[mlir][tosa] Remove tosa.identityn operator

[sjarus]

Summary

Removes the identityn operator from TOSA MLIR definition.
Removes TosaToLinAlg mappings

mlir/docs/Dialects/TOSA.md

 specification of the operation.
 
 ## TOSA Operator Rationale
 
 The general basis of selection of the operator set that constitutes TOSA is
 described in the TOSA specification document  under Section 1.3 Operator
 Selection. Explanation of the thinking behind some operators is listed here:
 
-### IDENTITYN
-
-tosa.IDENTITYN is used to form a list of Operator results during
-lowering of operations such as tf.Split from a sequence of tosa.SLICE
-ops.  If there are alternate ways to express this lowering without the
-tosa.IDENTITYN op, the tosa.IDENTITYN op could be removed from TOSA.
-
-```
-Value lower_split_op(Value %value, size_t axis, size_t
-num_split) { Value %output[]
-
-    size_t slice_size = %value.shape[axis] / num_split
-
-    for (int i = 0; i < num_split; i++) {
-        vector <size_t> begin_vals, size_vals
-
-        for (int j = 0; j < %value.rank; j++) {
-            if (j == axis) {
-               begin_vals.push_back(slice_size * i)
-               size_vals.push_back(slice_size)
-            } else {
-               begin_vals.push_back(0)
-               size_vals.push_bac(%value.shape[j])
-            }
-
-            %output[i] = tosa.SLICE(%value) {start=begin_vals, size=size_vals} (tensor<%value.type>) -> tensor<size_vals, %value.dtype>
-        }
-
-    }
-
-    %output_list = tosa.IDENTITYN(%output) (tensor<%output:*.type>) -> tensor<%output_list:*.type>
-    return %output_list
-}
-```
-
 ### COND\_IF and WHILE\_LOOP
 
 Several neural networks express conditional control flow at the tensor level.
 A survey of multiple high level frameworks indicated that conditional if and
 a loop construct are common in all major frameworks, with some variation.
 Since TOSA endeavors to be complete in expressing tensor level functionality
 including control flow, it implements these constructs.
 

mlir/include/mlir/Dialect/Tosa/IR/TosaOps.td

def Tosa_IdentityOp: Tosa_Op<"identity", [NoSideEffect]> {
   );
 
   let results = (outs
     Tosa_TensorUpto6D:$output
   );
 }
 
 //===----------------------------------------------------------------------===//
-// Operator: identityn
-//===----------------------------------------------------------------------===//
-//===----------------------------------------------------------------------===//
-// Further described in docs/Rationale/RationaleTOSADialect.md .
-//===----------------------------------------------------------------------===//
-def Tosa_IdentityNOp: Tosa_Op<"identityn", [NoSideEffect]> {
-  let summary = "IdentityN operator";
-  let description = [{
-    Returns a list of tensors with the same shape, type, and contents as the
-    input list of tensors.
-  }];
-
-  let arguments = (ins
-    Variadic<Tosa_TensorUpto6D>:$input1
-  );
-
-  let results = (outs
-     Variadic<Tosa_TensorUpto6D>:$output
-  );
-}
-
-//===----------------------------------------------------------------------===//
 // TOSA Spec Section 2.14
 // Operator Class: Custom Operators.
 //===----------------------------------------------------------------------===//
 
 //===----------------------------------------------------------------------===//
 // Operator: custom
 //===----------------------------------------------------------------------===//
 def Tosa_CustomOp : Tosa_Op<"custom"> {

mlir/lib/Conversion/TosaToLinalg/TosaToLinalg.cpp

patterns->add<
       PointwiseConverter<tosa::MaximumOp>,
       PointwiseConverter<tosa::MinimumOp>,
       PointwiseConverter<tosa::CeilOp>,
       PointwiseConverter<tosa::FloorOp>,
       PointwiseConverter<tosa::ClampOp>,
       PointwiseConverter<tosa::ReluNOp>,
       PointwiseConverter<tosa::SigmoidOp>,
       IdentityNConverter<tosa::IdentityOp>,
-      IdentityNConverter<tosa::IdentityNOp>,
       ReduceConverter<tosa::ReduceAllOp>,
       ReduceConverter<tosa::ReduceAnyOp>,
       ReduceConverter<tosa::ReduceMinOp>,
       ReduceConverter<tosa::ReduceMaxOp>,
       ReduceConverter<tosa::ReduceSumOp>,
       ReduceConverter<tosa::ReduceProdOp>,
       ArgMaxConverter,
       ConcatConverter,

mlir/test/Conversion/TosaToLinalg/tosa-to-linalg.mlir

 
 // -----
 
 // CHECK-LABEL: @test_identity
 func @test_identity(%arg0: tensor<1xf32>, %arg1: tensor<1xi32>) -> (tensor<1xf32>, tensor<1xi32>) {
   %0 = "tosa.identity"(%arg0) : (tensor<1xf32>) -> tensor<1xf32>
   %1 = "tosa.identity"(%arg1) : (tensor<1xi32>) -> tensor<1xi32>
 
-  %2:2 = "tosa.identityn"(%0, %1) : (tensor<1xf32>, tensor<1xi32>) -> (tensor<1xf32>, tensor<1xi32>)
-
   // CHECK: return %arg0, %arg1
-  return %2#0, %2#1 : tensor<1xf32>, tensor<1xi32>
+  return %0, %1 : tensor<1xf32>, tensor<1xi32>
 }
 
 // -----
 
 // CHECK: #[[$MAP0:.*]] = affine_map<(d0, d1, d2) -> (d2, d0, d1)>
 // CHECK: #[[$MAP1:.*]] = affine_map<(d0, d1, d2) -> (d0, d1, d2)>
 
 // CHECK-LABEL: @test_transpose

mlir/test/Dialect/Tosa/ops.mlir

 // -----
 // CHECK-LABEL: identity
 func @test_identity(%arg0: tensor<13x21x3xi32>) -> tensor<13x21x3xi32> {
   %0 = "tosa.identity"(%arg0) : (tensor<13x21x3xi32>) -> tensor<13x21x3xi32>
   return %0 : tensor<13x21x3xi32>
 }
 
 // -----
-// CHECK-LABEL: identityn
-func @test_identityn(%arg0: tensor<1xi32>, %arg1: tensor<1xi32>) -> tensor<1xi32> {
-  %0:2 = "tosa.identityn"(%arg0, %arg1) : (tensor<1xi32>, tensor<1xi32>) -> (tensor<1xi32>, tensor<1xi32>)
-  return %0#0 : tensor<1xi32>
-}
-
-// -----
 // CHECK-LABEL: cond_if
 func @test_cond_if(%arg0: tensor<f32>, %arg1: tensor<f32>, %arg2: tensor<i1>) -> tensor<f32> {
   %0 = "tosa.cond_if"(%arg2, %arg0, %arg1) ( {
   ^bb0(%arg3: tensor<f32>, %arg4: tensor<f32>):  // no predecessors
     %1 = "tosa.add"(%arg3, %arg4) : (tensor<f32>, tensor<f32>) -> tensor<f32>
     "tosa.yield"(%1) : (tensor<f32>) -> ()
   },  {
   ^bb0(%arg3: tensor<f32>, %arg4: tensor<f32>):  // no predecessors