1u)};
+  Option<unsigned> numThreadDims{
+      *this, "gpu-thread-dims",
+      llvm::cl::desc("Number of GPU thread dimensions for mapping"),
+      llvm::cl::init(1u)};
 };
 
 // A pass that traverses top-level loops in the function and convertes them to
@@ -81,10 +68,13 @@
 // to be perfectly nested upto depth equal to size of `workGroupSize`.
 struct ImperfectlyNestedForLoopMapper
     : public FunctionPass<ImperfectlyNestedForLoopMapper> {
+  ImperfectlyNestedForLoopMapper() = default;
+  ImperfectlyNestedForLoopMapper(const ImperfectlyNestedForLoopMapper &) {}
   ImperfectlyNestedForLoopMapper(ArrayRef<int64_t> numWorkGroups,
-                                 ArrayRef<int64_t> workGroupSize)
-      : numWorkGroups(numWorkGroups.begin(), numWorkGroups.end()),
-        workGroupSize(workGroupSize.begin(), workGroupSize.end()) {}
+                                 ArrayRef<int64_t> workGroupSize) {
+    this->numWorkGroups->assign(numWorkGroups.begin(), numWorkGroups.end());
+    this->workGroupSize->assign(workGroupSize.begin(), workGroupSize.end());
+  }
 
   void runOnFunction() override {
     // Insert the num work groups and workgroup sizes as constant values. This
@@ -113,8 +103,14 @@
       }
     }
   }
-  SmallVector<int64_t, 3> numWorkGroups;
-  SmallVector<int64_t, 3> workGroupSize;
+  ListOption<int64_t> numWorkGroups{
+      *this, "gpu-num-workgroups",
+      llvm::cl::desc("Num workgroups in the GPU launch"), llvm::cl::ZeroOrMore,
+      llvm::cl::MiscFlags::CommaSeparated};
+  ListOption<int64_t> workGroupSize{
+      *this, "gpu-workgroup-size",
+      llvm::cl::desc("Workgroup Size in the GPU launch"), llvm::cl::ZeroOrMore,
+      llvm::cl::MiscFlags::CommaSeparated};
 };
 
 struct ParallelLoopToGpuPass : public OperationPass<ParallelLoopToGpuPass> {
@@ -152,20 +148,11 @@
 }
 
 static PassRegistration<ForLoopMapper>
-    registration(PASS_NAME, "Convert top-level loops to GPU kernels", [] {
-      return std::make_unique<ForLoopMapper>(clNumBlockDims.getValue(),
-                                             clNumThreadDims.getValue());
-    });
-
-static PassRegistration<ImperfectlyNestedForLoopMapper> loopOpToGPU(
-    LOOPOP_TO_GPU_PASS_NAME, "Convert top-level loop::ForOp to GPU kernels",
-    [] {
-      SmallVector<int64_t, 3> numWorkGroups, workGroupSize;
-      numWorkGroups.assign(clNumWorkGroups.begin(), clNumWorkGroups.end());
-      workGroupSize.assign(clWorkGroupSize.begin(), clWorkGroupSize.end());
-      return std::make_unique<ImperfectlyNestedForLoopMapper>(numWorkGroups,
-                                                              workGroupSize);
-    });
+    registration(PASS_NAME, "Convert top-level loops to GPU kernels");
+
+static PassRegistration<ImperfectlyNestedForLoopMapper>
+    loopOpToGPU(LOOPOP_TO_GPU_PASS_NAME,
+                "Convert top-level loop::ForOp to GPU kernels");
 
 static PassRegistration<ParallelLoopToGpuPass>
     pass("convert-parallel-loops-to-gpu", "Convert mapped loop.parallel ops"
diff --git a/mlir/lib/Dialect/Linalg/Transforms/Fusion.cpp b/mlir/lib/Dialect/Linalg/Transforms/Fusion.cpp
--- a/mlir/lib/Dialect/Linalg/Transforms/Fusion.cpp
+++ b/mlir/lib/Dialect/Linalg/Transforms/Fusion.cpp
@@ -55,14 +55,6 @@
 /// More advanced use cases, analyses as well as profitability heuristics are
 /// left for future work.
 
-static llvm::cl::OptionCategory clOptionsCategory(DEBUG_TYPE " options");
-static llvm::cl::list<unsigned> clTileSizes(
-    "linalg-fusion-tile-sizes",
-    llvm::cl::desc(
-        "Tile sizes by which to tile linalg operations during linalg fusion"),
-    llvm::cl::ZeroOrMore, llvm::cl::MiscFlags::CommaSeparated,
-    llvm::cl::cat(clOptionsCategory));
-
 // Return a cloned version of `op` that operates on `loopRanges`, assumed to be
 // a subset of the original loop ranges of `op`.
 // This is achieved by applying the `loopToOperandRangesMaps` permutation maps
diff --git a/mlir/lib/Dialect/Linalg/Transforms/Promotion.cpp b/mlir/lib/Dialect/Linalg/Transforms/Promotion.cpp
--- a/mlir/lib/Dialect/Linalg/Transforms/Promotion.cpp
+++ b/mlir/lib/Dialect/Linalg/Transforms/Promotion.cpp
@@ -43,12 +43,6 @@
 
 #define DEBUG_TYPE "linalg-promotion"
 
-static llvm::cl::OptionCategory clOptionsCategory(DEBUG_TYPE " options");
-static llvm::cl::opt<bool> clPromoteDynamic(
-    "test-linalg-promote-dynamic",
-    llvm::cl::desc("Test generation of dynamic promoted buffers"),
-    llvm::cl::cat(clOptionsCategory), llvm::cl::init(false));
-
 static Value allocBuffer(Type elementType, Value size, bool dynamicBuffers) {
   auto *ctx = size.getContext();
   auto width = llvm::divideCeil(elementType.getIntOrFloatBitWidth(), 8);
@@ -238,13 +232,19 @@
 namespace {
 struct LinalgPromotionPass : public FunctionPass<LinalgPromotionPass> {
   LinalgPromotionPass() = default;
-  LinalgPromotionPass(bool dynamicBuffers) : dynamicBuffers(dynamicBuffers) {}
+  LinalgPromotionPass(const LinalgPromotionPass &) {}
+  LinalgPromotionPass(bool dynamicBuffers) {
+    this->dynamicBuffers = dynamicBuffers;
+  }
 
   void runOnFunction() override {
     promoteSubViews(getFunction(), dynamicBuffers);
   }
 
-  bool dynamicBuffers;
+  Option<bool> dynamicBuffers{
+      *this, "test-promote-dynamic",
+      llvm::cl::desc("Test generation of dynamic promoted buffers"),
+      llvm::cl::init(false)};
 };
 } // namespace
 
@@ -254,6 +254,4 @@
 }
 
 static PassRegistration<LinalgPromotionPass>
-    pass("linalg-promote-subviews", "promote subview ops to local buffers", [] {
-      return std::make_unique<LinalgPromotionPass>(clPromoteDynamic);
-    });
+    pass("linalg-promote-subviews", "promote subview ops to local buffers");
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
@@ -39,13 +39,6 @@
 
 #define DEBUG_TYPE "linalg-tiling"
 
-static llvm::cl::OptionCategory clOptionsCategory(DEBUG_TYPE " options");
-static llvm::cl::list<unsigned>
-    clTileSizes("linalg-tile-sizes",
-                llvm::cl::desc("Tile sizes by which to tile linalg operations"),
-                llvm::cl::ZeroOrMore, llvm::cl::MiscFlags::CommaSeparated,
-                llvm::cl::cat(clOptionsCategory));
-
 static bool isZero(Value v) {
   return isa_and_nonnull<ConstantIndexOp>(v.getDefiningOp()) &&
          cast<ConstantIndexOp>(v.getDefiningOp()).getValue() == 0;
@@ -513,15 +506,19 @@
 template <typename LoopTy>
 struct LinalgTilingPass : public FunctionPass<LinalgTilingPass<LoopTy>> {
   LinalgTilingPass() = default;
+  LinalgTilingPass(const LinalgTilingPass &) {}
   LinalgTilingPass(ArrayRef<int64_t> sizes) {
-    this->tileSizes.assign(sizes.begin(), sizes.end());
+    this->tileSizes->assign(sizes.begin(), sizes.end());
   }
 
   void runOnFunction() override {
     tileLinalgOps<LoopTy>(this->getFunction(), tileSizes);
   }
 
-  SmallVector<int64_t, 8> tileSizes;
+  Pass::ListOption<int64_t> tileSizes{
+      *this, "linalg-tile-sizes",
+      llvm::cl::desc("Tile sizes by which to tile linalg operations"),
+      llvm::cl::ZeroOrMore, llvm::cl::MiscFlags::CommaSeparated};
 };
 
 } // namespace
@@ -537,17 +534,9 @@
 }
 
 static PassRegistration<LinalgTilingPass<loop::ForOp>>
-    tiling_pass("linalg-tile", "Tile operations in the linalg dialect", [] {
-      auto pass = std::make_unique<LinalgTilingPass<loop::ForOp>>();
-      pass->tileSizes.assign(clTileSizes.begin(), clTileSizes.end());
-      return pass;
-    });
+    tiling_pass("linalg-tile", "Tile operations in the linalg dialect");
 
 static PassRegistration<LinalgTilingPass<loop::ParallelOp>>
     tiling_to_parallel_loops(
         "linalg-tile-to-parallel-loops",
-        "Tile operations in the linalg dialect to parallel loops", [] {
-          auto pass = std::make_unique<LinalgTilingPass<loop::ParallelOp>>();
-          pass->tileSizes.assign(clTileSizes.begin(), clTileSizes.end());
-          return pass;
-        });
+        "Tile operations in the linalg dialect to parallel loops");
diff --git a/mlir/lib/Transforms/Vectorize.cpp b/mlir/lib/Transforms/Vectorize.cpp
--- a/mlir/lib/Transforms/Vectorize.cpp
+++ b/mlir/lib/Transforms/Vectorize.cpp
@@ -414,7 +414,7 @@
 ///
 /// The -affine-vectorize pass with the following arguments:
 /// ```
-/// -affine-vectorize -virtual-vector-size 256 --test-fastest-varying=0
+/// -affine-vectorize="virtual-vector-size=256 test-fastest-varying=0"
 /// ```
 ///
 /// produces this standard innermost-loop vectorized code:
@@ -468,8 +468,7 @@
 ///
 /// The -affine-vectorize pass with the following arguments:
 /// ```
-/// -affine-vectorize -virtual-vector-size 32 -virtual-vector-size 256
-/// --test-fastest-varying=1 --test-fastest-varying=0
+/// -affine-vectorize="virtual-vector-size=32,256 test-fastest-varying=1,0"
 /// ```
 ///
 /// produces this more interesting mixed outer-innermost-loop vectorized code:
@@ -531,21 +530,6 @@
 using llvm::dbgs;
 using llvm::SetVector;
 
-static llvm::cl::OptionCategory clOptionsCategory("vectorize options");
-
-static llvm::cl::list<int> clVirtualVectorSize(
-    "virtual-vector-size",
-    llvm::cl::desc("Specify an n-D virtual vector size for vectorization"),
-    llvm::cl::ZeroOrMore, llvm::cl::cat(clOptionsCategory));
-
-static llvm::cl::list<int> clFastestVaryingPattern(
-    "test-fastest-varying",
-    llvm::cl::desc(
-        "Specify a 1-D, 2-D or 3-D pattern of fastest varying memory"
-        " dimensions to match. See defaultPatterns in Vectorize.cpp for a"
-        " description and examples. This is used for testing purposes"),
-    llvm::cl::ZeroOrMore, llvm::cl::cat(clOptionsCategory));
-
 /// Forward declaration.
 static FilterFunctionType
 isVectorizableLoopPtrFactory(const DenseSet<Operation *> &parallelLoops,
@@ -590,33 +574,35 @@
 /// Base state for the vectorize pass.
 /// Command line arguments are preempted by non-empty pass arguments.
 struct Vectorize : public FunctionPass<Vectorize> {
-  Vectorize();
+  Vectorize() = default;
+  Vectorize(const Vectorize &) {}
   Vectorize(ArrayRef<int64_t> virtualVectorSize);
   void runOnFunction() override;
 
-  // The virtual vector size that we vectorize to.
-  SmallVector<int64_t, 4> vectorSizes;
-  // Optionally, the fixed mapping from loop to fastest varying MemRef dimension
-  // for all the MemRefs within a loop pattern:
-  //   the index represents the loop depth, the value represents the k^th
-  //   fastest varying memory dimension.
-  // This is voluntarily restrictive and is meant to precisely target a
-  // particular loop/op pair, for testing purposes.
-  SmallVector<int64_t, 4> fastestVaryingPattern;
+  /// The virtual vector size that we vectorize to.
+  ListOption<int64_t> vectorSizes{
+      *this, "virtual-vector-size",
+      llvm::cl::desc("Specify an n-D virtual vector size for vectorization"),
+      llvm::cl::ZeroOrMore, llvm::cl::CommaSeparated};
+  /// Optionally, the fixed mapping from loop to fastest varying MemRef
+  /// dimension for all the MemRefs within a loop pattern:
+  ///   the index represents the loop depth, the value represents the k^th
+  ///   fastest varying memory dimension.
+  /// This is voluntarily restrictive and is meant to precisely target a
+  /// particular loop/op pair, for testing purposes.
+  ListOption<int64_t> fastestVaryingPattern{
+      *this, "test-fastest-varying",
+      llvm::cl::desc(
+          "Specify a 1-D, 2-D or 3-D pattern of fastest varying memory"
+          " dimensions to match. See defaultPatterns in Vectorize.cpp for a"
+          " description and examples. This is used for testing purposes"),
+      llvm::cl::ZeroOrMore, llvm::cl::CommaSeparated};
 };
 
 } // end anonymous namespace
 
-Vectorize::Vectorize()
-    : vectorSizes(clVirtualVectorSize.begin(), clVirtualVectorSize.end()),
-      fastestVaryingPattern(clFastestVaryingPattern.begin(),
-                            clFastestVaryingPattern.end()) {}
-
-Vectorize::Vectorize(ArrayRef<int64_t> virtualVectorSize) : Vectorize() {
-  if (!virtualVectorSize.empty()) {
-    this->vectorSizes.assign(virtualVectorSize.begin(),
-                             virtualVectorSize.end());
-  }
+Vectorize::Vectorize(ArrayRef<int64_t> virtualVectorSize) {
+  vectorSizes->assign(virtualVectorSize.begin(), virtualVectorSize.end());
 }
 
 /////// TODO(ntv): Hoist to a VectorizationStrategy.cpp when appropriate.
diff --git a/mlir/test/Conversion/LoopsToGPU/imperfect_2D.mlir b/mlir/test/Conversion/LoopsToGPU/imperfect_2D.mlir
--- a/mlir/test/Conversion/LoopsToGPU/imperfect_2D.mlir
+++ b/mlir/test/Conversion/LoopsToGPU/imperfect_2D.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt -convert-loop-op-to-gpu -gpu-num-workgroups=2,2 -gpu-workgroup-size=32,4 %s | FileCheck %s
+// RUN: mlir-opt -convert-loop-op-to-gpu="gpu-num-workgroups=2,2 gpu-workgroup-size=32,4" %s | FileCheck %s
 
 module {
   // arg2 = arg0 * transpose(arg1) ; with intermediate buffer and tile size passed as argument
diff --git a/mlir/test/Conversion/LoopsToGPU/imperfect_3D.mlir b/mlir/test/Conversion/LoopsToGPU/imperfect_3D.mlir
--- a/mlir/test/Conversion/LoopsToGPU/imperfect_3D.mlir
+++ b/mlir/test/Conversion/LoopsToGPU/imperfect_3D.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt -convert-loop-op-to-gpu -gpu-num-workgroups=4,2,2 -gpu-workgroup-size=32,2,2 %s | FileCheck %s
+// RUN: mlir-opt -convert-loop-op-to-gpu="gpu-num-workgroups=4,2,2 gpu-workgroup-size=32,2,2" %s | FileCheck %s
 
 module {
   func @imperfect_3D(%arg0 : memref<?x?x?xf32>, %arg1 : memref<?x?x?xf32>, %arg2 : memref<?x?x?xf32>, %arg3 : memref<?x?x?xf32>, %t1 : index, %t2 : index, %t3 : index, %step1 : index, %step2 : index, %step3 : index) {
@@ -80,4 +80,4 @@
     }
     return
   }
-}
\ No newline at end of file
+}
diff --git a/mlir/test/Conversion/LoopsToGPU/imperfect_4D.mlir b/mlir/test/Conversion/LoopsToGPU/imperfect_4D.mlir
--- a/mlir/test/Conversion/LoopsToGPU/imperfect_4D.mlir
+++ b/mlir/test/Conversion/LoopsToGPU/imperfect_4D.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt -convert-loop-op-to-gpu -gpu-num-workgroups=4,2,2 -gpu-workgroup-size=32,2,2 %s | FileCheck %s
+// RUN: mlir-opt -convert-loop-op-to-gpu="gpu-num-workgroups=4,2,2 gpu-workgroup-size=32,2,2" %s | FileCheck %s
 
 module {
   func @imperfect_3D(%arg0 : memref<?x?x?x?xf32>, %arg1 : memref<?x?x?x?xf32>, %arg2 : memref<?x?x?x?xf32>, %arg3 : memref<?x?x?x?xf32>, %t1 : index, %t2 : index, %t3 : index, %t4 : index, %step1 : index, %step2 : index, %step3 : index, %step4 : index) {
@@ -83,4 +83,4 @@
     }
     return
   }
-}
\ No newline at end of file
+}
diff --git a/mlir/test/Conversion/LoopsToGPU/imperfect_linalg.mlir b/mlir/test/Conversion/LoopsToGPU/imperfect_linalg.mlir
--- a/mlir/test/Conversion/LoopsToGPU/imperfect_linalg.mlir
+++ b/mlir/test/Conversion/LoopsToGPU/imperfect_linalg.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt %s -convert-loop-op-to-gpu -gpu-num-workgroups=2,16 -gpu-workgroup-size=32,4 | FileCheck %s
+// RUN: mlir-opt %s -convert-loop-op-to-gpu="gpu-num-workgroups=2,16 gpu-workgroup-size=32,4" | FileCheck %s
 
 module {
   func @fmul(%arg0: memref<?x?xf32>, %arg1: memref<?x?xf32>, %arg2: memref<?x?xf32>) {
diff --git a/mlir/test/Conversion/LoopsToGPU/no_blocks_no_threads.mlir b/mlir/test/Conversion/LoopsToGPU/no_blocks_no_threads.mlir
--- a/mlir/test/Conversion/LoopsToGPU/no_blocks_no_threads.mlir
+++ b/mlir/test/Conversion/LoopsToGPU/no_blocks_no_threads.mlir
@@ -1,5 +1,5 @@
-// RUN: mlir-opt -convert-loops-to-gpu -gpu-block-dims=0 -gpu-thread-dims=1 %s | FileCheck --check-prefix=CHECK-THREADS %s --dump-input-on-failure
-// RUN: mlir-opt -convert-loops-to-gpu -gpu-block-dims=1 -gpu-thread-dims=0 %s | FileCheck --check-prefix=CHECK-BLOCKS %s --dump-input-on-failure
+// RUN: mlir-opt -convert-loops-to-gpu="gpu-block-dims=0 gpu-thread-dims=1" %s | FileCheck --check-prefix=CHECK-THREADS %s --dump-input-on-failure
+// RUN: mlir-opt -convert-loops-to-gpu="gpu-block-dims=1 gpu-thread-dims=0" %s | FileCheck --check-prefix=CHECK-BLOCKS %s --dump-input-on-failure
 
 // CHECK-THREADS-LABEL: @one_d_loop
 // CHECK-BLOCKS-LABEL: @one_d_loop
diff --git a/mlir/test/Conversion/LoopsToGPU/perfect_1D_setlaunch.mlir b/mlir/test/Conversion/LoopsToGPU/perfect_1D_setlaunch.mlir
--- a/mlir/test/Conversion/LoopsToGPU/perfect_1D_setlaunch.mlir
+++ b/mlir/test/Conversion/LoopsToGPU/perfect_1D_setlaunch.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt -convert-loop-op-to-gpu -gpu-num-workgroups=2 -gpu-workgroup-size=32 %s | FileCheck %s
+// RUN: mlir-opt -convert-loop-op-to-gpu="gpu-num-workgroups=2 gpu-workgroup-size=32" %s | FileCheck %s
 
 module {
   func @foo(%arg0: memref<?x?xf32>, %arg1 : memref<?x?xf32>, %arg2 : memref<?x?xf32>) {
@@ -23,4 +23,4 @@
      }
     return
   }
-}
\ No newline at end of file
+}
diff --git a/mlir/test/Conversion/LoopsToGPU/step_one.mlir b/mlir/test/Conversion/LoopsToGPU/step_one.mlir
--- a/mlir/test/Conversion/LoopsToGPU/step_one.mlir
+++ b/mlir/test/Conversion/LoopsToGPU/step_one.mlir
@@ -1,5 +1,5 @@
-// RUN: mlir-opt -convert-loops-to-gpu -gpu-block-dims=1 -gpu-thread-dims=1 %s | FileCheck --check-prefix=CHECK-11 %s
-// RUN: mlir-opt -convert-loops-to-gpu -gpu-block-dims=2 -gpu-thread-dims=2 %s | FileCheck --check-prefix=CHECK-22 %s
+// RUN: mlir-opt -convert-loops-to-gpu="gpu-block-dims=1 gpu-thread-dims=1" %s | FileCheck --check-prefix=CHECK-11 %s
+// RUN: mlir-opt -convert-loops-to-gpu="gpu-block-dims=2 gpu-thread-dims=2" %s | FileCheck --check-prefix=CHECK-22 %s
 
 // CHECK-11-LABEL: @step_1
 // CHECK-22-LABEL: @step_1
diff --git a/mlir/test/Conversion/LoopsToGPU/step_positive.mlir b/mlir/test/Conversion/LoopsToGPU/step_positive.mlir
--- a/mlir/test/Conversion/LoopsToGPU/step_positive.mlir
+++ b/mlir/test/Conversion/LoopsToGPU/step_positive.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt -convert-loops-to-gpu -gpu-block-dims=1 -gpu-thread-dims=1 %s | FileCheck %s
+// RUN: mlir-opt -convert-loops-to-gpu="gpu-block-dims=1 gpu-thread-dims=1" %s | FileCheck %s
 
 // CHECK-LABEL: @step_var
 func @step_var(%A : memref<?x?xf32>, %B : memref<?x?xf32>) {
diff --git a/mlir/test/Dialect/Linalg/promote.mlir b/mlir/test/Dialect/Linalg/promote.mlir
--- a/mlir/test/Dialect/Linalg/promote.mlir
+++ b/mlir/test/Dialect/Linalg/promote.mlir
@@ -1,5 +1,5 @@
 // RUN: mlir-opt %s -linalg-promote-subviews | FileCheck %s
-// RUN: mlir-opt %s -linalg-promote-subviews -test-linalg-promote-dynamic | FileCheck %s --check-prefix=DYNAMIC
+// RUN: mlir-opt %s -linalg-promote-subviews="test-promote-dynamic" | FileCheck %s --check-prefix=DYNAMIC
 
 #map0 = affine_map<(d0, d1)[s0, s1] -> (d0 * s1 + s0 + d1)>
 #map1 = affine_map<(d0) -> (d0 + 2)>
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 | FileCheck %s -check-prefix=TILE-2
-// RUN: mlir-opt %s -linalg-tile -linalg-tile-sizes=0,2 | FileCheck %s -check-prefix=TILE-02
-// RUN: mlir-opt %s -linalg-tile -linalg-tile-sizes=0,0,2 | FileCheck %s -check-prefix=TILE-002
-// RUN: mlir-opt %s -linalg-tile -linalg-tile-sizes=2,3,4 | FileCheck %s -check-prefix=TILE-234
+// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2" | FileCheck %s -check-prefix=TILE-2
+// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=0,2" | FileCheck %s -check-prefix=TILE-02
+// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=0,0,2" | FileCheck %s -check-prefix=TILE-002
+// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,3,4" | 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/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="linalg-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: #[[S0x10p90:.*]] = affine_map<()[s0] -> (s0 * 10 + 90)>
diff --git a/mlir/test/Dialect/Linalg/tile_indexed_generic.mlir b/mlir/test/Dialect/Linalg/tile_indexed_generic.mlir
--- a/mlir/test/Dialect/Linalg/tile_indexed_generic.mlir
+++ b/mlir/test/Dialect/Linalg/tile_indexed_generic.mlir
@@ -1,6 +1,6 @@
-// RUN: mlir-opt %s -linalg-tile -linalg-tile-sizes=10,25 | FileCheck %s -check-prefix=TILE-10n25
-// RUN: mlir-opt %s -linalg-tile -linalg-tile-sizes=25,0 | FileCheck %s -check-prefix=TILE-25n0
-// RUN: mlir-opt %s -linalg-tile -linalg-tile-sizes=0,25 | FileCheck %s -check-prefix=TILE-0n25
+// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=10,25" | FileCheck %s -check-prefix=TILE-10n25
+// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=25,0" | FileCheck %s -check-prefix=TILE-25n0
+// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=0,25" | FileCheck %s -check-prefix=TILE-0n25
 
 #id_1d = affine_map<(i) -> (i)>
 #pointwise_1d_trait = {
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 --dump-input-on-failure
-// RUN: mlir-opt %s -linalg-tile-to-parallel-loops -linalg-tile-sizes=0,2 | FileCheck %s -check-prefix=TILE-02 --dump-input-on-failure
-// RUN: mlir-opt %s -linalg-tile-to-parallel-loops -linalg-tile-sizes=0,0,2 | FileCheck %s -check-prefix=TILE-002 --dump-input-on-failure
-// RUN: mlir-opt %s -linalg-tile-to-parallel-loops -linalg-tile-sizes=2,3,4 | FileCheck %s -check-prefix=TILE-234 --dump-input-on-failure
+// RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=2" | FileCheck %s -check-prefix=TILE-2 --dump-input-on-failure
+// RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=0,2" | FileCheck %s -check-prefix=TILE-02 --dump-input-on-failure
+// RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=0,0,2" | FileCheck %s -check-prefix=TILE-002 --dump-input-on-failure
+// RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=2,3,4" | FileCheck %s -check-prefix=TILE-234 --dump-input-on-failure
 
 #id_2d = affine_map<(i, j) -> (i, j)>
 #pointwise_2d_trait = {
diff --git a/mlir/test/Transforms/Vectorize/vectorize_1d.mlir b/mlir/test/Transforms/Vectorize/vectorize_1d.mlir
--- a/mlir/test/Transforms/Vectorize/vectorize_1d.mlir
+++ b/mlir/test/Transforms/Vectorize/vectorize_1d.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt %s -affine-vectorize -virtual-vector-size 128 --test-fastest-varying=0 | FileCheck %s
+// RUN: mlir-opt %s -affine-vectorize="virtual-vector-size=128 test-fastest-varying=0" | FileCheck %s
 
 // Permutation maps used in vectorization.
 // CHECK: #[[map_proj_d0d1_0:map[0-9]+]] = affine_map<(d0, d1) -> (0)>
diff --git a/mlir/test/Transforms/Vectorize/vectorize_2d.mlir b/mlir/test/Transforms/Vectorize/vectorize_2d.mlir
--- a/mlir/test/Transforms/Vectorize/vectorize_2d.mlir
+++ b/mlir/test/Transforms/Vectorize/vectorize_2d.mlir
@@ -1,5 +1,5 @@
-// RUN: mlir-opt %s -affine-vectorize -virtual-vector-size 4 -virtual-vector-size 8 | FileCheck %s -check-prefix=VECT
-// RUN: mlir-opt %s -affine-vectorize -virtual-vector-size 32 -virtual-vector-size 256 --test-fastest-varying=1 --test-fastest-varying=0 | FileCheck %s
+// RUN: mlir-opt %s -affine-vectorize="virtual-vector-size=4,8" | FileCheck %s -check-prefix=VECT
+// RUN: mlir-opt %s -affine-vectorize="virtual-vector-size=32,256 test-fastest-varying=1,0" | FileCheck %s
 
 // Permutation maps used in vectorization.
 // CHECK-DAG: #[[map_id1:map[0-9]+]] = affine_map<(d0) -> (d0)>
diff --git a/mlir/test/Transforms/Vectorize/vectorize_3d.mlir b/mlir/test/Transforms/Vectorize/vectorize_3d.mlir
--- a/mlir/test/Transforms/Vectorize/vectorize_3d.mlir
+++ b/mlir/test/Transforms/Vectorize/vectorize_3d.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt %s -affine-vectorize -virtual-vector-size 32 -virtual-vector-size 64 -virtual-vector-size 256 --test-fastest-varying=2 --test-fastest-varying=1 --test-fastest-varying=0 | FileCheck %s
+// RUN: mlir-opt %s -affine-vectorize="virtual-vector-size=32,64,256 test-fastest-varying=2,1,0" | FileCheck %s
 
 // Permutation maps used in vectorization.
 // CHECK: #[[map_proj_d0d1d2_d0d1d2:map[0-9]+]] = affine_map<(d0, d1, d2) -> (d0, d1, d2)>
diff --git a/mlir/test/Transforms/Vectorize/vectorize_outer_loop_2d.mlir b/mlir/test/Transforms/Vectorize/vectorize_outer_loop_2d.mlir
--- a/mlir/test/Transforms/Vectorize/vectorize_outer_loop_2d.mlir
+++ b/mlir/test/Transforms/Vectorize/vectorize_outer_loop_2d.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt %s -affine-vectorize -virtual-vector-size 32 -virtual-vector-size 256 --test-fastest-varying=2 --test-fastest-varying=0 | FileCheck %s
+// RUN: mlir-opt %s -affine-vectorize="virtual-vector-size=32,256 test-fastest-varying=2,0" | FileCheck %s
 
 // Permutation maps used in vectorization.
 // CHECK: #[[map_proj_d0d1d2_d0d2:map[0-9]+]] = affine_map<(d0, d1, d2) -> (d0, d2)>
diff --git a/mlir/test/Transforms/Vectorize/vectorize_outer_loop_transpose_2d.mlir b/mlir/test/Transforms/Vectorize/vectorize_outer_loop_transpose_2d.mlir
--- a/mlir/test/Transforms/Vectorize/vectorize_outer_loop_transpose_2d.mlir
+++ b/mlir/test/Transforms/Vectorize/vectorize_outer_loop_transpose_2d.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt %s -affine-vectorize -virtual-vector-size 32 -virtual-vector-size 256 --test-fastest-varying=0 --test-fastest-varying=2 | FileCheck %s
+// RUN: mlir-opt %s -affine-vectorize="virtual-vector-size=32,256 test-fastest-varying=0,2" | FileCheck %s
 
 // Permutation maps used in vectorization.
 // CHECK: #[[map_proj_d0d1d2_d2d0:map[0-9]+]] = affine_map<(d0, d1, d2) -> (d2, d0)>
diff --git a/mlir/test/Transforms/Vectorize/vectorize_transpose_2d.mlir b/mlir/test/Transforms/Vectorize/vectorize_transpose_2d.mlir
--- a/mlir/test/Transforms/Vectorize/vectorize_transpose_2d.mlir
+++ b/mlir/test/Transforms/Vectorize/vectorize_transpose_2d.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt %s -affine-vectorize -virtual-vector-size 32 -virtual-vector-size 256 --test-fastest-varying=0 --test-fastest-varying=1 | FileCheck %s
+// RUN: mlir-opt %s -affine-vectorize="virtual-vector-size=32,256 test-fastest-varying=0,1" | FileCheck %s
 
 // Permutation maps used in vectorization.
 // CHECK-DAG: #[[map_proj_d0d1d2_d2d1:map[0-9]+]] = affine_map<(d0, d1, d2) -> (d2, d1)>
diff --git a/mlir/test/mlir-cpu-runner/linalg_integration_test.mlir b/mlir/test/mlir-cpu-runner/linalg_integration_test.mlir
--- a/mlir/test/mlir-cpu-runner/linalg_integration_test.mlir
+++ b/mlir/test/mlir-cpu-runner/linalg_integration_test.mlir
@@ -2,8 +2,8 @@
 // RUN: mlir-opt %s -convert-linalg-to-loops -convert-linalg-to-llvm | mlir-cpu-runner -e dot -entry-point-result=f32 -shared-libs=%linalg_test_lib_dir/libcblas%shlibext,%linalg_test_lib_dir/libcblas_interface%shlibext | FileCheck %s
 // RUN: mlir-opt %s -convert-linalg-to-llvm | mlir-cpu-runner -e matmul -entry-point-result=f32 -shared-libs=%linalg_test_lib_dir/libcblas%shlibext,%linalg_test_lib_dir/libcblas_interface%shlibext | FileCheck %s
 // RUN: mlir-opt %s -convert-linalg-to-loops -convert-linalg-to-llvm | mlir-cpu-runner -e matmul -entry-point-result=f32 -shared-libs=%linalg_test_lib_dir/libcblas%shlibext,%linalg_test_lib_dir/libcblas_interface%shlibext | FileCheck %s
-// RUN: mlir-opt %s -linalg-tile -linalg-tile-sizes=2,3,4 -linalg-promote-subviews -convert-linalg-to-loops -convert-linalg-to-llvm | mlir-cpu-runner -e matmul -entry-point-result=f32 -shared-libs=%linalg_test_lib_dir/libcblas%shlibext,%linalg_test_lib_dir/libcblas_interface%shlibext | FileCheck %s
-// RUN: mlir-opt %s -linalg-tile -linalg-tile-sizes=2,3,4 -linalg-promote-subviews -convert-linalg-to-llvm | mlir-cpu-runner -e matmul -entry-point-result=f32 -shared-libs=%linalg_test_lib_dir/libcblas%shlibext,%linalg_test_lib_dir/libcblas_interface%shlibext | FileCheck %s
+// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,3,4" -linalg-promote-subviews -convert-linalg-to-loops -convert-linalg-to-llvm | mlir-cpu-runner -e matmul -entry-point-result=f32 -shared-libs=%linalg_test_lib_dir/libcblas%shlibext,%linalg_test_lib_dir/libcblas_interface%shlibext | FileCheck %s
+// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,3,4" -linalg-promote-subviews -convert-linalg-to-llvm | mlir-cpu-runner -e matmul -entry-point-result=f32 -shared-libs=%linalg_test_lib_dir/libcblas%shlibext,%linalg_test_lib_dir/libcblas_interface%shlibext | FileCheck %s
 
 #strided1D = affine_map<(d0) -> (d0)>
 #strided2D = affine_map<(d0, d1)[s0] -> (d0 * s0 + d1)>