aboutsummaryrefslogtreecommitdiff
path: root/src/backends/reference
AgeCommit message (Collapse)Author
2019-04-10IVGCVSW-2947 Remove boost dependency from include/TypesUtils.hppAron Virginas-Tar
!android-nn-driver:968 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I03ccb4842b060a9893567542bfcadc180bbc7311
2019-04-10IVGCVSW-2946 RefElementwiseWorkload configures prior to first executeDerek Lamberti
+ Added PostAllocationConfigure() method to workload interface + Elementwise function now deduces types based on Functor - Replaced RefComparisonWorkload with RefElementwiseWorkload specialization + Fixed up unit tests and minor formatting Change-Id: I33d08797767bba01cf4efb2904920ce0f950a4fe Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-04-10IVGCVSW-2912 Make get_compute_library.sh sole source for clframework pinJim Flynn
* Also incorporated fix for break in master build 32-bit NEDepthwiseConvolution errors in clframework * Fixed a failure in the Float16 workloads for ElementwiseOperations !android-nn-driver:963 Change-Id: Ic2cdb0e6c9399fa42b56001c6f4b46b7f150f143 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-04-09IVGCVSW-2862 Extend the Elementwise Workload to support QSymm16 Data TypeSadik Armagan
IVGCVSW-2863 Unit test per Elementwise operator with QSymm16 Data Type * Added QSymm16 support for Elementwise Operators * Added QSymm16 unit tests for Elementwise Operators Change-Id: I4e4e2938f9ed2cbbb1f05fb0f7dc476768550277 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
2019-04-08IVGCVSW-2861 Refactor the Reference Elementwise workloadSadik Armagan
* Refactor Reference Comparison workload * Removed templating based on the DataType * Implemented BaseIterator to do decode/encode Change-Id: I18f299f47ee23772f90152c1146b42f07465e105 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Signed-off-by: Kevin May <kevin.may@arm.com>
2019-04-02IVGCVSW-2875 Enable QuantisedSymm16 support for ref Dequantize workloadNattapat Chaimanowong
Change-Id: I4b1c1f963214433ad67d5a311fbea5f21177f6a2 Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-04-02IVGCVSW-2872 Unit tests for Quantize layer and reference workloadNattapat Chaimanowong
Change-Id: I291c08cb6e359453978b398255cf8ff051ed2686 Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-04-01IVGCVSW-2871 Ref QuantizeLayer workloadDerek Lamberti
Change-Id: If048b2a053c542b31ae344fe0af04d9b4f40eb6d Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-03-29IVGCVSW-2875 Reference implementation and unit tests for DequantizeNattapat Chaimanowong
Change-Id: Ie4ade0519cb0bbe35dc36be6c9cd749b9171c74b Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-03-29IVGCVSW-2866 Implement RegisterDebugCallback for RefDebugWorkloadNattapat Chaimanowong
Change-Id: I9144fb6b7d05561b5b8fd9db5dbe31c9257f10ca Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-03-26IVGCVSW-2881 Remove DebugDescriptorNattapat Chaimanowong
* Also update Debug layer to use layer guid information Change-Id: I9ec1f639299c3f855b670ff031a0e88d685cfc6b Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-03-25IVGCVSW-2861 Refactor the Reference Elementwise workloadsSadik Armagan
* Refactored Elementwise Workload into the single workload. * Execute() function will react based on the DataType. Change-Id: I6d4d6a74cec150ed8cb252e70b629ed968e7093d Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
2019-03-20IVGCVSW-2814 AllTypesAreEqualImpl handles odd num params correctly.Derek Lamberti
Change-Id: I9b661cabab41f6997dac808cca15995834bb0313 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-03-20IVGCVSW-2814 Extensive ref IsSupported for Activation & AdditionDerek Lamberti
Change-Id: Ib1a795eb129de1ec3f02807a2dff7613d7c6c28d Signed-off-by: Derek Lamberti <derek.lamberti@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>
2019-03-12IVGCVSW-2709 Serialize / de-serialize the Splitter layerJim Flynn
* fixed typo in Ref Merger Workload comment * fixed typo in ViewsDescriptor comment * made the origins descriptor accessable in the ViewsDescriptor (needed for serialization) * based the unit test on the use of the splitter in the CaffeParser Change-Id: I3e716839adb4eee5a695633377b49e7e18ec2aa9 Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-02-28IVGCVSW-2763 Fix bug in BatchToSpaceNdLayer::InferOutputShapesNattapat Chaimanowong
*Also added test case for non-zero crop and moved BatchToSpaceNd test functions together Change-Id: I142ba356165618b2811a4ab650ca6ced35220d9c Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-02-27IVGCVSW-2632 Fix RefMerger from QAsymm8 types with different quantization ↵Ferran Balaguer
parameters Change-Id: Ie67ce4966c5e5fef618876b027292da429de1485 Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
2019-02-26IVGCVSW-2560 Verify Inference test for TensorFlow Lite MobileNet SSDNarumol Prangnawarat
* Assign output shape of MobileNet SSD to ArmNN network * Add m_OverridenOutputShapes to TfLiteParser to set shape in GetNetworkOutputBindingInfo * Use input quantization instead of output quantization params * Correct data and datatype in Inference test Change-Id: I01ac2e07ed08e8928ba0df33a4847399e1dd8394 Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-02-08IVGCVSW-2557 Add layer tests for Ref Detection PostProcessNarumol Prangnawarat
Change-Id: Ia2e512c0ed035bc6ee46cd67df5e619da9770900 Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
2019-02-08IVGCVSW-2559 End to end tests for Detection PostProcessNarumol Prangnawarat
* end to end tests for Detection PostProcess float and uint8 * add anchors to AddDetectionPostProcessLayer * add anchors to VisitDetectionPostProcessLayer * refactor code Change-Id: I3c5a9a4a60b74c2246b4a27692bbf3c235163f90 Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
2019-02-04IVGCVSW-2557 Ref Workload Implementation for Detection PostProcessNarumol Prangnawarat
* implementation of DetectionPostProcessQueueDescriptor validate * add Uint8ToFloat32Workload * add implementation of Detection PostProcess functionalities * add ref workload implemenentation for float and uint8 * add layer support for Detection PostProcess in ref * unit tests Change-Id: I650461f49edbb3c533d68ef8700377af51bc3592
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
2019-01-24IVGCVSW-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-2510 Ref workload implementation for Gather operatornarpra01
* add implemenentation for GatherQueueDescriptor validate function * add FirstInputTypedWorkload to allow type check on the first input tensor only * add ref workload implemenentation for float and uint8 * add Gather layer support in Ref * unit tests Change-Id: I4578a3211f11d24aa29d15bcf7f45b0445bcd1ee
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
2019-01-07IVGCVSW-2371 Add Rsqrt Ref implementationMohamed Nour Abouelseoud
*Added Unit Tests Change-Id: I6cceb8e6dcda35ce08415f8e5ca86019a64d26e3
2019-01-07IVGCVSW-2421 Remove the template-based version of armnnUtils::PermuteMatteo Martincigh
in favor of a type-indepent implementation that takes void-pointers * The new implementation requires the size of the type to be passed to the function * Updated all the usages accordingly * Removed the old implementation no longer used !android-nn-driver:469 Change-Id: I37f4e6d62a38fbb8ec8c39bb559a2c54c83365d4
2019-01-04MLCE-77 Depthwise Convolution with depth multiplier > 1 doesn't workMatteo Martincigh
* Unified ArmNN's weight format to [ M, I, H, W ] for the depthwise convolution * Added conversion utilities to permute/reshape the weights as appropriate when using CL and Neon backends * Updated the reference implementation of the convolution * Updated the relevant unit tests accordingly !android-nn-driver:459 Change-Id: I07d0818efa9d1ca1e5dad82983aac1fe78eadb18
2019-01-03IVGCVSW-2370 Code clean up after Equal operator implementation where necessaryruoyan01
StringMapping was located in the backendsCommon Change-Id: I1c4a0bfca986722c721fcb2b460c03d6e1cd4568
2019-01-02IVGCVSW-2308 Add Conv2d tests where stride > 1Mike Kelly
Change-Id: Iae6a3bfad06cb669ef0abea465d03163bb8316f5
2018-12-20IVGCVSW-2401 & IVGCVSW-2402 Add end-to-end test for Greater/Equal OperatorFrancisMurtagh
* Add Arithmetic end-to-end test implementation * Enable tests for float, Uint8 and Broadcast Change-Id: I81c7096e9b6ad29eaa935b74ad5f30f823be2331
2018-12-19IVGCVSW-2379 Add Greater Ref workload implementationFrancisMurtagh
* Added the Greater operation as an element-wise workload * Added the unit tests Change-Id: Ie00ee30e47a5f5e17a728032eeb11a085d06c8f2
2018-12-18IVGCVSW-2365 Add Reference Equal Workload ImplementationFrancisMurtagh
* Add reference equal workload * Add Reference Workload Unit Test Change-Id: If2848e7dde4248566b99d91726d08143c40ff80d
2018-12-17IVGCVSW-2398 Add no-op factory implementations for all backends for theFrancisMurtagh
Equal operation * Add QueueDescriptor in WorkloadData.hpp * Add CreateEqual function in WorkloadFactory.hpp * Added stub implementation of the CreateEqual function in RefWorkloadFactory, NeonWorkloadFactory and ClWorkloadFactory Change-Id: Iec6dc2f989c67fa6f0c32cfb93508995c8580783
2018-12-14IVGCVSW-2377 Add no-op factory implementations for all backends for theMatteo Martincigh
Greater operation * Added QueueDescriptor in WorkloadData.hpp * Added CreateGreater function in WorkloadFactory.hpp * Added stub implementation of the CreateGreater function in RefWorkloadFactory, NeonWorkloadFactory and ClWorkloadFactory * Added GreaterLayer stub implementation * Renamed ArithmeticBaseLayer to ElementwiseBaseLayer Change-Id: I7e38c2936de905da921a92ba3f918478169ec7f5
2018-12-11IVGCVSW-1434 Add debug mode to Optimizerkeidav01
* Modified optimizer to support debug mode via DebugLayer Change-Id: Ic8f313778e55540c182cf99876c44a0823be04c6
2018-12-07IVGCVSW-2316 Add reference implementation and unit tests for DebugNattapat Chaimanowong
Change-Id: Ib2e5de2a057da57ef77a9f5c4367d699d4773294
2018-12-05IVGCVSW-2264 Remove input swizzling from ParseConv2D in the TF parserMatteo Martincigh
* Removed the input swizzling when the data layout is NHWC * Permuting weights depending on the data layout used * Added getter methods to ParsedConstTfOperation to get the tensor info and the storage memory area, needed for swizzling the weights * Added unit tests for both NHWC and NCHW data layouts Change-Id: I6543900c594417df630b2663d8551158b93b7836
2018-12-05IVGCVSW-2296 Add ParsePad method to TfParserjimfly01
* Also added unit test armnnTfParser/test/Pad.cpp * Added missing 'Pad' entry to GetLayerTypeAsCString(LayerType) * Fixed the RefLayerSupport.IsPadSupported, now it returns true * Small fix in Optimize. Only resolve stringstream to string once Change-Id: Ieaa1886858a48cd761ac5f30454f73e44bdd4b8f
2018-12-05IVGCVSW-2264 Move DataLayoutIndexed to armnnUtilsMatteo Martincigh
* Since DataLayoutIndexed is now required in the TF parser, this changes move it to the armnnUtils library so that it'll be accessible by the armnnTfParser * Modified CMake files and Android.mk files accordingly Change-Id: Ie2620359ef288aeff64cb9e9bec068a466eee0e9
2018-12-04IVGCVSW-2247 Adding a min Elementwise Workload and testsÉanna Ó Catháin
Change-Id: I017ca6c23b62a8978982de0ca4ad204cb8cf7c67
2018-12-03IVGCVSW-2315 Add DebugLayer and no-op factory methodNattapat Chaimanowong
Change-Id: I5455b720565248ff94278e76887d63f8434a7b58
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-06 03:20:07 +0000