static SmallVector<Value, 4>
makeTiledShapes(OpBuilder &b, Location loc, LinalgOp linalgOp,
- ValueRange operands, AffineMap map, ValueRange ivs,
+ ArrayRef<Value> tiledOperands, AffineMap map, ValueRange ivs,
ValueRange tileSizes, ValueRange allShapeSizes) {
- assert(operands.size() == linalgOp.getShapedOperands().size());
assert(ivs.size() == static_cast<size_t>(llvm::count_if(
llvm::make_range(tileSizes.begin(), tileSizes.end()),
[](Value v) { return !isZero(v); })) &&
subShapeSizes.push_back(size - std_constant_index(1));
}
- auto *op = linalgOp.getOperation();
-
SmallVector<Value, 4> res;
- res.reserve(op->getNumOperands());
- for (auto en : llvm::enumerate(operands)) {
+ res.reserve(tiledOperands.size());
+ for (auto en : llvm::enumerate(tiledOperands)) {
Value shapedOp = en.value();
ShapedType shapedType = shapedOp.getType().cast<ShapedType>();
unsigned rank = shapedType.getRank();
LoopIndexToRangeIndexMap loopIndexToRangeIndex;
std::tie(loopRanges, loopIndexToRangeIndex) = makeTiledLoopRanges(
b, op.getLoc(), shapeSizesToLoopsMap, allShapeSizes, tileSizes);
+
SmallVector<Attribute, 4> iteratorTypes;
for (auto attr :
enumerate(op.iterator_types().cast<ArrayAttr>().getValue())) {
static void insertTilingPatterns(OwningRewritePatternList &patterns,
const LinalgTilingOptions &options,
MLIRContext *ctx) {
- RewritePatternList<
+ RewritePatternList<GenericOp, IndexedGenericOp,
#define GET_OP_LIST
#include "mlir/Dialect/Linalg/IR/LinalgStructuredOps.cpp.inc"
- >::insert(patterns, options, ctx);
+ >::insert(patterns, options, ctx);
}
static void applyTilingToLoopPatterns(LinalgTilingLoopType loopType,
-// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,3,4" | FileCheck %s
+// RUN: mlir-opt %s -linalg-tile="linalg-tile-sizes=2,3,4" -split-input-file | FileCheck %s
// CHECK-LABEL: func @matmul_tensors(
// CHECK-SAME: %[[TA:[0-9a-z]+]]: tensor<?x?xf32>
// CHECK: return %[[TD0]] : tensor<?x?xf32>
return %0 : tensor<?x?xf32>
}
+
+// -----
+
+func @generic_op_tensors(
+ %arg0 : tensor<?x?x?xf32>, %arg1 : tensor<?x?x?xf32>) -> tensor<?x?x?xf32> {
+ %c0 = constant 0 : index
+ %c1 = constant 1 : index
+ %c2 = constant 2 : index
+ %0 = dim %arg0, %c0 : tensor<?x?x?xf32>
+ %1 = dim %arg0, %c1 : tensor<?x?x?xf32>
+ %2 = dim %arg0, %c2 : tensor<?x?x?xf32>
+ %3 = linalg.init_tensor [%0, %1, %2] : tensor<?x?x?xf32>
+ %4 = linalg.generic
+ {indexing_maps = [affine_map<(d0, d1, d2) -> (d0, d1, d2)>,
+ affine_map<(d0, d1, d2) -> (d0, d2, d1)>,
+ affine_map<(d0, d1, d2) -> (d2, d1, d0)>],
+ iterator_types = ["parallel", "parallel", "parallel"]}
+ ins(%arg0, %arg1 : tensor<?x?x?xf32>, tensor<?x?x?xf32>)
+ outs(%3 : tensor<?x?x?xf32>) {
+ ^bb0(%arg2 : f32, %arg3: f32, %arg4: f32):
+ %5 = addf %arg2, %arg3 : f32
+ linalg.yield %5 : f32
+ } -> tensor<?x?x?xf32>
+ return %4 : tensor<?x?x?xf32>
+}
+
+// CHECK-LABEL: func @generic_op_tensors
+// CHECK-SAME: %[[ARG0:[a-zA-Z0-9_]+]]: tensor<?x?x?xf32>
+// CHECK-SAME: %[[ARG1:[a-zA-Z0-9_]+]]: tensor<?x?x?xf32>
+// CHECK: %[[INIT:.+]] = linalg.init_tensor
+// CHECK: %[[TD0:.+]] = scf.for %{{.+}} to %{{.+}} step %{{.+}} iter_args(%[[TC0:.+]] = %[[INIT]]) -> (tensor<?x?x?xf32>) {
+// CHECK: %[[TD1:.+]] = scf.for %{{.+}} to %{{.+}} step %{{.+}} iter_args(%[[TC1:.+]] = %[[TC0]]) -> (tensor<?x?x?xf32>) {
+// CHECK: %[[TD2:.+]] = scf.for %{{.+}} to %{{.+}} step %{{.+}} iter_args(%[[TC2:.+]] = %[[TC1]]) -> (tensor<?x?x?xf32>) {
+// CHECK: %[[STARG0:.+]] = subtensor %[[ARG0]][{{.+}}] : tensor<?x?x?xf32> to tensor<?x?x?xf32>
+// CHECK: %[[STARG1:.+]] = subtensor %[[ARG1]][{{.+}}] : tensor<?x?x?xf32> to tensor<?x?x?xf32>
+// CHECK: %[[STARG2:.+]] = subtensor %[[TC2]][{{.+}}] : tensor<?x?x?xf32> to tensor<?x?x?xf32>
+// CHECK: %[[STRETURN:.+]] = linalg.generic
+// CHECK-SAME: ins(%[[STARG0]], %[[STARG1]] : tensor<?x?x?xf32>, tensor<?x?x?xf32>)
+// CHECK-SAME: outs(%[[STARG2]] : tensor<?x?x?xf32>)
+// CHECK: %[[TD:.+]] = subtensor_insert %[[STRETURN]] into %[[TC2]]
+// CHECK: scf.yield %[[TD]]
+// CHECK: }
+// CHECK: scf.yield %[[TD2]]
+// CHECK: }
+// CHECK: scf.yield %[[TD1]]
+// CHECK: }
+// CHECK: return %[[TD0]]
+
+// -----
+
+func @indexed_generic_op_tensors(
+ %arg0 : tensor<?x?x?xf32>, %arg1 : tensor<?x?x?xf32>) -> tensor<?x?x?xf32> {
+ %c0 = constant 0 : index
+ %c1 = constant 1 : index
+ %c2 = constant 2 : index
+ %0 = dim %arg0, %c0 : tensor<?x?x?xf32>
+ %1 = dim %arg0, %c1 : tensor<?x?x?xf32>
+ %2 = dim %arg0, %c2 : tensor<?x?x?xf32>
+ %3 = linalg.init_tensor [%0, %1, %2] : tensor<?x?x?xf32>
+ %4 = linalg.indexed_generic
+ {indexing_maps = [affine_map<(d0, d1, d2) -> (d0, d1, d2)>,
+ affine_map<(d0, d1, d2) -> (d0, d2, d1)>,
+ affine_map<(d0, d1, d2) -> (d2, d1, d0)>],
+ iterator_types = ["parallel", "parallel", "parallel"]}
+ ins(%arg0, %arg1 : tensor<?x?x?xf32>, tensor<?x?x?xf32>)
+ outs(%3 : tensor<?x?x?xf32>) {
+ ^bb0(%arg2 : index, %arg3 : index, %arg4 : index, %arg5 : f32, %arg6: f32, %arg7: f32):
+ %5 = addf %arg5, %arg6 : f32
+ linalg.yield %5 : f32
+ } -> tensor<?x?x?xf32>
+ return %4 : tensor<?x?x?xf32>
+}
+
+// CHECK-LABEL: func @indexed_generic_op_tensors
+// CHECK-SAME: %[[ARG0:[a-zA-Z0-9_]+]]: tensor<?x?x?xf32>
+// CHECK-SAME: %[[ARG1:[a-zA-Z0-9_]+]]: tensor<?x?x?xf32>
+// CHECK: %[[INIT:.+]] = linalg.init_tensor
+// CHECK: %[[TD0:.+]] = scf.for %{{.+}} to %{{.+}} step %{{.+}} iter_args(%[[TC0:.+]] = %[[INIT]]) -> (tensor<?x?x?xf32>) {
+// CHECK: %[[TD1:.+]] = scf.for %{{.+}} to %{{.+}} step %{{.+}} iter_args(%[[TC1:.+]] = %[[TC0]]) -> (tensor<?x?x?xf32>) {
+// CHECK: %[[TD2:.+]] = scf.for %{{.+}} to %{{.+}} step %{{.+}} iter_args(%[[TC2:.+]] = %[[TC1]]) -> (tensor<?x?x?xf32>) {
+// CHECK: %[[STARG0:.+]] = subtensor %[[ARG0]][{{.+}}] : tensor<?x?x?xf32> to tensor<?x?x?xf32>
+// CHECK: %[[STARG1:.+]] = subtensor %[[ARG1]][{{.+}}] : tensor<?x?x?xf32> to tensor<?x?x?xf32>
+// CHECK: %[[STARG2:.+]] = subtensor %[[TC2]][{{.+}}] : tensor<?x?x?xf32> to tensor<?x?x?xf32>
+// CHECK: %[[STRETURN:.+]] = linalg.indexed_generic
+// CHECK-SAME: ins(%[[STARG0]], %[[STARG1]] : tensor<?x?x?xf32>, tensor<?x?x?xf32>)
+// CHECK-SAME: outs(%[[STARG2]] : tensor<?x?x?xf32>)
+// CHECK: %[[TD:.+]] = subtensor_insert %[[STRETURN]] into %[[TC2]]
+// CHECK: scf.yield %[[TD]]
+// CHECK: }
+// CHECK: scf.yield %[[TD2]]
+// CHECK: }
+// CHECK: scf.yield %[[TD1]]
+// CHECK: }
+// CHECK: return %[[TD0]]