format and add test

Author: srcarroll

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

@@ -109,8 +109,9 @@ static bool isOpOperandCanBeDroppedAfterFusedLinalgs(
 /// * There is a chance that the implementation of the transformation does not
 /// agree with the result of this method. This function gives a prediction based
 /// on an optimized fusion.
-llvm::SmallDenseSet<int> mlir::linalg::getPreservedProducerResults(
-    LinalgOp producer, LinalgOp consumer, OpOperand *fusedOperand) {
+llvm::SmallDenseSet<int>
+mlir::linalg::getPreservedProducerResults(LinalgOp producer, LinalgOp consumer,
+                                          OpOperand *fusedOperand) {
   llvm::SmallDenseSet<int> preservedProducerResults;
   llvm::SmallVector<OpOperand *> opOperandsToIgnore;
 
@@ -416,14 +417,9 @@ mlir::linalg::fuseElementwiseOps(RewriterBase &rewriter,
   }
 
   // Generate the fused op.
-  // auto fusedOp = cloneWithoutRegions(rewriter, consumer,
-  //                              fusedResultTypes, fusedInputOperands);
-  // fusedOp.setIndexingMapsAttr(idxMap);
-  // fusedOp.setIteratorTypesAttr(itTp);
   auto fusedOp = rewriter.create<GenericOp>(
       consumer.getLoc(), fusedResultTypes, fusedInputOperands,
-      fusedOutputOperands, fusedIndexMaps,
-      consumer.getIteratorTypesArray());
+      fusedOutputOperands, fusedIndexMaps, consumer.getIteratorTypesArray());
   if (!fusedOp.getShapesToLoopsMap()) {
     // Fused op has invalid indexing maps. Typically this means something is off
     // in the input, but going ahead here would result in verification errors.

mlir/test/Dialect/Linalg/fusion-elementwise.mlir

@@ -59,3 +59,24 @@ func.func @handle_unused_operands(%arg0: tensor<8xf32>, %arg1: tensor<8xf32>) ->
 //       CHECK:   %[[FUSED_OP:.+]] = linalg.generic
 //  CHECK-SAME:       outs(%[[EMPTY]] :
 //   CHECK-NOT:   linalg.generic
+
+// -----
+
+func.func @map_ops(%in1: tensor<8xf32>, %in2: tensor<8xf32>) -> tensor<8xf32> {
+    %fill = tensor.empty() : tensor<8xf32>
+    %add = linalg.map {arith.addf} ins(%in1, %in2: tensor<8xf32>, tensor<8xf32>) outs(%fill: tensor<8xf32>)
+    %mapped_65 = linalg.map { math.sqrt } ins(%add : tensor<8xf32>) outs(%fill : tensor<8xf32>)
+    return %mapped_65 : tensor<8xf32>
+}
+
+// CHECK-LABEL: func @map_ops
+//  CHECK-SAME:   %[[ARG0:[a-zA-Z0-9]+]]: tensor<8xf32>
+//  CHECK-SAME:   %[[ARG1:[a-zA-Z0-9]+]]: tensor<8xf32>
+//       CHECK:   %[[EMPTY:.+]] = tensor.empty() : tensor<8xf32>
+//       CHECK:   %[[FUSED_OP:.+]] = linalg.generic
+//  CHECK-SAME:       ins(%[[ARG0]], %[[ARG1]] : {{.}}) outs(%[[EMPTY]] :
+//  CHECK-NEXT:   ^bb0(%[[IN0:.*]]: f32, %[[IN1:.*]]: f32, %[[OUT:.*]]: f32):
+//  CHECK-NEXT:     %[[ADD:.*]] = arith.addf %[[IN0]], %[[IN1]]
+//  CHECK-NEXT:     %[[SQRT:.*]] = math.sqrt %[[ADD]]
+//  CHECK-NEXT:     linalg.yield %[[SQRT]] 
+//   CHECK-NOT:   linalg.generic