COMPMID-1725: Implement Pack

Change-Id: I13f6e4c600f39355f69e015409bf30dafdc5e3aa
Reviewed-on: https://review.mlplatform.org/332
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>

4 files changed, 118 insertions, 0 deletions

diff --git a/arm_compute/core/CL/CLKernels.h b/arm_compute/core/CL/CLKernels.h
index c707265c23..0fe1e04ccd 100644
--- a/arm_compute/core/CL/CLKernels.h
+++ b/arm_compute/core/CL/CLKernels.h
@@ -121,6 +121,7 @@
 #include "arm_compute/core/CL/kernels/CLSobel7x7Kernel.h"
 #include "arm_compute/core/CL/kernels/CLSoftmaxLayerKernel.h"
 #include "arm_compute/core/CL/kernels/CLSpaceToBatchLayerKernel.h"
+#include "arm_compute/core/CL/kernels/CLStackLayerKernel.h"
 #include "arm_compute/core/CL/kernels/CLStridedSliceKernel.h"
 #include "arm_compute/core/CL/kernels/CLTableLookupKernel.h"
 #include "arm_compute/core/CL/kernels/CLThresholdKernel.h"
diff --git a/arm_compute/core/CL/kernels/CLStackLayerKernel.h b/arm_compute/core/CL/kernels/CLStackLayerKernel.h
new file mode 100644
index 0000000000..4d377daf8b
--- /dev/null
+++ b/arm_compute/core/CL/kernels/CLStackLayerKernel.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (c) 2018 ARM Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __ARM_COMPUTE_CLSTACKLAYERKERNEL_H__
+#define __ARM_COMPUTE_CLSTACKLAYERKERNEL_H__
+
+#include "arm_compute/core/CL/ICLKernel.h"
+#include "arm_compute/core/Types.h"
+
+namespace arm_compute
+{
+class ICLTensor;
+
+/** OpenCL kernel to stacks a rank-R tensor into one with rank-(R+1) along the axis dimension.*/
+class CLStackLayerKernel : public ICLKernel
+{
+public:
+    /** Default constructor */
+    CLStackLayerKernel();
+    /** Prevent instances of this class from being copied (As this class contains pointers) */
+    CLStackLayerKernel(const CLStackLayerKernel &) = delete;
+    /** Prevent instances of this class from being copied (As this class contains pointers) */
+    CLStackLayerKernel &operator=(const CLStackLayerKernel &) = delete;
+    /** Allow instances of this class to be moved */
+    CLStackLayerKernel(CLStackLayerKernel &&) = default;
+    /** Allow instances of this class to be moved */
+    CLStackLayerKernel &operator=(CLStackLayerKernel &&) = default;
+    /** Default destructor */
+    ~CLStackLayerKernel() = default;
+    /** Initialise the kernel's inputs and output
+     *
+     * @param[in]  input       Input tensor. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
+     * @param[in]  axis        The dimension to stack the tensors along. It must be smaller than the number of input dimensions.
+     * @param[in]  idx_input   Index of the input tensor in the list of tensors to stack.
+     *                         All tensors in the list must have the same shape
+     * @param[in]  num_tensors Number of tensors to stack
+     * @param[out] output      Output tensor. Data types supported: Same as @p input.
+     *
+     */
+    void configure(const ICLTensor *input, unsigned int axis, unsigned int idx_input, unsigned int num_tensors, ICLTensor *output);
+    /**  Static function to check if given info will lead to a valid configuration of @ref CLStackLayerKernel
+     *
+     * @param[in] input       Input tensor info. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
+     * @param[in] axis        The dimension to stack the tensors along. It must be smaller than the number of input dimensions.
+     * @param[in] idx_input   Index of the input tensor in the list of tensors to stack
+     *                        All tensors in the list must have the same shape
+     * @param[in] num_tensors Number of tensors to stack
+     * @param[in] output      Output tensor info. Data types supported: Same as @p input.
+     *
+     * @return a status
+     */
+    static Status validate(const ITensorInfo *input, unsigned int axis, unsigned int idx_input, unsigned int num_tensors, const ITensorInfo *output);
+
+    // Inherited methods overridden:
+    void run(const Window &window, cl::CommandQueue &queue) override;
+
+private:
+    const ICLTensor *_input;
+    ICLTensor       *_output;
+};
+} // namespace arm_compute
+#endif /* __ARM_COMPUTE_CLSTACKLAYERKERNEL_H__ */
diff --git a/arm_compute/core/Helpers.h b/arm_compute/core/Helpers.h
index ef59323073..8f4220fb80 100644
--- a/arm_compute/core/Helpers.h
+++ b/arm_compute/core/Helpers.h
@@ -710,6 +710,18 @@ inline Size2D compute_winograd_convolution_tiles(const Size2D &in_dims, const Si
     return Size2D(num_tiles_x, num_tiles_y);
 }
 
+/** Wrap-around a number within the range 0 <= x < m
+ *
+ * @param[in] x Input value
+ * @param[in] m Range
+ *
+ * @return the wrapped-around number
+ */
+template <typename T>
+inline T wrap_around(T x, T m)
+{
+    return x >= 0 ? x % m : (x % m + m) % m;
+}
 } // namespace arm_compute
 
 #include "arm_compute/core/Helpers.inl"
diff --git a/arm_compute/core/utils/misc/ShapeCalculator.h b/arm_compute/core/utils/misc/ShapeCalculator.h
index 38906dfc9b..c625a07a7f 100644
--- a/arm_compute/core/utils/misc/ShapeCalculator.h
+++ b/arm_compute/core/utils/misc/ShapeCalculator.h
@@ -754,6 +754,28 @@ inline TensorShape calculate_width_concatenate_shape(const std::vector<T *> &inp
 
     return out_shape;
 }
+
+inline TensorShape compute_stack_shape(const ITensorInfo &a, unsigned int axis, unsigned int num_tensors)
+{
+    ARM_COMPUTE_ERROR_ON(axis > a.num_dimensions());
+    ARM_COMPUTE_ERROR_ON(a.num_dimensions() > 4);
+
+    TensorShape shape_out{ a.tensor_shape() };
+    shape_out.set(axis, num_tensors);
+
+    unsigned int i_shift = 0;
+
+    for(unsigned int i = 0; i < a.num_dimensions(); ++i)
+    {
+        if(i == axis)
+        {
+            i_shift++;
+        }
+
+        shape_out.set(i + i_shift, a.tensor_shape()[i]);
+    }
+    return shape_out;
+}
 } // namespace shape_calculator
 } // namespace misc
 } // namespace arm_compute