aboutsummaryrefslogtreecommitdiff
path: root/src/backends/reference/RefLayerSupport.cpp
AgeCommit message (Collapse)Author
2021-02-03backends/reference: Add ReduceSum operation supportSadik Armagan
This patch addes ReduceSum operation support for reference backend, which computes the sum of elements across dimensions of a tensor. Changelog v1: - Fix file header descriptions. Chagelog v2: - Fix line limit issue. - Fix type conversion issue. Changelog v3: - Remove tabs. - Modify newly added file headers. Changelog v4: - Symbol on header isn't allowed so drop it from newly added file headers. Changelog v5: - Remove tabs, fix the use of brackets and align lines correctly. Changelog v6: - Add serializer and deserializer support. Changelog v7: - Fix build error add missed code. Changelog v8: - Rename ReduceSumDecriptor to ReduceDescriptor - Update m_KeepDims field data type to bool on ReduceDescriptor - Add ReduceOperation field to ReduceDescriptor - Rename ReduceSumLayer to ReduceLayer - Update ReduceLayer to use ReduceDescriptor - Update ReduceLayer::ValidateTensorShapesFromInputs() function - Rename RefReduceSumWokload to RefReduceWorkload - Update workload to use ReduceDescriptor - Update workload to use Decoders and Encoders - Remove ReduceSum.hpp and ReduceSum.cpp - Added Reduce.hpp and Reduce.cpp - Move Mean.cpp (which is implementing REDUCE_MEAN) functionality to Reduce.cpp - Update RefMeanWorkload to call Reduce function with ReduceOperation::Mean argument - Remove Mean.hpp and Mean.cpp - Update the Serializer/Deserializer ArmnnSchema.fbs for ReduceLayer, ReduceDescriptor, and ReduceOperation - Update Serializer and Deserializer for serializing/parsing ReduceLayer - Added TfLiter parser Sum test for REDUCE_SUM operator - Make corresponding changes on front-end and Ref backend to support REDUCE_SUM operator Changelog v9: - Fixed build errors. Change-Id: I8c8e034f3df73f9565b3c18eff51ecca6c542195 Signed-off-by: Inki Dae <inki.dae@samsung.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
2020-11-19IVGCVSW-5093 Remove redundant LogicalUnary functionsJames Conroy
* In favour of ElementwiseUnary functions which are the currently used code path. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I34964d2dcabd4b7ddf0b455df17c48e3c6812ee4
2020-11-18Fix logical vts skipNarumol Prangnawarat
* Add Boolean support for Reshape * Use LogicalUnary factory and data type for LogicalNot Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I8e072fde200b7716556ae67f79616458cf98ff20
2020-11-17IVGCVSW-5530 'Cannot run SSD Mobilenet f16/uint8 on CpuRef via ExecuteNetwork'Sadik Armagan
* Added FP16 DataType support to DetectionPostProcess * For DetectionPostProcess layer output is always Float32 regardless of input type Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I21f63dd08f0863e9a98e105b3009bab3da1ab0c3
2020-11-09IVGCVSW-5091 Add Logical ops frontend and ref implJames Conroy
* Add frontend and reference implementation for logical ops NOT, AND, OR. * Unary NOT uses existing ElementwiseUnary layer and ElementwiseUnary descriptor. * Binary AND/OR uses new layer LogicalBinary and new LogicalBinary descriptor. * Add serialization/deserializion support and add missing ElementwiseUnary deserializer code. * Add additional Boolean decoder in BaseIterator.hpp. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: Id343b01174053a166de1b98b6175e04a5065f720
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
2020-08-27Export Armnn cmakeDerek Lamberti
Change-Id: I3c317e835aba5feafda240393ca26b6aebe8d655 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2020-07-31IVGCVSW-4712 Fill layer datatype adjustmentsTeresa Charlin
* Input layer to be int32 instead of same type as output * Enable float16 end to end tests * Neon and Cl layer support check for backend Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I6bc889077c8da63eeff66bd45730ce5d8783c419
2020-07-30IVGCVSW-5174 Fix i386 Floor and AbsTestFrancis Murtagh
* Remove QSymm16 support for Floor to match NNApi and disable RefLayerTest * Return nullptr for floor workload if quantized type * Fix SimpleAbsTest incorrect output Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I80d9e2fb78777d0a3fc7ce6d12b5eb4af3fd1d3a
2020-07-28IVGCVSW-4712 Add EndToEnd test for FILLTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ic89bcbbd580abe1b05bd26748db704e83cf65bea
2020-07-06IVGCVSW-4624 Add a RANK Reference ImplementationFinn Williams
* Add Rank front end * Add Rank reference implementation * Add Rank serialization support * Add Scalar serialization support Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I06e4a468c2a84e79bae2e6c5348596bbbf853b4b
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
2020-06-22Remove per-channel quantization support in ref fully connectedJan Eilers
* was added accidentally Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I332036ffd35868b0fe1226aba5522af3b91d25da
2020-06-15IVGCVSW-4620 Add Fill Reference ImplementationRyan OShea
* Add Fill Reference Implementation * Refactor FP converter to use static_cast Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com> Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I532e2f982981d047690755fac43a0e9cf8b17dcd
2020-05-29IVGCVSW-3847 Correction of 9349246cfce1cc3192aea8fb3a830506cf794abdTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ia69ded99f753e278bc467492907f6a7ca92c7239
2020-05-29IVGCVSW-3847 Support INT32 in Gather operatorTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ica217d3e4fbcdef1315554ea5d5c4720124696c3
2020-05-25IVGCVSW-4863 ADD,SUB,DIV,MUL,MAXIMUM and MINIMUM int32 VTS testTeresa Charlin
skipped in CpuRef Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I1c870ac258e8c3805a95b259cb40731f8e81541e
2020-05-25IVGCVSW-4604 ARGMINMAX float16 VTS test skipped in CpuRefTeresa Charlin
Change-Id: I75cca9804a67f629cddc83671397a84640e9bf0e Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
2020-05-25IVGCVSW-4611 PRELU float16 VTS test skipped in CpuRefTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Id908e0bcbefd3284da51cdbe8ec0c2181b9b553e
2020-05-02IVGCVSW-4449 Add QLstm ref implementationJames Conroy
* Adds ref implemenation for new HAL 1.3 operator, QLstm. * Adds Layer and CreateWorkload unit tests. * Adds WorkloadData validate for QLstm. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I8a721f07ff06105e6495a1a0561b9503aa8146dc
2020-04-29IVGCVSW-4686 Fix NNT GeneratedTests.TestsNarumol Prangnawarat
* Add bias dimension check for FullyConnected layer support Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I66db5332069a606b5d1f6c10faee38760b26a8f8
2020-04-27IVGCVSW-4668 Add TENSOR_QUANT8_ASYMM_SIGNED data type support to CpuRef ↵Sadik Armagan
operators Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I094125ba80699cc3cf5226bda6662a54e6caa988
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
2020-04-01IVGCVSW-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
2020-03-26IVGCVSW-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
2020-03-19IVGCVSW-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
2020-03-17IVGCVSW-4515 Add ConvertBf16ToFp32Layer and Ref workload supportNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ida6d7e1d2c9abe0618f8b711bab9d62c011090d6
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
2020-03-02IVGCVSW-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
2020-02-19IVGCVSW-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>
2020-02-07IVGCVSW-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
2020-02-04IVGCVSW-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
2020-01-31IVGCVSW-4390 Refactor QUANTIZE to make use of Decoder/Encoder typesKeith Davis
* Add no-ops for CL/NEON Uint8 * Refactor Quantize workload to Decoder/Encoder types Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I80b09de528299b925e2ac38acd9a5019b8d3e4ac
2020-01-28IVGCVSW-4306 Verify the tflite Yolo v3Keith Davis
* Added debug layer support for QSymmS8 * QSymmS8 support for workloads Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I51af92fadc0be290629dd9198beab5abef9e351f
2020-01-24IVGCVSW-4262 Use ACL Permute and Reshape Validate function in Neon and CLKevin May
!android-nn-driver:2642 Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Ibabb73c0ae0df2e530a68398f75c76e6b80c0701
2020-01-24IVGCVSW-4370 Deprecate DataType::QuantizedSymm8PerAxisDerek Lamberti
!android-nn-driver:2622 Change-Id: If99d3eff71ff66ba28af1e5af248299fe04511b9 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2020-01-23IVGCVSW-4259 Add frontend and reference workload for UnaryOperationLayerjosh minor
* Added new layer named ElementwiseUnary * Deprecated existing Abs/Rsqrt layer functions * Updated existing Abs/Rsqrt test infrastructure to use new layer * Added boilerplate for new Exp,Neg,Sqrt elemwise op layers * AbsQuantize test removed pending future commit * Serialization support added !android-nn-driver:2550 Change-Id: Ic595c645925e17b45db568187fd05646daf2e87f Signed-off-by: josh minor <josh.minor@arm.com>
2020-01-17Add Signed32 to debug layerNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Iedfc196bfd18e8280e99a06db68df9c15c8ea835
2020-01-13Rename quantized data types to remove ambiguity for signed/unsigned payloadsDerek Lamberti
!android-nn-driver:2572 Change-Id: I8fe52ceb09987b3d05c539409510f535165455cc Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2020-01-02IVGCVSW-4246 Clean build of backends with -WextraDerek Lamberti
Change-Id: I9e8d5576b3ec04c871785d5f2f9545bf1136e59b Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-12-09IVGCVSW-4211 Add Signed 8 bit Quantisation support into the Reference backendFinn Williams
!android-nn-driver:2435 Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I10ecd4a8937725953396805f33a3562a5384c4d4
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-26 04:17:23 +0000