aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2023-01-17IVGCVSW-7382 Implementation of Conv2d within GpuFsaexperimental/GpuFsaCathal Corbett
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I6802687bb959c74afb1b9aebed133b2b17c036dc
2023-01-13IVGCVSW-7381 Add IsLayerSupported implementation to GpuFsa backendMatthew Sloyan
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ib18af4a4be4a87e301ff0d0fea5205e985052846
2023-01-12IVGCVSW-7380 Update the GpuFsa Skeleton to build and load ACLCathal Corbett
* Reuse cl backend to be able to create ClRuntime, ClContexts etc. for the new GpuFsa backend. * Can access code defined in the experimental interface dynamic_fusion. * No BackendModelContext as model/backend options not required for now. * Any of the serializer and deserializer is emitted as context caching not required. * No ImportTensorHandle and ImportTensorHandleFactory for now. * Moved tuning and IClTensorHandle code to aclCommon as it is accessed by both cl and gpuFsa. * Small code refactor of cl backend. * Added DefaultAllocatorTests to GpuFsa backend. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I6ae591360e9d2a783aafd06e2d7bf8e0b3e623ee
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
2022-12-19Github #712: Use static libraries not object libraries for support libraryFrancis Murtagh
* .o files were being installed by cmake. Change-Id: Ie2056e09b4800fe208d784a90f3908d508b8cadf Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2022-12-16Bump pillow from 9.0.1 to 9.3.0 in /samples/ImageClassificationMike Kelly
* From dependabot Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Ibf4dc2a679b4d588f823b8b1f1d34f7d4a2125c5
2022-12-16Update ACL pin to a0ae8d2e6c57fd95c0edaf659b9df8b8c540d051Nikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I75ff1d006d27d53898e6749a18f52359c043ec3a
2022-12-16IVGCVSW-7379 Add xxd package to build toolKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I5ac1f1032cc2507ce0b8677a08e9debefab2779c
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
2022-12-14Update ACL pin to 32741725ac6e6c9658c51ed8585d314a1707ee8cNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I6cd834ffaba9c7d598ba5c86df3d1e8bc9c86418
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
2022-12-13IVGCVSW-7365 Fix behaviour of --import-inputs-if-aligned in ExecuteNetworkMatthew Bentham
Move call to 'SetupInputAndOutputs' to after LoadedNetwork is available. Change-Id: I101e297d1d7b2517011d4ef3f1a4927566845474 Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
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
2022-12-12Optimize the calling of IsLayerSupported().Cathal Corbett
* Done as part of 22.11/23.02 innovation days. * IsLayerSupported() is called in model prepare (delegate, android-nn-driver and shim/support_library) and again in ArmNN once model otimization is performed. * From calling IsLayerSupported() the first time, we should know that the layers are supported and what backend they are supported on. * Solution is to set the BackendId of the IConnectableLayer when IsLayerSupported() is called the first time, * In the Optimize() function we then check if the backend is set. If so, we do not call IsLayerSupported() again. * In the case a layer that is supported gets optimized, then the BackendId of that layer get set to "Unknown" for the new optimized layer and IsLayerSupported() will get called on the newly optimized layer. * Includes bug fix IVGCVSW-7213 for Android Mean FP16 CpuAcc tests. Also related to bug IVGCVSW-7211. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I7a7820d0cdb079ffb5a3a2e0c44e252f652df53b
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
2022-12-07Add Arm NN include in build-tool outputJames Conroy
* Usability improvement Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I973e2c29e5974db9f2da04e39b549ecb1b12cb48
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
2022-12-07Fix some memory overruns / undefined behaviour in ShapeInferenceTestsMatthew Bentham
In several cases the address of a single float value on the stack was passed as a pointer to the constructor of ScopedTensor (which needs a backing-store of size equal to GetNumBytes()). Replace by using a std::vector to explicitly create and initialize the right number of elements. Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: I8a1f4bf169bd89983f2d68047173ec901a21e1fb
2022-12-06Print BatchMatMul and Gather Descriptors on dot graphTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I01de14cd46fe614dfcb11b2b4f9323f32e01ee9d
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
2022-12-05Fix build error due to missing includePablo Marquez Tello
Change-Id: I38fa4b49b0cdb506293c7b0e75146b56649839b8 Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
2022-12-01Update ACL pin to f16973b8b4605f12608bffa9f0ca6ed590202d41Nikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: If47571cfc531cca81e983daaf7c13a7f608e9365
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
2022-11-30IVGCVSW-7220 Remove referencetests repo and testing of itKevin May
* Remove mentions of reference tests Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Idd3c8b2e48f03531b1ec6cc67fd3bd32e50086c3
2022-11-29Update ACL pin to 03b2971ac69a86f10a1566938d1a25afee15746cNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Ia9b59fd3482c5a12d7f6a369b1bdf91f06596a66
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
2022-11-22IVGCVSW-7080 Remove deprecated code due to be removed in 23.02Keith Davis
* Extended deprecation time of SubgraphView interface to 23.08 Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: Ic0a729ea31402f0b39724da47212ae5cc04465c4
2022-11-22IVGCVSW-6980 Delegate support for slice operatorCathal Corbett
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I90d800160b070e25d999b5102a7ce6d3e0ed6a81
2022-11-22Remove link to Crosscompile guide in the DoxygenNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I3362442456df2bc5ee71080238881b390a9029d8
2022-11-21Change name of AAR file in the Readme download pathNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Id5521e527b4b8d738acf673c4c51e54c80b71a74
2022-11-18IVGCVSW-7330 Add end-to-end dynamic sample build stepsJames Conroy
* Moving from other build guides which are being removed and/or consolidated. Provides steps on how to build the standalone backend unit tests using the build-tool. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I3994bffc9038632ab7271ac31db25a38157f2bb7
2022-11-18Update FAQ with GCC8.3 Tflite 2.10 IssueRyan OShea
* Inform users of potential gcc8.3 issue when linking against TfLite 2.10 Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: Ie58b7f8a9c11f9d5088c531ecffd4cc06a4ab7ca
2022-11-18IVGCVSW-7330 Fix build-tool args for Docker buildsJames Conroy
* This change requests users to supply a comma separated string of CMake/scons args so that they can passed down from Docker into the bash script correctly. * Updated documentation to reflect this. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: Icbd1d1458e11382936690ca6cc4417677e063ddb
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
2022-11-15IVGCVSW-7332 Fix Delegate Profiling in ExNet with multiple iterationsKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: If837e4bec7940b53d18d0da32f3e736215dd2a03
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
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-17 22:15:07 +0000