COMPMID-1932: Implement CLHeightConcatenateLayer.

Change-Id: I244ff2352c3c9620148dab6475aee62b218b96ef
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/871
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
diff --git a/arm_compute/runtime/CL/functions/CLConcatenateLayer.h b/arm_compute/runtime/CL/functions/CLConcatenateLayer.h
index 4d4c624..25a0153 100644
--- a/arm_compute/runtime/CL/functions/CLConcatenateLayer.h
+++ b/arm_compute/runtime/CL/functions/CLConcatenateLayer.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2018 ARM Limited.
+ * Copyright (c) 2018-2019 ARM Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -26,6 +26,7 @@
 
 #include "arm_compute/runtime/IFunction.h"
 
+#include "arm_compute/core/CL/kernels/CLHeightConcatenateLayerKernel.h"
 #include "arm_compute/core/Types.h"
 
 #include <memory>
@@ -41,6 +42,7 @@
 /** Basic function to execute concatenate tensors along a given axis. This function calls the following kernels:
  *
  * -# @ref CLWidthConcatenateLayer (if underlying concatenation axis is 0).
+ * -# @ref CLHeightConcatenateLayerKernel (if underlying concatenation axis is 1).
  * -# @ref CLDepthConcatenateLayer (if underlying concatenation axis is 2).
  */
 class CLConcatenateLayer : public IFunction
@@ -51,21 +53,21 @@
     /** Initialise the kernel's inputs vector and output.
      *
      * @note Input and output tensor dimensions preconditions defer depending on the concatenation axis.
-     * @note Preconditions can be found respectively at @ref CLWidthConcatenateLayer and @ref CLDepthConcatenateLayer.
+     * @note Preconditions can be found respectively at @ref CLWidthConcatenateLayer, @ref CLHeightConcatenateLayerKernel and @ref CLDepthConcatenateLayer.
      *
      * @param[in,out] inputs_vector The vectors containing all the tensors to concatenate. Data types supported: QASYMM8/F16/F32.
      * @param[out]    output        Output tensor. Data types supported: Same as @p input.
-     * @param[in]     axis          Concatenation axis. Supported underlying concatenation axis are 0 and 2.
+     * @param[in]     axis          Concatenation axis. Supported underlying concatenation axis are 0, 1 and 2.
      */
     void configure(const std::vector<ICLTensor *> &inputs_vector, ICLTensor *output, DataLayoutDimension axis);
     /** Static function to check if given info will lead to a valid configuration of @ref CLConcatenateLayer
      *
      * @note Input and output tensor dimensions preconditions defer depending on the concatenation axis.
-     * @note Preconditions can be found respectively at @ref CLWidthConcatenateLayer and @ref CLDepthConcatenateLayer.
+     * @note Preconditions can be found respectively at @ref CLWidthConcatenateLayer, @ref CLHeightConcatenateLayerKernel and @ref CLDepthConcatenateLayer.
      *
      * @param[in] inputs_vector The vectors containing all the tensors info to concatenate. Data types supported: QASYMM8/F16/F32.
      * @param[in] output        Output tensor info. Data types supported: Same as @p input.
-     * @param[in] axis          Concatenation axis. Supported underlying concatenation axis are 0 and 2.
+     * @param[in] axis          Concatenation axis. Supported underlying concatenation axis are 0, 1 and 2.
      *
      * @return a status
      */
@@ -75,7 +77,13 @@
     void run() override;
 
 private:
-    std::unique_ptr<IFunction> _concat_function;
+    void configure_h_concatenate(std::vector<ICLTensor *> inputs_vector, ICLTensor *output);
+    static Status validate_h_concatenate(const std::vector<ITensorInfo *> &inputs_vector, const ITensorInfo *output);
+
+    std::unique_ptr<IFunction>                        _concat_function;
+    std::unique_ptr<CLHeightConcatenateLayerKernel[]> _hconcat_kernels;
+    unsigned int                                      _num_inputs;
+    unsigned int                                      _axis;
 };
 }
 #endif /* __ARM_COMPUTE_CLCONCATENATELAYER_H__ */