aboutsummaryrefslogtreecommitdiff
path: root/src/backends/neon/workloads
AgeCommit message (Collapse)Author
2021-08-10IVGCVSW-6249 Add ProfilingDetails Macros to all workloads in NeonKeith Davis
Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I7be77712a9f790928219ce91222d46cc766ab9dd
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
2021-08-04IVGCVSW-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
2021-06-16IVGCVSW-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
2021-05-20MLCE-418 Reduce layer does not support multiple axesMatthew Sloyan
* Added backend specific optimization to chain new reduces layers for each axis to simulate behaviour of a layer with multiple axes. * Added function to calculate reduced output shape. * Added unit tests. * Includes rework to fix IVGCVSW-5987. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I154b3698b5e6756b05b2a0b5a3f0896184efce72
2021-05-07Revert "MLCE-418 Reduce layer does not support multiple axes"Matthew Sloyan
This reverts commit d905decd256558bbee165e636ce4242ac3b9c917. Reason for revert: LargeGraph_TENSOR_FLOAT32/FLOAT16 CTS tests failures Change-Id: Ie69826549e73775825f45134375b5b2c41aebd01
2021-05-06MLCE-418 Reduce layer does not support multiple axesMatthew Sloyan
* Added backend specific optimization to chain new reduces layers for each axis to simulate behaviour of a layer with multiple axes. * Added function to calculate reduced output shape. * Added unit tests. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I180b0b111b7bcf3d0c283f1db0b82d5f17757682
2021-05-06IVGCVSW-5815 Generalise ConstCpuTensorHandleJames Conroy
* Generalises ConstCpuTensorHandle and inherited classes by removing 'Cpu' from aliases. * New renamed classes: ConstTensorHandle, TensorHandle, ScopedTensorHandle, PassthroughTensorHandle, ConstPassthroughTensorHandle. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I1824e0e134202735fb77051f20a7252f161dfe16
2021-04-22IVGCVSW-5419 'Add ACL Support for CAST Operator'Sadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I481343af311cf3cbc81eee80e80d8b5581fdfd7b
2021-02-09MLCE-347 'REDUCE_MIN, REDUCE_MAX, REDUCE_SUM Support'Sadik Armagan
* Added TfLiteParser support for REDUCE_MIN and REDUCE_MAX operators * Added ACL workloads support for REDUCE_MIN, REDUCE_MAX, and REDUCE_SUM operators * Added TfLite Delegate support for REDUCE_MIN, REDUCE_MAX, and REDUCE_SUM operators Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I8085d59946bfd4ab78a59a61f899031ae53371a8
2020-12-17IVGCVSW-4625 Add CL Rank WorkloadDavid Monahan
* Added CL implementation of Rank Workload * Removed references to memcpy_s as it's a windows only function Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: Ia63666b9640d76a775f2ab98b3cd7e9f77b5a507
2020-12-03IVGCVSW-4626 Add Neon Rank WorkloadDavid Monahan
Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: I5a85597e75d2b879ae234c6929686fabe99d7bc8
2020-11-30IVGCVSW-5568 Revert "IVGCVSW-5563 Fix Crash on model with FullyConnected ↵Teresa Charlin
Sigmoid Activation" * This reverts commit be25d94aefe53f221304b1f5f344913b708f808b. * Add Unit Test: any receiver layer + any activation layer in float and QAsymmU8 * Tidy up fuse activation tests Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ie059d03b85cd17eaaafe5188bb173672a1fb9ae0
2020-11-19IVGCVSW-5563 Fix Crash on model with Fullyconnected Sigmoid ActivationKevin May
* Add supported activations check to Neon FullyConected validate Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I67a36eb83d0568d000e928e27eba3c84e32cdc72
2020-11-18IVGCVSW-5093 Add NEON Logical workloadJames Conroy
* Add NEON Logical workloads for NOT, AND and OR. * Enable Layer and IsSupported tests on NEON. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: Ibca59530457a664ca3d77751825642f8daf52fab
2020-11-13IVGCVSW-5328-5329 Fuse ActivationMike Kelly
* Added Fused Activation Optimization to both CL and Neon backends. * Added Fused Activation support to all the CL and Neon workloads that support it. * Changed ProfilingTest network to be a Convolution layer followed by an Abs layer rather than an Activation layer. * Added IBackendInternal::OptimizeSubgraphView function that can accept a ModelOptions. * Network will now call OptimizeSubgraphView passing in the ModelOptions. Signed-off-by: Keith Davis <keith.davis@arm.com> Signed-off-by: Mike Kelly <mike.kelly@arm.com> Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ib536ac3cbafc7d9b35c139ad9a65b7735262cd9d
2020-11-12Update ACL pin to d7341fb9e3b24b904edf7ac9d83e1e063bc77765Teresa Charlin
* Use NEConvolutionLayer Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ieb81fafaf34a63be8daf297ebe1bb0e4079daf4e
2020-10-05Update ACL pin to fc2f6d0427e1d886fcccc68867d1af1ccd96608bTeresa Charlin
* Set use_padding to false in neon workload Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ia5367de331efe1d28dea4dfbefc0713720da81f9
2020-10-02IVGCVSW-5334 Remove remaining boost::numeric_cast from armnnMatthew Sloyan
* Floating point casts now use armnn::numeric_cast. * Also removed remaining header imports. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I2d37847d67f164fc0a0ae17f34d49ff3d2210c30
2020-10-01COMPMID-3784 Fix 1 CTS MUL INT32 failure due to using SATURATETeresa Charlin
* LargeGraph_TENSOR_INT32_Rank4/26 Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I9d07444db56e26c13a77bf022938644ed7953d6b
2020-09-25Update ACL pin to 840a72cc745c60eccbd26fe192b035ec68b2ee41Nikhil Raj
* Change tensor to non const to fix build error caused by ACL fix for QLSTM Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I7ab0f644dfb3cb3cf21bda73028e9368f3354f4a
2020-09-17IVGCVSW-5300 Remove some boost::numeric_cast from armnn/backendsMatthew Sloyan
* Replaced with armnn/utility/NumericCast.hpp * Some exclusions in reference backend * Excluded as requires float implementation in NumericCast.hpp Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I9e4e9cd502c865452128fa04415fd6f250baa855
2020-09-14IVGCVSW-5157 'Pipe ModelOption through Network::LoadNetwork() to Workload ↵Sadik Armagan
factory' * Pass ModelOptions to WorkloadFactory * Updated signature of CL and NEON Convolution2d workloads added FastMathEnabled param. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I536178be8e4dd4083489e69febadaf0feeba46d2
2020-09-10IVGCVSW-5156 Introduce ModelOptions to OptimizedNetworkSadik Armagan
* Introduced ModelOptions to IBackendInternal * Introduced ModelOptions to Network * Added FastMathEnabled parameter to Conv2d Validate function in CL and NEON * Added Optimizer tests Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ib54c1e82cb3d89a52756ed499cf91b6a7fdb2063
2020-09-03Update ACL pin to ec4dee8c68a3d0f6d63db184bfb2f4589429778eTeresa Charlin
* Axis for LogSoftMax and SoftMax can be either positive or negative Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I36b0507ad7600c0a98c3b8be3c0350045ee05b84 Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
2020-08-10Update ACL pin to 4aed4aafa2ddb0b6f4b76aef5008c8bb45599ea4Teresa Charlin
* Use axis=-1 in all softmax tests as ACL only accepts this dimension (the most right dimension, in ACL is 0 and in ArmNN is -1). Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I4be83f60aa9505b4bf2367c4489e6f12d644c6d4
2020-07-29IVGCVSW-5167 Use a generic axis in CL/Neon LogSoftmax and Softmax workloadTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Id72d2c2851adcc1dd8f00a6103642b16ebe3a964
2020-07-28IVGCVSW-4973 Enable QLstm projection unit tests on NEONTeresa Charlin
*Cosmetic changes on NeonQLstmWorkload Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I53e00ec31845d4c7d1f00d53d179b8540dcee608
2020-07-24IVGCVSW-3897 Add NEON LOG_SOFTMAX WorkloadKeith Davis
Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I632b5ac7f188853de68e232e81568b3fca238d42
2020-07-22Update ACL pin to aa95ddc2abb7cef0b2edd03f7c4c9d9c6b9d7cf4Teresa Charlin
IVGCVSW-5136 Adapt to change in ConcatenateLayer in ACL Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I5bc1752215a7b5a91c449e62809ae06f501c6108
2020-07-08IVGCVSW-5005 Fix Deprecated Functions in CL/NEON Resize WorkloadDavid Monahan
* Update CL pin to f3ad9513dd46fca1d6c5e4550286480fdbaba056 IVGCVSW-5005: Fix Deprecated Functions in CL/NEON Resize Workload * Add missing virtual function to NeonIntercepterScheduler * Update CL/Neon Resize Workloads to use ScaleKernelInfo * Update CL/Neon Resize workloads to set correct Sampling Policy for Half Pixels IVGCVSW-4981: Change CL/NEON Softmax axis value * Default value is now 0 Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: I8a14c6a64e5a24bc1a66a7d3685cd388c2245702
2020-07-01IVGCVSW-4903 Connect axis parameter in Gather from android to ACL.Teresa Charlin
!android-nn-driver:3302 Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ifbc49acb5272f8a36719bb68676e44817190537d
2020-06-23IVGCVSW-4622 Add NEON FILL WorkloadSadik Armagan
* Added Neon workload for Fill Operator * Enabled Fill operator tests on Neon * NEFill function does not have validate() function yet IsLayerSupported() function return true at the moment * Added INT32 supported type for CpuRef Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I17bf5ec13750f46322a30653e15ba2a514f61f08
2020-06-03remove BOM from filesLaurent Carlier
Change-Id: Ia4b4bb3be0ed6e933c77d58f8e9879b1370e9537 Signed-off-by: Laurent Carlier <laurent.carlier@arm.com>
2020-05-30IVGCVSW-4888 Update Resize Front end for new parametersDavid Monahan
* Added AlignCorners and HalfPixelCenters to Resize and ResizeBilinear * Updated Serializer and Serializer tests !android-nn-driver:3280 Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: Ice3bb448c239b04323854641525bfe0808c03b2e
2020-05-29IVGCVSW-3846 Add NEON GATHER WorkloadTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I1a66fdad63cef16866d9dfcb8a339647f856e1d4
2020-05-27IVGCVSW-4200 Add CL EXP WorkloadSadik Armagan
IVGCVSW-4203 Add Neon EXP Workload * Added CL EXP operator workload * Added EXP test suite * Enabled EXP tests on ACL and Ref Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I793d31af1b2e3fe86b0bec6d9e5de503c5dab970
2020-05-20IVGCVSW-4451 Add QLstm NEON workloadJames Conroy
* Adds QLstm workload. * Adds CreateWorkload and Layer tests. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I585eb2691395ee4ccd45b5a853660f90fc5cc821
2020-05-15IVGCVSW-4831 Fix Packet header includes in backendsFinn Williams
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: Iedfcf0ef487bd7836b1bc4ba8a0e4337dc4da391
2020-05-13Update ACL pin to 4efe5dc9b39a87eface43e7468e08279976ae9efTeresa Charlin
* change neon softmax axis to be int Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I7a9486c11494ed4993abd683a50d6b4483f283e1
2020-05-13IVGCVSW-4753 Refactor CL Softmax workload generalizing for different datatypeTeresa Charlin
* Change ComputeSoftmaxAclAxis to work with int and uint axis Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ibbfa9ec7e2f0416e6885673212a767419c871cca
2020-04-30IVGCVSW-4753 Fix CpuAcc Hal 1.3 Softmax FailuresSadik Armagan
* Refactor Neon Softmax workload to accept supported data types Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I54aa72d5cbb862cafcc1eabe48f6a00d61050cd7
2020-04-29IVGCVSW-4203 Add Exp support to Neon backendDerek Lamberti
Change-Id: Ief6b79297b66a57643b7c5d6c7d820c35024dd08 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2020-04-27MLCE-190: Neon and CL Constant Workloads do not support newer DataTypesMike Kelly
* Added support for QASYMM8_SIGNED, QSYMM16, QSYMM8 and QSYMM8_PER_CHANNEL to Neon and CL backends * Added unit tests to Neon, CL and Ref backends Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I4c726b6d86b4d75abedd130dcea372d1e82be5c2
2020-04-14IVGCVSW-4483 Removes boost::polymorphic_pointer_downcastJan Eilers
* replace boost::polymorphic_pointer_downcast by PolymorphicPointerDowncast * replaced/removed includes Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I0ef934a3804cf05e4c38dec6c4ec49c76111a302
2020-04-10IVGCVSW-4483 Remove boost::polymorphic_downcastJan Eilers
* exchange boost::polymorphic_downcast with armnn::PolymorphicDowncast * remove unnecessary includes of boost::polymorphic_downcast Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ie603fb82860fe05fee547dc78073230cc62b2e1f
2020-04-09IVGCVSW-4641 Investigate Hal 1.3 VTS FailuresSadik Armagan
* Add QASYMM8_SIGNED data type support to NeonTensorHandle Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Iae34f7d67de83642606ccd8c61a1b72df7f2bb3a
2020-04-06IVGCVSW-4485 Remove Boost assertNarumol Prangnawarat
* Change boost assert to armnn assert * Change include file to armnn assert * Fix ARMNN_ASSERT_MSG issue with multiple conditions * Change BOOST_ASSERT to BOOST_TEST where appropriate * Remove unused include statements Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I5d0fa3a37b7c1c921216de68f0073aa34702c9ff
2020-03-31IVGCVSW-4633 Add conversion of BF16 support to NeonNarumol Prangnawarat
* Add NeonConvertBf16ToFp32Workload * Add NeonConvertFp32ToBf16Workload * Add BFloat16 type support to NeonConstantWorkload and NeonTensorHandle * Add ConvertBf16ToFp32Weight when ConvertBf16ToFp32Layer is added * Unit tests Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Id5b44a203add5e0c98c1ca4e2162115741b56644
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-07 02:49:10 +0000