aboutsummaryrefslogtreecommitdiff
path: root/src/backends
AgeCommit message (Collapse)Author
2020-04-02IVGCVSW-4455 Add an Activate and Deactivate control packet to the protocolKeith Davis
* Add Activate/Deactivate command handlers * Add IReportStructure, INotifyBackends single function interfaces * Add overrided mechanism to report structure in Runtime.cpp * Add overrided mechanism to notify backends in ProfilingService.cpp * Add optional IReportStructure argument to ProfilingService constructor for use in ActivateTimelineReportingCommandHandler * Refactoring and tidying up indentation * Removal of unused code in ProfilingUtils.cpp and ProfilingService.cpp * Added GatordMock end to end test * Fixed an issue with SendCounterPacket sending duplicate packets * Fixed an issue with DirectoryCaptureCommandHandler handling of Optional Signed-off-by: Keith Davis <keith.davis@arm.com> Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I5ef1b74171459bfc649861dedf99921d22c9e63f
2020-04-01IVGCVSW-4643 Add Convolution2D tests with Bfloat16 input and Float32 outputNarumol Prangnawarat
* Modify SimpleConvolution2dNhwcTestImpl to allow different input and out types * Add unit tests for Conv2D with Bfloat16 input and Float32 output to compare the accuracy with Float32 for small value inputs and big value inputs Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ia59c92a22001b41f2681dafb951203a2223d3367
2020-04-01IVGCVSW-4641 Investigate Hal 1.3 VTS FailuresSadik Armagan
* Added QAsymmS8 data type support for bias Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I1dfe50b23a4ba479d35f5e6996ea8e25aee0033b
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
2020-03-31IVGCVSW-4590 Fix Lstm layers CellToInputWeightsJan Eilers
* CellToInputWeights were not handeled correctly * Changed CellToInputWeights from Cifg to peephole parameter * Modified exiting unit tests * Added unit test to cover new configuration * Added more descriptive error messages Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ied5dc1253d3df1fd1a79b887a58603d0a9c8f396
2020-03-30IVGCVSW-4603 Support comparison operators in NeonTeresa Charlin
* Deprecate NeonGreaterWorkload * Add NeonComparisonWorkload to encompass all comparison operators Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I5e828088d17e994fc5cb0b908719b53ee01fa959
2020-03-30IVGCVSW-4603 Support comparison operators in CLTeresa Charlin
* Deprecate ClGreaterWorkload * Add ClComparisonWorkload to encompass all comparison operators Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ida0ed7f59899d75b0fe7de1e7433b1ade018c6f1
2020-03-26IVGCVSW-4597 Modify BF16 optimizer to Convert only inputs and weights ofNarumol Prangnawarat
Convolution2d and FullyConnected layers * Add InsertConvertFp32ToBf16LayersBefore * Add ConvertWeight to ConvertFp32NetworkToBf16Impl for Conv2d and FullyConnected * Allow different input and output when input is BF16 and output is FP32 Conv2d and FullyConnected layers * Unit tests Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ic8f92ff28edcae08a72a3114a28f50c4619f919b
2020-03-24IVGCVSW-3813 Add Unary Elementwise Operation 'NEG' support to the ↵Sadik Armagan
android-nn-driver * Implemented ClNegWorkload * Implemented NeonNegWorkload * Enabled 'NEG' operator on CL and Neon as well as Ref * Implemented unit tests for 'NEG' operator Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I3d7a892692716636cae6bdf8ddd238e3d1ea064f
2020-03-20IVGCVSW-4549 Add front end for new QLSTM layerJames Conroy
* Added new layer QLstm (Android R HAL 1.3) * Made necessary updates to APIs * Added unit tests * This layer is functionally equivalent to the original unquantized LSTM layer with some additonal quantization features added. Due to this, original LstmParams are used for this layer. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I5b7f2d2fb6e17e81573b41a31bc55f49ae79608f
2020-03-20IVGCVSW-4582 Undefined reference to GetProfilingService causes failure in ↵Sadik Armagan
the Backends CI job * Enable the GetProfilingService() function to BackendProfilingTests and ProfilingTestUtils Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I32e3625db0f465883f2ec27fb7c2fad4e91b6306
2020-03-19IVGCVSW-4565 TENSOR_BOOL8 data type not supported in AndroidNN DriverSadik Armagan
* Enabled Boolean and Int32 data types in Reference Comparison inputs * Added decoder for Boolean data type * Refactored ClGreaterWorkload to work with any data type * Refactored NeonGreaterWorkload to work with any data type !android-nn-driver:2902 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I92772810b744b388831c9dca0119ebf8cb7a447e
2020-03-19IVGCVSW-4516 Add ConvertFp32ToBf16Layer and Ref workload supportNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I9099a4f840fb747336f77d20a0868b64e801a310
2020-03-18IVGCVSW-4446 Add HardSwish EndToEnd testsJan Eilers
* adds convert from armnn HardSwish to Acl HardSwish * adds EndToEnd tests for Ref, Cl and Neon Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: If997dad783ff45d7f061254e7e30bb69d4d4d564
2020-03-18IVGCVSW-4444 Adding Elu end to end testJan Eilers
* implemented activation layer end to end test * adds support for different tolerances in layer tests * added tests for Elu (Ref, Cl, Neon) Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I81e28cfb4456e815bae2fb31f5c345134ff2432f
2020-03-18IVGCVSW-4463 Change ProfilingService to a member of runtime from a singletonSadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I345c39a10a4693a500aa1687d9a5cee76da791c3
2020-03-17IVGCVSW-4515 Add ConvertBf16ToFp32Layer and Ref workload supportNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ida6d7e1d2c9abe0618f8b711bab9d62c011090d6
2020-03-13IVGCVSW-4531 Fix for failing strided slice NNT/VTS tests on Android RDavid Monahan
Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: I7f6932f0d21b5678ab9822b0fc69f589bbbb07e5
2020-03-13IVGCVSW-4512 Add BFloat16 Debug WorkloadNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Id179cb4774a4565e5e905e5fe4c34299178644de
2020-03-13IVGCVSW-4511 Add BFloat16 to RefLayerSupport and unit testsNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ifaae4d5aac468ba927b2c6a4bf31b8c8522aeb2e
2020-03-10MLCE-159 Add QAsymmS8 to ArmnnQuantizerFrancis Murtagh
* Allow per layer quantization from Fp32 to Int8 (QAsymmS8) like TfLite Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I5bbf770aa29d81af3568c15b47d2b2c18e55bb28
2020-03-10IVGCVSW-4482 Remove boost::ignore_unusedJan Eilers
!referencetests:229377 Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ia9b360b4a057fe7bbce5b268092627c09a0dba82
2020-03-09IVGCVSW-4517 Implement BFloat16 Encoder and DecoderNarumol Prangnawarat
* Add ConvertFloat32ToBFloat16 * Add ConvertBFloat16ToFloat32 * Add BFloat16Encoder * Add BFloat16Decoder * Unit tests Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I198888384c923aba28cfbed09a02edc6f8194b3e
2020-03-09MLCE-160 Error loading quantized model containing BatchNorm LayerMike Kelly
* Relaxed restrictions in BatchNormalizationQueueDescriptor::Validate Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I3101971c2101e90144bbbf7b63367cb0ef09573f
2020-03-05IVGCVSW-4539 Add missing Activation Unit Test to CL and NeonTeresa Charlin
*Square, Tanh, SoftReLu, LeakyReLu, Abs, ReLU Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Id7beed0b6770177722bf0f93957706620df81b0d
2020-03-03IVGCVSW-4532 Update Acl Pin to fec13b8e20dc9d71d729f750633fa52c3a8a0036Kevin May
* Fix NeonLayerSupport/IsLayerSupportedUint8Neon Quantize layer Unit Test Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I71deb10dd3bb18e30c77b72d6ca25a9a4f8842c3
2020-03-03IVGCVSW-4426 Add missing Neon tests for quantized typesKeith Davis
Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I3b33a88801b65697d7580f1f4ebd96cfab6b796e
2020-03-03Modifying the IBackendProfilingContext interface to return a bool onDavid Monahan
EnableProfiling and adding error checking to the Runtime Invocation Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: I65b8bb16c6f1c7d668de31238ce0408a48974997
2020-03-02IVGCVSW-4440 : Add HARD_SWISH Support to Activation in CpuRefColm Donelan
* Add a new Activiation type of HardSwish. * Add CpuRef support and tests. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I68c3840aa45b7a27d5e416a5d50fe8f99f003ce8
2020-03-02IVGCVSW-4375 Add support for TransposeMike Kelly
* Added TransposeLayer * Added CL, Neon and Ref Workloads * Added Transpose utilities * Added Serializer and Deserializer support * Added Quantizer support Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I04c755ba7cb5b1edf72b3c9f3c0314878032e3c7
2020-02-28IVGCVSW-4439: Adding Elu support to ActivationDavid Monahan
* Added CpuRef implementation * Added Unit Tests * Added Quantizer Test * Enabled Tests for Neon and CL backends on fp32 only * Added to Serializer Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: Ic23e1797dbc9352b40678c389d7fe2b836b582ea
2020-02-24IVGCVSW-4368 Update Android.mk and backend.mk files with latest unit testsColm Donelan
* Sync up the Android build files with the CMakeLists.txt Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I1675b0937fed7c74833e46af6d077ced57cf5bed
2020-02-21IVGCVSW-4456 Disable NEON PostDetectionProcessJames Conroy
* Reverting to CpuRef workload because it currently has better performance. * Disabling NEON EndToEnd tests. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: Idd5314e46c50581ef4bec24e391779188f20951b
2020-02-20IVGCVSW-4456 Fix MobileNet SSD perf regressionJames Conroy
* Now use accelerated DetectionPostProcess NEON workload, originally was using vanilla version. Change-Id: Ib64653801024a191f841d601932fa3c54baa5c3b Signed-off-by: James Conroy <james.conroy@arm.com>
2020-02-19IVGCVSW-4472 Yolo v3 ExecuteNetwork failingKeith Davis
* Add Debug workload for QAsymmS8/U8 * Change Dequantize tests to test AsymmS8 instead of SymmS8 * Fix incorrect supportedness within RefLayerSupport Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: Ie51f1e33c564d46c86bf0150b1addda3fc093d13
2020-02-17IVGCVSW-4436 Add ExecuteNetwork test for mobilenet_v2_int8Keith Davis
* Add QAsymmS8 to QueueDescriptor supportedTypes * Add QSymmS8/QAsymmS8 to RefLayerSupport supportedTypes * Some additional comments and refactoring Change-Id: I8567314452e6e8f6f69cb6e458ee147d3fc92fab Signed-off-by: Keith Davis <keith.davis@arm.com>
2020-02-17IVGCVSW-4340 Backend profiling: Add tests for Timeline functionsColm Donelan
* Add tests for the timeline functions that are part of IBackendProfiling: GetSendTimelinePacket & GetProfilingGuidGenerator * Modify MockBackendProfilingService to store a MockBackendProfilingContext shared pointer. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I99fc4b1da019858b9f29409cd59ef8f590c0d3a2
2020-02-14IVGCVSW-4420 Failing Unit Test Cl: Quantize layerKeith Davis
* Fix bug with missing ValidateInputsOutputs in Cl Workload * Renamed data type tests to be more specific * Future proofing Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I157acc318e40d727fcfb3f36f7f577fc87472f3d
2020-02-14IVGCVSW-4338 Implement the Activation of Counters in backendsFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I4a2465f06e046f78242ff0a246c651638b205498
2020-02-13IVGCVSW-4400 Backend Counter Registry FunctionalityDavid Monahan
* Adding BackendProfilingContext to the MockBackend * Made IBackendProfilingContext pure Virtual * Added UnitTest using MockBackend for testing Backend Counter Registration * Moved Registry of backend counters from Initialize() to AddBackendProfilingContext() * Added m_MaxGlobalCounterId to ProfilingService * Removed automatic registration of MockBack in BackendRegistry() Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: Ie1c6c31e56d1ac7079d6116ecad041961014aedc
2020-02-12Fix legacy ClTuner APIDerek Lamberti
Change-Id: Ib96446c753f7b794f5dc08cb9ff59888987cdf80 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2020-02-10Clean up header inclusion in CL workloads.Matthew Bentham
Remove usage of CLFunctions.h and replace with specific header for each function. Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com> Change-Id: I255a843b36a5dd8cf90a52786282192b8fe04f83
2020-02-07IVGCVSW-4386 Add ArmNN reference support for QAsymmS8Ryan OShea
* Added Quantization Scheme for QAsymmS8 * Added Unit Tests for QAsymmS8 * Renamed QAsymm8 calls to QAsymmU8 Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com> Change-Id: I897b4e018ba1d808cc3f8c113f2be2dbad49c8db
2020-02-07MLCE-139: add capability to align corners for bilinear resizeSang-Hoon Park
* Add parsing of the related parameter to TfLiteParser * Update ResizeDescriptor to store the additional parameter * Update NEON/CL workload to pass the additional parameter. * Update Reference workload to pass and handle the additional parameter. !ComputeLibrary:2538 !ComputeLibrary:2569 !armnn:2612 Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Change-Id: Id149e1c24c2abed7e9dd81939acf54dfabfcdfd2
2020-02-07IVGCVSW-4317 Implement the Profiling Context InitialisationColm Donelan
* Call CreateBackendProfilingContext on each backend from Runtime passing an instance of the BackendProfiling interface. * Modify the signature of CreateBackendProfilingContext to remove const and return a shared_ptr to BackendProfilingContext * Add concrete BackendProfiling class. * Store BackendProfilingContexts in Profiling service. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I975eaa2093ae91fa623835f65f9e5b25eb65117a
2020-02-05IVGCVSW-4389 Enable ClTuner in ClContextControlDerek Lamberti
Change-Id: If169736c4523a92f9aa10eac13e320eb41088624 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2020-02-04Clean up header usage a bit in NEON backendMatthew Bentham
Including NEFunctions.h is unnecessary and adds about a second to compile time each translation unit in which it appears, so we should use just the header file with the arm compute function declarations that we need. Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: I605d0eb82ccf2aafa35381a5d9d54337d3fe17a7
2020-02-04IVGCVSW-4390 Refactor QUANTIZE to make use of Decoder/Encoder typesKeith Davis
* Fix bug where QSymmS8 is duplicated and F16 is missing Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I312815868e74a9dff913bac052f1a86585644098
2020-02-03IVGCVSW-4399 Create Sample Dynamic backendNarumol Prangnawarat
* Move IWorkload and WorkloadInfo to include/armnn/backends * Add simple sample dynamic backend with addition workload * Add sample example to run dynamic backend * Unit tests Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I0753ce35b8e8a6223a1471388b49246d82438a44
2020-02-03IVGCVSW-4334 Wire Signed Quantized 8 bit type into ACLKeith Davis
* Add QSymmS8 LayerSupport tests for all backends * Update BatchNormalization IsLayerSupport Bias' QSymmS8 case Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: Ib66befe11f9df5956869eb80699fc415a4d3fa16
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-06 04:22:30 +0000