COMPMID-344 Updated doxygen

Change-Id: I32f7b84daa560e460b77216add529c8fa8b327ae

8 files changed, 1017 insertions, 0 deletions

diff --git a/examples/SConscript b/examples/SConscript
new file mode 100644
index 0000000000..748f771ec7
--- /dev/null
+++ b/examples/SConscript
@@ -0,0 +1,70 @@
+# Copyright (c) 2017 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.
+import SCons
+import os.path
+
+Import('env')
+Import('arm_compute_a')
+Import('arm_compute_so')
+
+if env['opencl']:
+    Import('opencl')
+
+examples_env = env.Clone()
+
+examples_env.Append(CPPPATH = ["#"])
+examples_env.Append(LIBPATH = ["#build/%s" % env['build_dir']])
+examples_env.Append(LIBPATH = ["#build/%s/opencl-1.2-stubs" % env['build_dir']])
+
+# Build examples
+utils = examples_env.Object("../utils/Utils.cpp")
+
+if env['os'] in ['android', 'bare_metal']:
+    arm_compute_lib = arm_compute_a
+    arm_compute_dependency = arm_compute_a
+else:
+    arm_compute_lib = "arm_compute"
+    arm_compute_dependency = arm_compute_so
+
+if env['opencl'] and env['neon']:
+    for file in Glob("./neoncl_*.cpp"):
+        example = os.path.basename(os.path.splitext(str(file))[0])
+        prog = examples_env.Program(example, ["{}.cpp".format(example), utils], LIBS = [arm_compute_lib, "OpenCL"])
+        Depends(prog, [arm_compute_dependency, opencl])
+        alias = examples_env.Alias(example, prog)
+        Default(alias)
+
+if env['opencl']:
+    for file in Glob("./cl_*.cpp"):
+        example = os.path.basename(os.path.splitext(str(file))[0])
+        prog = examples_env.Program(example, ["{}.cpp".format(example), utils], LIBS = [arm_compute_lib, "OpenCL"])
+        Depends(prog, [arm_compute_dependency, opencl])
+        alias = examples_env.Alias(example, prog)
+        Default(alias)
+
+if env['neon']:
+    for file in Glob("./neon_*.cpp"):
+        example = os.path.basename(os.path.splitext(str(file))[0])
+        prog = examples_env.Program(example, ["{}.cpp".format(example), utils], LIBS = [arm_compute_lib])
+        Depends(prog, arm_compute_dependency)
+        alias = examples_env.Alias(example, prog)
+        Default(alias)
diff --git a/examples/cl_convolution.cpp b/examples/cl_convolution.cpp
new file mode 100644
index 0000000000..06f6f144e1
--- /dev/null
+++ b/examples/cl_convolution.cpp
@@ -0,0 +1,118 @@
+/*
+ * Copyright (c) 2016, 2017 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.
+ */
+#define ARM_COMPUTE_CL /* So that OpenCL exceptions get caught too */
+#include "arm_compute/core/Types.h"
+#include "arm_compute/runtime/CL/CLFunctions.h"
+#include "arm_compute/runtime/CL/CLScheduler.h"
+#include "utils/Utils.h"
+
+using namespace arm_compute;
+using namespace utils;
+
+/** Gaussian 3x3 matrix
+ */
+const int16_t gaussian3x3[] =
+{
+    1, 2, 1,
+    2, 4, 2,
+    1, 2, 1
+};
+
+/** Gaussian 5x5 matrix
+ */
+const int16_t gaussian5x5[] =
+{
+    1, 4, 6, 4, 1,
+    4, 16, 24, 16, 4,
+    6, 24, 36, 24, 6,
+    4, 16, 24, 16, 4,
+    1, 4, 6, 4, 1
+};
+
+void main_cl_convolution(int argc, const char **argv)
+{
+    PPMLoader ppm;
+    CLImage   src, tmp, dst;
+
+    CLScheduler::get().default_init();
+
+    if(argc < 2)
+    {
+        // Print help
+        std::cout << "Usage: ./build/cl_convolution [input_image.ppm]\n\n";
+        std::cout << "No input_image provided, creating a dummy 640x480 image\n";
+        // Create an empty grayscale 640x480 image
+        src.allocator()->init(TensorInfo(640, 480, Format::U8));
+    }
+    else
+    {
+        ppm.open(argv[1]);
+        ppm.init_image(src, Format::U8);
+    }
+
+    // Configure the temporary and destination images
+    tmp.allocator()->init(*src.info());
+    dst.allocator()->init(*src.info());
+
+    CLConvolution3x3 conv3x3;
+    CLConvolution5x5 conv5x5;
+
+    // Apply a Gaussian 3x3 filter to the source image followed by a Gaussian 5x5:
+    conv3x3.configure(&src, &tmp, gaussian3x3, 0 /* Let arm_compute calculate the scale */, BorderMode::UNDEFINED);
+    conv5x5.configure(&tmp, &dst, gaussian5x5, 0 /* Let arm_compute calculate the scale */, BorderMode::UNDEFINED);
+
+    // Allocate all the images
+    src.allocator()->allocate();
+    tmp.allocator()->allocate();
+    dst.allocator()->allocate();
+    // Fill the input image with the content of the PPM image if a filename was provided:
+    if(ppm.is_open())
+    {
+        ppm.fill_image(src);
+    }
+
+    // Execute the functions:
+    conv3x3.run();
+    conv5x5.run();
+
+    // Make sure all the OpenCL jobs are done executing:
+    CLScheduler::get().sync();
+
+    // Save the result to file:
+    if(ppm.is_open())
+    {
+        const std::string output_filename = std::string(argv[1]) + "_out.ppm";
+        save_to_ppm(dst, output_filename); // save_to_ppm maps and unmaps the image to store as PPM
+    }
+}
+
+/** Main program for convolution test
+ *
+ * @param[in] argc Number of arguments
+ * @param[in] argv Arguments ( [optional] Path to PPM image to process )
+ */
+int main(int argc, const char **argv)
+{
+    return utils::run_example(argc, argv, main_cl_convolution);
+}
diff --git a/examples/cl_events.cpp b/examples/cl_events.cpp
new file mode 100644
index 0000000000..768f620622
--- /dev/null
+++ b/examples/cl_events.cpp
@@ -0,0 +1,114 @@
+/*
+ * Copyright (c) 2017 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.
+ */
+#define ARM_COMPUTE_CL /* So that OpenCL exceptions get caught too */
+#include "arm_compute/core/Types.h"
+#include "arm_compute/runtime/CL/CLFunctions.h"
+#include "arm_compute/runtime/CL/CLScheduler.h"
+#include "utils/Utils.h"
+
+using namespace arm_compute;
+using namespace utils;
+
+void main_cl_events(int argc, const char **argv)
+{
+    /** [OpenCL events] **/
+    PPMLoader     ppm;
+    CLImage       src, tmp_scale_median, tmp_median_gauss, dst;
+    constexpr int scale_factor = 2;
+
+    CLScheduler::get().default_init();
+
+    if(argc < 2)
+    {
+        // Print help
+        std::cout << "Usage: ./build/cl_events [input_image.ppm]\n\n";
+        std::cout << "No input_image provided, creating a dummy 640x480 image\n";
+        // Create an empty grayscale 640x480 image
+        src.allocator()->init(TensorInfo(640, 480, Format::U8));
+    }
+    else
+    {
+        ppm.open(argv[1]);
+        ppm.init_image(src, Format::U8);
+    }
+
+    // Declare and configure the functions to create the following pipeline: scale -> median -> gauss
+    CLScale       scale;
+    CLMedian3x3   median;
+    CLGaussian5x5 gauss;
+
+    TensorInfo dst_info(src.info()->dimension(0) / scale_factor, src.info()->dimension(1) / scale_factor, Format::U8);
+
+    // Configure the temporary and destination images
+    dst.allocator()->init(dst_info);
+    tmp_scale_median.allocator()->init(dst_info);
+    tmp_median_gauss.allocator()->init(dst_info);
+
+    //Configure the functions:
+    scale.configure(&src, &tmp_scale_median, InterpolationPolicy::NEAREST_NEIGHBOR, BorderMode::REPLICATE);
+    median.configure(&tmp_scale_median, &tmp_median_gauss, BorderMode::REPLICATE);
+    gauss.configure(&tmp_median_gauss, &dst, BorderMode::REPLICATE);
+
+    // Allocate all the images
+    src.allocator()->allocate();
+    dst.allocator()->allocate();
+    tmp_scale_median.allocator()->allocate();
+    tmp_median_gauss.allocator()->allocate();
+    // Fill the input image with the content of the PPM image if a filename was provided:
+    if(ppm.is_open())
+    {
+        ppm.fill_image(src);
+    }
+
+    // Enqueue and flush the scale OpenCL kernel:
+    scale.run();
+    // Create a synchronisation event between scale and median:
+    cl::Event scale_event = CLScheduler::get().enqueue_sync_event();
+    // Enqueue and flush the median OpenCL kernel:
+    median.run();
+    // Enqueue and flush the Gaussian OpenCL kernel:
+    gauss.run();
+
+    //Make sure all the OpenCL jobs are done executing:
+    scale_event.wait();        // Block until Scale is done executing (Median3x3 and Gaussian5x5 might still be running)
+    CLScheduler::get().sync(); // Block until Gaussian5x5 is done executing
+
+    // Save the result to file:
+    if(ppm.is_open())
+    {
+        const std::string output_filename = std::string(argv[1]) + "_out.ppm";
+        save_to_ppm(dst, output_filename); // save_to_ppm maps and unmaps the image to store as PPM
+    }
+    /** [OpenCL events] **/
+}
+
+/** Main program for convolution test
+ *
+ * @param[in] argc Number of arguments
+ * @param[in] argv Arguments ( [optional] Path to PPM image to process )
+ */
+int main(int argc, const char **argv)
+{
+    return utils::run_example(argc, argv, main_cl_events);
+}
diff --git a/examples/neon_cnn.cpp b/examples/neon_cnn.cpp
new file mode 100644
index 0000000000..952ae4d485
--- /dev/null
+++ b/examples/neon_cnn.cpp
@@ -0,0 +1,230 @@
+/*
+ * Copyright (c) 2016, 2017 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.
+ */
+#include "arm_compute/runtime/NEON/NEFunctions.h"
+
+#include "arm_compute/core/Types.h"
+#include "utils/Utils.h"
+
+using namespace arm_compute;
+using namespace utils;
+
+void main_cnn(int argc, const char **argv)
+{
+    ARM_COMPUTE_UNUSED(argc);
+    ARM_COMPUTE_UNUSED(argv);
+
+    // The src tensor should contain the input image
+    Tensor src;
+
+    // The weights and biases tensors should be initialized with the values inferred with the training
+    Tensor weights0;
+    Tensor weights1;
+    Tensor weights2;
+    Tensor biases0;
+    Tensor biases1;
+    Tensor biases2;
+
+    Tensor out_conv0;
+    Tensor out_conv1;
+    Tensor out_act0;
+    Tensor out_act1;
+    Tensor out_act2;
+    Tensor out_pool0;
+    Tensor out_pool1;
+    Tensor out_fc0;
+    Tensor out_softmax;
+
+    NEConvolutionLayer    conv0;
+    NEConvolutionLayer    conv1;
+    NEPoolingLayer        pool0;
+    NEPoolingLayer        pool1;
+    NEFullyConnectedLayer fc0;
+    NEActivationLayer     act0;
+    NEActivationLayer     act1;
+    NEActivationLayer     act2;
+    NESoftmaxLayer        softmax;
+
+    /* [Initialize tensors] */
+
+    // Initialize src tensor
+    constexpr unsigned int width_src_image  = 32;
+    constexpr unsigned int height_src_image = 32;
+    constexpr unsigned int ifm_src_img      = 1;
+
+    const TensorShape src_shape(width_src_image, height_src_image, ifm_src_img);
+    src.allocator()->init(TensorInfo(src_shape, 1, DataType::F32));
+
+    // Initialize tensors of conv0
+    constexpr unsigned int kernel_x_conv0 = 5;
+    constexpr unsigned int kernel_y_conv0 = 5;
+    constexpr unsigned int ofm_conv0      = 8;
+
+    const TensorShape weights_shape_conv0(kernel_x_conv0, kernel_y_conv0, src_shape.z(), ofm_conv0);
+    const TensorShape biases_shape_conv0(weights_shape_conv0[3]);
+    const TensorShape out_shape_conv0(src_shape.x(), src_shape.y(), weights_shape_conv0[3]);
+
+    weights0.allocator()->init(TensorInfo(weights_shape_conv0, 1, DataType::F32));
+    biases0.allocator()->init(TensorInfo(biases_shape_conv0, 1, DataType::F32));
+    out_conv0.allocator()->init(TensorInfo(out_shape_conv0, 1, DataType::F32));
+
+    // Initialize tensor of act0
+    out_act0.allocator()->init(TensorInfo(out_shape_conv0, 1, DataType::F32));
+
+    // Initialize tensor of pool0
+    TensorShape out_shape_pool0 = out_shape_conv0;
+    out_shape_pool0.set(0, out_shape_pool0.x() / 2);
+    out_shape_pool0.set(1, out_shape_pool0.y() / 2);
+    out_pool0.allocator()->init(TensorInfo(out_shape_pool0, 1, DataType::F32));
+
+    // Initialize tensors of conv1
+    constexpr unsigned int kernel_x_conv1 = 3;
+    constexpr unsigned int kernel_y_conv1 = 3;
+    constexpr unsigned int ofm_conv1      = 16;
+
+    const TensorShape weights_shape_conv1(kernel_x_conv1, kernel_y_conv1, out_shape_pool0.z(), ofm_conv1);
+
+    const TensorShape biases_shape_conv1(weights_shape_conv1[3]);
+    const TensorShape out_shape_conv1(out_shape_pool0.x(), out_shape_pool0.y(), weights_shape_conv1[3]);
+
+    weights1.allocator()->init(TensorInfo(weights_shape_conv1, 1, DataType::F32));
+    biases1.allocator()->init(TensorInfo(biases_shape_conv1, 1, DataType::F32));
+    out_conv1.allocator()->init(TensorInfo(out_shape_conv1, 1, DataType::F32));
+
+    // Initialize tensor of act1
+    out_act1.allocator()->init(TensorInfo(out_shape_conv1, 1, DataType::F32));
+
+    // Initialize tensor of pool1
+    TensorShape out_shape_pool1 = out_shape_conv1;
+    out_shape_pool1.set(0, out_shape_pool1.x() / 2);
+    out_shape_pool1.set(1, out_shape_pool1.y() / 2);
+    out_pool1.allocator()->init(TensorInfo(out_shape_pool1, 1, DataType::F32));
+
+    // Initialize tensor of fc0
+    constexpr unsigned int num_labels = 128;
+
+    const TensorShape weights_shape_fc0(out_shape_pool1.x() * out_shape_pool1.y() * out_shape_pool1.z(), num_labels);
+    const TensorShape biases_shape_fc0(num_labels);
+    const TensorShape out_shape_fc0(num_labels);
+
+    weights2.allocator()->init(TensorInfo(weights_shape_fc0, 1, DataType::F32));
+    biases2.allocator()->init(TensorInfo(biases_shape_fc0, 1, DataType::F32));
+    out_fc0.allocator()->init(TensorInfo(out_shape_fc0, 1, DataType::F32));
+
+    // Initialize tensor of act2
+    out_act2.allocator()->init(TensorInfo(out_shape_fc0, 1, DataType::F32));
+
+    // Initialize tensor of softmax
+    const TensorShape out_shape_softmax(out_shape_fc0.x());
+    out_softmax.allocator()->init(TensorInfo(out_shape_softmax, 1, DataType::F32));
+
+    /* -----------------------End: [Initialize tensors] */
+
+    /* [Configure functions] */
+
+    // in:32x32x1: 5x5 convolution, 8 output features maps (OFM)
+    conv0.configure(&src, &weights0, &biases0, &out_conv0, PadStrideInfo());
+
+    // in:32x32x8, out:32x32x8, Activation function: relu
+    act0.configure(&out_conv0, &out_act0, ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU));
+
+    // in:32x32x8, out:16x16x8 (2x2 pooling), Pool type function: Max
+    pool0.configure(&out_act0, &out_pool0, PoolingLayerInfo(PoolingType::MAX, 2));
+
+    // in:16x16x8: 3x3 convolution, 16 output features maps (OFM)
+    conv1.configure(&out_pool0, &weights1, &biases1, &out_conv1, PadStrideInfo());
+
+    // in:16x16x16, out:16x16x16, Activation function: relu
+    act1.configure(&out_conv1, &out_act1, ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU));
+
+    // in:16x16x16, out:8x8x16 (2x2 pooling), Pool type function: Average
+    pool1.configure(&out_act1, &out_pool1, PoolingLayerInfo(PoolingType::AVG, 2));
+
+    // in:8x8x16, out:128
+    fc0.configure(&out_pool1, &weights2, &biases2, &out_fc0);
+
+    // in:128, out:128, Activation function: relu
+    act2.configure(&out_fc0, &out_act2, ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU));
+
+    // in:128, out:128
+    softmax.configure(&out_act2, &out_softmax);
+
+    /* -----------------------End: [Configure functions] */
+
+    /* [Allocate tensors] */
+
+    // Now that the padding requirements are known we can allocate the images:
+    src.allocator()->allocate();
+    weights0.allocator()->allocate();
+    weights1.allocator()->allocate();
+    weights2.allocator()->allocate();
+    biases0.allocator()->allocate();
+    biases1.allocator()->allocate();
+    biases2.allocator()->allocate();
+    out_conv0.allocator()->allocate();
+    out_conv1.allocator()->allocate();
+    out_act0.allocator()->allocate();
+    out_act1.allocator()->allocate();
+    out_act2.allocator()->allocate();
+    out_pool0.allocator()->allocate();
+    out_pool1.allocator()->allocate();
+    out_fc0.allocator()->allocate();
+    out_softmax.allocator()->allocate();
+
+    /* -----------------------End: [Allocate tensors] */
+
+    /* [Initialize weights and biases tensors] */
+
+    // Once the tensors have been allocated, the src, weights and biases tensors can be initialized
+    // ...
+
+    /* -----------------------[Initialize weights and biases tensors] */
+
+    /* [Execute the functions] */
+
+    conv0.run();
+    act0.run();
+    pool0.run();
+    conv1.run();
+    act1.run();
+    pool1.run();
+    fc0.run();
+    act2.run();
+    softmax.run();
+
+    /* -----------------------End: [Execute the functions] */
+}
+
+/** Main program for cnn test
+ *
+ * The example implements the following CNN architecture:
+ *
+ * Input -> conv0:5x5 -> act0:relu -> pool:2x2 -> conv1:3x3 -> act1:relu -> pool:2x2 -> fc0 -> act2:relu -> softmax
+ *
+ * @param[in] argc Number of arguments
+ * @param[in] argv Arguments
+ */
+int main(int argc, const char **argv)
+{
+    return utils::run_example(argc, argv, main_cnn);
+}
\ No newline at end of file
diff --git a/examples/neon_convolution.cpp b/examples/neon_convolution.cpp
new file mode 100644
index 0000000000..222c8f9a37
--- /dev/null
+++ b/examples/neon_convolution.cpp
@@ -0,0 +1,117 @@
+/*
+ * Copyright (c) 2016, 2017 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.
+ */
+#include "arm_compute/runtime/NEON/NEFunctions.h"
+
+#include "arm_compute/core/Types.h"
+#include "utils/Utils.h"
+
+using namespace arm_compute;
+using namespace utils;
+
+/** Gaussian 3x3 matrix
+ */
+const int16_t gaussian3x3[] =
+{
+    1, 2, 1,
+    2, 4, 2,
+    1, 2, 1
+};
+
+/** Gaussian 5x5 matrix
+ */
+const int16_t gaussian5x5[] =
+{
+    1, 4, 6, 4, 1,
+    4, 16, 24, 16, 4,
+    6, 24, 36, 24, 6,
+    4, 16, 24, 16, 4,
+    1, 4, 6, 4, 1
+};
+
+void main_neon_convolution(int argc, const char **argv)
+{
+    /** [Accurate padding] **/
+    PPMLoader ppm;
+    Image     src, tmp, dst;
+
+    if(argc < 2)
+    {
+        // Print help
+        std::cout << "Usage: ./build/neon_convolution [input_image.ppm]\n\n";
+        std::cout << "No input_image provided, creating a dummy 640x480 image\n";
+        // Initialize just the dimensions and format of your buffers:
+        src.allocator()->init(TensorInfo(640, 480, Format::U8));
+    }
+    else
+    {
+        ppm.open(argv[1]);
+        // Initialize just the dimensions and format of your buffers:
+        ppm.init_image(src, Format::U8);
+    }
+
+    // Initialize just the dimensions and format of the temporary and destination images:
+    tmp.allocator()->init(*src.info());
+    dst.allocator()->init(*src.info());
+
+    NEConvolution3x3 conv3x3;
+    NEConvolution5x5 conv5x5;
+
+    // Apply a Gaussian 3x3 filter to the source image followed by a Gaussian 5x5:
+    // The function will automatically update the padding information inside input and output to match its requirements
+    conv3x3.configure(&src, &tmp, gaussian3x3, 0 /* Let arm_compute calculate the scale */, BorderMode::UNDEFINED);
+    conv5x5.configure(&tmp, &dst, gaussian5x5, 0 /* Let arm_compute calculate the scale */, BorderMode::UNDEFINED);
+
+    // Now that the padding requirements are known we can allocate the images:
+    src.allocator()->allocate();
+    tmp.allocator()->allocate();
+    dst.allocator()->allocate();
+
+    // Fill the input image with the content of the PPM image if a filename was provided:
+    if(ppm.is_open())
+    {
+        ppm.fill_image(src);
+    }
+
+    //Execute the functions:
+    conv3x3.run();
+    conv5x5.run();
+
+    // Save the result to file:
+    if(ppm.is_open())
+    {
+        const std::string output_filename = std::string(argv[1]) + "_out.ppm";
+        save_to_ppm(dst, output_filename);
+    }
+    /** [Accurate padding] **/
+}
+
+/** Main program for convolution test
+ *
+ * @param[in] argc Number of arguments
+ * @param[in] argv Arguments ( [optional] Path to PPM image to process )
+ */
+int main(int argc, const char **argv)
+{
+    return utils::run_example(argc, argv, main_neon_convolution);
+}
diff --git a/examples/neon_copy_objects.cpp b/examples/neon_copy_objects.cpp
new file mode 100644
index 0000000000..191f455557
--- /dev/null
+++ b/examples/neon_copy_objects.cpp
@@ -0,0 +1,152 @@
+/*
+ * Copyright (c) 2016, 2017 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.
+ */
+
+#include "arm_compute/runtime/NEON/NEFunctions.h"
+
+#include "arm_compute/core/Types.h"
+#include "utils/Utils.h"
+
+#include <cstring>
+#include <iostream>
+
+using namespace arm_compute;
+
+void main_neon_copy_objects(int argc, const char **argv)
+{
+    ARM_COMPUTE_UNUSED(argc);
+    ARM_COMPUTE_UNUSED(argv);
+
+    /** [Copy objects example] */
+    constexpr unsigned int width  = 4;
+    constexpr unsigned int height = 3;
+    constexpr unsigned int batch  = 2;
+
+    auto *src_data = new float[width * height * batch];
+    auto *dst_data = new float[width * height * batch];
+
+    // Fill src_data with dummy values:
+    for(unsigned int b = 0; b < batch; b++)
+    {
+        for(unsigned int h = 0; h < height; h++)
+        {
+            for(unsigned int w = 0; w < width; w++)
+            {
+                src_data[b * (width * height) + h * width + w] = static_cast<float>(100 * b + 10 * h + w);
+            }
+        }
+    }
+
+    Tensor         input, output;
+    NESoftmaxLayer softmax;
+
+    // Initialize the tensors dimensions and type:
+    const TensorShape shape(width, height, batch);
+    input.allocator()->init(TensorInfo(shape, 1, DataType::F32));
+    output.allocator()->init(TensorInfo(shape, 1, DataType::F32));
+
+    // Configure softmax:
+    softmax.configure(&input, &output);
+
+    // Allocate the input / output tensors:
+    input.allocator()->allocate();
+    output.allocator()->allocate();
+
+    // Fill the input tensor:
+    // Simplest way: create an iterator to iterate through each element of the input tensor:
+    Window input_window;
+    input_window.use_tensor_dimensions(input.info());
+    std::cout << " Dimensions of the input's iterator:\n";
+    std::cout << " X = [start=" << input_window.x().start() << ", end=" << input_window.x().end() << ", step=" << input_window.x().step() << "]\n";
+    std::cout << " Y = [start=" << input_window.y().start() << ", end=" << input_window.y().end() << ", step=" << input_window.y().step() << "]\n";
+    std::cout << " Z = [start=" << input_window.z().start() << ", end=" << input_window.z().end() << ", step=" << input_window.z().step() << "]\n";
+
+    // Create an iterator:
+    Iterator input_it(&input, input_window);
+
+    // Iterate through the elements of src_data and copy them one by one to the input tensor:
+    // This is equivalent to:
+    // for( unsigned int z = 0; z < batch; ++z)
+    // {
+    //   for( unsigned int y = 0; y < height; ++y)
+    //   {
+    //     for( unsigned int x = 0; x < width; ++x)
+    //     {
+    //       *reinterpret_cast<float*>( input.buffer() + input.info()->offset_element_in_bytes(Coordinates(x,y,z))) = src_data[ z * (width*height) + y * width + x];
+    //     }
+    //   }
+    // }
+    // Except it works for an arbitrary number of dimensions
+    execute_window_loop(input_window, [&](const Coordinates & id)
+    {
+        std::cout << "Setting item [" << id.x() << "," << id.y() << "," << id.z() << "]\n";
+        *reinterpret_cast<float *>(input_it.ptr()) = src_data[id.z() * (width * height) + id.y() * width + id.x()];
+    },
+    input_it);
+
+    // Run NEON softmax:
+    softmax.run();
+
+    // More efficient way: create an iterator to iterate through each row (instead of each element) of the output tensor:
+    Window output_window;
+    output_window.use_tensor_dimensions(output.info(), /* first_dimension =*/Window::DimY); // Iterate through the rows (not each element)
+    std::cout << " Dimensions of the output's iterator:\n";
+    std::cout << " X = [start=" << output_window.x().start() << ", end=" << output_window.x().end() << ", step=" << output_window.x().step() << "]\n";
+    std::cout << " Y = [start=" << output_window.y().start() << ", end=" << output_window.y().end() << ", step=" << output_window.y().step() << "]\n";
+    std::cout << " Z = [start=" << output_window.z().start() << ", end=" << output_window.z().end() << ", step=" << output_window.z().step() << "]\n";
+
+    // Create an iterator:
+    Iterator output_it(&output, output_window);
+
+    // Iterate through the rows of the output tensor and copy them to dst_data:
+    // This is equivalent to:
+    // for( unsigned int z = 0; z < batch; ++z)
+    // {
+    //   for( unsigned int y = 0; y < height; ++y)
+    //   {
+    //     memcpy( dst_data + z * (width*height) + y * width, input.buffer() + input.info()->offset_element_in_bytes(Coordinates(0,y,z)), width * sizeof(float));
+    //   }
+    // }
+    // Except it works for an arbitrary number of dimensions
+    execute_window_loop(output_window, [&](const Coordinates & id)
+    {
+        std::cout << "Copying one row starting from [" << id.x() << "," << id.y() << "," << id.z() << "]\n";
+        // Copy one whole row:
+        memcpy(dst_data + id.z() * (width * height) + id.y() * width, output_it.ptr(), width * sizeof(float));
+    },
+    output_it);
+
+    delete[] src_data;
+    delete[] dst_data;
+    /** [Copy objects example] */
+}
+
+/** Main program for the copy objects test
+ *
+ * @param[in] argc Number of arguments
+ * @param[in] argv Arguments
+ */
+int main(int argc, const char **argv)
+{
+    return utils::run_example(argc, argv, main_neon_copy_objects);
+}
diff --git a/examples/neon_scale.cpp b/examples/neon_scale.cpp
new file mode 100644
index 0000000000..75780c9bdb
--- /dev/null
+++ b/examples/neon_scale.cpp
@@ -0,0 +1,90 @@
+/*
+ * Copyright (c) 2016, 2017 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.
+ */
+#include "arm_compute/runtime/NEON/NEFunctions.h"
+
+#include "arm_compute/core/Types.h"
+#include "utils/Utils.h"
+
+using namespace arm_compute;
+using namespace utils;
+
+void main_neon_scale(int argc, const char **argv)
+{
+    PPMLoader ppm;
+    Image     src, dst;
+
+    if(argc < 2)
+    {
+        // Print help
+        std::cout << "Usage: ./build/neon_scale[input_image.ppm]\n\n";
+        std::cout << "No input_image provided, creating a dummy 640x480 image\n";
+        // Create an empty grayscale 640x480 image
+        src.allocator()->init(TensorInfo(640, 480, Format::U8));
+    }
+    else
+    {
+        ppm.open(argv[1]);
+        ppm.init_image(src, Format::U8);
+    }
+
+    constexpr int scale_factor = 2;
+
+    TensorInfo dst_tensor_info(src.info()->dimension(0) / scale_factor, src.info()->dimension(1) / scale_factor, Format::U8);
+
+    // Configure the destination image
+    dst.allocator()->init(dst_tensor_info);
+
+    // Create and initialize a Scale function object:
+    NEScale scale;
+    scale.configure(&src, &dst, InterpolationPolicy::NEAREST_NEIGHBOR, BorderMode::UNDEFINED);
+
+    // Allocate all the images
+    src.allocator()->allocate();
+    dst.allocator()->allocate();
+    // Fill the input image with the content of the PPM image if a filename was provided:
+    if(ppm.is_open())
+    {
+        ppm.fill_image(src);
+    }
+
+    // Run the scale operation:
+    scale.run();
+
+    // Save the result to file:
+    if(ppm.is_open())
+    {
+        const std::string output_filename = std::string(argv[1]) + "_out.ppm";
+        save_to_ppm(dst, output_filename);
+    }
+}
+
+/** Main program for convolution test
+ *
+ * @param[in] argc Number of arguments
+ * @param[in] argv Arguments ( [optional] Path to PPM image to process )
+ */
+int main(int argc, const char **argv)
+{
+    return utils::run_example(argc, argv, main_neon_scale);
+}
diff --git a/examples/neoncl_scale_median_gaussian.cpp b/examples/neoncl_scale_median_gaussian.cpp
new file mode 100644
index 0000000000..a32ba6daf6
--- /dev/null
+++ b/examples/neoncl_scale_median_gaussian.cpp
@@ -0,0 +1,126 @@
+/*
+ * Copyright (c) 2016, 2017 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.
+ */
+#define ARM_COMPUTE_CL /* So that OpenCL exceptions get caught too */
+#include "arm_compute/core/Types.h"
+#include "arm_compute/runtime/CL/CLFunctions.h"
+#include "arm_compute/runtime/CL/CLScheduler.h"
+#include "arm_compute/runtime/NEON/NEFunctions.h"
+#include "utils/Utils.h"
+
+using namespace arm_compute;
+using namespace utils;
+
+/** Example demonstrating how to use both CL and NEON functions in the same pipeline
+ *
+ * @param[in] argc Number of arguments
+ * @param[in] argv Arguments ( [optional] Path to PPM image to process )
+ */
+void main_neoncl_scale_median_gaussian(int argc, const char **argv)
+{
+    /** [NEON / OpenCL Interop] */
+    PPMLoader ppm;
+    CLImage   src, scale_median, median_gauss, dst;
+
+    CLScheduler::get().default_init();
+
+    if(argc < 2)
+    {
+        // Print help
+        std::cout << "Usage: ./build/cl_convolution [input_image.ppm]\n\n";
+        std::cout << "No input_image provided, creating a dummy 640x480 image\n";
+        // Create an empty grayscale 640x480 image
+        src.allocator()->init(TensorInfo(640, 480, Format::U8));
+    }
+    else
+    {
+        ppm.open(argv[1]);
+        ppm.init_image(src, Format::U8);
+    }
+
+    TensorInfo scale_median_info(TensorInfo(src.info()->dimension(0) / 2, src.info()->dimension(1) / 2, Format::U8));
+
+    // Configure the temporary and destination images
+    scale_median.allocator()->init(scale_median_info);
+    median_gauss.allocator()->init(scale_median_info);
+    dst.allocator()->init(scale_median_info);
+
+    // Declare and configure the functions to create the following pipeline: scale -> median -> gauss
+    CLScale       scale;
+    NEMedian3x3   median;
+    CLGaussian5x5 gauss;
+
+    scale.configure(&src, &scale_median, InterpolationPolicy::NEAREST_NEIGHBOR, BorderMode::REPLICATE);
+    median.configure(&scale_median, &median_gauss, BorderMode::REPLICATE);
+    gauss.configure(&median_gauss, &dst, BorderMode::REPLICATE);
+
+    // Allocate all the images
+    src.allocator()->allocate();
+    scale_median.allocator()->allocate();
+    median_gauss.allocator()->allocate();
+    dst.allocator()->allocate();
+
+    // Fill the input image with the content of the PPM image if a filename was provided:
+    if(ppm.is_open())
+    {
+        ppm.fill_image(src);
+    }
+
+    // Enqueue and flush the OpenCL kernel:
+    scale.run();
+
+    // Do a blocking map of the input and output buffers of the NEON function:
+    scale_median.map();
+    median_gauss.map();
+
+    // Run the NEON function:
+    median.run();
+
+    // Unmap the output buffer before it's used again by OpenCL:
+    scale_median.unmap();
+    median_gauss.unmap();
+
+    // Run the final OpenCL function:
+    gauss.run();
+
+    // Make sure all the OpenCL jobs are done executing:
+    CLScheduler::get().sync();
+
+    // Save the result to file:
+    if(ppm.is_open())
+    {
+        const std::string output_filename = std::string(argv[1]) + "_out.ppm";
+        save_to_ppm(dst, output_filename); // save_to_ppm maps and unmaps the image to store as PPM
+    }
+    /** [NEON / OpenCL Interop] */
+}
+
+/** Main program for convolution test
+ *
+ * @param[in] argc Number of arguments
+ * @param[in] argv Arguments ( [optional] Path to PPM image to process )
+ */
+int main(int argc, const char **argv)
+{
+    return utils::run_example(argc, argv, main_neoncl_scale_median_gaussian);
+}