diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox
new file mode 100644
index 0000000..1fb94ed
--- /dev/null
+++ b/docs/00_introduction.dox
@@ -0,0 +1,563 @@
+/** @mainpage Introduction
+
+@tableofcontents
+
+The Computer Vision and Machine Learning library is a set of functions optimised for both ARM CPUs and GPUs using SIMD technologies.
+
+Several builds of the library are available using various configurations:
+ - OS: Linux, Android or bare metal.
+ - Architecture: armv7a (32bit) or arm64-v8a (64bit)
+ - Technology: NEON / OpenCL / NEON and OpenCL
+ - Debug / Asserts / Release: Use a build with asserts enabled to debug your application and enable extra validation. Once you are sure your application works as expected you can switch to a release build of the library for maximum performance.
+
+@section S0_1_contact Contact / Support
+
+Please email developer@arm.com
+
+In order to facilitate the work of the support team please provide the build information of the library you are using. To get the version of the library you are using simply run:
+
+    $ strings android-armv7a-cl-asserts/libarm_compute.so | grep arm_compute_version
+    arm_compute_version=v16.12 Build options: {'embed_kernels': '1', 'opencl': '1', 'arch': 'armv7a', 'neon': '0', 'asserts': '1', 'debug': '0', 'os': 'android', 'Werror': '1'} Git hash=f51a545d4ea12a9059fe4e598a092f1fd06dc858
+
+@section S1_file_organisation File organisation
+
+This archive contains:
+ - The arm_compute header and source files
+ - The latest Khronos OpenCL 1.2 C headers from the <a href="https://www.khronos.org/registry/cl/">Khronos OpenCL registry</a>
+ - The latest Khronos cl2.hpp from the <a href="https://www.khronos.org/registry/cl/">Khronos OpenCL registry</a> (API version 2.1 when this document was written)
+ - The sources for a stub version of libOpenCL.so to help you build your application.
+ - An examples folder containing a few examples to compile and link against the library.
+ - A @ref utils folder containing headers with some boiler plate code used by the examples.
+ - This documentation.
+
+You should have the following file organisation:
+
+	.
+	├── arm_compute --> All the arm_compute headers
+	│   ├── core
+	│   │   ├── CL
+	│   │   │   ├── CLKernels.h --> Includes all the OpenCL kernels at once
+	│   │   │   ├── CL specialisation of all the generic objects interfaces (ICLTensor, ICLImage, etc.)
+	│   │   │   ├── kernels --> Folder containing all the OpenCL kernels
+	│   │   │   │   └── CL*Kernel.h
+	│   │   │   └── OpenCL.h --> Wrapper to configure the Khronos OpenCL C++ header
+	│   │   ├── CPP
+	│   │   │   └── kernels --> Folder containing all the CPP kernels
+	│   │   │   │   └── CPP*Kernel.h
+	│   │   ├── NEON
+	│   │   │   ├── kernels --> Folder containing all the NEON kernels
+	│   │   │   │   └── NE*Kernel.h
+	│   │   │   └── NEKernels.h --> Includes all the NEON kernels at once
+	│   │   ├── All common basic types (Types.h, Window, Coordinates, Iterator, etc.)
+	│   │   ├── All generic objects interfaces (ITensor, IImage, etc.)
+	│   │   └── Objects metadata classes (ImageInfo, TensorInfo, MultiImageInfo)
+	│   └── runtime
+	│       ├── CL
+	│       │   ├── CL objects & allocators (CLArray, CLImage, CLTensor, etc.)
+	│       │   ├── functions --> Folder containing all the OpenCL functions
+	│       │   │   └── CL*.h
+	│       │   └── CLFunctions.h --> Includes all the OpenCL functions at once
+	│       ├── CPP
+	│       │   └── Scheduler.h --> Basic pool of threads to execute CPP/NEON code on several cores in parallel
+	│       ├── NEON
+	│       │   ├── functions --> Folder containing all the NEON functions
+	│       │   │   └── NE*.h
+	│       │   └── NEFunctions.h --> Includes all the NEON functions at once
+	│       └── Basic implementations of the generic object interfaces (Array, Image, Tensor, etc.)
+	├── documentation
+	│   ├── index.xhtml
+	│   └── ...
+	├── documentation.xhtml -> documentation/index.xhtml
+	├── examples
+	│   ├── cl_convolution.cpp
+	│   ├── neoncl_scale_median_gaussian.cpp
+	│   ├── neon_convolution.cpp
+	│   └── neon_scale.cpp
+	├── include
+	│   └── CL
+	│       └── Khronos OpenCL C headers and C++ wrapper
+	├── opencl-1.2-stubs
+	│   └── opencl_stubs.c
+	├── src
+	│   ├── core
+	│   │   └── ... (Same structure as headers)
+	│   │       └── CL
+	│   │           └── cl_kernels --> All the OpenCL kernels
+	│   └── runtime
+	│       └── ... (Same structure as headers)
+	├── tests
+	│   ├── All test related files shared between validation and benchmark
+	│   ├── CL --> OpenCL specific files (shared)
+	│   ├── NEON --> NEON specific files (shared)
+	│   ├── benchmark --> Sources for benchmarking
+	│   │   ├── Benchmark specific files
+	│   │   ├── main.cpp --> Entry point for benchmark test framework
+	│   │   ├── CL --> OpenCL benchmarking tests
+	│   │   └── NEON --> NEON benchmarking tests
+	│   ├── validation --> Sources for validation
+	│   │   ├── Validation specific files
+	│   │   ├── main.cpp --> Entry point for validation test framework
+	│   │   ├── CL --> OpenCL validation tests
+	│   │   ├── NEON --> NEON validation tests
+	│   │   └── UNIT --> Library validation tests
+	│   └── dataset --> Datasets defining common sets of input parameters
+	└── utils --> Boiler plate code used by examples
+	    └── Utils.h
+
+@section S2_versions_changelog Release versions and changelog
+
+@subsection S2_1_versions Release versions
+
+All releases are numbered vYY.MM Where YY are the last two digits of the year, and MM the month number.
+If there is more than one release in a month then an extra sequential number is appended at the end:
+
+	v17.03 (First release of March 2017)
+	v17.03.1 (Second release of March 2017)
+	v17.04 (First release of April 2017)
+
+@note We're aiming at releasing one major public release with new features per quarter. All releases in between will only contain bug fixes.
+
+@subsection S2_2_changelog Changelog
+
+v17.06 Public major release
+ - Various bug fixes
+ - Added support for fixed point 8 bit (QS8) to the various NEON machine learning kernels.
+ - Added unit tests and benchmarks (AlexNet, LeNet)
+ - Added support for sub tensors.
+ - Added infrastructure to provide GPU specific optimisation for some OpenCL kernels.
+ - Added @ref arm_compute::OMPScheduler (OpenMP) scheduler for NEON
+ - Added @ref arm_compute::SingleThreadScheduler scheduler for NEON (For bare metal)
+ - User can specify his own scheduler by implementing the @ref arm_compute::IScheduler interface.
+ - New OpenCL kernels / functions:
+    - @ref arm_compute::CLBatchNormalizationLayerKernel / @ref arm_compute::CLBatchNormalizationLayer
+    - @ref arm_compute::CLDepthConcatenateKernel / @ref arm_compute::CLDepthConcatenate
+    - @ref arm_compute::CLHOGOrientationBinningKernel @ref arm_compute::CLHOGBlockNormalizationKernel, @ref arm_compute::CLHOGDetectorKernel / @ref arm_compute::CLHOGDescriptor @ref arm_compute::CLHOGDetector @ref arm_compute::CLHOGGradient @ref arm_compute::CLHOGMultiDetection
+    - @ref arm_compute::CLLocallyConnectedMatrixMultiplyKernel / @ref arm_compute::CLLocallyConnectedLayer
+    - @ref arm_compute::CLWeightsReshapeKernel / @ref arm_compute::CLConvolutionLayerReshapeWeights
+ - New C++ kernels:
+    - @ref arm_compute::CPPDetectionWindowNonMaximaSuppressionKernel
+ - New NEON kernels / functions:
+    - @ref arm_compute::NEBatchNormalizationLayerKernel / @ref arm_compute::NEBatchNormalizationLayer
+    - @ref arm_compute::NEDepthConcatenateKernel / @ref arm_compute::NEDepthConcatenate
+    - @ref arm_compute::NEDirectConvolutionLayerKernel / @ref arm_compute::NEDirectConvolutionLayer
+    - @ref arm_compute::NELocallyConnectedMatrixMultiplyKernel / @ref arm_compute::NELocallyConnectedLayer
+    - @ref arm_compute::NEWeightsReshapeKernel / @ref arm_compute::NEConvolutionLayerReshapeWeights
+
+v17.05 Public bug fixes release
+ - Various bug fixes
+ - Remaining of the functions ported to use accurate padding.
+ - Library does not link against OpenCL anymore (It uses dlopen / dlsym at runtime instead to determine whether or not OpenCL is available).
+ - Added "free" method to allocator.
+ - Minimum version of g++ required for armv7 Linux changed from 4.8 to 4.9
+
+v17.04 Public bug fixes release
+
+ The following functions have been ported to use the new accurate padding:
+ -  @ref arm_compute::CLColorConvertKernel
+ -  @ref arm_compute::CLEdgeNonMaxSuppressionKernel
+ -  @ref arm_compute::CLEdgeTraceKernel
+ -  @ref arm_compute::CLGaussianPyramidHorKernel
+ -  @ref arm_compute::CLGaussianPyramidVertKernel
+ -  @ref arm_compute::CLGradientKernel
+ -  @ref arm_compute::NEChannelCombineKernel
+ -  @ref arm_compute::NEFillArrayKernel
+ -  @ref arm_compute::NEGaussianPyramidHorKernel
+ -  @ref arm_compute::NEGaussianPyramidVertKernel
+ -  @ref arm_compute::NEHarrisScoreFP16Kernel
+ -  @ref arm_compute::NEHarrisScoreKernel
+ -  @ref arm_compute::NEHOGDetectorKernel
+ -  @ref arm_compute::NELogits1DMaxKernel
+ -  @ref arm_compute::NELogits1DShiftExpSumKernel
+ -  @ref arm_compute::NELogits1DNormKernel
+ -  @ref arm_compute::NENonMaximaSuppression3x3FP16Kernel
+ -  @ref arm_compute::NENonMaximaSuppression3x3Kernel
+
+
+v17.03.1 First Major public release of the sources
+ - Renamed the library to arm_compute
+ - New CPP target introduced for C++ kernels shared between NEON and CL functions.
+ - New padding calculation interface introduced and ported most kernels / functions to use it.
+ - New OpenCL kernels / functions:
+   - @ref arm_compute::CLGEMMLowpMatrixMultiplyKernel / @ref arm_compute::CLGEMMLowp
+ - New NEON kernels / functions:
+   - @ref arm_compute::NENormalizationLayerKernel / @ref arm_compute::NENormalizationLayer
+   - @ref arm_compute::NETransposeKernel / @ref arm_compute::NETranspose
+   - @ref arm_compute::NELogits1DMaxKernel, @ref arm_compute::NELogits1DShiftExpSumKernel, @ref arm_compute::NELogits1DNormKernel / @ref arm_compute::NESoftmaxLayer
+   - @ref arm_compute::NEIm2ColKernel, @ref arm_compute::NECol2ImKernel, arm_compute::NEConvolutionLayerWeightsReshapeKernel / @ref arm_compute::NEConvolutionLayer
+   - @ref arm_compute::NEGEMMMatrixAccumulateBiasesKernel / @ref arm_compute::NEFullyConnectedLayer
+   - @ref arm_compute::NEGEMMLowpMatrixMultiplyKernel / @ref arm_compute::NEGEMMLowp
+
+v17.03 Sources preview
+ - New OpenCL kernels / functions:
+   - @ref arm_compute::CLGradientKernel, @ref arm_compute::CLEdgeNonMaxSuppressionKernel, @ref arm_compute::CLEdgeTraceKernel / @ref arm_compute::CLCannyEdge
+   - GEMM refactoring + FP16 support: @ref arm_compute::CLGEMMInterleave4x4Kernel, @ref arm_compute::CLGEMMTranspose1xWKernel, @ref arm_compute::CLGEMMMatrixMultiplyKernel, @ref arm_compute::CLGEMMMatrixAdditionKernel / @ref arm_compute::CLGEMM
+   - @ref arm_compute::CLGEMMMatrixAccumulateBiasesKernel / @ref arm_compute::CLFullyConnectedLayer
+   - @ref arm_compute::CLTransposeKernel / @ref arm_compute::CLTranspose
+   - @ref arm_compute::CLLKTrackerInitKernel, @ref arm_compute::CLLKTrackerStage0Kernel, @ref arm_compute::CLLKTrackerStage1Kernel, @ref arm_compute::CLLKTrackerFinalizeKernel / @ref arm_compute::CLOpticalFlow
+   - @ref arm_compute::CLNormalizationLayerKernel / @ref arm_compute::CLNormalizationLayer
+   - @ref arm_compute::CLLaplacianPyramid, @ref arm_compute::CLLaplacianReconstruct
+ - New NEON kernels / functions:
+   - @ref arm_compute::NEActivationLayerKernel / @ref arm_compute::NEActivationLayer
+   - GEMM refactoring + FP16 support (Requires armv8.2 CPU): @ref arm_compute::NEGEMMInterleave4x4Kernel, @ref arm_compute::NEGEMMTranspose1xWKernel, @ref arm_compute::NEGEMMMatrixMultiplyKernel, @ref arm_compute::NEGEMMMatrixAdditionKernel / @ref arm_compute::NEGEMM
+   - @ref arm_compute::NEPoolingLayerKernel / @ref arm_compute::NEPoolingLayer
+
+v17.02.1 Sources preview
+ - New OpenCL kernels / functions:
+   - @ref arm_compute::CLLogits1DMaxKernel, @ref arm_compute::CLLogits1DShiftExpSumKernel, @ref arm_compute::CLLogits1DNormKernel / @ref arm_compute::CLSoftmaxLayer
+   - @ref arm_compute::CLPoolingLayerKernel / @ref arm_compute::CLPoolingLayer
+   - @ref arm_compute::CLIm2ColKernel, @ref arm_compute::CLCol2ImKernel, @ref arm_compute::CLConvolutionLayerWeightsReshapeKernel / @ref arm_compute::CLConvolutionLayer
+   - @ref arm_compute::CLRemapKernel / @ref arm_compute::CLRemap
+   - @ref arm_compute::CLGaussianPyramidHorKernel, @ref arm_compute::CLGaussianPyramidVertKernel / @ref arm_compute::CLGaussianPyramid, @ref arm_compute::CLGaussianPyramidHalf, @ref arm_compute::CLGaussianPyramidOrb
+   - @ref arm_compute::CLMinMaxKernel, @ref arm_compute::CLMinMaxLocationKernel / @ref arm_compute::CLMinMaxLocation
+   - @ref arm_compute::CLNonLinearFilterKernel / @ref arm_compute::CLNonLinearFilter
+ - New NEON FP16 kernels (Requires armv8.2 CPU)
+   - @ref arm_compute::NEAccumulateWeightedFP16Kernel
+   - @ref arm_compute::NEBox3x3FP16Kernel
+   - @ref arm_compute::NENonMaximaSuppression3x3FP16Kernel
+
+v17.02 Sources preview
+ - New OpenCL kernels / functions:
+   - @ref arm_compute::CLActivationLayerKernel / @ref arm_compute::CLActivationLayer
+   - @ref arm_compute::CLChannelCombineKernel / @ref arm_compute::CLChannelCombine
+   - @ref arm_compute::CLDerivativeKernel / @ref arm_compute::CLChannelExtract
+   - @ref arm_compute::CLFastCornersKernel / @ref arm_compute::CLFastCorners
+   - @ref arm_compute::CLMeanStdDevKernel / @ref arm_compute::CLMeanStdDev
+ - New NEON kernels / functions:
+   - HOG / SVM: @ref arm_compute::NEHOGOrientationBinningKernel, @ref arm_compute::NEHOGBlockNormalizationKernel, @ref arm_compute::NEHOGDetectorKernel, arm_compute::NEHOGNonMaximaSuppressionKernel / @ref arm_compute::NEHOGDescriptor, @ref arm_compute::NEHOGDetector, @ref arm_compute::NEHOGGradient, @ref arm_compute::NEHOGMultiDetection
+   - @ref arm_compute::NENonLinearFilterKernel / @ref arm_compute::NENonLinearFilter
+ - Introduced a CLScheduler to manage the default context and command queue used by the runtime library and create synchronisation events.
+ - Switched all the kernels / functions to use tensors instead of images.
+ - Updated documentation to include instructions to build the library from sources.
+
+v16.12 Binary preview release
+ - Original release
+
+@section S3_how_to_build How to build the library and the examples
+
+@subsection S3_1_build_options Build options
+
+scons 2.3 or above is required to build the library.
+To see the build options available simply run ```scons -h```:
+
+	debug: Debug (yes|no)
+		default: False
+		actual: False
+
+	asserts: Enable asserts (this flag is forced to 1 for debug=1) (yes|no)
+		default: False
+		actual: False
+
+	arch: Target Architecture (armv7a|arm64-v8a|arm64-v8.2-a|x86_32|x86_64)
+		default: armv7a
+		actual: armv7a
+
+	os: Target OS (linux|android|bare_metal)
+		default: linux
+		actual: linux
+
+	build: Build type (native|cross_compile)
+		default: cross_compile
+		actual: cross_compile
+
+	examples: Build example programs (yes|no)
+		default: True
+		actual: True
+
+	Werror: Enable/disable the -Werror compilation flag (yes|no)
+		default: True
+		actual: True
+
+	opencl: Enable OpenCL support (yes|no)
+		default: True
+		actual: True
+
+	neon: Enable Neon support (yes|no)
+		default: False
+		actual: False
+
+	embed_kernels: Embed OpenCL kernels in library binary (yes|no)
+		default: False
+		actual: False
+
+	set_soname: Set the library's soname and shlibversion (requires SCons 2.4 or above) (yes|no)
+		default: False
+		actual: False
+
+	openmp: Enable OpenMP backend (yes|no)
+		default: False
+		actual: False
+
+	cppthreads: Enable C++11 threads backend (yes|no)
+		default: True
+		actual: True
+
+	build_dir: Specify sub-folder for the build ( /path/to/build_dir )
+		default: .
+		actual: .
+
+	extra_cxx_flags: Extra CXX flags to be appended to the build command
+		default:
+		actual:
+
+	pmu: Enable PMU counters (yes|no)
+		default: False
+		actual: False
+
+	validation_tests: Build validation test programs (yes|no)
+		default: False
+		actual: False
+
+	benchmark_tests: Build benchmark test programs (yes|no)
+		default: False
+		actual: False
+
+@b debug / @b asserts:
+ - With debug=1 asserts are enabled, and the library is built with symbols and no optimisations enabled.
+ - With debug=0 and asserts=1: Optimisations are enabled and symbols are removed, however all the asserts are still present (This is about 20% slower than the release build)
+ - With debug=0 and asserts=0: All optimisations are enable and no validation is performed, if the application misuses the library it is likely to result in a crash. (Only use this mode once you are sure your application is working as expected).
+
+@b arch: The x86_32 and x86_64 targets can only be used with neon=0 and opencl=1.
+
+@b os: Choose the operating system you are targeting: Linux, Android or bare metal.
+@note bare metal can only be used for NEON (not OpenCL), only static libraries get built and NEON's multi-threading support is disabled.
+
+@b build: you can either build directly on your device (native) or cross compile from your desktop machine (cross-compile). In both cases make sure the compiler is available in your path.
+
+@note If you want to natively compile for 32bit on a 64bit ARM device running a 64bit OS then you will have to use cross-compile too.
+
+@b Werror: If you are compiling using the same toolchains as the ones used in this guide then there shouldn't be any warning and therefore you should be able to keep Werror=1. If with a different compiler version the library fails to build because of warnings interpreted as errors then, if you are sure the warnings are not important, you might want to try to build with Werror=0 (But please do report the issue either on Github or by an email to developer@arm.com so that the issue can be addressed).
+
+@b opencl / @b neon: Choose which SIMD technology you want to target. (NEON for ARM Cortex-A CPUs or OpenCL for ARM Mali GPUs)
+
+@b embed_kernels: For OpenCL only: set embed_kernels=1 if you want the OpenCL kernels to be built in the library's binaries instead of being read from separate ".cl" files. If embed_kernels is set to 0 then the application can set the path to the folder containing the OpenCL kernel files by calling CLKernelLibrary::init(). By default the path is set to "./cl_kernels".
+
+@b set_soname: Do you want to build the versioned version of the library ?
+
+If enabled the library will contain a SONAME and SHLIBVERSION and some symlinks will automatically be created between the objects.
+Example:
+  libarm_compute_core.so -> libarm_compute_core.so.1.0.0
+  libarm_compute_core.so.1 -> libarm_compute_core.so.1.0.0
+  libarm_compute_core.so.1.0.0
+
+@note This options is disabled by default as it requires SCons version 2.4 or above.
+
+@b extra_cxx_flags: Custom CXX flags which will be appended to the end of the build command.
+
+@b build_dir: Build the library in a subfolder of the "build" folder. (Allows to build several configurations in parallel).
+
+@b examples: Build or not the examples
+
+@b validation_tests: Enable the build of the validation suite.
+
+@note You will need the Boost Test and Program options headers and libraries to build the validation tests. See @ref building_boost for more information.
+
+@b benchmark_tests: Enable the build of the benchmark tests
+
+@b pmu: Enable the PMU cycle counter to measure execution time in benchmark tests. (Your device needs to support it)
+
+@note You will need the Boost Program options and Google Benchmark headers and libraries to build the benchmark tests. See @ref building_google_benchmark for more information.
+
+@b openmp Build in the OpenMP scheduler for NEON.
+
+@note Only works when building with g++ not clang++
+
+@b cppthreads Build in the C++11 scheduler for NEON.
+
+@sa arm_compute::Scheduler::set
+
+@subsection S3_2_linux Linux
+
+@subsubsection S3_2_1_library How to build the library ?
+
+For Linux, the library was successfully built and tested using the following Linaro GCC toolchain:
+
+ - gcc-linaro-arm-linux-gnueabihf-4.9-2014.07_linux
+ - gcc-linaro-4.9-2016.02-x86_64_aarch64-linux-gnu
+ - gcc-linaro-6.3.1-2017.02-i686_aarch64-linux-gnu
+
+@note If you are building with opencl=1 then scons will expect to find libOpenCL.so either in the current directory or in "build" (See the section below if you need a stub OpenCL library to link against)
+
+To cross-compile the library in debug mode, with NEON only support, for Linux 32bit:
+
+	scons Werror=1 -j8 debug=1 neon=1 opencl=0 os=linux arch=armv7a
+
+To cross-compile the library in asserts mode, with OpenCL only support, for Linux 64bit:
+
+	scons Werror=1 -j8 debug=0 asserts=1 neon=0 opencl=1 embed_kernels=1 os=linux arch=arm64-v8a
+
+You can also compile the library natively on an ARM device by using <b>build=native</b>:
+
+	scons Werror=1 -j8 debug=0 neon=1 opencl=0 os=linux arch=arm64-v8a build=native
+	scons Werror=1 -j8 debug=0 neon=1 opencl=0 os=linux arch=armv7a build=native
+
+@note g++ for ARM is mono-arch, therefore if you want to compile for Linux 32bit on a Linux 64bit platform you will have to use a cross compiler.
+
+For example on a 64bit Debian based system you would have to install <b>g++-arm-linux-gnueabihf</b>
+
+	apt-get install g++-arm-linux-gnueabihf
+
+Then run
+
+	scons Werror=1 -j8 debug=0 neon=1 opencl=0 os=linux arch=armv7a build=cross_compile
+
+or simply remove the build parameter as build=cross_compile is the default value:
+
+	scons Werror=1 -j8 debug=0 neon=1 opencl=0 os=linux arch=armv7a
+
+@attention To cross compile with opencl=1 you need to make sure to have a version of libOpenCL matching your target architecture.
+
+@subsubsection S3_2_2_examples How to manually build the examples ?
+
+The examples get automatically built by scons as part of the build process of the library described above. This section just describes how you can build and link your own application against our library.
+
+@note The following command lines assume the arm_compute and libOpenCL binaries are present in the current directory or in the system library path. If this is not the case you can specify the location of the pre-built library with the compiler option -L. When building the OpenCL example the commands below assume that the CL headers are located in the include folder where the command is executed.
+
+To cross compile a NEON example for Linux 32bit:
+
+	arm-linux-gnueabihf-g++ examples/neon_convolution.cpp utils/Utils.cpp -I. -std=c++11 -mfpu=neon -L. -larm_compute -o neon_convolution
+
+To cross compile a NEON example for Linux 64bit:
+
+	aarch64-linux-gnu-g++ examples/neon_convolution.cpp utils/Utils.cpp -I. -std=c++11 -L. -larm_compute -o neon_convolution
+
+(notice the only difference with the 32 bit command is that we don't need the -mfpu option and the compiler's name is different)
+
+To cross compile an OpenCL example for Linux 32bit:
+
+	arm-linux-gnueabihf-g++ examples/cl_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -mfpu=neon -L. -larm_compute -lOpenCL -o cl_convolution
+
+To cross compile an OpenCL example for Linux 64bit:
+
+	aarch64-linux-gnu-g++ examples/cl_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -L. -larm_compute -lOpenCL -o cl_convolution
+
+(notice the only difference with the 32 bit command is that we don't need the -mfpu option and the compiler's name is different)
+
+To compile natively (i.e directly on an ARM device) for NEON for Linux 32bit:
+
+	g++ examples/neon_convolution.cpp utils/Utils.cpp -I. -std=c++11 -mfpu=neon -larm_compute -o neon_convolution
+
+To compile natively (i.e directly on an ARM device) for NEON for Linux 64bit:
+
+	g++ examples/neon_convolution.cpp utils/Utils.cpp -I. -std=c++11 -larm_compute -o neon_convolution
+
+(notice the only difference with the 32 bit command is that we don't need the -mfpu option)
+
+To compile natively (i.e directly on an ARM device) for OpenCL for Linux 32bit or Linux 64bit:
+
+	g++ examples/cl_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -larm_compute -lOpenCL -o cl_convolution
+
+
+@note These two commands assume libarm_compute.so is available in your library path, if not add the path to it using -L
+
+To run the built executable simply run:
+
+	LD_LIBRARY_PATH=build ./neon_convolution
+
+or
+
+	LD_LIBRARY_PATH=build ./cl_convolution
+
+@note If you built the library with support for both OpenCL and NEON you will need to link against OpenCL even if your application only uses NEON.
+
+@subsection S3_3_android Android
+
+For Android, the library was successfully built and tested using Google's standalone toolchains:
+ - arm-linux-androideabi-4.9 for armv7a (clang++)
+ - aarch64-linux-android-4.9 for arm64-v8a (g++)
+
+Here is a guide to <a href="https://developer.android.com/ndk/guides/standalone_toolchain.html">create your Android standalone toolchains from the NDK</a>
+
+- Download the NDK r14 from here: https://developer.android.com/ndk/downloads/index.html
+- Make sure you have Python 2 installed on your machine.
+- Generate the 32 and/or 64 toolchains by running the following commands:
+
+
+	$NDK/build/tools/make_standalone_toolchain.py --arch arm64 --install-dir $MY_TOOLCHAINS/aarch64-linux-android-4.9 --stl gnustl
+	$NDK/build/tools/make_standalone_toolchain.py --arch arm --install-dir $MY_TOOLCHAINS/arm-linux-androideabi-4.9 --stl gnustl
+
+@attention Due to some NDK issues make sure you use g++ & gnustl for aarch64 and clang++ & gnustl for armv7
+
+@note Make sure to add the toolchains to your PATH: export PATH=$PATH:$MY_TOOLCHAINS/aarch64-linux-android-4.9/bin:$MY_TOOLCHAINS/arm-linux-androideabi-4.9/bin
+
+@subsubsection S3_3_1_library How to build the library ?
+
+@note If you are building with opencl=1 then scons will expect to find libOpenCL.so either in the current directory or in "build" (See the section below if you need a stub OpenCL library to link against)
+
+To cross-compile the library in debug mode, with NEON only support, for Android 32bit:
+
+	CXX=clang++ CC=clang scons Werror=1 -j8 debug=1 neon=1 opencl=0 os=android arch=armv7a
+
+To cross-compile the library in asserts mode, with OpenCL only support, for Android 64bit:
+
+	scons Werror=1 -j8 debug=0 asserts=1 neon=0 opencl=1 embed_kernels=1 os=android arch=arm64-v8a
+
+@subsubsection S3_3_2_examples How to manually build the examples ?
+
+The examples get automatically built by scons as part of the build process of the library described above. This section just describes how you can build and link your own application against our library.
+
+@note The following command lines assume the arm_compute and libOpenCL binaries are present in the current directory or in the system library path. If this is not the case you can specify the location of the pre-built library with the compiler option -L. When building the OpenCL example the commands below assume that the CL headers are located in the include folder where the command is executed.
+
+Once you've got your Android standalone toolchain built and added to your path you can do the following:
+
+To cross compile a NEON example:
+
+	#32 bit:
+	arm-linux-androideabi-clang++ examples/neon_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -larm_compute-static -L. -o neon_convolution_arm -static-libstdc++ -pie
+	#64 bit:
+	aarch64-linux-android-g++ examples/neon_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -larm_compute-static -L. -o neon_convolution_aarch64 -static-libstdc++ -pie
+
+To cross compile an OpenCL example:
+
+	#32 bit:
+	arm-linux-androideabi-clang++ examples/cl_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -larm_compute-static -L. -o cl_convolution_arm -static-libstdc++ -pie -lOpenCL
+	#64 bit:
+	aarch64-linux-android-g++ examples/cl_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -larm_compute-static -L. -o cl_convolution_aarch64 -static-libstdc++ -pie -lOpenCL
+
+@note Due to some issues in older versions of the Mali OpenCL DDK (<= r13p0), we recommend to link arm_compute statically on Android.
+
+Then you need to do is upload the executable and the shared library to the device using ADB:
+
+	adb push neon_convolution_arm /data/local/tmp/
+	adb push cl_convolution_arm /data/local/tmp/
+	adb shell chmod 777 -R /data/local/tmp/
+
+And finally to run the example:
+
+	adb shell /data/local/tmp/neon_convolution_arm
+	adb shell /data/local/tmp/cl_convolution_arm
+
+For 64bit:
+
+	adb push neon_convolution_aarch64 /data/local/tmp/
+	adb push cl_convolution_aarch64 /data/local/tmp/
+	adb shell chmod 777 -R /data/local/tmp/
+
+And finally to run the example:
+
+	adb shell /data/local/tmp/neon_convolution_aarch64
+	adb shell /data/local/tmp/cl_convolution_aarch64
+
+@subsection S3_4_cl_stub_library The OpenCL stub library
+
+In the opencl-1.2-stubs folder you will find the sources to build a stub OpenCL library which then can be used to link your application or arm_compute against.
+
+If you preferred you could retrieve the OpenCL library from your device and link against this one but often this library will have dependencies on a range of system libraries forcing you to link your application against those too even though it is not using them.
+
+@warning This OpenCL library provided is a stub and *not* a real implementation. You can use it to resolve OpenCL's symbols in arm_compute while building the example but you must make sure the real libOpenCL.so is in your PATH when running the example or it will not work.
+
+To cross-compile the stub OpenCL library simply run:
+
+	<target-prefix>-gcc -o libOpenCL.so -Iinclude opencl-1.2-stubs/opencl_stubs.c -fPIC -shared
+
+For example:
+
+	<target-prefix>-gcc -o libOpenCL.so -Iinclude opencl-1.2-stubs/opencl_stubs.c -fPIC -shared
+	#Linux 32bit
+	arm-linux-gnueabihf-gcc -o libOpenCL.so -Iinclude opencl-1.2-stubs/opencl_stubs.c -fPIC -shared
+	#Linux 64bit
+	aarch64-linux-gnu-gcc -o libOpenCL.so -Iinclude -shared opencl-1.2-stubs/opencl_stubs.c -fPIC
+	#Android 32bit
+	arm-linux-androideabi-clang -o libOpenCL.so -Iinclude -shared opencl-1.2-stubs/opencl_stubs.c -fPIC -shared
+	#Android 64bit
+	aarch64-linux-android-gcc -o libOpenCL.so -Iinclude -shared opencl-1.2-stubs/opencl_stubs.c -fPIC -shared
+*/