[mlir] Add verification for `linalg.tiled_loop` op.

[gysit]

mlir/lib/Dialect/Linalg/IR/LinalgOps.cpp

1989

nit: are provided?

mlir/lib/Dialect/Linalg/IR/LinalgOps.cpp

if (op.getNumOperands() != 1)
              << op->getNumOperands() << ")";
     if (op.getOperand(0).getType() !=
         padTensorOp.getType().cast<ShapedType>().getElementType())
       return op.emitOpError("expected yield type to match shape element type");
     return success();
   }
 
   if (auto tiledLoopOp = dyn_cast<linalg::TiledLoopOp>(parentOp)) {
+    // Check if output args with tensor types match results types.
+    SmallVector<Value, 2> tensorOuts;
+    llvm::copy_if(
+        tiledLoopOp.outputs(), std::back_inserter(tensorOuts),
+        [&](Value out) { return out.getType().isa<RankedTensorType>(); });
+    if (tensorOuts.size() != op.values().size())
+      return op.emitOpError("expected number of tensor output args = ")
+             << tensorOuts.size() << " to match the number of yield operands = "
+             << op.values().size();
+
+    TypeRange tensorTypes(llvm::makeArrayRef(tensorOuts));
+    for (auto &item :
+         llvm::enumerate(llvm::zip(tensorTypes, op.getOperandTypes()))) {
+      Type outType, resultType;
+      unsigned index = item.index();
+      std::tie(outType, resultType) = item.value();
+      if (outType != resultType)
+        return op.emitOpError("expected yield operand ")
+               << index << " with type = " << resultType
+               << " to match output arg type = " << outType;
+    }
     return success();
   }
   return op.emitOpError("expected parent op with LinalgOp interface");
 }
 
 //===----------------------------------------------------------------------===//
 // TiledLoopOp
 //===----------------------------------------------------------------------===//
for (auto *op : ops)
     op->moveBefore(*this);
   return success();
 }
 
 bool TiledLoopOp::isDefinedOutsideOfLoop(Value value) {
   return !region().isAncestor(value.getParentRegion());
 }
 
-static LogicalResult verify(TiledLoopOp op) { return success(); }
+static LogicalResult verify(TiledLoopOp op) {
+  // Check if iterator types is provided for every loop dimension.
+  if (op.iterator_types().size() != op.getNumLoops())
+    return op.emitOpError("expected iterator types array attribute size = ")
+           << op.iterator_types().size()
+           << " to match the number of loops = " << op.getNumLoops();
+  return success();
+}
 
 namespace {
 
 // Folds away TiledLoopOp output tensors when the following conditions are met:
 // * result of `linalg.tiled_loop` has no uses
 // * output tensor is the argument of `linalg.yield`
 //
 // Example:

mlir/test/Dialect/Linalg/invalid.mlir

 func @invalid_static_2d_conv(%input : memref<1x3x4x2xf32>, %filter: memref<3x2x2x1xf32>, %output: memref<1x2x3x1xf32>) {
   // expected-error @+1 {{inferred shaped operand #0 has shape's dimension #1 to be greater than or equal to 4, but found 3}}
   linalg.conv_2d_input_nhwc_filter_hwcf
     { dilations = dense<1> : tensor<2xi64>, strides = dense<1> : tensor<2xi64>}
     ins(%input, %filter : memref<1x3x4x2xf32>, memref<3x2x2x1xf32>)
     outs(%output : memref<1x2x3x1xf32>)
   return
 }
+
+// -----
+
+#map0 = affine_map<(d0) -> (24, -d0 + 192)>
+#map1 = affine_map<(d0, d1)[s0] -> (d0 * 192 + s0 + d1)>
+#map2 = affine_map<(d0) -> (16, -d0 + 192)>
+
+func private @foo(%A: memref<192x192xf32>, %B: memref<192x192xf32>,
+                  %C: memref<192x192xf32>) -> ()
+
+func @tiled_loop_incorrent_num_yield_operands(%A: memref<192x192xf32>,
+    %B: memref<192x192xf32>, %C: memref<192x192xf32>,
+    %C_tensor: tensor<192x192xf32>) {
+  %c24 = constant 24 : index
+  %c0 = constant 0 : index
+  %c192 = constant 192 : index
+  %0 = linalg.tiled_loop (%i, %j) = (%c0, %c0) to (%c192, %c192)
+      step (%c24, %c24)
+      ins (%A, %B: memref<192x192xf32>, memref<192x192xf32>)
+      outs (%C_tensor, %C :tensor<192x192xf32>, memref<192x192xf32>) {
+        call @foo(%A, %B, %C)
+          : (memref<192x192xf32>, memref<192x192xf32>, memref<192x192xf32>)-> ()
+    // expected-error @+1 {{expected number of tensor output args = 1 to match the number of yield operands = 0}}
+    linalg.yield
+  }
+  return
+}
+
+// -----
+
+#map0 = affine_map<(d0) -> (24, -d0 + 192)>
+#map1 = affine_map<(d0, d1)[s0] -> (d0 * 192 + s0 + d1)>
+#map2 = affine_map<(d0) -> (16, -d0 + 192)>
+
+func private @foo(%A: memref<192x192xf32>, %B: memref<192x192xf32>,
+                  %C: memref<192x192xf32>) -> tensor<f32>
+
+func @tiled_loop_incorrent_yield_operand_type(%A: memref<192x192xf32>,
+    %B: memref<192x192xf32>, %C: memref<192x192xf32>,
+    %C_tensor: tensor<192x192xf32>) {
+  %c24 = constant 24 : index
+  %c0 = constant 0 : index
+  %c192 = constant 192 : index
+  %0 = linalg.tiled_loop (%i, %j) = (%c0, %c0) to (%c192, %c192)
+      step (%c24, %c24)
+      ins (%A, %B: memref<192x192xf32>, memref<192x192xf32>)
+      outs (%C_tensor, %C :tensor<192x192xf32>, memref<192x192xf32>) {
+        %1 = call @foo(%A, %B, %C)
+          : (memref<192x192xf32>, memref<192x192xf32>, memref<192x192xf32>)-> tensor<f32>
+    // expected-error @+1 {{expected yield operand 0 with type = 'tensor<f32>' to match output arg type = 'tensor<192x192xf32>}}
+    linalg.yield %1 : tensor<f32>
+  }
+  return
+}
+
+// -----
+
+#map0 = affine_map<(d0) -> (24, -d0 + 192)>
+#map1 = affine_map<(d0, d1)[s0] -> (d0 * 192 + s0 + d1)>
+#map2 = affine_map<(d0) -> (16, -d0 + 192)>
+
+func private @foo(%A: memref<192x192xf32>, %B: memref<192x192xf32>,
+                  %C: memref<192x192xf32>) -> ()
+
+func @tiled_loop_incorrent_iterator_types_count(%A: memref<192x192xf32>,
+    %B: memref<192x192xf32>, %C: memref<192x192xf32>,
+    %C_tensor: tensor<192x192xf32>) {
+  %c24 = constant 24 : index
+  %c0 = constant 0 : index
+  %c192 = constant 192 : index
+  // expected-error @+1 {{expected iterator types array attribute size = 1 to match the number of loops = 2}}
+  %0 = "linalg.tiled_loop"(%c0, %c0, %c192, %c192, %c24, %c24, %A, %B, %C_tensor, %C) ( {
+    ^bb0(%arg4: index, %arg5: index):  // no predecessors
+      call @foo(%A, %B, %C)
+          : (memref<192x192xf32>, memref<192x192xf32>, memref<192x192xf32>)-> ()
+      linalg.yield %C_tensor : tensor<192x192xf32>
+    }) {
+      iterator_types = ["parallel"],
+      operand_segment_sizes = dense<2> : vector<5xi32>
+    } : (index, index, index, index, index, index, memref<192x192xf32>,
+      memref<192x192xf32>, tensor<192x192xf32>, memref<192x192xf32>
+    ) -> tensor<192x192xf32>
+  return
+}