aboutsummaryrefslogtreecommitdiff
path: root/src/backends/neon
AgeCommit message (Collapse)Author
2019-06-26Update the CL pin to the latest masterFerran Balaguer
* Update SoftMaxUint8Workload for CL and NEON to deal with quantization parameters as vectors. * Change Sigmoid Activation function QAsymm8 tests to use scale=1.f/256.f and offset=0 as quatization output parameters. !android-nn-driver:1417 Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Change-Id: Ief91f10193fbbbad0c0124ece41f0bf4e0dcd992
2019-06-19IVGCVSW-3288 Add L2Normalization epsilon Neon workload supportFerran Balaguer
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Change-Id: I938d97e6a2bfab8ff5f4548efeeaa43b7f5ccda2
2019-06-18IVGCVSW-3234 Add unit test for Concat with different quantization paramsNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ia655b1b6c5f57d2b7c0d9dd17be342cd01f36c09
2019-06-17IVGCVSW-3221 Refactor Mean ref workload and testsJames Conroy
* Renamed RefMeanFloat32Workload and RefMeanUint8Workload to RefMeanWorkload, updated references to reflect this change. * Refactored RefFloorWorkload to use Decoders/Encoders, to support the use of multiple data types. * Deleted reference Unit8 Mean tests as they were duplicates of the Float32 tests. Refactored these tests to support multiple data types and updated references. * Adjusted the values used in the tests' input tensors so that they are more like floating point numbers e.g. change 1.0f to 1.5f. * Replace size_t with unsigned int in Mean ref workload, for better compatibility with the Encoder/Decoder, removed some unnecessary casts after this. * Added ValidateTensorDataTypesMatch() function to WorkloadData.cpp, added CreateIncorrectDimensionsErrorMsg function to RefLayerSupport.cpp. * Added passing and failing tests for ref IsMeanSupported. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: Id3d44463d1385255c727a497d4026d21a49e7eb2
2019-06-14IVGCVSW-3278 Cl and Neon TensorHandles inherit from common base interfaceDerek Lamberti
Change-Id: Ia68da09d8f0fb0a04af9cb61062d7edaa5f1b887 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-06-14MLCE-121 Github: Build error on GCC 9Mike Kelly
* Fixed an error encountered when building on GCC 9 error: moving a local object in a return statement prevents copy elision * Fixed failures in unit tests due to std::initializer_list handling in GCC 9 Change-Id: I4bfdd2113dfedcecd29479ee556e4ae22278755d Signed-off-by: Mike Kelly <mike.kelly@arm.com>
2019-06-12IVGCVSW-3217 Refactor the Layer tests for ResizeBilinear to make them genericEllen Norris-Thompson
* Refactored the ResizeBilinear tests so can be used for both Float32 and Uint8. * Moved to .hpp file and renamed tests accordingly. Signed-off-by: Ellen Norris-Thompson <ellen.norris-thompson@arm.com> Change-Id: Icf79b0616db0c307cfcf94747fe0a6d4343588bd
2019-06-04Update the CL pin to the latest masterMatteo Martincigh
* Updated the pinned CL revision * Changed the type for axis in L2Norm workloads !clframework:d7dd15c445397ab879439de6659859db09f4b752 !android-nn-driver:1268 Change-Id: Ib568869ae8259c4c7d62fc8b434c74a7f8242988 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-06-03IVGCVSW-3148 Add end to end test for Dequantize layer to Ref, Cl, NeonNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Iaf9c290c093b7d84949993439568e55433938b4e
2019-05-31IVGCVSW-3177 Refactor Floor reference workloadJames Conroy
* Renamed RefFloorFloat32Workload to RefFloorWorkload and updated references to reflect this change. * RefFloorWorkload now uses Decoders/Encoders and supports the use of multiple data types. * Deleted FloorTestImpl.hpp and moved its contents into LayerTests.hpp. Change-Id: Ie079d05f2f6a578172f0fe3024f9607c030bce64 Signed-off-by: James Conroy <james.conroy@arm.com>
2019-05-31IVGCVSW-3165 Added accidentally removed CreateFakeQuantization FunctionSadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I50a1a364f13df03dea0833023ec0f2c2794f24db
2019-05-31IVGCVSW-3148 Add Neon backend support for DequantizeNarumol Prangnawarat
* Add NeonDequantizeWorkload * Add IsDequantizeSupported to call validate from ACL function * Add CreateDequantize to NeonWorkloadFactory * Unit tests Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I96a216ef78cc3f6a57aa439a16ae6aafd783ff93
2019-05-31IVGCVSW-3185 Add NeonQuantizeWorkloadSadik Armagan
* Added NeonQuantizeWorkload to ArmNN Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I41f8707dda35c894841eddae2d3b78f088038c8e
2019-05-30IVGCVSW-2771 Add more end to end tests for splitter on Cl, Neon, RefNarumol Prangnawarat
to cover different number of dimensions and split axis Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ia9a111c8dcfc08d04b54aa770d1ae5312c6b1c93
2019-05-29IVGCVSW-3172 Add QSymm16 support for reshape workloadNina Drozd
* Added QSymm16 to supported types in WorkloadData * Added QSymm16 to supported types in RefLayerSupport * Created templated SimpleReshapeTest in LayerTests * Updated ClLayerTests to use templated SimpleReshapeTest * Updated NeonLayerTests to use templated SimpleReshapeTest * Added test for QSymm16 to RefCreateWorkloadTests, RefLayerTests * Removed ReshapeTestImpl as all reshape test methods were moved * Added FloorTestImpl for existing SimpleFloorTest Change-Id: I78efede8aab74c2d4cb0841dd426b8e06186133d Signed-off-by: Nina Drozd <nina.drozd@arm.com>
2019-05-29IVGCVSW-2745 Unit test error running ArmNN on Raspberry PiConor Kennedy
* Fix bad_alloc on NeonTimerMeasure test Change-Id: Ia4ab24abfe0305a3d7773162dc423bc049e1a3cc Signed-off-by: Conor Kennedy <conor.kennedy@arm.com>
2019-05-28IVGCVSW-3119 Rename MergerLayer to ConcatLayerJim Flynn
!android-nn-driver:1210 Change-Id: I940b3b9e421c92bfd55ae996f7bc54ac077f2604 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-05-28IVGCVSW-2771 Add end to end tests for splitter on Cl, Neon, RefNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I44f8f1799f6182721751b1d117c9ada5b91f52e1
2019-05-28IVGCVSW-2970 Support QSymm16 for FullyConnected workloadsFrancis Murtagh
* Add support for QSymm16 for FullyConnected * Add templating to Uint8 RefLayerTest to test QSymm16 Change-Id: Ie6e989daf2ca966d6c6805b8017126eb77ebfec4 Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2019-05-23IVGCVSW-2771 Fix SubTensor error in vgg16 ExecuteNetwork NEONNarumol Prangnawarat
* Add check if Sub-tensors cannot be used, call ACL function * Add computation of SplitAxis from SplitterDescriptor * Add NeonSplitterWorkload functions * Modify IsSplitterSupported to call ACL validate function if sub-tensor cannot be used * Also check if quantization parameters match when using sub-tensors * Add more unit tests for Splitter in TfParser and TfLiteParser Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I31e4c7d055117c83c65b598c4125442173242226
2019-05-22IVGCVSW-3132 Reintroduce SubGraph definition, but deprecatedMatteo Martincigh
* Restored old SubGraph class definition as an alias of SubgraphView for backward compatibility * Restored SubGraphUniquePtr * Restored CreateSubGraphConverter method (and the corresponding ISubGraphConverterPtr type) as a deprecated method that's been removed from the backend interface * Chaged the defautl implementation of OptimizeSubgraphView to call the deprecated OptimizeSubGraph * Changed the default implementation of OptimizeSubgraphView in the backends Change-Id: If69903926bf5ff2aae52c9b64b4572b355662757 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-05-20IVGCVSW-3124 Rename workloadFactory CreateMerger to CreateConcatJim Flynn
Change-Id: Id836372c0e4ef0c3996085facc4da6263366abcf Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-05-20IVGCVSW-2967 Support QSymm16 for Constant workloadsNina Drozd
* Validate that output is any of supported types in WorkloadData * Validate that output is any of supported types in RefLayerSupport * Add test for constant with QuantisedSymm16 in LayerTests * Add test for creating constant workload in RefCreateWorkloadTests * Add test for constant with QuantisedSymm16 in RefLayerTests * Refactor RefConstantWorkload - BaseWorkload instead of TypedWorkload * Refactor RefConstantWorkload - remove m_RanOnce, use PostAllocationConfigure() Signed-off-by: Nina Drozd <nina.drozd@arm.com> Change-Id: Ic30e61319ef4ff9c367689901f7c6d498142a9c5
2019-05-20IVGCVSW-3117 Rename NeonMergerWorkload to NeonConcatWorkloadJim Flynn
Change-Id: I9a373a31bfabbe0f691d7f9e240ac08e072b2c7d Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-05-14IVGCVSW-3076 Add ConcatLayer methods to public APIJim Flynn
!android-nn-driver:1120 Change-Id: I5192fa3deb4ea9766d38ad0bf4dfbfa0b4924c41 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-05-14MLCE-101 Add dilation support for DepthWiseConv workloadBruno Goncalves
Adds unit tests for dilated depthwise conv Change-Id: Iad0a1b33d07fb0ef8f9f6edf0fd0f83a5800a36d Signed-off-by: Bruno Goncalves <bruno.slackware@gmail.com> Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
2019-05-13MLCE-101: Adding dilation support in conv and dconvPablo Tello
Added support for dilation in DepthwiseConvolution2d in the Neon and CL backends. Change-Id: Ie1522b498c07f80d6efcf9dc79e926c8cfa06ca5 Signed-off-by: Pablo Tello <pablo.tello@arm.com>
2019-05-03IVGCVSW-3030 Update the backend code to create also a list ofMatteo Martincigh
non-optimized SubgraphViews * Removed pointless CreateSubgraphViewConverter method in the IBackendInternal interface Change-Id: Ie2d3c0e74fb3d53e67f76924ac6d05050a5e6e2e Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-04-30IVGCVSW-2405 Rename SubGraph to SubgraphViewDerek Lamberti
Change-Id: Ie50aeccf053c20c3a01a75042bbc3acd824375af Signed-off-by: Derek Lamberti <derek.lamberti@arm.com> Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-04-29IVGCVSW-2396 Go back to using offset memory managerSadik Armagan
Change-Id: If6cf69b1569eb69c9481369a99ca7066be0fdd9d Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
2019-04-16IVGCVSW-2957 MergerLayer subtensor optimization now backend agnosticDerek Lamberti
+ Update clframework pin + Cl and Neon Merger workloads updated to use MemoryLayout agnostic API + Workloads only use sub-tensor optimization if ALL input tensors are sub-tensors + Refactor LayerSupportCommon code to be a bit more succinct Change-Id: Ib61ad4ccbd767e924dff07e61022e0cda4069828 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-04-16IVGCVSW-2425 Add unit test for Logistic (Sigmoid) in NEONNarumol Prangnawarat
Change-Id: I557b76ea8c066161f3eb866daabca63694d46f4e Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
2019-03-15IVGCVSW-2354 Caffe SqueezeNet through armnn Cl and NeonNarumol Prangnawarat
* Compute Softmax Acl axis for Cl and Neon * Add unittests for Softmax in 3D and 4D * Correct input and output layer names in CaffeSqueezeNet inference test Change-Id: I2d369d9a2db19c40f2af3341039dd33f0c5637b1 Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
2019-03-11IVGCVSW-2792 Update Neon Mul/Sub workload for latest CL masterConor Kennedy
* Update Neon Subtraction/Multiplication to use BaseWorkload * Add Uint8 tests for Subtraction/Multiplication Change-Id: Ied2aa048924817a4db0025b9bd9e54151667bd74 Signed-off-by: Conor Kennedy <conor.kennedy@arm.com>
2019-02-01IVGCVSW-2280 Add unit tests for RESIZE_BILINEAR NEON operatorConor Kennedy
* Add uint8 tests Change-Id: I178e34a638411fa065bdc4c722136a02ba9e000b Signed-off-by: Conor Kennedy <conor.kennedy@arm.com>
2019-02-01IVGCVSW-2603 The macros ARMCOMPUTECL_ENABLED and ARMCOMPUTENEON_ENABLEDMatteo Martincigh
no longer work * Added two master variables ARMNN_COMPUTE_CL_ENABLED and ARMNN_COMPUTE_NEON_ENABLED to android-nn-driver/Android.mk to easily control backend support * Setting either of those two new variables then properly sets the corresponding build macro * If a specific backend gets disabled, the corresponding source files will be excluded from the build * Unified the usage of the pre-compile macros !android-nn-driver:613 Change-Id: I582ff73493b70ba9e22ca2e38d875a0f19566c8a Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-01-31MLCE-90 Fixing issues with NEON pad testsÉanna Ó Catháin
Change-Id: I3e971c66798610d2c96445fa3babb7cc90cf8031 Signed-off-by: Éanna Ó Catháin <eanna.ocathain@arm.com>
2019-01-30IVGCVSW-2458 Refactor the Optimize function (Network.cpp) so thatMatteo Martincigh
subgraphs are optimized by the backends * Added a new method OptimizeSubGraph to the backend interface * Refactored the Optimize function so that the backend-specific optimization is performed by the backend itself (through the new OptimizeSubGraph interface method) * Added a new ApplyBackendOptimizations function to apply the new changes * Added some new convenient constructors to the SubGraph class * Added AddLayer method and a pointer to the parent graph to the SubGraph class * Updated the sub-graph unit tests to match the changes * Added SelectSubGraphs and ReplaceSubGraphConnections overloads that work with sub-graphs * Removed unused code and minor refactoring where necessary Change-Id: I46181794c6a9e3b10558944f804e06a8f693a6d0
2019-01-29IVGCVSW-2447 Add Greater Workload to Neonkevmay01
Change-Id: Ic165061cc61534e7e391a398ea7c2918240e2d3b
2019-01-25MLCE-84 Add Neon Pad support and unit testsÉanna Ó Catháin
Change-Id: I0d949a9f23a61af5013efdd18572b29fae585f2a
2019-01-24IVGCVSW-2554 Update NEON scheduler to output workload names rather than unknownsaoste01
Change-Id: I0d14baf9002c894790da171a6d60c0e4ac929078
2019-01-24IVGCVSW-2555 Add no-op implementation for Detection PostProcessNarumol Prangnawarat
* Added DetectionPostProcessQueueDescriptor to WorkloadData * Added CreateDetectionPostProcess function in WorkloadFactory.hpp * Added stub implementation of the CreateDetectionPostProcess in workload factories * Added DetectionPostProcessLayer stub implementation * Added AddDetectionPostProcessLayer to Network * Added IsDetectionPostProcessSupported to LayerSupportBase Change-Id: Ifc071b3b6b12877c997bdcc43d769c8f891d5c6c
2019-01-24IVGCVSW-2503 Refactor RefElementwiseWorkload around Equal and Greaterkevmay01
* Remove Equal and Greater from RefElementwiseWorkload * Create RefComparisonWorkload and add Equal and Greater * Update ElementwiseFunction for different input/output types * Update TfParser to create Equal/Greater with Boolean output * Update relevant tests to check for Boolean comparison Change-Id: I299b7f2121769c960ac0c6139764a5f3c89c9c32
2019-01-23IVGCVSW-2511 Add end to end Gather layer testnarpra01
* Add end to end test for Gather operator * Add Support for int32 to Constant layer for Ref * Add Int32Workload * Add RefConstantWorkload as template for float, uint8, int32 * Remove unused RefBaseConstantWorkload * Remove unused RefConstantFloat32Workload * Remove unused RefConstantUint8Workload * Add support check for int32 in LayerSupport functions Change-Id: Ic970588a49ebe2aafb12be8adef52371feacaa7b
2019-01-23IVGCVSW-1048 RESIZE_BILINEAR NEON operatorSadik Armagan
* Implemented NeonResizeBilinearWorkload * Enable ResizeBilinear Operator unit tests for Neon !android-nn-driver:405 Change-Id: Iec3100ccaf7d246e8eaf683d1f3ec9191df5241e
2019-01-23IVGCVSW-2455 Move the extra backend code to a new git repoMatteo Martincigh
* Refactored all the workload factories to use "virtual" properly * Removed the precompiled layer support from the optimizer * Disabled compiler optimization for debug build to ease debugging Change-Id: I6ab83abd78f422771359295e25b79bb9be613cfd
2019-01-22IVGCVSW-2467 Remove GetDataType<T> functionNattapat Chaimanowong
Change-Id: I7359617a307b9abb4c30b3d5f2364dc6d0f828f0
2019-01-16IVGCVSW-2508 Add no-op factory implementations and layer for Gather operatornarpra01
* Added GatherQueueDescriptor to WorkloadData * Added CreateGather function in WorkloadFactory.hpp * Added stub implementation of the CreateGreater function in workload factories * Added GatherLayer stub implementation * Added AddGatherLayer to Network * Added IsGatherSupported to LayerSupportBase Change-Id: I0408fd54e88a7d4e3d9e1c2811a9323f0da52a04
2019-01-15IVGCVSW-2454 Merge together the pluggable backends work (was in aMatteo Martincigh
separate branch) and master * Brings in all the changes done for the pluggable backends * Added sub-graph support and tests * Added precompiled layer support and tests * Moved BackendSettings to a separate file * Removed the backend-specific code * Ported DebugLayer and associated functionality * Included fixes to make those changes work with master Change-Id: Id7028fa7917527b844628d5aff5732e3d94c0488
2019-01-11IVGCVSW-2454 Refactor ArmNN to support pluggable backends from a separateMatteo Martincigh
code base * Made the virtual functions in ILayerSupport.hpp pure * Created a LayerSupportBase class with the default implementation of the interface * Made the backend layer support classes inherit from the base class, instead of directly from the interface * Refactored the profiler and the profiling event classes to use the BackendId instead of the Compute * Implemented a proper MemCopy support method * Changed Compute to BackendId in the profiling API and objects * Removed static references to pluggable backends !android-nn-driver:492 Change-Id: Id6332b5f48c980819e0a09adc818d1effd057296
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-03 17:46:47 +0000