[mlir][Vector] Enable masking for static shapes

[dcaballe]

Summary

Support for masking static shapes was already implemented in the past
but not enabled so this patch is just removing a pre-condition check and
adding some tests with static shapes.

[ThomasRaoux]

awesome!

mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp

assert(
               int64_t inputSize = std::get<1>(sizePair);
               return ShapedType::isDynamic(staticSize) ||
                      staticSize <= inputSize;
             }) &&
         "Input vector sizes must be greater than or equal to iteration space "
         "static sizes");
   }
 
-  // TODO: Masking is only supported for dynamic shapes so input vector sizes
-  // must be empty if the op is not dynamic.
-  if (!linalgOp.hasDynamicShape() && !inputVectorSizes.empty())
-    return failure();
-
   if (linalgOp.hasDynamicShape() &&
       failed(vectorizeDynamicLinalgOpPrecondition(linalgOp))) {
     LDBG("Dynamically-shaped op failed vectorization pre-conditions\n");
     return failure();
   }
 
   SmallVector<CustomVectorizationPrecondition> customPreconditions;
 
LogicalResult mlir::linalg::vectorize(RewriterBase &rewriter, LinalgOp linalgOp,
                                       ArrayRef<int64_t> inputVectorSizes,
                                       bool vectorizeNDExtract) {
   LDBG("Attempting to vectorize:\n" << linalgOp << "\n");
   LDBG("Input vector sizes: ");
   LLVM_DEBUG(llvm::interleaveComma(inputVectorSizes, llvm::dbgs()));
   LLVM_DEBUG(llvm::dbgs() << "\n");
 
   if (failed(vectorizeLinalgOpPrecondition(linalgOp, inputVectorSizes,
-                                           vectorizeNDExtract)))
+                                           vectorizeNDExtract))) {
+    LDBG("Vectorization pre-conditions failed\n");
     return failure();
+  }
 
   // Initialize vectorization state.
   VectorizationState state(rewriter);
   if (failed(state.initState(rewriter, linalgOp, inputVectorSizes))) {
     LDBG("Vectorization state couldn't be initialized\n");
     return failure();
   }
 

mlir/test/Dialect/Linalg/vectorization.mlir

 
 transform.sequence failures(propagate) {
 ^bb1(%arg1: !pdl.operation):
   %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!pdl.operation) -> !pdl.operation
   %1 = get_closest_isolated_parent %0 : (!pdl.operation) -> !pdl.operation
   %2 = transform.structured.vectorize %1
 }
 
+// -----
+
+func.func @vectorize_partial_dynamic_identity(%arg0: tensor<8x?xf32>,
+                                              %arg1: tensor<8x?xf32>,
+                                              %arg2: tensor<8x?xf32>) -> tensor<8x?xf32> {
+  %0 = linalg.generic { indexing_maps = [affine_map<(d0, d1) -> (d0, d1)>,
+                                         affine_map<(d0, d1) -> (d0, d1)>,
+                                         affine_map<(d0, d1) -> (d0, d1)>],
+                   iterator_types = ["parallel", "parallel"] }
+    ins(%arg0, %arg1 : tensor<8x?xf32>, tensor<8x?xf32>)
+    outs(%arg2 : tensor<8x?xf32>) {
+    ^bb(%in0: f32, %in1: f32, %out: f32) :
+      %0 = arith.addf %in0, %in1 : f32
+      linalg.yield %0 : f32
+    } -> tensor<8x?xf32>
+  return %0 : tensor<8x?xf32>
+}
+
+// CHECK-LABEL:   func.func @vectorize_partial_dynamic_identity(
+// CHECK-SAME:      %[[VAL_0:.*]]: tensor<8x?xf32>, %[[VAL_1:.*]]: tensor<8x?xf32>, %[[VAL_2:.*]]: tensor<8x?xf32>) -> tensor<8x?xf32> {
+// CHECK:           %[[VAL_3:.*]] = arith.constant 1 : index
+// CHECK:           %[[VAL_4:.*]] = tensor.dim %[[VAL_0]], %[[VAL_3]] : tensor<8x?xf32>
+// CHECK:           %[[VAL_5:.*]] = arith.constant 0 : index
+// CHECK:           %[[VAL_6:.*]] = arith.constant 0.000000e+00 : f32
+// CHECK:           %[[VAL_7:.*]] = arith.constant 8 : index
+// CHECK:           %[[VAL_8:.*]] = vector.create_mask %[[VAL_7]], %[[VAL_4]] : vector<8x32xi1>
+// CHECK:           %[[VAL_9:.*]] = vector.mask %[[VAL_8]] { vector.transfer_read %[[VAL_0]][%[[VAL_5]], %[[VAL_5]]], %[[VAL_6]] {in_bounds = [true, true]} : tensor<8x?xf32>, vector<8x32xf32> } : vector<8x32xi1> -> vector<8x32xf32>
+// CHECK:           %[[VAL_10:.*]] = arith.constant 0.000000e+00 : f32
+// CHECK:           %[[VAL_11:.*]] = vector.mask %[[VAL_8]] { vector.transfer_read %[[VAL_1]][%[[VAL_5]], %[[VAL_5]]], %[[VAL_10]] {in_bounds = [true, true]} : tensor<8x?xf32>, vector<8x32xf32> } : vector<8x32xi1> -> vector<8x32xf32>
+// CHECK:           %[[VAL_12:.*]] = arith.constant 0.000000e+00 : f32
+// CHECK:           %[[VAL_13:.*]] = vector.mask %[[VAL_8]] { vector.transfer_read %[[VAL_2]][%[[VAL_5]], %[[VAL_5]]], %[[VAL_12]] {in_bounds = [true, true]} : tensor<8x?xf32>, vector<8x32xf32> } : vector<8x32xi1> -> vector<8x32xf32>
+// CHECK:           %[[VAL_14:.*]] = arith.addf %[[VAL_9]], %[[VAL_11]] : vector<8x32xf32>
+// CHECK:           %[[VAL_15:.*]] = arith.constant 0 : index
+// CHECK:           %[[VAL_16:.*]] = vector.mask %[[VAL_8]] { vector.transfer_write %[[VAL_14]], %[[VAL_2]][%[[VAL_15]], %[[VAL_15]]] {in_bounds = [true, true]} : vector<8x32xf32>, tensor<8x?xf32> } : vector<8x32xi1> -> tensor<8x?xf32>
+
+
+transform.sequence failures(propagate) {
+^bb1(%arg1: !pdl.operation):
+  %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!pdl.operation) -> !pdl.operation
+  transform.structured.masked_vectorize %0 vector_sizes [8, 32]
+}
+
+// -----
+
+func.func @do_not_generate_masks(%arg0: tensor<8x32xf32>,
+                                 %arg1: tensor<8x32xf32>,
+                                 %arg2: tensor<8x32xf32>) -> tensor<8x32xf32> {
+  %0 = linalg.generic { indexing_maps = [affine_map<(d0, d1) -> (d0, d1)>,
+                                         affine_map<(d0, d1) -> (d0, d1)>,
+                                         affine_map<(d0, d1) -> (d0, d1)>],
+                   iterator_types = ["parallel", "parallel"] }
+    ins(%arg0, %arg1 : tensor<8x32xf32>, tensor<8x32xf32>)
+    outs(%arg2 : tensor<8x32xf32>) {
+    ^bb(%in0: f32, %in1: f32, %out: f32) :
+      %0 = arith.addf %in0, %in1 : f32
+      linalg.yield %0 : f32
+    } -> tensor<8x32xf32>
+  return %0 : tensor<8x32xf32>
+}
+
+// CHECK-LABEL: func.func @do_not_generate_masks
+// CHECK-NOT: vector.mask
+
+transform.sequence failures(propagate) {
+^bb1(%arg1: !pdl.operation):
+  %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!pdl.operation) -> !pdl.operation
+  transform.structured.masked_vectorize %0 vector_sizes [8, 32]
+}
+
+// -----
+
+func.func @vectorize_static_shape_with_mask(%arg0: tensor<8x30xf32>,
+                                            %arg1: tensor<8x30xf32>,
+                                            %arg2: tensor<8x30xf32>) -> tensor<8x30xf32> {
+  %0 = linalg.generic { indexing_maps = [affine_map<(d0, d1) -> (d0, d1)>,
+                                         affine_map<(d0, d1) -> (d0, d1)>,
+                                         affine_map<(d0, d1) -> (d0, d1)>],
+                   iterator_types = ["parallel", "parallel"] }
+    ins(%arg0, %arg1 : tensor<8x30xf32>, tensor<8x30xf32>)
+    outs(%arg2 : tensor<8x30xf32>) {
+    ^bb(%in0: f32, %in1: f32, %out: f32) :
+      %0 = arith.addf %in0, %in1 : f32
+      linalg.yield %0 : f32
+    } -> tensor<8x30xf32>
+  return %0 : tensor<8x30xf32>
+}
+
+// CHECK-LABEL:   func.func @vectorize_static_shape_with_mask(
+// CHECK-SAME:      %[[VAL_0:.*]]: tensor<8x30xf32>, %[[VAL_1:.*]]: tensor<8x30xf32>, %[[VAL_2:.*]]: tensor<8x30xf32>) -> tensor<8x30xf32> {
+// CHECK:           %[[VAL_3:.*]] = arith.constant 0 : index
+// CHECK:           %[[VAL_4:.*]] = arith.constant 0.000000e+00 : f32
+// CHECK:           %[[VAL_5:.*]] = arith.constant 8 : index
+// CHECK:           %[[VAL_6:.*]] = arith.constant 30 : index
+// CHECK:           %[[VAL_7:.*]] = vector.create_mask %[[VAL_5]], %[[VAL_6]] : vector<8x32xi1>
+// CHECK:           %[[VAL_8:.*]] = vector.mask %[[VAL_7]] { vector.transfer_read %[[VAL_0]][%[[VAL_3]], %[[VAL_3]]], %[[VAL_4]] {in_bounds = [true, true]} : tensor<8x30xf32>, vector<8x32xf32> } : vector<8x32xi1> -> vector<8x32xf32>
+// CHECK:           %[[VAL_9:.*]] = arith.constant 0.000000e+00 : f32
+// CHECK:           %[[VAL_10:.*]] = vector.mask %[[VAL_7]] { vector.transfer_read %[[VAL_1]][%[[VAL_3]], %[[VAL_3]]], %[[VAL_9]] {in_bounds = [true, true]} : tensor<8x30xf32>, vector<8x32xf32> } : vector<8x32xi1> -> vector<8x32xf32>
+// CHECK:           %[[VAL_11:.*]] = arith.constant 0.000000e+00 : f32
+// CHECK:           %[[VAL_12:.*]] = vector.mask %[[VAL_7]] { vector.transfer_read %[[VAL_2]][%[[VAL_3]], %[[VAL_3]]], %[[VAL_11]] {in_bounds = [true, true]} : tensor<8x30xf32>, vector<8x32xf32> } : vector<8x32xi1> -> vector<8x32xf32>
+// CHECK:           %[[VAL_13:.*]] = arith.addf %[[VAL_8]], %[[VAL_10]] : vector<8x32xf32>
+// CHECK:           %[[VAL_14:.*]] = arith.constant 0 : index
+// CHECK:           %[[VAL_15:.*]] = vector.mask %[[VAL_7]] { vector.transfer_write %[[VAL_13]], %[[VAL_2]][%[[VAL_14]], %[[VAL_14]]] {in_bounds = [true, true]} : vector<8x32xf32>, tensor<8x30xf32> } : vector<8x32xi1> -> tensor<8x30xf32>
+
+transform.sequence failures(propagate) {
+^bb1(%arg1: !pdl.operation):
+  %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!pdl.operation) -> !pdl.operation
+  transform.structured.masked_vectorize %0 vector_sizes [8, 32]
+}