aboutsummaryrefslogtreecommitdiff
path: root/src/backends
AgeCommit message (Collapse)Author
2023-01-12Merge 'main' onto 'experimental/GpuFsa'.Cathal Corbett
* I6c71be11e9b73694747b27fe9febab8d9669b4d4 Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Iccaf50e2484559979d801ee9d0e130e848554733
2022-12-23IVGCVSW-7159 Add GpuFsa backend skeletonJames Conroy
* Basic skeleton code added for GPU Dynamic Fusion backend. Signed-off-by: James Conroy <james.conroy@arm.com> Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ia49ecf994e278d034e85238be37fefaca84c543d
2022-12-15IVGCVSW-7170 Add Concat support to TOSA Reference BackendKevin May
* Change comment for the unique tensor names in all tosa common operators Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I247b4b2365d5f0173218c5dfd11fba12d2399959
2022-12-15Small fixes in TOSA common and TOSA reference:Teresa Charlin
* alphabetical order, * specify floats * fix order of parameters in convolution operator * fix uninitiated variable in ConvertConstantTensorDataToBuffer Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ic82e6127cac6b94da4c859a284893b838ab248bc
2022-12-15Change the semantics of RefTensorHandle::Import to 'overlay' existing memoryMatthew Bentham
This makes it possible to call Import on an Allocated() or memory-managed Tensor, which is needed for the current implementation of OptimizerOptions::m_ExportEnabled to work (as the last layer before the OutputLayer needs to be able to Import the user's OutputTensor, but this is done after other memory allocation). Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: I1a885c2da7b1f0f3964ae53b8135b5e96a66614f
2022-12-15IVGCVSW-7168 Support simple model in the TOSA Reference BackendMatthew Sloyan
* Fixed issue where duplicate tensors where being created. * Fixed issue where output name could be generated with the wrong id. * Updated bias tensor for Conv2d, so the size matches the channel. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I1de6947e036b3e629ec6446d24d69e50603a5593
2022-12-15IVGCVSW-7204 Add TransposeConv2d support to TOSA Reference BackendMatthew Sloyan
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I9bfd597afd41468f304edfbe5d7141378ce60d4f
2022-12-14Update TOSA Reference Backend IsLayerSupportedMatthew Sloyan
* Replace current IsLayerSupported checks with ModelRunner for better validation. * Added options to be able to disable the output from the TOSA Reference Model during layer support. * Updated layer support tests to reflect actual support. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Iaea17343d0ad51b495477024c44a34d9335d1438
2022-12-14Fix bug in EthosNAcc backend detection in unit testMatthew Bentham
Test was checking a freshly constructed BackendRegistry, rather than the single instance. Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: I7c64cf089cb406ac4e5ceefedb17163f39801b07
2022-12-14Refactor: Remove m_ImportFlags from RefTensorHandleMatthew Bentham
The import flags for a RefTensorHandle shouldn't be a data member, as RefTensorHandle can only import from MemorySource::Malloc. Instead, use m_ImportEnabled to determine what to return from GetImportFlags(). Simplifies the code in Import and CanBeImported. Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: Ic629858920f7dd32f99ee27f150b81d8b67144cf
2022-12-13Include armnn/IRuntime.hpp in TosaCommon OneToManyMappingTestsCathal Corbett
* Error thrown when building in CLion Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I533f11e7ce2d883e254472097fee3817584d2f49
2022-12-13IVGCVSW-7342 Add Slice support to TOSA Reference BackendCathal Corbett
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I8be286b69bebd4cd36033e3145632bb043938d16
2022-12-13Specified Linker Language for Tosa Reference BackendMike Kelly
* Required for building within the IDE. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Icbf1b7e24cc20f579bcb6f8d82666ed480378dd4
2022-12-12IVGCVSW-7174 Add Reshape support to TOSA Reference BackendCathal Corbett
* Spelling corrections and code refactors added to TosaCommon * TosaDTypeToString() implemented and used in TosaRef IsLayerSupported() instead of enum integer. * Using namespace armnn in TosaCommon OneToOneMappingTests and TosaReference TosaRefLayerSupportTests instead of armnn::ClassName. * Updated VerifyTosaAttribute() to also verify certain attributes from input and output shapes. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I71dfca404d081a665f748ab724153c6dc36b7eca
2022-12-12IVGCVSW-7209 Remove deprecated code due to be removed in 23.02Mike Kelly
* Removed weights and bias from Convolution, DepthwiseConv & FullyConnected layers * Removed the weight and bias ConstTensorHandles from the QueueDescriptors * Updated Workloads to take tensors from WorkloadInfo rather than the QueueDescriptors * Removed unused RedirectMembersToConstantInputs optimization and tests. Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I9ffcdc4a1c0dff725539dd69fc435b700bd98a56
2022-12-12Updates following execution of Includewhatyouuse on armnn/include.Colm Donelan
This tool forces explicit includes of all dependencies and highlights unused dependencies. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I92e449245246452a0227cbd13f9c082e2088bf8c
2022-12-08IVGCVSW-7168 Add Conv2d and Constant support to TOSA Reference BackendMatthew Sloyan
* Added TOSA Conv2d and Constant mappings. * Added unique naming to mappings based on previous and following layers, so they are connected correctly. * Updated existing mappings with new naming convention. * Added all mappings to one main block in OptimizeSubgraphView. * Removed isMain from mapping functions. * Added Conv2d EndToEnd test. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I27c3e238407c32379ce25a1f01dad11523ef5d2b
2022-12-07IVGCVSW-6853 Rewrite BuildArmComputePermutationVector()Teresa Charlin
* Some pemutation vectors were not converted correctly. * Add Transpose end to end test. * Comments added with an example to clarify the differences betweeen Transpose and Permute Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I6c0954ca6ce00ef5f2a6f3625abe6f4fd27b5cdf
2022-12-05IVGCVSW-4926 Add support in CpuRef implementation for Gather for axis ↵Nikhil Raj
different to 0 !android-nn-driver:8727 Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I4336007ad5a8552f7893ce6253f93cf9d1f5474f
2022-12-01IVGCVSW-7272 Add Exception for handling Fp16 infinity valuesKevin May
* Float values which cannot fit in Half are converted as inf/-inf * Add an InvalidArgumentException for infinity displaying the value and data type Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Iaa5671374364c531e29e37fdfe40732b4fdbcfcb
2022-11-23IVGCVSW-7297 When creating multiple Executors only the lastMike Kelly
one works fine * Each CLBackend created its own ClContextControlWrapper which invalidated the OpenCL context's from all CLBackends that were created before that one. * Now CLBackends will keep a shared_ptr to a ClContextControlWrapper which more closely matches the functionality within ACL. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I0744c2cb6a2f0d6b0c5fa54d786f88cf97775559
2022-11-16IVGCVSW-7214 Disable BF16-Turbo-Mode and remove conversion layersRyan OShea
- Remove Bf16ToFp32 Conversion Layer - Remove Fp32ToBf16 Conversion Layer - Remove B16 Conversion tests * Throw exception if m_ReduceFp32ToBf16 optimzer option is set to true * Provide comments to enable fast math in order to use bf16 * Update docs to inform users to enable fast math for bf16 Execute Network Changes * Require bf16_turbo_mode to also have fast_math_enabled set to true - Remove setting m_ReduceFp32ToBf16 optimizer option Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: Ibaa6da9d29c96a1ce32ff5196b0847fde9f04a1c
2022-11-16IVGCVSW-7345 Add Pooling2d support to TOSA Reference BackendCathal Corbett
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I73a47e513fe2d064ef233b121a68ef2edf0396dc
2022-11-15Minor error formatting fixes.Colm Donelan
Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I17823fb8b6bbabc4da327187167ce9582ee29b32
2022-11-14Add additional data type support to TOSA Reference BackendMatthew Sloyan
* Added all data types to TosaRefPreCompiledWorkload::Execute(). * Generalised IsTosaLayerSupported and fixed Addition support. * Added Fp16 and Int32 Addition End to End tests. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I1f89c310ede33615427343e89bcec7e7bb643fa1
2022-11-09IVGCVSW-7318 Support basic addition model in the TOSA Reference BackendRyan OShea
* Create Simple Addition EndtoEnd test * Create EndToEndTest file in TosaRef/test directory * Add AdditionEndToEnd test to CpuRef,CpuAcc,GpuAcc,TosaRef Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: Ic44e2b457c25dcb41bb3b17c05cce0e74bf17a80
2022-11-09IVGCVSW-7165 Implement TosaRefPreCompiledWorkload::Execute()Matthew Sloyan
* Added FP32 support for TOSA Reference Backend. * Added main block creation to OptimizeSubgraphView, this will only occur once. Change-Id: I169dac50b78e2c693da6327962c9f1d3ae3bd712 Signed-off-by: James Conroy <james.conroy@arm.com> Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
2022-11-02IVGCVSW-7164 Implement TosaRefBackend::OptimizeSubgraphViewMatthew Sloyan
* Added TosaRefBackend::OptimizeSubgraphView implementation. * Generalised TosaRefLayerSupport::IsLayerSupported to work with any operator. * Changed TosaCommon.hpp utils to inline functions. * Added source files for TosaMappings.hpp and AdditionOperator.hpp. * Fixed multiple defines issue with HALF_ROUND_STYLE and HALF_ROUND_TIES_TO_EVEN. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ib2576ec3fb97faa3a2256b2fb93ec16ac8745760
2022-11-01IVGCVSW-6496 Add EndToEnd Layer test for Batch MatMul WorkloadTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I6a541db9a602609282cc6f33af930ca141b83c41
2022-10-28IVGCVSW-6494 Add CpuAcc Batch MatMul Workload Fp32Teresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I2def6995f81d33e68f1ea45d8d19a1e6294049b1
2022-10-27IVGCVSW-7273 Fix TOSA Serialization Library integrationMatthew Sloyan
* half.hpp is now required as an include for numpy_utils.h * DType_FLOAT was changed to DType_FP32. * DType_FP16 support has been added to ArmNNToDType utility function. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ib25be9a5abfbd9db2a90b3e42d592259a6df0e01
2022-10-27IVGCVSW-7273 Integrate TOSA Reference Model into Arm NNMatthew Sloyan
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ie9aa1aa20a5bc837e005a7a36d4d07b4cd8d021b
2022-10-19MLCE-545 INT8 TFLite model execution abnormalKeith Davis
* Bug fix where files were being overwritten at each debug layer Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I609fdc82afcee925824efb02183c7dbc942fced0
2022-10-19MLCE-545 INT8 TFLite model execution abnormalKeith Davis
* Add functionality to print output tensors to file in tempdir * UnitTests Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: Idfb4c186544187db1fecdfca11c662540f645439
2022-10-11IVGCVSW-7222 Fix incorrect kernel measurements in profiling outputKevin May
* Some CL kernels are not run after the first inference and this breaks the profiler which is expecting a measurement for every kernel each run * Add a function HasKernelMeasurements() to ascertain if the Event is returning kernel measurements and if so insert 0.0 values for any missing kernel measurements. * Fix ExecuteNetwork to only print a json object after all inferences have completed Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I99f2bb0db847f5a52ab4c5705b072155c6b6f333
2022-10-11Fix TosaOperatorMapping tests when building for releaseMatthew Sloyan
* Asserts are removed during a release build, which causes build failures due to unused variables. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ie36f2bd22f5b2916b03ba7e64c1895fdf21f11f0
2022-09-21IVGCVSW-6790 Adding runtime options to Doxygen.Colm Donelan
* Add a breakdown of the runtime options to the documentation. * Exclude test classes from Doxygen generation. * Limit the file extension selection for Doxygen generation. * Add the support library to be generated. * Fix some broken markups. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I81896f2d7fff503a1d51d6d4ac3876aa8b84118e
2022-09-07IVGCVSW-7159 Implement simple TOSA Reference Backend skeletonFrancis Murtagh
* Added files based on RefBackend * Added PreCompiled Workload skeleton * Increment ABI version of armnnTestUtils for CreateInput which had been left as pure virtual, added base implementation for it. * Add IsTosaLayerSupported() for Addition Change-Id: I4c963adf3f50593d17ecdf21554502a64ad3bd76
2022-09-07IVGCVSW-7209 Remove deprecated code due to be removed in 22.11Teresa Charlin
* Files deleted when Stabilizing the API Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I0ae73ee36968fa880761c10358bfa827be5fe054
2022-09-06IVGCVSW-7006 Remove deprecated code due to be removed in 22.08Teresa Charlin
* AddConv and AddDWConv with weights and bias * ResizeBilinearDescriptor * b,blacklist option in accuracy tool !android-nn-driver:8172 Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ibbc04fd18be7f938b11590bf67cd7af103cb4d99
2022-08-30IVGCVSW-7105: BatchMatMul Optional Parameter SupportSamuel Yap
* Added transpose parameters to pre-transpose each input tensor's slices * Added adjoint parameters to pre-adjoint each input tensor's slices * Small refactoring (BatchMatMulDescriptor static helpers and BatchMatMulImpl constructor) * Updated input validation and output shape inference for parameters * Additional layer unit tests for parameters added * Versionings incremented Signed-off-by: Samuel Yap <samuel.yap@arm.com> Change-Id: Ibe5242a8a5bf604c13de0dc65844fd6c421cc667
2022-08-30IVGCVSW-7133 Add TosaMappings backbone structure with support for Addition ↵Cathal Corbett
TosaMappings operator. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Ibea0cf625b3af4ab38e8b985f7a129c983ca9659
2022-08-05IVGCVSW-7111 change backend deprecation from 22.11 to 23.08Jim Flynn
Signed-off-by: Jim Flynn <jim.flynn@arm.com> Change-Id: I3a3aab7b5042349cb2df8517678306665e037610
2022-08-05IVGCVSW-7145: BatchMatMul Fix for Raspi Cross Compile FailingSamuel Yap
* Changed long variable declaration to int Signed-off-by: Samuel Yap <samuel.yap@arm.com> Change-Id: I2df6f8f6df8780e48e09f7e68c04626a8a8a207d
2022-08-05IVGCVSW-6889 Seg fault running ExeNet with --bf16-turbo-mode on fpgaFrancis Murtagh
* Added case for Bf16 to switch and changed Assertion to Exception so it shows up in Release build. Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I817260dc7b7667386c4aa734bea649383866a785
2022-08-05GitHub #667: Neon fold padding into average pool 2D quantization bug fix.Cathal Corbett
* Originated from a GitHub issue: https://github.com/ARM-software/armnn/issues/667 * Initially, Arm NN supports the pool 2D operation because there is no padding on the pool2d. Neon failure occurs when padding is followed by average pool 2D due to folding optimization. * Here we prevent the folding optimization from happening for the above special case and add it in as a backend specific optimization. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Ia0fd90c3a6b4b9d29c81106f154617d2e893e26b
2022-07-27IVGCVSW-7109: Add Batch MatMul front end support - ReferenceSamuel Yap
* Descriptors added for BatchMatMul * Layer definition added * Input validation added (will likely change when opt. param support comes in) * Ref workload implementation for BatchMatMul added (will also change with opt. param support) * Ref layer tests made for BatchMatMul * CMake and other build files updated Signed-off-by: Samuel Yap <samuel.yap@arm.com> Change-Id: Ic885301da543ee0fbe7922b85e7f9658c4efc617
2022-07-27IVGCVSW-6896 Fix pre-import when using sync execute.Colm Donelan
* Refactor backend capability checks in LoadedNetwork. * ImportInputs should check the number of tensors does not exceed the number of inputs. * In EnqueueWorkload the check for for the count of input tensors was ignoring pre-imported inputs. * Added checks to verify ImportInputs/ImportOutputs worked as expected in EndToEndTestImpl. * Improve documentation on ImportInputs/ImportOutputs in IRuntime.hpp. * Disabled import tests in CL and Neon EndToEndTests that cannot work. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: Iae4b2644a1c9f01ee72bce1afb211661cc9ae2e3
2022-07-27IVGCVSW-6620 Update the async api to use ExecutionDataMatthew Sloyan
* ExecutionData holds a void* which can be assigned to data required for execution in a backend. WorkingMemDescriptors are used in the Ref backend which hold TensorHandles for inputs and outputs. * Updated ExecuteAsync functions to take ExecutionData. * Added CreateExecutionData and UpdateExectutionData to IBackendInternal. * Streamlined experimental IWorkingMemHandle API by removing map related function and unused m_workingMemDescriptorMap from WorkingMemHandle. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I54b0aab12872011743a141eb42dae200227769af
2022-07-08IVGCVSW-7024 Add missing license info for reuse lintJim Flynn
Signed-off-by: Jim Flynn <jim.flynn@arm.com> Change-Id: I97dee6982e0a7be01c13e9e803c0997547a39ff1
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-10 00:18:08 +0000