aboutsummaryrefslogtreecommitdiff
path: root/src/armnn
AgeCommit message (Collapse)Author
2019-10-08IVGCVSW-3948 Add Profiling config to Runtime constructorJim Flynn
Change-Id: Ib5cb85e620ed2cd76a85d423b2674b5d80981be9 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-10-04IVGCVSW-3935 Add Quantizer support for INSTANCE_NORMALIZATIONAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I175008c81da028fb5bdc71e0abff06bc6e58734c
2019-10-04IVGCVSW-3925 Add Backward compatibility for ITensorHandle CreateTensorHandle ↵David Monahan
functions Change-Id: I940b7ca706c9a8bc38743176eb7959aa629a6876 Signed-off-by: David Monahan <david.monahan@arm.com>
2019-10-03IVGCVSW-3932 Add frontend for INSTANCE_NORMALIZATIONKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Ib152148ccd8d2733c617d0cf9402661fc6b71316
2019-10-01IVGCVSW-3922 Fix Arm NN build issue - memory access violationKevin May
* Only run breaking test if Ref backend is available Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I64850c902f7b900fe9f50d357c283c9a2bf73c19
2019-09-27NNXSW-1826 Add an optimization step which combines Permute and BatchToSpace ↵Rob Hughes
into DepthToSpace This is only possible in some limited cases, but removes an extra layer from the graph and so should improve performance in all cases. Change-Id: I7b3e6ba5dacb4fdb816ad270edaecda1436ab4cf Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2019-09-27IVGCVSW-3689 Support Import of Output Tensors for the Neon BackendFerran Balaguer
Change-Id: I6323c5f68248b54b3ed3b4cb92f1e8bf9c279b8d Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
2019-09-25NNXSW-1826 Move tests for Optimization classes to separate filesRob Hughes
This splits up the >1000 line OptimizerTests.cpp file. Each Optimization class now has its own test file, all of which are in a subfolder of tests called "optimizations". The original OptimizerTests.cpp now contains mostly (completely?) tests for validating output shapes, which perhaps should be moved to test files specific to the layer types they are testing. Change-Id: Icd1196cad8b720abcb156921aab1adbd4026756b Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2019-09-24IVGCVSW-3900 Add deserialization test for DepthToSpaceAron Virginas-Tar
* Fixed bug in DepthToSpaceLayer::InferOutputShapes by removing leftover throw UnimplementedException * Added Deserializer/DepthToSpaceFloat32 deserialization test Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I8fc31d0270b4de1dac45ee12c2b798df81f312a7
2019-09-24NNXSW-1826 OptimizeConsecutiveReshapes: remove unnecessary call to ↵Rob Hughes
MoveAllConnections This is called at a time when newReshape has nothing connected to its output slot (as it has just been created) and so is a no-op. The code comment indicated that the intention was to connect the newReshape to its *input*, but that has already been done in the InsertNewLayer() call above, so the comment was incorrect. There is a unit test covering this case ("OptimizeConsecutiveReshapesTest") Change-Id: I933d5d1c6eb32f5a8269fb5d7c809cd7c89680d1 Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2019-09-24IVGCVSW-3623 Implement NeonTensorHandle::ImportDavid Monahan
Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: I7213788725fd4e4cf1176998604e999d0b7ed6cc
2019-09-23IVGCVSW-3887 Add Quantizer support for DepthToSpaceAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I144c04f920ba3329886367f5e73fe758505ab96e
2019-09-20Fix some minor issues around SpaceToDepthAron Virginas-Tar
* Removed unnecessary code from SpaceToDepthLayer::InferOutputShapes() * Refactored SpaceToDepthQueueDescriptor::Validate() and added extra checks for block size and output depth Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Ieeed3144e2589b2e8695ef65ce17752bc595332f
2019-09-20IVGCVSW-3883 Add frontend for DepthToSpace layerAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I18d957af6e988ffb6b9ee46ac836d1f38600e10b
2019-09-19IVGCVSW-3727 Add LayerType::Slice to GetLayerTypeAsCString()Aron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I878fc65b0462289f61721cad12319c58f923c0c0
2019-09-19IVGCVSW-3725 Adding quantization support for ArgMinMaxNikhil Raj
Change-Id: I7582a9ee36b4d1764a5a137cefe9b7b7dfe30254 Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
2019-09-18IVGCVSW-3881 Add Quantizer support for SLICEAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I72bc00888d416fee177ea2e6e5006f8ff04f612e
2019-09-17IVGCVSW-3879 Fix output shape inference formula for TransposeConvolution2dAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I766f4297b9daa26edacc2079fe62a083ba2fa68f
2019-09-17IVGCVSW-3877 Reduce code duplication in TestNameOnlyLayerVisitorAron Virginas-Tar
* Defined macros for common class structure and near-identical test cases Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I47a2ece3e1797496c196f63c7fcd71e5748295c6
2019-09-17IVGCVSW-3875 Add frontend for SLICE layerAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Iebe675a0cee02db6f133d48ce58cbc1e233061db
2019-09-16Fix typo int comment surrounding constructor in ResizeLayer.hppAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I9739e2f685a49d00efaa873207c7b38d98b9b14c
2019-09-16IVGCVSW-3687 Add INetworkProperties to LoadNetworkDavid Monahan
* Allows users to specify if Import/Export should be used Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: I64da26a6acbeb91ef72d31b6ccc01bb1447f624d
2019-09-12Add "explicit" qualifier to Optional -> bool conversion methodRob Hughes
This prevents unintended conversions that could lead to incorrect code compiling, e.g. Optional<a> == Optional<b> Also add comparison (==) operator to compare two Optionals. Update unit tests accordingly Change-Id: I6f975de7e666ba1ffe16c3ab50643116c6317135 Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2019-09-10IVGCVSW-3722 Add ArgMinMax to GetLayerAsCString InternalTypesKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I304aec5c2f83d062a8b0c14d6c8ad01123dc7435
2019-09-10IVGCVSW-3829 Add CL workload for RSQRTAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Idf40ed0ebf2af3170137bf3a3cb5a9635a203d4a
2019-09-10IVGCVSW-3822 Add NEON workload support for ABSAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I0c2ead004200e053d748ea39937f2f9ed35a636b
2019-09-06IVGCVSW-3742 Add Quantizer support for ABSFinnWilliamsArm
Signed-off-by: FinnWilliamsArm <Finn.Williams@arm.com> Change-Id: I3f8e716ae432737bb314e26792d18aa518aa1952
2019-09-05IVGCVSW-3722 Add front end support for ArgMinMaxNikhil Raj
Change-Id: I31c5616bea3097f30cde68442d3222e0b0fe2235 Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
2019-09-05IVGCVSW-3739 Add Arm NN front end support for Abs LayerKevin May
* Add Abs Layer * Add no-op factory implementations for CpuRef, CpuAcc, GpuAcc * Add Queue Descriptor in WorkloadData * Add IsAbsLayerSupported to LayerSupport * Add LayerVisitor tests Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Ib0992571d1c80de851cea466291be904e9bdb430
2019-09-04IVGCVBENCH-1337 Added additional layer parameters to dot file and -v optionAndre Ghattas
* Generic layer parameters now show up in dot file * Convolution layer parameters have also been added to dot file * ExecucteNetwork has an additional -v flag which generated dot file if there Change-Id: I210bb19b45384eb3639b7e488c7a89049fa6f18d Signed-off-by: Andre Ghattas <andre.ghattas@arm.com> Signed-off-by: Szilard Papp <szilard.papp@arm.com>
2019-08-27IVGCVSW-3656 Rename ARMCOMPUTEREF to ARMNNREFMatteo Martincigh
* Renamed ARMCOMPUTEREF to ARMNNREF (and relative symbols) as the previous name was misleading !android-nn-driver:1819 Change-Id: I912e9f521750b91539e48f8a2fb4de73fb6f7425 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-08-27IVGCVSW-3277 Fix RequiresCopy in case a tensor handle factory is not availableMatteo Martincigh
* Added null checks prior of using either the source or the destination handle factory when checking if the tensor requires to be copied Change-Id: Icc6737562849be5e7d1a62243327366e06312eb9 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-08-23Fix Windows build:Rob Hughes
* CMake "install" commands require a RUNTIME argument for platforms with DLLs (e.g. Windows). * Replace use of non-standard variable length array with vector * Remove unnecessary #include of unistd.h * Add #ifdefs to dynamic backend code to disable for non-Unix platforms where you can't use dlopen etc. We could implement this properly for Windows later using LoadLibrary etc., but for now erroring is fine. * Add missing #include of <algorithm> Change-Id: Ic8ef5fd599b37bf8772510157b6e479819f6a1eb
2019-08-22IVGCVSW-3656 Make the reference backend optionalMatteo Martincigh
* Made the build of the reference backend depend on a new ARMCOMPUTEREF macro * Made the relevant targets dependent on the ref backend * Moved Cl and Neon static registry initializers to separate files * Wrapped some of the unit tests into proper ifdefs where necessary Change-Id: I7f2c42699682630233a4c4b6aed2f005083de189 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-08-20IVGCVSW-3163 Support Neon TransposeConv2dSadik Armagan
* NEON support for TransposeConolution2d * Indentation fix on SpaceToDepth LayerSupport method Signed-off-by: Keith Davis <keith.davis@arm.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Signed-off-by: Aron Virginas-Tar <aron.virginas-tar@arm.com> Change-Id: Ie3a01a22e05f62f475f768dfe05ce561d2f3b0ad
2019-08-20IVGCVSW-3606 Support memory import for Reference backendFerran Balaguer
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Change-Id: I94bd191f88e0911ad4e4727610e81cd7afa95512
2019-08-19IVGCVSW-3545 Update the device specs with the dynamic backend idsMatteo Martincigh
* Now the utility function RegisterDynamicBackends returns a list of the backend ids that have been registered * The list of registered ids is added to the list of supported backends in the Runtime * Added unit tests Change-Id: I97bbe1f680920358f5baba5a4666e4983b849cac Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-08-16IVGCVSW-3639 Add 5d tensor supportMatthew Jackson
* Increased MaxNumOfTensorDimensions and fixed issues related to its use * Fixed issues caused by assuming 5d tensors are invalid * Updated ArmComputeTensorUtils for 5d tensors * Added 5d tensor unit tests for add, mul, stack and reshape (needed by IVGCVSW-3527) Signed-off-by: Matthew Jackson <matthew.jackson@arm.com> Change-Id: I5bcd64942d0d04efcc6c5acb240ad4b88e010743
2019-08-14IVGCVSW-3622 Add Neon TensorHandleFactoryNarumol Prangnawarat
Signed-off-by: James Conroy <james.conroy@arm.com> Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I9f24f7d97c1e7d37ee7d58ff85c6c3f8496e52ec
2019-08-14IVGCVSW-3636 Fix Graph and WorkloaData to support backend Import functionalityFerran Balaguer
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Change-Id: I634aa3b1d609ca33b196fd68ce7fb7881be73e6e
2019-08-14IVGCVSW-3474 Refactor Lstm and QuantizedLstm Param GettersFrancis Murtagh
* Change Getter Signatures to follow coding guidelines Change-Id: Ic02621e834dbf79b9df63f8b4c6339f71651e944 Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2019-08-13IVGCVSW-3607 Add CreateWorkloadFactory with TensorHandleFactoryRegistryNarumol Prangnawarat
in IBackendInternal Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Id40b825649d0447058273b8bc4f7133a3ac3c96c
2019-08-09IVGCVSW-3474 Add end to end tests for Quantized_LSTMFrancis Murtagh
Change-Id: Iaec6956b5c459308d77d29f699ae4558bee66cd5 Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2019-08-09IVGCVSW-3603 *Json printer prints full profiling hierarchyDerek Lamberti
Change-Id: Ide5acbf993c2bcff5265b72fc979caa6f183bb22 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-08-09IVGCVSW-3597 Add complete test suite for the dynamic backendsMatteo Martincigh
* Added Runtime tests with dynamic backends * All other unit tests have already implemented in previous stories Change-Id: I0167b3b45dd00c1956514e2df051e4445727f014 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-08-09IVGCVSW-3596 Register the dynamic backends in the BackendRegistryMatteo Martincigh
* Added getter for the factory function in the DynamicBackend class * Added new RegisterDynamicBackends method in utils class * Added dynamic backend registration process in the Runtime class * Added new dummy dynamic backend objects for testing * Added unit tests for dynamic backend registration * Added convenience methods to BackendId Change-Id: I01e147d1d6f01bf56747ad946f73f867af5770c4 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-08-07IVGCVSW-3595 Implement the LoadDynamicBackends function in the Runtime classMatteo Martincigh
* Changed the way the handle is acquired, loaded symbols are now kept local * Updated the makefiles to add more test files for the dynamic backends * Fixed the GetSharedObjects method so that the files are parsed in alphabetical order * Updated the unit tests to make them more strict wrt the order of the files * Created a new CreateDynamicBackends method in the utils class * Added new unit tests for the new function * Added LoadDynamicBackends in the Runtime class !android-nn-driver:1707 Change-Id: I1ef9ff3d5455ca6a7fd51cb7cfb3819686234f70 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-08-06GitHub #240 Fix bias shape in CreatePreCompiledWorkloadTest()Aron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I10b8d5e2e95eb8f48a6be29005136459c3da2957
2019-08-05IVGCVSW-3277 Mem export/import suppor for TensorsDerek Lamberti
* Rename MemoryStrategy to EdgeStrategy * Add MemImportLayer * Import memory rather than copy when possible Change-Id: I1d3a9414f2cbe517dc2aae9bbd4fdd92712b38ef Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-08-05IVGCVSW-3342 Add CL backend support for Quantized_LSTM (16bit cell state)Ferran Balaguer
!android-nn-driver:1685 Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: I17278562f72d4b77e22c3af25bf7199b9150a765
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-05 07:33:34 +0000