aboutsummaryrefslogtreecommitdiff
path: root/src/armnn
AgeCommit message (Collapse)Author
2021-10-15Instrument runtime network loadDerek Lamberti
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com> Change-Id: I2705fe04b5ec3a6046584d443f10d2d5cb3b5b87
2021-10-14IVGCVSW-6416 AddFullyConnected API crashes without connected weights/bias layersCathal Corbett
* Created method in Graph.cpp/hpp ConstructErrorMessageForUnconnectedInputs() to verify weights and bias are set for FullyConnected layers. * Above method called in Graph.cpp InferTensorInfos() to print a more descriptive message when the weights or bias for a FullyConnectedLayer is not set. * Added try-catch in TestUtils.cpp Connect() to ensure input slot is available when connecting two layers. This ensures we catch the case where bias is is not enabled and we try and set a bias layer. * Added unit tests to check for LayerValidationError when weights or bias is not set on a FullyConnectedLayer. * Added unit test to check for LayerValidationError when bias is not enabled and we try and connect bias to FullyConnected Layer. * Seperated FullyConnected EndToEnd unit test method into two methods. First, performs tests on EndToEnd examples asserting output value. Second, performs tests on error catching. * Added comments to created methods. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I5207d8c5ebacfff598556742ccd4f53eef7dee0c
2021-10-12Github 581 - Upgrade doctestJan Eilers
* Upgrade doctest to version 2.4.6 to allow Arm NN to build with glibc 2.34 Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Iff2ef286ba5ad0e0ec0f54f510253a2ec4b464d3
2021-10-08IVGCVSW-6313 Support pre-importing outputsFinn Williams
* Add ClearImportedInputs/Outputs function to IRuntime * Add UnImport function to ITensorHandle * Remove mutex from IWorkingMemHandle Change-Id: I34c9b6e1618755e10f3b4597afa1d9a9ea97e5fe Signed-off-by: Finn Williams <finwil01@e127804.cambridge.arm.com>
2021-10-08IVGCVSW-6417: Catch AddFullyConnected API error when weights TensorInfo ↵Cathal Corbett
isn't set * Updated code in Graph.cpp InferTensorInfos() to be more descriptive. * Added method VerifyConstantLayerSetTensorInfo() in Graph.cpp/hpp to error when ConstantLayer TensorInfo is not set. * Updated Optimize() in Network.cpp to call VerifyConstantLayerSetTensorInfo(). * Added unit test with ConstantLayer TensorInfo not set to catch error in VerifyConstantLayerSetTensorInfo(). * Added comments around method VerifyConstantLayerSetTensorInfo(). Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I366596243f7c5823676222e2d0cce1335bc8c325
2021-10-07IVGCVSW-6459 Add support of scalar and flexible output datatypes to ONNX parserNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Id1e933f6ae55ddc1a57c80c9f6a5757ccb61f018
2021-10-06IVGCVSW-6300 'IMemoryOptimizerStrategy Add strategy library and add support ↵Sadik Armagan
in BackendRegistry' * Updated IRuntime interface for providing custom memory optimizer strategy. * Enabled selecting existing memory optimizer strategy by using BackendOptions * Added MemoryOptimizerStrategyLibrary that sets one of the existing memory optimizer strategies selected by user Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I037f8ac8efa79c0f71bd63e379101e3ad92d80c9
2021-10-02IVGCVSW-5985 Remove deprecated codeJan Eilers
* Removes deprecated AddLayer, IsLayerSupported functions * Marks the whole LayerVisitor class as deprecated not just the constructor. This required to wrap all Accept functions in a no deprecate macro because the LayerVisitor is used as a parameter in there * Removes usage of deprecated LayerVisitor and replaces it with ExecuteStrategy. This required a few structural changes in the unit tests * Adds a default implementation for IStrategy called StrategyBase * Changes pyarmnn to use non deprecated constructor for INetworkProperties and adds related unit test * Marks usage of deprecated code in pyarmnn as deprecated. This required to extend INetworkProperties to allow backwards compatibility * Removes deprecated functions from CpuAcc, GpuAcc and Ref backends Note: This patch breaks compatibility with backends that are not updated in this patch !android-nn-driver:6325 Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Id13b6f37a74d26eadeda2da1dc92915e725ed5a5
2021-10-01IVGCVSW-6163 Add Conv3d FrontEnd and Ref ImplementationMatthew Sloyan
* Added front-end * Added Reference workload * Added Serializer & Deserializer support * Added unit tests * Added NDHWC DataLayout Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Iec4d39e7433b5334d52fa44cf8efc6bcd39319d8
2021-09-24IVGCVSW-3705 Add Channel Shuffle Front end and Ref ImplementationSimon Obute
* Add front end * Add reference workload * Add unit tests * Add Serializer and Deserializer * Update ArmNN Versioning Signed-off-by: Simon Obute <simon.obute@arm.com> Change-Id: I9ac1f953af3974382eac8e8d62d794d2344e8f47
2021-09-24IVGCVSW-6382 Add Gather operator support to ONNX parserNarumol Prangnawarat
* Add ParseGather to support Gather operator on ONNX * Add Support of int64 converted to int32 for constant * Add OnnxParserTestUtils * Refactor ValidateTensorShapesFromInputs of GatherLayer * Unit tests Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ie9dff640240e14a062fef38f7faf0ccc212de5f7
2021-09-23Fix catch by valueFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I257c3e79fa715170ac57caafc59131057c3a3b9c
2021-09-15IVGCVSW-6331 Fixup include directive in RedirectMembersToConstantInputsFrancis Murtagh
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I2503e6995c83316094257318743a756da600bb6c
2021-09-15IVGCVSW-6312 Support pre-importing inputsFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: Ifc5e6f2e36767cb2a5cbf281d40ec9989b581abc
2021-08-26IVGCVSW-6311 Add the pre-import backend capabilityFinn Williams
* Update acl and ref backend capabilities * Add check for AsyncExecution capability in LoadedNetwork * Add new exception for capabilities Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I2f053c845a64f336e96d452793639c6e0d3eaa89
2021-08-20IVGCVSW-6294 Detect and remove extraneous fp16 conversion layersJan Eilers
Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I69a6ceda0d3e8d39947df71a2ad0d365ac7767d8 Signed-off-by: Finn Williams <Finn.Williams@arm.com>
2021-08-20IVGCVSW-6249 Add ProfilingDetails Macros to all workloads in Ref, Neon, CLKeith Davis
* Add functionality to only output network details in ExNet Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I0c45e67193f308ce7b86f1bb1a918a266fefba2e
2021-08-17IVGCVSW-6119: Restore FullyConnectedDescriptor::GetNumViews for backward ↵Francis Murtagh
compatibility * Deprecate publicly visible API and forward to new function name Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I25fe8a303b50ecb478abd35ca034ad09bd737fe4
2021-08-17IVGCVSW-6317 Cleaning up BackendRegistry following negative tests.Colm Donelan
* Deregister backends in BackendHintTest. * Deregister backend in ThrowBackendUnavailableException * Clean up dynamic backends when an exception is thrown from RuntimeImpl::RuntimeImpl. * Use CHECK_THROWS_AS_MESSAGE syntax in ClCustomAllocatorTests. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I0e6e5413dd074b5fcfc9515c85cb8d40a4a0b73c
2021-08-13IVGCVSW-6291 'Issue parsing profiling layer details'Sadik Armagan
* Initialized the new variable. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I3d86d43455dd2df4246d76a2ac7cb49d8a48b786
2021-08-13Fixed logic error.Mike Kelly
* Condition used to check if m_BiasTensorInfo had a value then obtain a value from m_WeightsTensorInfo Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I1b68ed98baa54a20663728b8871dcfa35c3347f0
2021-08-12IVGCVSW-6077 Add Custom Allocator testsFrancis Murtagh
* Add test for invalid backend and nullptr * Small refactor * Throw exception on nullptr allocator instead of assert Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I94ce4f61d7cb3123831f1acd98165ae14c40033a
2021-08-11IVGCVSW-6297 'Issue with Profiling output'Sadik Armagan
* Added missing comma to output. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I10dde7666ea1e6ea7ebe5bd497d18fc838cb9812
2021-08-11IVGCVSW-6087 Add an Assertion check to make sure we aren't given null allocatorsDavid Monahan
Add conditional compilation check to Cl specific header Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: Ib196b8ef4dc5fcfd1d1ccd3f29abf8e0ecd020cb
2021-08-10Adds CustomAllocator interface and Sample AppJan Eilers
* Updates the runtime options with a CustomAllocatorMap which allows to define a CustomAllocator for specific backends * Change IBackendInternal interface to use a shared pointer to a custom allocator * Update ClBackend.hpp/cpp to use the CustomAllocator * Adds an example application and unit test which uses a CustomAllocator for GpuAcc * Refactor of the interface to use MemorySource instead of the user Mapping cl_mem directly * Modify the BackendRegistry to also hold a registry of CustomAllocators * BackendRegistry Deregister will also deregister any allocators associated with that backend id * set_global_allocator within the BaseMemoryManager so that it always matches the currently used allocator Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I156d819686021865f4375e6cb7a5c5dec8fee9e8 Signed-off-by: David Monahan <david.monahan@arm.com>
2021-08-10IVGCVSW-6292 Allow profiling details to be switched off during profilingKeith Davis
* Add switch for network details during profiling Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I8bd49fd58f0e0255598106e9ab36806ee78391d6
2021-08-10IVGCVSW-6289 Separate tensor shape inference and validation callsFinn Williams
* Pass m_shapeInferenceMethod to OptimizerOptions in ExecuteNetwork Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I90280fb7629092d3b66e8a3968ca9e35a0df854a
2021-08-09IVGCVSW-6119 ConstTensorsAsInput: FullyConnected Bug FixMatthew Sloyan
* Updated FullyConnected layer member variables when cloning as some backends still require them. * Added SetConstant call when using deprecated AddFullyConnectedLayer method to ensure backwards compatibility. * Added SetConstant to SimpleSample to ensure it runs on all backends. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ie7b4e4b868f23f8fcf9c41ffd12e2ea9ea53afca
2021-08-06Infer tensor shapes before graph optimizationFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I2a7a9b7b21848e2b3258788f06b01159f95a0d6c
2021-08-06IVGCVSW-6119 ConstTensorsAsInput: FullyConnectedMatthew Sloyan
* Constant weights and biases are now stored as Constant layers. * Updated Serializer, Deserializer and unit tests to reflect this. * Updated TfLiteDelegate, TfLiteParser and OnnxParser. * Updated Schema with IsConstant and ConstantTensorsAsInputs. * Updated Ref backend to handle constant weights and bias as inputs rather than reading from member variables. * Added dynamic or constant input EndToEnd tests. !android-nn-driver:5959 Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ibf3cf437df1100e4b322b0d303c575c6339f9696
2021-08-05IVGCVSW-6258 'Unittest failures'Sadik Armagan
* Fixed unit test failures happening on threads. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I2a6048f75ece4a9f4c2116306838ff55385aabe7
2021-08-05IVGCVSW-5980 Add Descriptor, TensorInfo and Convolution algorithm to JSONKeith Davis
* Add GUID as field to layer details and profiling events * Add Optional GUID param to existing tests * Improve Details macro to be inline function * Fix some formatting Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I66f192a90a7642b3ee8e7dda0d3f428cce002581
2021-08-04Fixed bugs in PreCompiledLayerMike Kelly
* Fixed PreCompiledObject type (was const void** instead of void*) * Fixed bug where a new shared_ptr was being created instead of allowing std::move to convert the unique_ptr into a shared_ptr. * Improved tests to ensure that the original pointer is maintained. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I3f50d51775ee0180c894c2843ed7bc990a771dea
2021-08-04IVGCVSW-5980 JSON profiling outputKeith Davis
* Add new ProfilingDetails class to construct operator details string * Add new macro which helps append layer details to ostream * Add ProfilingEnabled to NetworkProperties so that profiling can be realised when loading the network * Add further optional info to WorkloadInfo specific to convolutions * Generalise some JsonPrinter functions into JsonUtils for reusability * Remove explicit enabling of profiling within InferenceModel as it is done when loading network * Add ProfilingDetails macros to ConvolutionWorkloads for validation Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: Ie84bc7dc667e72e6bcb635544f9ead7af1765690
2021-07-22MLCE-530 Add front end support for UnidirectionalSequenceLstm on ArmNNNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I57bcbdec3eb0155f41af0fe7d6abf9bac2ec86eb
2021-07-22IVGCVSW-6073 Add protected mode to ArmNN CreationOptionsJan Eilers
* Adds logic to the Runtime to activate protected mode * Adds ProtectedContentAllocation backend capability to ClBackend It's not fully activated yet because the CustomAllocator is missing. Will print an error message and won't register the backend but won't fail. * Extends IBackendInternal with an UseCustomAllocator function. * Adds related unit tests Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I64f465c5800eb104aa90db1bbf772a4148b5072f
2021-07-16Avoid empty test suitesMatthew Bentham
Refactor code around conditionally-compiled tests to avoid declaring empty test suites, as this can cause unused function warnings to be issued under certain combinations of compiler, warning level, and doctest version. Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: Ib501aef80475538a725b857d9c31d1d2f96b124d
2021-07-16Avoid undefined behaviour in NumericCast unit testMatthew Bentham
Because the maximum value of an int32_t isn't exactly representable by a 32-bit float, casting it to a float produces a greater value, and then casting that back to an int32_t is undefined. (In tested implementations the cast saturates, so accidentally the correct result is returned). Using double for the intermediate value instead gives a high enough precision that this test case can be safely expressed. Silences warning from Undefioned Behaviour Sanitiser. Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: I6fe3e89cb6ac695049c92f3b75aca0c14d0e14aa
2021-07-15Fix some compile warnings & errorsRob Hughes
* Fix type of literals * Add explicit casts * #include missing headers * Replace use of non-standard u_int8_t * Remove name of unused variables * Fix DLL export macro - this was broken when some of the exporting headers were moved to a different library. Change-Id: Ie569c8df41a077b46c608798f39526352e2aeb3a Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2021-07-05Remove excess trace messages from unit testsMatthew Bentham
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: I5889a5f44c0c22da6421d9bd06494c75d74e0440
2021-06-30IVGCVSW-6161 ConstTensorsAsInput: Optimizer - Redirect ConstTensor layer membersMatthew Sloyan
* Optimization that searches for layers with ConstantLayers as inputs. * The layer member variables are then redirected to these ConstantLayers. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I24a2bf0e8575b808343e0bbe3897b344e94796ad
2021-06-30IVGCVSW-6114 Create multiple LoadedNetworks from one OptimizedNetworkMike Kelly
* Added IOptimizedNetwork constructor that takes another IOptimizedNetwork and a ModelOptions. * Changed PreCompiledLayer to use shared_ptr rather than unique_ptr to store the PreCompiledObject (no interface changes). * Added unit tests to ensure that PreCompiledLayer::Clone() clones the pointer to the PreCompiledObject correctly. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I3ef56055e0d189ffce9e651882d34da16c70a240
2021-06-29IVGCVSW-6027 Add IsConstant flag to TensorInfoJan Eilers
Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I7cb0a6a8856d8cd9949bec83c1ddce0a454fdf63
2021-06-23IVGCVSW-6062 Rework the async threadpoolFinn Williams
!android-nn-driver:5802 * Extract the threadpool from LoadedNetwork/Runtime * Refactor the threadpool to be handle multiple networks * Trim IAsyncExecutionCallback and add an InferenceId to AsyncExecutionCallback * Add AsyncCallbackManager class Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I36aa2ad29c16bc10ee0706adfeb6b27f60012afb
2021-06-16Refactor Network.hpp to be in alphabetical orderKeith Davis
Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: Ib31d239ce0b85639e1984ed91edccdbdeb12a57e
2021-06-16MLCE-510 Add CpuRef Shape Operator to ArmNNKeith Davis
* Add front end * Add reference workload * Serialization/Deserialization * Add unit tests * Update ArmNN Versioning Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I6fcb1fa341d6f08dea4003b13544e6e9f53fefd3
2021-06-16IVGCVSW-6088 Add Sin and Log to ElementWiseUnaryTeresa Charlin
* Ref workload * Cl workload * Neon workload * Serializer * Deserializer * Remove boost include from TensorTest.cpp Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I498548169cc77609c55cf3105f1de5a7429772cf
2021-06-16IVGCVSW-5826 Change weights layout for depthwise to [1,H,W,I*M]Jan Eilers
* This change is necessary because tflite uses a [1,H,W,I*M] format and uses the I*M dimension for per axis quantization. Our previous layout [M,I,H,W] can't handle the correlating quantization scales. * Updates Onnx-, TfLiteParser and TfliteDelegate * Updates the CpuRef, CpuAcc and GpuAcc backends * Adjusts unit tests * Adds test to ensure models with old layout can still be read and executed * Adds conversion function to previous layout [1,H,W,I*M] --> [M,I,H,W] which can be used by backend developers !android-nn-driver:5553 Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ifef23368b8c3702cf315a5838d214f7dc13c0152
2021-06-16IVGCVSW-5835 Move the src/profiling/LabelsAndEventClasses class to ↵Nikhil Raj
profiling/common Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I83de0fe9c83ec7e698817095ce5cfe3319c36ea6
2021-06-11IVGCVSW-5963 'Move unit tests to new framework'Sadik Armagan
* Used doctest in ArmNN unit tests Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ia9cf5fc72775878885c5f864abf2c56b3a935f1a
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-06 18:58:28 +0000