backends/reference: Add ReduceSum operation support

This patch addes ReduceSum operation support for reference backend,
which computes the sum of elements across dimensions of a tensor.

Changelog v1:
- Fix file header descriptions.

Chagelog v2:
- Fix line limit issue.
- Fix type conversion issue.

Changelog v3:
- Remove tabs.
- Modify newly added file headers.

Changelog v4:
- Symbol on header isn't allowed so drop it from newly added file headers.

Changelog v5:
- Remove tabs, fix the use of brackets and align lines correctly.

Changelog v6:
- Add serializer and deserializer support.

Changelog v7:
- Fix build error add missed code.

Changelog v8:
- Rename ReduceSumDecriptor to ReduceDescriptor
    - Update m_KeepDims field data type to bool on ReduceDescriptor
    - Add ReduceOperation field to ReduceDescriptor

- Rename ReduceSumLayer to ReduceLayer
    - Update ReduceLayer to use ReduceDescriptor
    - Update ReduceLayer::ValidateTensorShapesFromInputs() function

- Rename RefReduceSumWokload to RefReduceWorkload
    - Update workload to use ReduceDescriptor
    - Update workload to use Decoders and Encoders

- Remove ReduceSum.hpp and ReduceSum.cpp
- Added Reduce.hpp and Reduce.cpp
     - Move Mean.cpp (which is implementing REDUCE_MEAN) functionality to Reduce.cpp
     - Update RefMeanWorkload to call Reduce function with ReduceOperation::Mean argument

- Remove Mean.hpp and Mean.cpp
- Update the Serializer/Deserializer ArmnnSchema.fbs for ReduceLayer, ReduceDescriptor, and ReduceOperation
- Update Serializer and Deserializer for serializing/parsing ReduceLayer
- Added TfLiter parser Sum test for REDUCE_SUM operator
- Make corresponding changes on front-end and Ref backend to support REDUCE_SUM operator

Changelog v9:
- Fixed build errors.

Change-Id: I8c8e034f3df73f9565b3c18eff51ecca6c542195
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>

1 files changed, 42 insertions, 0 deletions

diff --git a/src/armnn/layers/ReduceLayer.hpp b/src/armnn/layers/ReduceLayer.hpp
new file mode 100644
index 0000000000..fd4f2073f1
--- /dev/null
+++ b/src/armnn/layers/ReduceLayer.hpp
@@ -0,0 +1,42 @@
+//
+// Copyright © 2020 Samsung Electronics Co Ltd and Contributors. All rights reserved.
+// SPDX-License-Identifier: MIT
+//
+#pragma once
+
+#include "LayerWithParameters.hpp"
+
+namespace armnn
+{
+
+/// This layer represents a reduction operation.
+class ReduceLayer : public LayerWithParameters<ReduceDescriptor>
+{
+public:
+    /// Makes a workload for the Reduce type.
+    /// @param [in] graph The graph where this layer can be found.
+    /// @param [in] factory The workload factory which will create the workload.
+    /// @return A pointer to the created workload, or nullptr if not created.
+    virtual std::unique_ptr<IWorkload>CreateWorkload(const IWorkloadFactory& factory) const override;
+
+    /// Creates a dynamically-allocated copy of this layer.
+    /// @param [in] graph The graph into which this layer is being cloned.
+    ReduceLayer* Clone(Graph& graph) const override;
+
+    /// Check if the input tensor shape(s)
+    /// will lead to a valid configuration of @ref ReduceLayer.
+    void ValidateTensorShapesFromInputs() override;
+
+    void Accept(ILayerVisitor& visitor) const override;
+
+protected:
+    /// Constructor to create a ReduceLayer.
+    /// @param [in] param ReduceDescriptor to configure the reduction operation.
+    /// @param [in] name Optional name for the layer.
+    ReduceLayer(const ReduceDescriptor& param, const char* name);
+
+    /// Default destructor
+    ~ReduceLayer() = default;
+};
+
+} // namespace armnn