Blame - docs/00_introduction.dox - ml/ComputeLibrary

blob: 9cabb9707b38ea3c18dea69544c9200519d56093 [file] [log] [blame]

Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	1	/** @mainpage Introduction
				2
				3	@tableofcontents
				4
				5	The Computer Vision and Machine Learning library is a set of functions optimised for both ARM CPUs and GPUs using SIMD technologies.
				6
				7	Several builds of the library are available using various configurations:
				8	- OS: Linux, Android or bare metal.
				9	- Architecture: armv7a (32bit) or arm64-v8a (64bit)
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	10	- Technology: NEON / OpenCL / GLES_COMPUTE / NEON and OpenCL and GLES_COMPUTE
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	11	- 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.
				12
				13	@section S0_1_contact Contact / Support
				14
				15	Please email developer@arm.com
				16
				17	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:
				18
				19	$ strings android-armv7a-cl-asserts/libarm_compute.so \| grep arm_compute_version
				20	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
				21
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	22	@section S0_2_prebuilt_binaries Pre-built binaries
				23
				24	For each release we provide some pre-built binaries of the library [here](https://github.com/ARM-software/ComputeLibrary/releases)
				25
				26	These binaries have been built using the following toolchains:
				27	- Linux armv7a: gcc-linaro-arm-linux-gnueabihf-4.9-2014.07_linux
				28	- Linux arm64-v8a: gcc-linaro-4.9-2016.02-x86_64_aarch64-linux-gnu
				29	- Android armv7a: clang++ / gnustl NDK r14
				30	- Android am64-v8a: clang++ / gnustl NDK r14
				31
				32	@warning Make sure to use a compatible toolchain to build your application or you will get some std::bad_alloc errors at runtime.
				33
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	34	@section S1_file_organisation File organisation
				35
				36	This archive contains:
				37	- The arm_compute header and source files
				38	- The latest Khronos OpenCL 1.2 C headers from the <a href="https://www.khronos.org/registry/cl/">Khronos OpenCL registry</a>
				39	- 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)
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	40	- The latest Khronos OpenGL ES 3.1 C headers from the <a href="https://www.khronos.org/registry/gles/">Khronos OpenGL ES registry</a>
				41	- The latest Khronos EGL 1.5 C headers from the <a href="https://www.khronos.org/registry/gles/">Khronos EGL registry</a>
				42	- The sources for a stub version of libOpenCL.so, libGLESv1_CM.so, libGLESv2.so and libEGL.so to help you build your application.
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	43	- An examples folder containing a few examples to compile and link against the library.
				44	- A @ref utils folder containing headers with some boiler plate code used by the examples.
				45	- This documentation.
				46
				47	You should have the following file organisation:
				48
				49	.
				50	├── arm_compute --> All the arm_compute headers
				51	│ ├── core
				52	│ │ ├── CL
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	53	│ │ │ ├── CLKernelLibrary.h --> Manages all the OpenCL kernels compilation and caching, provides accessors for the OpenCL Context.
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	54	│ │ │ ├── CLKernels.h --> Includes all the OpenCL kernels at once
				55	│ │ │ ├── CL specialisation of all the generic objects interfaces (ICLTensor, ICLImage, etc.)
				56	│ │ │ ├── kernels --> Folder containing all the OpenCL kernels
				57	│ │ │ │ └── CL*Kernel.h
				58	│ │ │ └── OpenCL.h --> Wrapper to configure the Khronos OpenCL C++ header
				59	│ │ ├── CPP
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	60	│ │ │ ├── CPPKernels.h --> Includes all the CPP kernels at once
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	61	│ │ │ └── kernels --> Folder containing all the CPP kernels
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	62	│ │ │ └── CPP*Kernel.h
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	63	│ │ ├── GLES_COMPUTE
				64	│ │ │ ├── GCKernelLibrary.h --> Manages all the GLES kernels compilation and caching, provides accessors for the GLES Context.
				65	│ │ │ ├── GCKernels.h --> Includes all the GLES kernels at once
				66	│ │ │ ├── GLES specialisation of all the generic objects interfaces (IGCTensor, IGCImage, etc.)
				67	│ │ │ ├── kernels --> Folder containing all the GLES kernels
				68	│ │ │ │ └── GC*Kernel.h
				69	│ │ │ └── OpenGLES.h --> Wrapper to configure the Khronos EGL and OpenGL ES C header
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	70	│ │ ├── NEON
				71	│ │ │ ├── kernels --> Folder containing all the NEON kernels
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	72	│ │ │ │ ├── arm64 --> Folder containing the interfaces for the assembly arm64 NEON kernels
				73	│ │ │ │ ├── arm32 --> Folder containing the interfaces for the assembly arm32 NEON kernels
				74	│ │ │ │ ├── assembly --> Folder containing the NEON assembly routines.
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	75	│ │ │ │ └── NE*Kernel.h
				76	│ │ │ └── NEKernels.h --> Includes all the NEON kernels at once
				77	│ │ ├── All common basic types (Types.h, Window, Coordinates, Iterator, etc.)
				78	│ │ ├── All generic objects interfaces (ITensor, IImage, etc.)
				79	│ │ └── Objects metadata classes (ImageInfo, TensorInfo, MultiImageInfo)
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	80	│ ├── graph
				81	│ │ ├── CL --> OpenCL specific operations
				82	│ │ │ └── CLMap.h / CLUnmap.h
				83	│ │ ├── nodes
				84	│ │ │ └── The various nodes supported by the graph API
				85	│ │ ├── Nodes.h --> Includes all the Graph nodes at once.
				86	│ │ └── Graph objects ( INode, ITensorAccessor, Graph, etc.)
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	87	│ └── runtime
				88	│ ├── CL
				89	│ │ ├── CL objects & allocators (CLArray, CLImage, CLTensor, etc.)
				90	│ │ ├── functions --> Folder containing all the OpenCL functions
				91	│ │ │ └── CL*.h
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	92	│ │ ├── CLScheduler.h --> Interface to enqueue OpenCL kernels and get/set the OpenCL CommandQueue and ICLTuner.
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	93	│ │ └── CLFunctions.h --> Includes all the OpenCL functions at once
				94	│ ├── CPP
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	95	│ │ ├── CPPKernels.h --> Includes all the CPP functions at once.
				96	│ │ └── CPPScheduler.h --> Basic pool of threads to execute CPP/NEON code on several cores in parallel
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	97	│ ├── GLES_COMPUTE
				98	│ │ ├── GLES objects & allocators (GCArray, GCImage, GCTensor, etc.)
				99	│ │ ├── functions --> Folder containing all the GLES functions
				100	│ │ │ └── GC*.h
				101	│ │ ├── GCScheduler.h --> Interface to enqueue GLES kernels and get/set the GLES CommandQueue.
				102	│ │ └── GCFunctions.h --> Includes all the GLES functions at once
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	103	│ ├── NEON
				104	│ │ ├── functions --> Folder containing all the NEON functions
				105	│ │ │ └── NE*.h
				106	│ │ └── NEFunctions.h --> Includes all the NEON functions at once
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	107	│ ├── OMP
				108	│ │ └── OMPScheduler.h --> OpenMP scheduler (Alternative to the CPPScheduler)
				109	│ ├── Memory manager files (LifetimeManager, PoolManager, etc.)
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	110	│ └── Basic implementations of the generic object interfaces (Array, Image, Tensor, etc.)
				111	├── documentation
				112	│ ├── index.xhtml
				113	│ └── ...
				114	├── documentation.xhtml -> documentation/index.xhtml
				115	├── examples
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	116	│ ├── cl_*.cpp --> OpenCL examples
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	117	│ ├── gc_*.cpp --> GLES compute shaders examples
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	118	│ ├── graph_*.cpp --> Graph examples
				119	│ ├── neoncl_*.cpp --> NEON / OpenCL interoperability examples
				120	│ └── neon_*.cpp --> NEON examples
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	121	├── include
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	122	│ ├── CL
				123	│ │ └── Khronos OpenCL C headers and C++ wrapper
				124	│ ├── half --> FP16 library available from http://half.sourceforge.net
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	125	│ ├── libnpy --> Library to load / write npy buffers, available from https://github.com/llohse/libnpy
				126	│ └── linux --> Headers only needed for Linux builds
				127	│ └── Khronos EGL and OpenGLES headers
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	128	├── opencl-1.2-stubs
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	129	│ └── opencl_stubs.c --> OpenCL stubs implementation
				130	├── opengles-3.1-stubs
				131	│ ├── EGL.c --> EGL stubs implementation
				132	│ └── GLESv2.c --> GLESv2 stubs implementation
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	133	├── scripts
				134	│ ├── caffe_data_extractor.py --> Basic script to export weights from Caffe to npy files
				135	│ └── tensorflow_data_extractor.py --> Basic script to export weights from Tensor Flow to npy files
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	136	├── src
				137	│ ├── core
				138	│ │ └── ... (Same structure as headers)
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	139	│ │ ├── CL
				140	│ │ │ └── cl_kernels --> All the OpenCL kernels
				141	│ │ └── GLES_COMPUTE
				142	│ │ └── cs_shaders --> All the OpenGL ES Compute Shaders
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	143	│ ├── graph
				144	│ │ └── ... (Same structure as headers)
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	145	│ └── runtime
				146	│ └── ... (Same structure as headers)
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	147	├── support
				148	│ └── Various headers to work around toolchains / platform issues.
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	149	├── tests
				150	│ ├── All test related files shared between validation and benchmark
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	151	│ ├── CL --> OpenCL accessors
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	152	│ ├── GLES_COMPUTE --> GLES accessors
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	153	│ ├── NEON --> NEON accessors
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	154	│ ├── benchmark --> Sources for benchmarking
				155	│ │ ├── Benchmark specific files
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	156	│ │ ├── CL --> OpenCL benchmarking tests
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	157	│ │ ├── GLES_COMPUTE --> GLES benchmarking tests
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	158	│ │ └── NEON --> NEON benchmarking tests
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	159	│ ├── datasets
				160	│ │ └── Datasets for all the validation / benchmark tests, layer configurations for various networks, etc.
				161	│ ├── framework
				162	│ │ └── Boiler plate code for both validation and benchmark test suites (Command line parsers, instruments, output loggers, etc.)
				163	│ ├── networks
				164	│ │ └── Examples of how to instantiate networks.
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	165	│ ├── validation --> Sources for validation
				166	│ │ ├── Validation specific files
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	167	│ │ ├── CL --> OpenCL validation tests
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	168	│ │ ├── GLES_COMPUTE --> GLES validation tests
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	169	│ │ ├── CPP --> C++ reference implementations
				170	│ │ ├── fixtures
				171	│ │ │ └── Fixtures to initialise and run the runtime Functions.
				172	│ │ └── NEON --> NEON validation tests
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	173	│ └── dataset --> Datasets defining common sets of input parameters
				174	└── utils --> Boiler plate code used by examples
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	175	└── Various utilities to print types, load / store assets, etc.
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	176
				177	@section S2_versions_changelog Release versions and changelog
				178
				179	@subsection S2_1_versions Release versions
				180
				181	All releases are numbered vYY.MM Where YY are the last two digits of the year, and MM the month number.
				182	If there is more than one release in a month then an extra sequential number is appended at the end:
				183
				184	v17.03 (First release of March 2017)
				185	v17.03.1 (Second release of March 2017)
				186	v17.04 (First release of April 2017)
				187
				188	@note We're aiming at releasing one major public release with new features per quarter. All releases in between will only contain bug fixes.
				189
				190	@subsection S2_2_changelog Changelog
				191
Gian Marco	ff85093	2017-12-11 12:37:17 +0000	[diff] [blame]	192	v17.12 Public major release
				193	- Most machine learning functions on OpenCL support the new data type QASYMM8
				194	- Introduced logging interface
				195	- Introduced opencl timer
				196	- Reworked GEMMLowp interface
				197	- Added new NEON assembly kernels for GEMMLowp, SGEMM and HGEMM
				198	- Added validation method for most Machine Learning kernels / functions
				199	- Added new graph examples such as googlenet, mobilenet, squeezenet, vgg16 and vgg19
				200	- Added sgemm example for OpenCL
				201	- Added absolute difference example for GLES compute
				202	- Added new tests and benchmarks in validation and benchmark frameworks
				203	- Added new kernels / functions for GLES compute
				204
				205	- New OpenGL ES kernels / functions
				206	- @ref arm_compute::GCAbsoluteDifferenceKernel / @ref arm_compute::GCAbsoluteDifference
				207	- @ref arm_compute::GCActivationLayerKernel / @ref arm_compute::GCActivationLayer
				208	- @ref arm_compute::GCBatchNormalizationLayerKernel / @ref arm_compute::GCBatchNormalizationLayer
				209	- @ref arm_compute::GCCol2ImKernel
				210	- @ref arm_compute::GCDepthConcatenateLayerKernel / @ref arm_compute::GCDepthConcatenateLayer
				211	- @ref arm_compute::GCDirectConvolutionLayerKernel / @ref arm_compute::GCDirectConvolutionLayer
				212	- @ref arm_compute::GCDropoutLayerKernel / @ref arm_compute::GCDropoutLayer
				213	- @ref arm_compute::GCFillBorderKernel / @ref arm_compute::GCFillBorder
				214	- @ref arm_compute::GCGEMMInterleave4x4Kernel / @ref arm_compute::GCGEMMInterleave4x4
				215	- @ref arm_compute::GCGEMMMatrixAccumulateBiasesKernel / @ref arm_compute::GCGEMMMatrixAdditionKernel / @ref arm_compute::GCGEMMMatrixMultiplyKernel / @ref arm_compute::GCGEMM
				216	- @ref arm_compute::GCGEMMTranspose1xWKernel / @ref arm_compute::GCGEMMTranspose1xW
				217	- @ref arm_compute::GCIm2ColKernel
				218	- @ref arm_compute::GCNormalizationLayerKernel / @ref arm_compute::GCNormalizationLayer
				219	- @ref arm_compute::GCPixelWiseMultiplicationKernel / @ref arm_compute::GCPixelWiseMultiplication
				220	- @ref arm_compute::GCPoolingLayerKernel / @ref arm_compute::GCPoolingLayer
				221	- @ref arm_compute::GCLogits1DMaxKernel / @ref arm_compute::GCLogits1DShiftExpSumKernel / @ref arm_compute::GCLogits1DNormKernel / @ref arm_compute::GCSoftmaxLayer
				222	- @ref arm_compute::GCTransposeKernel / @ref arm_compute::GCTranspose
				223
				224	- New NEON kernels / functions
				225	- @ref arm_compute::NEGEMMLowpAArch64A53Kernel / @ref arm_compute::NEGEMMLowpAArch64Kernel / @ref arm_compute::NEGEMMLowpAArch64V8P4Kernel / arm_compute::NEGEMMInterleavedBlockedKernel / @ref arm_compute::NEGEMMLowpAssemblyMatrixMultiplyCore
				226	- @ref arm_compute::NEHGEMMAArch64FP16Kernel
				227	- @ref arm_compute::NEDepthwiseConvolutionLayer3x3Kernel / @ref arm_compute::NEDepthwiseIm2ColKernel / @ref arm_compute::NEGEMMMatrixVectorMultiplyKernel / @ref arm_compute::NEDepthwiseVectorToTensorKernel / @ref arm_compute::NEDepthwiseConvolutionLayer
				228	- @ref arm_compute::NEGEMMLowpOffsetContributionKernel / @ref arm_compute::NEGEMMLowpMatrixAReductionKernel / @ref arm_compute::NEGEMMLowpMatrixBReductionKernel / @ref arm_compute::NEGEMMLowpMatrixMultiplyCore
				229	- @ref arm_compute::NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel / @ref arm_compute::NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint
				230	- @ref arm_compute::NEGEMMLowpQuantizeDownInt32ToUint8ScaleKernel / @ref arm_compute::NEGEMMLowpQuantizeDownInt32ToUint8Scale
				231	- @ref arm_compute::NEWinogradLayerKernel / @ref arm_compute::NEWinogradLayer
				232
				233	- New OpenCL kernels / functions
				234	- @ref arm_compute::CLGEMMLowpOffsetContributionKernel / @ref arm_compute::CLGEMMLowpMatrixAReductionKernel / @ref arm_compute::CLGEMMLowpMatrixBReductionKernel / @ref arm_compute::CLGEMMLowpMatrixMultiplyCore
				235	- @ref arm_compute::CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel / @ref arm_compute::CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint
				236	- @ref arm_compute::CLGEMMLowpQuantizeDownInt32ToUint8ScaleKernel / @ref arm_compute::CLGEMMLowpQuantizeDownInt32ToUint8Scale
				237
				238	- New graph nodes for NEON and OpenCL
				239	- @ref arm_compute::graph::BranchLayer
				240	- @ref arm_compute::graph::DepthConvertLayer
				241	- @ref arm_compute::graph::DepthwiseConvolutionLayer
				242	- @ref arm_compute::graph::DequantizationLayer
				243	- @ref arm_compute::graph::FlattenLayer
				244	- @ref arm_compute::graph::QuantizationLayer
				245	- @ref arm_compute::graph::ReshapeLayer
				246
Anthony Barbier	3c5b4ff	2017-10-12 13:20:52 +0100	[diff] [blame]	247	v17.10 Public maintenance release
				248	- Bug fixes:
				249	- Check the maximum local workgroup size supported by OpenCL devices
				250	- Minor documentation updates (Fixed instructions to build the examples)
				251	- Introduced a arm_compute::graph::GraphContext
				252	- Added a few new Graph nodes, support for branches and grouping.
				253	- Automatically enable cl_printf in debug builds
				254	- Fixed bare metal builds for armv7a
				255	- Added AlexNet and cartoon effect examples
				256	- Fixed library builds: libraries are no longer built as supersets of each other.(It means application using the Runtime part of the library now need to link against both libarm_compute_core and libarm_compute)
				257
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	258	v17.09 Public major release
				259	- Experimental Graph support: initial implementation of a simple stream API to easily chain machine learning layers.
				260	- Memory Manager (@ref arm_compute::BlobLifetimeManager, @ref arm_compute::BlobMemoryPool, @ref arm_compute::ILifetimeManager, @ref arm_compute::IMemoryGroup, @ref arm_compute::IMemoryManager, @ref arm_compute::IMemoryPool, @ref arm_compute::IPoolManager, @ref arm_compute::MemoryManagerOnDemand, @ref arm_compute::PoolManager)
				261	- New validation and benchmark frameworks (Boost and Google frameworks replaced by homemade framework).
				262	- Most machine learning functions support both fixed point 8 and 16 bit (QS8, QS16) for both NEON and OpenCL.
				263	- New NEON kernels / functions:
				264	- @ref arm_compute::NEGEMMAssemblyBaseKernel @ref arm_compute::NEGEMMAArch64Kernel
				265	- @ref arm_compute::NEDequantizationLayerKernel / @ref arm_compute::NEDequantizationLayer
				266	- @ref arm_compute::NEFloorKernel / @ref arm_compute::NEFloor
Giorgio Arena	04a8f8c	2017-11-23 11:45:24 +0000	[diff] [blame]	267	- @ref arm_compute::NEL2NormalizeLayerKernel / @ref arm_compute::NEL2NormalizeLayer
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	268	- @ref arm_compute::NEQuantizationLayerKernel @ref arm_compute::NEMinMaxLayerKernel / @ref arm_compute::NEQuantizationLayer
				269	- @ref arm_compute::NEROIPoolingLayerKernel / @ref arm_compute::NEROIPoolingLayer
				270	- @ref arm_compute::NEReductionOperationKernel / @ref arm_compute::NEReductionOperation
				271	- @ref arm_compute::NEReshapeLayerKernel / @ref arm_compute::NEReshapeLayer
				272
				273	- New OpenCL kernels / functions:
Giorgio Arena	04a8f8c	2017-11-23 11:45:24 +0000	[diff] [blame]	274	- @ref arm_compute::CLDepthwiseConvolutionLayer3x3Kernel @ref arm_compute::CLDepthwiseIm2ColKernel @ref arm_compute::CLDepthwiseVectorToTensorKernel @ref arm_compute::CLDepthwiseWeightsReshapeKernel / @ref arm_compute::CLDepthwiseConvolutionLayer3x3 @ref arm_compute::CLDepthwiseConvolutionLayer @ref arm_compute::CLDepthwiseSeparableConvolutionLayer
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	275	- @ref arm_compute::CLDequantizationLayerKernel / @ref arm_compute::CLDequantizationLayer
				276	- @ref arm_compute::CLDirectConvolutionLayerKernel / @ref arm_compute::CLDirectConvolutionLayer
				277	- @ref arm_compute::CLFlattenLayer
				278	- @ref arm_compute::CLFloorKernel / @ref arm_compute::CLFloor
				279	- @ref arm_compute::CLGEMMTranspose1xW
				280	- @ref arm_compute::CLGEMMMatrixVectorMultiplyKernel
Giorgio Arena	04a8f8c	2017-11-23 11:45:24 +0000	[diff] [blame]	281	- @ref arm_compute::CLL2NormalizeLayerKernel / @ref arm_compute::CLL2NormalizeLayer
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	282	- @ref arm_compute::CLQuantizationLayerKernel @ref arm_compute::CLMinMaxLayerKernel / @ref arm_compute::CLQuantizationLayer
				283	- @ref arm_compute::CLROIPoolingLayerKernel / @ref arm_compute::CLROIPoolingLayer
				284	- @ref arm_compute::CLReductionOperationKernel / @ref arm_compute::CLReductionOperation
				285	- @ref arm_compute::CLReshapeLayerKernel / @ref arm_compute::CLReshapeLayer
				286
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	287	v17.06 Public major release
				288	- Various bug fixes
				289	- Added support for fixed point 8 bit (QS8) to the various NEON machine learning kernels.
				290	- Added unit tests and benchmarks (AlexNet, LeNet)
				291	- Added support for sub tensors.
				292	- Added infrastructure to provide GPU specific optimisation for some OpenCL kernels.
				293	- Added @ref arm_compute::OMPScheduler (OpenMP) scheduler for NEON
				294	- Added @ref arm_compute::SingleThreadScheduler scheduler for NEON (For bare metal)
				295	- User can specify his own scheduler by implementing the @ref arm_compute::IScheduler interface.
				296	- New OpenCL kernels / functions:
				297	- @ref arm_compute::CLBatchNormalizationLayerKernel / @ref arm_compute::CLBatchNormalizationLayer
Giorgio Arena	04a8f8c	2017-11-23 11:45:24 +0000	[diff] [blame]	298	- @ref arm_compute::CLDepthConcatenateLayerKernel / @ref arm_compute::CLDepthConcatenateLayer
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	299	- @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
				300	- @ref arm_compute::CLLocallyConnectedMatrixMultiplyKernel / @ref arm_compute::CLLocallyConnectedLayer
				301	- @ref arm_compute::CLWeightsReshapeKernel / @ref arm_compute::CLConvolutionLayerReshapeWeights
				302	- New C++ kernels:
				303	- @ref arm_compute::CPPDetectionWindowNonMaximaSuppressionKernel
				304	- New NEON kernels / functions:
				305	- @ref arm_compute::NEBatchNormalizationLayerKernel / @ref arm_compute::NEBatchNormalizationLayer
Giorgio Arena	04a8f8c	2017-11-23 11:45:24 +0000	[diff] [blame]	306	- @ref arm_compute::NEDepthConcatenateLayerKernel / @ref arm_compute::NEDepthConcatenateLayer
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	307	- @ref arm_compute::NEDirectConvolutionLayerKernel / @ref arm_compute::NEDirectConvolutionLayer
				308	- @ref arm_compute::NELocallyConnectedMatrixMultiplyKernel / @ref arm_compute::NELocallyConnectedLayer
				309	- @ref arm_compute::NEWeightsReshapeKernel / @ref arm_compute::NEConvolutionLayerReshapeWeights
				310
				311	v17.05 Public bug fixes release
				312	- Various bug fixes
				313	- Remaining of the functions ported to use accurate padding.
				314	- Library does not link against OpenCL anymore (It uses dlopen / dlsym at runtime instead to determine whether or not OpenCL is available).
				315	- Added "free" method to allocator.
				316	- Minimum version of g++ required for armv7 Linux changed from 4.8 to 4.9
				317
				318	v17.04 Public bug fixes release
				319
				320	The following functions have been ported to use the new accurate padding:
				321	- @ref arm_compute::CLColorConvertKernel
				322	- @ref arm_compute::CLEdgeNonMaxSuppressionKernel
				323	- @ref arm_compute::CLEdgeTraceKernel
				324	- @ref arm_compute::CLGaussianPyramidHorKernel
				325	- @ref arm_compute::CLGaussianPyramidVertKernel
				326	- @ref arm_compute::CLGradientKernel
				327	- @ref arm_compute::NEChannelCombineKernel
				328	- @ref arm_compute::NEFillArrayKernel
				329	- @ref arm_compute::NEGaussianPyramidHorKernel
				330	- @ref arm_compute::NEGaussianPyramidVertKernel
				331	- @ref arm_compute::NEHarrisScoreFP16Kernel
				332	- @ref arm_compute::NEHarrisScoreKernel
				333	- @ref arm_compute::NEHOGDetectorKernel
				334	- @ref arm_compute::NELogits1DMaxKernel
				335	- @ref arm_compute::NELogits1DShiftExpSumKernel
				336	- @ref arm_compute::NELogits1DNormKernel
				337	- @ref arm_compute::NENonMaximaSuppression3x3FP16Kernel
				338	- @ref arm_compute::NENonMaximaSuppression3x3Kernel
				339
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	340	v17.03.1 First Major public release of the sources
				341	- Renamed the library to arm_compute
				342	- New CPP target introduced for C++ kernels shared between NEON and CL functions.
				343	- New padding calculation interface introduced and ported most kernels / functions to use it.
				344	- New OpenCL kernels / functions:
Gian Marco	05288a2	2017-11-21 10:57:50 +0000	[diff] [blame]	345	- @ref arm_compute::CLGEMMLowpMatrixMultiplyKernel / arm_compute::CLGEMMLowp
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	346	- New NEON kernels / functions:
				347	- @ref arm_compute::NENormalizationLayerKernel / @ref arm_compute::NENormalizationLayer
				348	- @ref arm_compute::NETransposeKernel / @ref arm_compute::NETranspose
				349	- @ref arm_compute::NELogits1DMaxKernel, @ref arm_compute::NELogits1DShiftExpSumKernel, @ref arm_compute::NELogits1DNormKernel / @ref arm_compute::NESoftmaxLayer
				350	- @ref arm_compute::NEIm2ColKernel, @ref arm_compute::NECol2ImKernel, arm_compute::NEConvolutionLayerWeightsReshapeKernel / @ref arm_compute::NEConvolutionLayer
				351	- @ref arm_compute::NEGEMMMatrixAccumulateBiasesKernel / @ref arm_compute::NEFullyConnectedLayer
Gian Marco	e75a02b	2017-11-08 12:24:09 +0000	[diff] [blame]	352	- @ref arm_compute::NEGEMMLowpMatrixMultiplyKernel / arm_compute::NEGEMMLowp
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	353
				354	v17.03 Sources preview
				355	- New OpenCL kernels / functions:
				356	- @ref arm_compute::CLGradientKernel, @ref arm_compute::CLEdgeNonMaxSuppressionKernel, @ref arm_compute::CLEdgeTraceKernel / @ref arm_compute::CLCannyEdge
				357	- GEMM refactoring + FP16 support: @ref arm_compute::CLGEMMInterleave4x4Kernel, @ref arm_compute::CLGEMMTranspose1xWKernel, @ref arm_compute::CLGEMMMatrixMultiplyKernel, @ref arm_compute::CLGEMMMatrixAdditionKernel / @ref arm_compute::CLGEMM
				358	- @ref arm_compute::CLGEMMMatrixAccumulateBiasesKernel / @ref arm_compute::CLFullyConnectedLayer
				359	- @ref arm_compute::CLTransposeKernel / @ref arm_compute::CLTranspose
				360	- @ref arm_compute::CLLKTrackerInitKernel, @ref arm_compute::CLLKTrackerStage0Kernel, @ref arm_compute::CLLKTrackerStage1Kernel, @ref arm_compute::CLLKTrackerFinalizeKernel / @ref arm_compute::CLOpticalFlow
				361	- @ref arm_compute::CLNormalizationLayerKernel / @ref arm_compute::CLNormalizationLayer
				362	- @ref arm_compute::CLLaplacianPyramid, @ref arm_compute::CLLaplacianReconstruct
				363	- New NEON kernels / functions:
				364	- @ref arm_compute::NEActivationLayerKernel / @ref arm_compute::NEActivationLayer
				365	- 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
				366	- @ref arm_compute::NEPoolingLayerKernel / @ref arm_compute::NEPoolingLayer
				367
				368	v17.02.1 Sources preview
				369	- New OpenCL kernels / functions:
				370	- @ref arm_compute::CLLogits1DMaxKernel, @ref arm_compute::CLLogits1DShiftExpSumKernel, @ref arm_compute::CLLogits1DNormKernel / @ref arm_compute::CLSoftmaxLayer
				371	- @ref arm_compute::CLPoolingLayerKernel / @ref arm_compute::CLPoolingLayer
Gian Marco Iodice	5cb4c42	2017-06-23 10:38:25 +0100	[diff] [blame]	372	- @ref arm_compute::CLIm2ColKernel, @ref arm_compute::CLCol2ImKernel, arm_compute::CLConvolutionLayerWeightsReshapeKernel / @ref arm_compute::CLConvolutionLayer
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	373	- @ref arm_compute::CLRemapKernel / @ref arm_compute::CLRemap
				374	- @ref arm_compute::CLGaussianPyramidHorKernel, @ref arm_compute::CLGaussianPyramidVertKernel / @ref arm_compute::CLGaussianPyramid, @ref arm_compute::CLGaussianPyramidHalf, @ref arm_compute::CLGaussianPyramidOrb
				375	- @ref arm_compute::CLMinMaxKernel, @ref arm_compute::CLMinMaxLocationKernel / @ref arm_compute::CLMinMaxLocation
				376	- @ref arm_compute::CLNonLinearFilterKernel / @ref arm_compute::CLNonLinearFilter
				377	- New NEON FP16 kernels (Requires armv8.2 CPU)
				378	- @ref arm_compute::NEAccumulateWeightedFP16Kernel
				379	- @ref arm_compute::NEBox3x3FP16Kernel
				380	- @ref arm_compute::NENonMaximaSuppression3x3FP16Kernel
				381
				382	v17.02 Sources preview
				383	- New OpenCL kernels / functions:
				384	- @ref arm_compute::CLActivationLayerKernel / @ref arm_compute::CLActivationLayer
				385	- @ref arm_compute::CLChannelCombineKernel / @ref arm_compute::CLChannelCombine
				386	- @ref arm_compute::CLDerivativeKernel / @ref arm_compute::CLChannelExtract
				387	- @ref arm_compute::CLFastCornersKernel / @ref arm_compute::CLFastCorners
				388	- @ref arm_compute::CLMeanStdDevKernel / @ref arm_compute::CLMeanStdDev
				389	- New NEON kernels / functions:
				390	- 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
				391	- @ref arm_compute::NENonLinearFilterKernel / @ref arm_compute::NENonLinearFilter
				392	- Introduced a CLScheduler to manage the default context and command queue used by the runtime library and create synchronisation events.
				393	- Switched all the kernels / functions to use tensors instead of images.
				394	- Updated documentation to include instructions to build the library from sources.
				395
				396	v16.12 Binary preview release
				397	- Original release
				398
				399	@section S3_how_to_build How to build the library and the examples
				400
				401	@subsection S3_1_build_options Build options
				402
				403	scons 2.3 or above is required to build the library.
				404	To see the build options available simply run ```scons -h```:
				405
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	406	debug: Debug (yes\|no)
				407	default: False
				408	actual: False
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	409
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	410	asserts: Enable asserts (this flag is forced to 1 for debug=1) (yes\|no)
				411	default: False
				412	actual: False
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	413
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	414	arch: Target Architecture (armv7a\|arm64-v8a\|arm64-v8.2-a\|x86_32\|x86_64)
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	415	default: armv7a
				416	actual: armv7a
				417
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	418	os: Target OS (linux\|android\|bare_metal)
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	419	default: linux
				420	actual: linux
				421
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	422	build: Build type (native\|cross_compile)
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	423	default: cross_compile
				424	actual: cross_compile
				425
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	426	examples: Build example programs (yes\|no)
				427	default: True
				428	actual: True
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	429
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	430	Werror: Enable/disable the -Werror compilation flag (yes\|no)
				431	default: True
				432	actual: True
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	433
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	434	opencl: Enable OpenCL support (yes\|no)
				435	default: True
				436	actual: True
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	437
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	438	neon: Enable Neon support (yes\|no)
				439	default: False
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	440	actual: False
				441
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	442	gles_compute: Enable OpenGL ES Compute Shader support (yes\|no)
				443	default: False
				444	actual: False
				445
				446	embed_kernels: Embed OpenCL kernels and OpenGL ES compute shader in library binary (yes\|no)
Anthony Barbier	cc0a80b	2017-12-15 11:37:29 +0000	[diff] [blame]	447	default: True
				448	actual: True
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	449
				450	set_soname: Set the library's soname and shlibversion (requires SCons 2.4 or above) (yes\|no)
				451	default: False
				452	actual: False
				453
				454	openmp: Enable OpenMP backend (yes\|no)
				455	default: False
				456	actual: False
				457
				458	cppthreads: Enable C++11 threads backend (yes\|no)
				459	default: True
				460	actual: True
				461
				462	build_dir: Specify sub-folder for the build ( /path/to/build_dir )
				463	default: .
				464	actual: .
				465
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	466	extra_cxx_flags: Extra CXX flags to be appended to the build command
				467	default:
				468	actual:
				469
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	470	pmu: Enable PMU counters (yes\|no)
				471	default: False
				472	actual: False
				473
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	474	mali: Enable Mali hardware counters (yes\|no)
				475	default: False
				476	actual: False
				477
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	478	validation_tests: Build validation test programs (yes\|no)
				479	default: False
				480	actual: False
				481
				482	benchmark_tests: Build benchmark test programs (yes\|no)
				483	default: False
				484	actual: False
				485
				486	@b debug / @b asserts:
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	487	- With debug=1 asserts are enabled, and the library is built with symbols and no optimisations enabled.
				488	- 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)
				489	- 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).
				490
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	491	@b arch: The x86_32 and x86_64 targets can only be used with neon=0 and opencl=1.
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	492
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	493	@b os: Choose the operating system you are targeting: Linux, Android or bare metal.
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	494	@note bare metal can only be used for NEON (not OpenCL), only static libraries get built and NEON's multi-threading support is disabled.
				495
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	496	@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.
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	497
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	498	@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.
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	499
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	500	@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).
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	501
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	502	@b opencl / @b neon / @b gles_compute: Choose which SIMD technology you want to target. (NEON for ARM Cortex-A CPUs or OpenCL / GLES_COMPUTE for ARM Mali GPUs)
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	503
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	504	@b embed_kernels: For OpenCL / GLES_COMPUTE only: set embed_kernels=1 if you want the OpenCL / GLES_COMPUTE kernels to be built in the library's binaries instead of being read from separate ".cl" / ".cs" files. If embed_kernels is set to 0 then the application can set the path to the folder containing the OpenCL / GLES_COMPUTE kernel files by calling CLKernelLibrary::init() / GCKernelLibrary::init(). By default the path is set to "./cl_kernels" / "./cs_shaders".
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	505
				506	@b set_soname: Do you want to build the versioned version of the library ?
				507
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	508	If enabled the library will contain a SONAME and SHLIBVERSION and some symlinks will automatically be created between the objects.
				509	Example:
				510	libarm_compute_core.so -> libarm_compute_core.so.1.0.0
				511	libarm_compute_core.so.1 -> libarm_compute_core.so.1.0.0
				512	libarm_compute_core.so.1.0.0
				513
				514	@note This options is disabled by default as it requires SCons version 2.4 or above.
				515
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	516	@b extra_cxx_flags: Custom CXX flags which will be appended to the end of the build command.
				517
				518	@b build_dir: Build the library in a subfolder of the "build" folder. (Allows to build several configurations in parallel).
				519
				520	@b examples: Build or not the examples
				521
				522	@b validation_tests: Enable the build of the validation suite.
				523
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	524	@b benchmark_tests: Enable the build of the benchmark tests
				525
				526	@b pmu: Enable the PMU cycle counter to measure execution time in benchmark tests. (Your device needs to support it)
				527
Anthony Barbier	6a5627a	2017-09-26 14:42:02 +0100	[diff] [blame]	528	@b mali: Enable the collection of Mali hardware counters to measure execution time in benchmark tests. (Your device needs to have a Mali driver that supports it)
				529
Anthony Barbier	79c6178	2017-06-23 11:48:24 +0100	[diff] [blame]	530	@b openmp Build in the OpenMP scheduler for NEON.
				531
				532	@note Only works when building with g++ not clang++
				533
				534	@b cppthreads Build in the C++11 scheduler for NEON.
				535
				536	@sa arm_compute::Scheduler::set
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	537
Moritz Pflanzer	07674de	2017-07-21 09:39:36 +0100	[diff] [blame]	538	@subsection S3_2_linux Building for Linux
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	539
				540	@subsubsection S3_2_1_library How to build the library ?
				541
				542	For Linux, the library was successfully built and tested using the following Linaro GCC toolchain:
				543
				544	- gcc-linaro-arm-linux-gnueabihf-4.9-2014.07_linux
				545	- gcc-linaro-4.9-2016.02-x86_64_aarch64-linux-gnu
				546	- gcc-linaro-6.3.1-2017.02-i686_aarch64-linux-gnu
				547
				548	@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)
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	549	@note If you are building with gles_compute=1 then scons will expect to find libEGL.so / libGLESv1_CM.so / libGLESv2.so either in the current directory or in "build" (See the section below if you need a stub OpenCL library to link against)
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	550
				551	To cross-compile the library in debug mode, with NEON only support, for Linux 32bit:
				552
				553	scons Werror=1 -j8 debug=1 neon=1 opencl=0 os=linux arch=armv7a
				554
				555	To cross-compile the library in asserts mode, with OpenCL only support, for Linux 64bit:
				556
				557	scons Werror=1 -j8 debug=0 asserts=1 neon=0 opencl=1 embed_kernels=1 os=linux arch=arm64-v8a
				558
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	559	To cross-compile the library in asserts mode, with GLES_COMPUTE only support, for Linux 64bit:
				560
				561	scons Werror=1 -j8 debug=0 asserts=1 neon=0 opencl=0 gles_compute=1 embed_kernels=1 os=linux arch=arm64-v8a
				562
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	563	You can also compile the library natively on an ARM device by using <b>build=native</b>:
				564
				565	scons Werror=1 -j8 debug=0 neon=1 opencl=0 os=linux arch=arm64-v8a build=native
				566	scons Werror=1 -j8 debug=0 neon=1 opencl=0 os=linux arch=armv7a build=native
				567
				568	@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.
				569
				570	For example on a 64bit Debian based system you would have to install <b>g++-arm-linux-gnueabihf</b>
				571
				572	apt-get install g++-arm-linux-gnueabihf
				573
				574	Then run
				575
				576	scons Werror=1 -j8 debug=0 neon=1 opencl=0 os=linux arch=armv7a build=cross_compile
				577
				578	or simply remove the build parameter as build=cross_compile is the default value:
				579
				580	scons Werror=1 -j8 debug=0 neon=1 opencl=0 os=linux arch=armv7a
				581
				582	@attention To cross compile with opencl=1 you need to make sure to have a version of libOpenCL matching your target architecture.
				583
				584	@subsubsection S3_2_2_examples How to manually build the examples ?
				585
				586	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.
				587
				588	@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.
				589
				590	To cross compile a NEON example for Linux 32bit:
				591
Anthony Barbier	b2881fc	2017-09-29 17:12:12 +0100	[diff] [blame]	592	arm-linux-gnueabihf-g++ examples/neon_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -mfpu=neon -L. -larm_compute -larm_compute_core -o neon_convolution
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	593
				594	To cross compile a NEON example for Linux 64bit:
				595
Anthony Barbier	b2881fc	2017-09-29 17:12:12 +0100	[diff] [blame]	596	aarch64-linux-gnu-g++ examples/neon_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -L. -larm_compute -larm_compute_core -o neon_convolution
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	597
				598	(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)
				599
				600	To cross compile an OpenCL example for Linux 32bit:
				601
Anthony Barbier	b2881fc	2017-09-29 17:12:12 +0100	[diff] [blame]	602	arm-linux-gnueabihf-g++ examples/cl_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -mfpu=neon -L. -larm_compute -larm_compute_core -lOpenCL -o cl_convolution -DARM_COMPUTE_CL
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	603
				604	To cross compile an OpenCL example for Linux 64bit:
				605
Anthony Barbier	b2881fc	2017-09-29 17:12:12 +0100	[diff] [blame]	606	aarch64-linux-gnu-g++ examples/cl_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -L. -larm_compute -larm_compute_core -lOpenCL -o cl_convolution -DARM_COMPUTE_CL
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	607
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	608	To cross compile a GLES example for Linux 32bit:
				609
				610	arm-linux-gnueabihf-g++ examples/gc_absdiff.cpp utils/Utils.cpp -I. -Iinclude/ -L. -larm_compute -larm_compute_core -std=c++11 -mfpu=neon -DARM_COMPUTE_GC -Iinclude/linux/ -o gc_absdiff
				611
				612	To cross compile a GLES example for Linux 64bit:
				613
				614	aarch64-linux-gnu-g++ examples/gc_absdiff.cpp utils/Utils.cpp -I. -Iinclude/ -L. -larm_compute -larm_compute_core -std=c++11 -DARM_COMPUTE_GC -Iinclude/linux/ -o gc_absdiff
				615
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	616	(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)
				617
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	618	To cross compile the examples with the Graph API, such as graph_lenet.cpp, you need to link the examples against arm_compute_graph.so too.
				619
				620	@note The compute library must currently be built with both neon and opencl enabled - neon=1 and opencl=1
Gian Marco Iodice	daec1aa	2017-09-29 12:03:18 +0100	[diff] [blame]	621
				622	i.e. to cross compile the "graph_lenet" example for Linux 32bit:
				623
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	624	arm-linux-gnueabihf-g++ examples/graph_lenet.cpp utils/Utils.cpp utils/GraphUtils.cpp -I. -Iinclude -std=c++11 -mfpu=neon -L. -larm_compute_graph -larm_compute -larm_compute_core -Wl,--allow-shlib-undefined -o graph_lenet
Gian Marco Iodice	daec1aa	2017-09-29 12:03:18 +0100	[diff] [blame]	625
				626	i.e. to cross compile the "graph_lenet" example for Linux 64bit:
				627
Isabella Gottardi	b28f29d	2017-11-09 17:05:07 +0000	[diff] [blame]	628	aarch64-linux-gnu-g++ examples/graph_lenet.cpp utils/Utils.cpp utils/GraphUtils.cpp -I. -Iinclude -std=c++11 -L. -larm_compute_graph -larm_compute -larm_compute_core -Wl,--allow-shlib-undefined -o graph_lenet
Gian Marco Iodice	daec1aa	2017-09-29 12:03:18 +0100	[diff] [blame]	629
				630	(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)
				631
Anthony Barbier	e500747	2017-10-27 15:01:44 +0100	[diff] [blame]	632	@note If compiling using static libraries, this order must be followed when linking: arm_compute_graph_static, arm_compute, arm_compute_core
				633
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	634	To compile natively (i.e directly on an ARM device) for NEON for Linux 32bit:
				635
Anthony Barbier	b2881fc	2017-09-29 17:12:12 +0100	[diff] [blame]	636	g++ examples/neon_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -mfpu=neon -larm_compute -larm_compute_core -o neon_convolution
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	637
				638	To compile natively (i.e directly on an ARM device) for NEON for Linux 64bit:
				639
Anthony Barbier	b2881fc	2017-09-29 17:12:12 +0100	[diff] [blame]	640	g++ examples/neon_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -larm_compute -larm_compute_core -o neon_convolution
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	641
				642	(notice the only difference with the 32 bit command is that we don't need the -mfpu option)
				643
				644	To compile natively (i.e directly on an ARM device) for OpenCL for Linux 32bit or Linux 64bit:
				645
Anthony Barbier	b2881fc	2017-09-29 17:12:12 +0100	[diff] [blame]	646	g++ examples/cl_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -larm_compute -larm_compute_core -lOpenCL -o cl_convolution -DARM_COMPUTE_CL
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	647
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	648	To compile natively (i.e directly on an ARM device) for GLES for Linux 32bit or Linux 64bit:
Gian Marco Iodice	daec1aa	2017-09-29 12:03:18 +0100	[diff] [blame]	649
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	650	g++ examples/gc_absdiff.cpp utils/Utils.cpp -I. -Iinclude/ -L. -larm_compute -larm_compute_core -std=c++11 -DARM_COMPUTE_GC -Iinclude/linux/ -o gc_absdiff
				651
				652	To compile natively the examples with the Graph API, such as graph_lenet.cpp, you need to link the examples against arm_compute_graph.so too.
				653	@note The compute library must currently be built with both neon and opencl enabled - neon=1 and opencl=1
				654
				655	i.e. to natively compile the "graph_lenet" example for Linux 32bit:
Gian Marco Iodice	daec1aa	2017-09-29 12:03:18 +0100	[diff] [blame]	656
Isabella Gottardi	b28f29d	2017-11-09 17:05:07 +0000	[diff] [blame]	657	g++ examples/graph_lenet.cpp utils/Utils.cpp utils/GraphUtils.cpp -I. -Iinclude -std=c++11 -mfpu=neon -L. -larm_compute_graph -larm_compute -larm_compute_core -Wl,--allow-shlib-undefined -o graph_lenet
Gian Marco Iodice	daec1aa	2017-09-29 12:03:18 +0100	[diff] [blame]	658
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	659	i.e. to natively compile the "graph_lenet" example for Linux 64bit:
Gian Marco Iodice	daec1aa	2017-09-29 12:03:18 +0100	[diff] [blame]	660
Isabella Gottardi	b28f29d	2017-11-09 17:05:07 +0000	[diff] [blame]	661	g++ examples/graph_lenet.cpp utils/Utils.cpp utils/GraphUtils.cpp -I. -Iinclude -std=c++11 L. -larm_compute_graph -larm_compute -larm_compute_core -Wl,--allow-shlib-undefined -o graph_lenet
Gian Marco Iodice	daec1aa	2017-09-29 12:03:18 +0100	[diff] [blame]	662
				663	(notice the only difference with the 32 bit command is that we don't need the -mfpu option)
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	664
Anthony Barbier	e500747	2017-10-27 15:01:44 +0100	[diff] [blame]	665	@note If compiling using static libraries, this order must be followed when linking: arm_compute_graph_static, arm_compute, arm_compute_core
				666
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	667	@note These two commands assume libarm_compute.so is available in your library path, if not add the path to it using -L
				668
				669	To run the built executable simply run:
				670
				671	LD_LIBRARY_PATH=build ./neon_convolution
				672
				673	or
				674
				675	LD_LIBRARY_PATH=build ./cl_convolution
				676
Moritz Pflanzer	07674de	2017-07-21 09:39:36 +0100	[diff] [blame]	677	@subsection S3_3_android Building for Android
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	678
				679	For Android, the library was successfully built and tested using Google's standalone toolchains:
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	680	- NDK r14 arm-linux-androideabi-4.9 for armv7a (clang++)
				681	- NDK r14 aarch64-linux-android-4.9 for arm64-v8a (clang++)
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	682
				683	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>
				684
				685	- Download the NDK r14 from here: https://developer.android.com/ndk/downloads/index.html
				686	- Make sure you have Python 2 installed on your machine.
				687	- Generate the 32 and/or 64 toolchains by running the following commands:
				688
				689
Anthony Barbier	e500747	2017-10-27 15:01:44 +0100	[diff] [blame]	690	$NDK/build/tools/make_standalone_toolchain.py --arch arm64 --install-dir $MY_TOOLCHAINS/aarch64-linux-android-4.9 --stl gnustl --api 21
				691	$NDK/build/tools/make_standalone_toolchain.py --arch arm --install-dir $MY_TOOLCHAINS/arm-linux-androideabi-4.9 --stl gnustl --api 21
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	692
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	693	@attention Due to some NDK issues make sure you use clang++ & gnustl
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	694
				695	@note Make sure to add the toolchains to your PATH: export PATH=$PATH:$MY_TOOLCHAINS/aarch64-linux-android-4.9/bin:$MY_TOOLCHAINS/arm-linux-androideabi-4.9/bin
				696
				697	@subsubsection S3_3_1_library How to build the library ?
				698
				699	@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)
				700
				701	To cross-compile the library in debug mode, with NEON only support, for Android 32bit:
				702
				703	CXX=clang++ CC=clang scons Werror=1 -j8 debug=1 neon=1 opencl=0 os=android arch=armv7a
				704
				705	To cross-compile the library in asserts mode, with OpenCL only support, for Android 64bit:
				706
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	707	CXX=clang++ CC=clang scons Werror=1 -j8 debug=0 asserts=1 neon=0 opencl=1 embed_kernels=1 os=android arch=arm64-v8a
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	708
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	709	To cross-compile the library in asserts mode, with GLES_COMPUTE only support, for Android 64bit:
				710
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	711	CXX=clang++ CC=clang scons Werror=1 -j8 debug=0 asserts=1 neon=0 opencl=0 gles_compute=1 embed_kernels=1 os=android arch=arm64-v8a
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	712
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	713	@subsubsection S3_3_2_examples How to manually build the examples ?
				714
				715	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.
				716
Anthony Barbier	fabb038	2017-06-23 14:42:52 +0100	[diff] [blame]	717	@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.
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	718
				719	Once you've got your Android standalone toolchain built and added to your path you can do the following:
				720
				721	To cross compile a NEON example:
				722
				723	#32 bit:
Georgios Pinitas	9873ea3	2017-12-05 15:28:55 +0000	[diff] [blame]	724	arm-linux-androideabi-clang++ examples/neon_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -larm_compute-static -larm_compute_core-static -L. -o neon_convolution_arm -static-libstdc++ -pie
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	725	#64 bit:
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	726	aarch64-linux-android-clang++ examples/neon_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -larm_compute-static -larm_compute_core-static -L. -o neon_convolution_aarch64 -static-libstdc++ -pie
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	727
				728	To cross compile an OpenCL example:
				729
				730	#32 bit:
Georgios Pinitas	9873ea3	2017-12-05 15:28:55 +0000	[diff] [blame]	731	arm-linux-androideabi-clang++ examples/cl_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -larm_compute-static -larm_compute_core-static -L. -o cl_convolution_arm -static-libstdc++ -pie -lOpenCL -DARM_COMPUTE_CL
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	732	#64 bit:
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	733	aarch64-linux-android-clang++ examples/cl_convolution.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -larm_compute-static -larm_compute_core-static -L. -o cl_convolution_aarch64 -static-libstdc++ -pie -lOpenCL -DARM_COMPUTE_CL
				734
				735	To cross compile a GLES example:
Anthony Barbier	cc0a80b	2017-12-15 11:37:29 +0000	[diff] [blame]	736
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	737	#32 bit:
				738	arm-linux-androideabi-clang++ examples/gc_absdiff.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -larm_compute-static -larm_compute_core-static -L. -o gc_absdiff_arm -static-libstdc++ -pie -DARM_COMPUTE_GC
				739	#64 bit:
				740	aarch64-linux-android-clang++ examples/gc_absdiff.cpp utils/Utils.cpp -I. -Iinclude -std=c++11 -larm_compute-static -larm_compute_core-static -L. -o gc_absdiff_aarch64 -static-libstdc++ -pie -DARM_COMPUTE_GC
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	741
Gian Marco Iodice	daec1aa	2017-09-29 12:03:18 +0100	[diff] [blame]	742	To cross compile the examples with the Graph API, such as graph_lenet.cpp, you need to link the library arm_compute_graph also.
				743	(notice the compute library has to be built with both neon and opencl enabled - neon=1 and opencl=1)
				744
				745	#32 bit:
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	746	arm-linux-androideabi-clang++ examples/graph_lenet.cpp utils/Utils.cpp utils/GraphUtils.cpp -I. -Iinclude -std=c++11 -Wl,--whole-archive -larm_compute_graph-static -Wl,--no-whole-archive -larm_compute-static -larm_compute_core-static -L. -o graph_lenet_arm -static-libstdc++ -pie -lOpenCL -DARM_COMPUTE_CL
Gian Marco Iodice	daec1aa	2017-09-29 12:03:18 +0100	[diff] [blame]	747	#64 bit:
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	748	aarch64-linux-android-clang++ examples/graph_lenet.cpp utils/Utils.cpp utils/GraphUtils.cpp -I. -Iinclude -std=c++11 -Wl,--whole-archive -larm_compute_graph-static -Wl,--no-whole-archive -larm_compute-static -larm_compute_core-static -L. -o graph_lenet_aarch64 -static-libstdc++ -pie -lOpenCL -DARM_COMPUTE_CL
Gian Marco Iodice	daec1aa	2017-09-29 12:03:18 +0100	[diff] [blame]	749
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	750	@note Due to some issues in older versions of the Mali OpenCL DDK (<= r13p0), we recommend to link arm_compute statically on Android.
Anthony Barbier	20dbb82	2017-12-13 21:19:39 +0000	[diff] [blame]	751	@note When linked statically the arm_compute_graph library currently needs the --whole-archive linker flag in order to work properly
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	752
				753	Then you need to do is upload the executable and the shared library to the device using ADB:
				754
				755	adb push neon_convolution_arm /data/local/tmp/
				756	adb push cl_convolution_arm /data/local/tmp/
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	757	adb push gc_absdiff_arm /data/local/tmp/
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	758	adb shell chmod 777 -R /data/local/tmp/
				759
				760	And finally to run the example:
				761
				762	adb shell /data/local/tmp/neon_convolution_arm
				763	adb shell /data/local/tmp/cl_convolution_arm
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	764	adb shell /data/local/tmp/gc_absdiff_arm
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	765
				766	For 64bit:
				767
				768	adb push neon_convolution_aarch64 /data/local/tmp/
				769	adb push cl_convolution_aarch64 /data/local/tmp/
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	770	adb push gc_absdiff_aarch64 /data/local/tmp/
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	771	adb shell chmod 777 -R /data/local/tmp/
				772
				773	And finally to run the example:
				774
				775	adb shell /data/local/tmp/neon_convolution_aarch64
				776	adb shell /data/local/tmp/cl_convolution_aarch64
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	777	adb shell /data/local/tmp/gc_absdiff_aarch64
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	778
Michalis Spyrou	6e52ba3	2017-10-04 15:40:38 +0100	[diff] [blame]	779	@subsection S3_4_bare_metal Building for bare metal
				780
				781	For bare metal, the library was successfully built using linaros's latest (gcc-linaro-6.3.1-2017.05) bare metal toolchains:
				782	- arm-eabi for armv7a
				783	- aarch64-elf for arm64-v8a
				784
				785	Download linaro for <a href="https://releases.linaro.org/components/toolchain/binaries/6.3-2017.05/arm-eabi/">armv7a</a> and <a href="https://releases.linaro.org/components/toolchain/binaries/6.3-2017.05/aarch64-elf/">arm64-v8a</a>.
				786
				787	@note Make sure to add the toolchains to your PATH: export PATH=$PATH:$MY_TOOLCHAINS/gcc-linaro-6.3.1-2017.05-x86_64_aarch64-elf/bin:$MY_TOOLCHAINS/gcc-linaro-6.3.1-2017.05-x86_64_arm-eabi/bin
				788
				789	@subsubsection S3_4_1_library How to build the library ?
				790
				791	To cross-compile the library with NEON support for baremetal arm64-v8a:
				792
				793	scons Werror=1 -j8 debug=0 neon=1 opencl=0 os=bare_metal arch=arm64-v8a build=cross_compile cppthreads=0 openmp=0 standalone=1
				794
				795	@subsubsection S3_4_2_examples How to manually build the examples ?
				796
				797	Examples are disabled when building for bare metal. If you want to build the examples you need to provide a custom bootcode depending on the target architecture and link against the compute library. More information about bare metal bootcode can be found <a href="http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.dai0527a/index.html">here</a>.
				798
				799	@subsection S3_5_windows_host Building on a Windows host system
Moritz Pflanzer	07674de	2017-07-21 09:39:36 +0100	[diff] [blame]	800
				801	Using `scons` directly from the Windows command line is known to cause
				802	problems. The reason seems to be that if `scons` is setup for cross-compilation
				803	it gets confused about Windows style paths (using backslashes). Thus it is
				804	recommended to follow one of the options outlined below.
				805
Michalis Spyrou	6e52ba3	2017-10-04 15:40:38 +0100	[diff] [blame]	806	@subsubsection S3_5_1_ubuntu_on_windows Bash on Ubuntu on Windows
Moritz Pflanzer	07674de	2017-07-21 09:39:36 +0100	[diff] [blame]	807
				808	The best and easiest option is to use
				809	<a href="https://msdn.microsoft.com/en-gb/commandline/wsl/about">Ubuntu on Windows</a>.
				810	This feature is still marked as beta and thus might not be available.
				811	However, if it is building the library is as simple as opening a *Bash on
				812	Ubuntu on Windows* shell and following the general guidelines given above.
				813
Michalis Spyrou	6e52ba3	2017-10-04 15:40:38 +0100	[diff] [blame]	814	@subsubsection S3_5_2_cygwin Cygwin
Moritz Pflanzer	07674de	2017-07-21 09:39:36 +0100	[diff] [blame]	815
				816	If the Windows subsystem for Linux is not available <a href="https://www.cygwin.com/">Cygwin</a>
				817	can be used to install and run `scons`. In addition to the default packages
				818	installed by Cygwin `scons` has to be selected in the installer. (`git` might
				819	also be useful but is not strictly required if you already have got the source
				820	code of the library.) Linaro provides pre-built versions of
				821	<a href="http://releases.linaro.org/components/toolchain/binaries/">GCC cross-compilers</a>
				822	that can be used from the Cygwin terminal. When building for Android the
				823	compiler is included in the Android standalone toolchain. After everything has
				824	been set up in the Cygwin terminal the general guide on building the library
				825	can be followed.
				826
Michalis Spyrou	6e52ba3	2017-10-04 15:40:38 +0100	[diff] [blame]	827	@subsection S3_6_cl_stub_library The OpenCL stub library
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	828
				829	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.
				830
				831	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.
				832
				833	@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.
				834
				835	To cross-compile the stub OpenCL library simply run:
				836
				837	<target-prefix>-gcc -o libOpenCL.so -Iinclude opencl-1.2-stubs/opencl_stubs.c -fPIC -shared
				838
				839	For example:
				840
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	841	#Linux 32bit
				842	arm-linux-gnueabihf-gcc -o libOpenCL.so -Iinclude opencl-1.2-stubs/opencl_stubs.c -fPIC -shared
				843	#Linux 64bit
				844	aarch64-linux-gnu-gcc -o libOpenCL.so -Iinclude -shared opencl-1.2-stubs/opencl_stubs.c -fPIC
				845	#Android 32bit
				846	arm-linux-androideabi-clang -o libOpenCL.so -Iinclude -shared opencl-1.2-stubs/opencl_stubs.c -fPIC -shared
				847	#Android 64bit
Anthony Barbier	14c86a9	2017-12-14 16:27:41 +0000	[diff] [blame]	848	aarch64-linux-android-clang -o libOpenCL.so -Iinclude -shared opencl-1.2-stubs/opencl_stubs.c -fPIC -shared
				849
				850	@subsection S3_7_gles_stub_library The Linux OpenGLES and EGL stub libraries
				851
				852	In the opengles-3.1-stubs folder you will find the sources to build stub EGL and OpenGLES libraries which then can be used to link your Linux application of arm_compute against.
				853
				854	@note The stub libraries are only needed on Linux. For Android, the NDK toolchains already provide the meta-EGL and meta-GLES libraries.
				855
				856	To cross-compile the stub OpenGLES and EGL libraries simply run:
				857
				858	<target-prefix>-gcc -o libEGL.so -Iinclude/linux opengles-3.1-stubs/EGL.c -fPIC -shared
				859	<target-prefix>-gcc -o libGLESv2.so -Iinclude/linux opengles-3.1-stubs/GLESv2.c -fPIC -shared
				860
				861	#Linux 32bit
				862	arm-linux-gnueabihf-gcc -o libEGL.so -Iinclude/linux opengles-3.1-stubs/EGL.c -fPIC -shared
				863	arm-linux-gnueabihf-gcc -o libGLESv2.so -Iinclude/linux opengles-3.1-stubs/GLESv2.c -fPIC -shared
				864
				865	#Linux 64bit
				866	aarch64-linux-gnu-gcc -o libEGL.so -Iinclude/linux opengles-3.1-stubs/EGL.c -fPIC -shared
				867	aarch64-linux-gnu-gcc -o libGLESv2.so -Iinclude/linux opengles-3.1-stubs/GLESv2.c -fPIC -shared
Anthony Barbier	6ff3b19	2017-09-04 18:44:23 +0100	[diff] [blame]	868	*/