[MLIR][Linalg] Introduce transpose/broadcast semantic to linalg.batch_reduce_matmul.

This patch exposes broadcast and transpose semantics on
'batch_reduce_matmul'. This is the last one in continuation of
other two variant of matmul ops.

The broadcast and transpose semantic are as follows:

Broadcast and Transpose semantics can be appiled by specifying the
explicit attribute 'indexing_maps' as shown below. This is a list
attribute, so must include maps for all arguments if specified.

    Example Transpose:
    ```
    linalg.batch_reduce_matmul indexing_maps = [
       affine_map<(d0, d1, d2, d3) -> (d0, d3, d1)>, // transpose
       affine_map<(d0, d1, d2, d3) -> (d0, d3, d2)>,
       affine_map<(d0, d1, d2, d3) -> (d1, d2)>
       ]
          ins(%arg0, %arg1 : memref<2x5x3xf32>,memref<2x5x7xf32>)
          outs(%arg2: memref<3x7xf32>)
    ```

    Example Broadcast:
    ```
    linalg.batch_reduce_matmul indexing_maps = [
       affine_map<(d0, d1, d2, d3) -> (d3)>,         // broadcast
       affine_map<(d0, d1, d2, d3) -> (d0, d3, d2)>,
       affine_map<(d0, d1, d2, d3) -> (d1, d2)>
       ]
          ins(%arg0, %arg1 : memref<5xf32>, memref<2x5x7xf32>)
          outs(%arg2: memref<3x7xf32>)
    ```

    Example Broadcast and Transpose:
    ```
    linalg.batch_reduce_matmul indexing_maps = [
       affine_map<(d0, d1, d2, d3) -> (d1, d3)>,     // broadcast
       affine_map<(d0, d1, d2, d3) -> (d0, d2, d3)>, // transpose
       affine_map<(d0, d1, d2, d3) -> (d1, d2)>
       ]
          ins(%arg0, %arg1 : memref<3x5xf32>, memref<2x7x5xf32>)
          outs(%arg2: memref<3x7xf32>)
    ```

RFCs and related PR:
https://discourse.llvm.org/t/rfc-linalg-opdsl-constant-list-attribute-definition/80149
https://discourse.llvm.org/t/rfc-op-explosion-in-linalg/82863
https://discourse.llvm.org/t/rfc-mlir-linalg-operation-tree/83586
llvm#115319
llvm#122275

Author: shahidact

mlir/include/mlir/Dialect/Linalg/IR/LinalgNamedStructuredOps.yaml

@@ -1717,76 +1717,6 @@ structured_op: !LinalgStructuredOpConfig
                     - !ScalarExpression
                       scalar_arg: BZp
 --- !LinalgOpConfig
-metadata: !LinalgOpMetadata
-  name: batch_reduce_matmul
-  cpp_class_name: BatchReduceMatmulOp
-  doc: |-
-    Performs a batch-reduce matrix multiplication of two 3D inputs.
-    The partial multiplication results are reduced into a 2D output.
-
-    Numeric casting is performed on the operands to the inner multiply, promoting
-    them to the same data type as the accumulator/output.
-  implements:
-  - LinalgContractionOpInterface
-structured_op: !LinalgStructuredOpConfig
-  args:
-  - !LinalgOperandDefConfig
-    name: A
-    kind: input_tensor
-    type_var: T1
-    shape_map: affine_map<()[s0, s1, s2, s3] -> (s0, s1, s2)>
-  - !LinalgOperandDefConfig
-    name: B
-    kind: input_tensor
-    type_var: T2
-    shape_map: affine_map<()[s0, s1, s2, s3] -> (s0, s2, s3)>
-  - !LinalgOperandDefConfig
-    name: C
-    kind: output_tensor
-    type_var: U
-    shape_map: affine_map<()[s0, s1, s2, s3] -> (s1, s3)>
-  indexing_maps: !LinalgIndexingMapsConfig
-    static_indexing_maps:
-    - affine_map<(d0, d1, d2, d3)[s0, s1, s2, s3] -> (d0, d1, d3)>
-    - affine_map<(d0, d1, d2, d3)[s0, s1, s2, s3] -> (d0, d3, d2)>
-    - affine_map<(d0, d1, d2, d3)[s0, s1, s2, s3] -> (d1, d2)>
-  iterator_types:
-  - reduction
-  - parallel
-  - parallel
-  - reduction
-  assignments:
-  - !ScalarAssign
-    arg: C
-    value: !ScalarExpression
-      scalar_fn:
-        kind: binary
-        fn_name: add
-        operands:
-        - !ScalarExpression
-          scalar_arg: C
-        - !ScalarExpression
-          scalar_fn:
-            kind: binary
-            fn_name: mul
-            operands:
-            - !ScalarExpression
-              scalar_fn:
-                kind: type
-                fn_name: cast_signed
-                type_var: U
-                operands:
-                - !ScalarExpression
-                  scalar_arg: A
-            - !ScalarExpression
-              scalar_fn:
-                kind: type
-                fn_name: cast_signed
-                type_var: U
-                operands:
-                - !ScalarExpression
-                  scalar_arg: B
---- !LinalgOpConfig
 metadata: !LinalgOpMetadata
   name: matvec
   cpp_class_name: MatvecOp

mlir/include/mlir/Dialect/Linalg/IR/LinalgStructuredOps.td

@@ -1065,6 +1065,137 @@ def BatchMatmulOp : LinalgStructuredBase_Op<"batch_matmul", !listconcat([AttrSiz
 }
 
 
+//===----------------------------------------------------------------------===//
+// Op definition for BatchReduceMatmulOp
+//===----------------------------------------------------------------------===//
+
+def BatchReduceMatmulOp : LinalgStructuredBase_Op<"batch_reduce_matmul", [
+                          AttrSizedOperandSegments,
+                          LinalgContractionOpInterface]> {
+    
+  let summary = [{Performs a batch-reduce matrix multiplication of two 3D inputs.
+The partial multiplication results are reduced into a 2D output.}];
+  let description = [{
+    Numeric casting is performed on the operands to the inner multiply, promoting
+    them to the same data type as the accumulator/output.
+
+    Broadcast and Transpose semantics can be appiled by specifying the explicit attribute
+    'indexing_maps' as shown below. This is a list attribute, so must include maps for all
+    arguments if specified.
+
+    Example Transpose:
+    ```
+    linalg.batch_reduce_matmul indexing_maps = [
+                   affine_map<(d0, d1, d2, d3) -> (d0, d3, d1)>, // transpose
+                   affine_map<(d0, d1, d2, d3) -> (d0, d3, d2)>,
+                   affine_map<(d0, d1, d2, d3) -> (d1, d2)>
+                   ]
+                   ins(%arg0, %arg1 : memref<2x5x3xf32>,memref<2x5x7xf32>)
+                   outs(%arg2: memref<3x7xf32>)
+    ```
+
+    Example Broadcast:
+    ```
+    linalg.batch_reduce_matmul indexing_maps = [
+                       affine_map<(d0, d1, d2, d3) -> (d3)>,         // broadcast
+                       affine_map<(d0, d1, d2, d3) -> (d0, d3, d2)>,
+                       affine_map<(d0, d1, d2, d3) -> (d1, d2)>
+                     ]
+                     ins(%arg0, %arg1 : memref<5xf32>, memref<2x5x7xf32>)
+                     outs(%arg2: memref<3x7xf32>)
+    ```
+
+    Example Broadcast and Transpose:
+    ```
+    linalg.batch_reduce_matmul indexing_maps = [
+                       affine_map<(d0, d1, d2, d3) -> (d1, d3)>,     // broadcast
+                       affine_map<(d0, d1, d2, d3) -> (d0, d2, d3)>, // transpose
+                       affine_map<(d0, d1, d2, d3) -> (d1, d2)>
+                     ]
+                     ins(%arg0, %arg1 : memref<3x5xf32>, memref<2x7x5xf32>)
+                     outs(%arg2: memref<3x7xf32>)
+    ```
+    }];
+
+    let arguments = (ins
+      Variadic<AnyType>:$inputs,
+      Variadic<AnyShaped>:$outputs,
+      DefaultValuedOptionalAttr<
+        AffineMapArrayAttr,
+        "BatchReduceMatmulOp::getDefaultIndexingMaps($_builder.getContext())"
+      >:$indexing_maps,
+      DefaultValuedOptionalAttr<TypeFnAttr, "TypeFn::cast_signed">:$cast
+    );
+    let results = (outs Variadic<AnyRankedTensor>:$result_tensors);
+    let regions = (region AnyRegion:$region);
+
+    let skipDefaultBuilders = 1;
+    let builders = [
+      OpBuilder<
+      (ins "ValueRange":$inputs, "ValueRange":$outputs,
+            CArg<"ArrayRef<NamedAttribute>", "{}">:$attributes),
+      [{
+        buildBatchReduceMatmulOp($_builder, $_state, std::nullopt, inputs, outputs,
+          attributes, BatchReduceMatmulOp::getRegionBuilder(),
+          BatchReduceMatmulOp::getDefaultIndexingMaps($_builder.getContext()));
+      }]>,
+      OpBuilder<
+      (ins "TypeRange":$resultTensorTypes, "ValueRange":$inputs,
+            "ValueRange":$outputs,
+            CArg<"ArrayRef<NamedAttribute>", "{}">:$attributes),
+      [{
+        buildBatchReduceMatmulOp($_builder, $_state, resultTensorTypes,
+          inputs, outputs, attributes, BatchReduceMatmulOp::getRegionBuilder(),
+          BatchReduceMatmulOp::getDefaultIndexingMaps($_builder.getContext()));
+      }]>,
+      OpBuilder<
+      (ins "TypeRange":$resultTensorTypes, "ValueRange":$inputs,
+       "ValueRange":$outputs,
+       "Attribute":$cast, CArg<"ArrayRef<NamedAttribute>", "{}">:$attributes),
+      [{
+        $_state.addAttribute("cast", cast);
+        buildBatchReduceMatmulOp($_builder, $_state, resultTensorTypes, inputs, outputs,
+          attributes, BatchReduceMatmulOp::getRegionBuilder(),
+          BatchReduceMatmulOp::getDefaultIndexingMaps($_builder.getContext()));
+      }]>
+      
+    ];
+    let hasCustomAssemblyFormat = 1;
+    let hasFolder = 1;
+    let hasVerifier = 1;
+
+    let extraClassDeclaration = structuredOpsBaseDecls # [{
+      SmallVector<utils::IteratorType> getIteratorTypesArray();
+
+      /// Implements the block region builder.
+      static void regionBuilder(ImplicitLocOpBuilder &b,
+                                Block &block, ArrayRef<NamedAttribute> attrs);
+
+      /// Returns a list of AffineMap with the typical batch_reducematmul indexing charactristic.
+      static SmallVector<AffineMap> getDefaultIndexingMaps(MLIRContext *context);
+
+      /// Returns true if the given broadcast map \p bcastMap is valid for this op.
+      bool isValidLhsRhsBroadcastMap(AffineMap bcastMap, bool isLHS = true);
+
+      static std::function<void(ImplicitLocOpBuilder &,
+                                Block &, ArrayRef<NamedAttribute>)>
+      getRegionBuilder() {
+        return regionBuilder;
+      }
+
+      ::mlir::MutableOperandRange getDpsInitsMutable() {
+        return getOutputsMutable();
+      }
+
+      // Generic methods.
+      static unsigned getNumRegionArgs();
+      std::string getLibraryCallName();
+      bool hasDynamicIndexingMaps() { return true; };
+      /// Returns true if the user defined indexing maps are not equal to default maps.
+      bool hasUserDefinedMaps();
+    }];
+}
+
 //===----------------------------------------------------------------------===//
 // Named Linalg ops, implemented as a declarative configurations of generic ops.
 //===----------------------------------------------------------------------===//