aboutsummaryrefslogtreecommitdiff
path: root/src/armnn/test/optimizations
AgeCommit message (Collapse)Author
2024-02-13MLCE-1165 Model failing to load when pad is folded into Conv2dTracy Narine
* Skipping the optimization which folds pad and conv2d together for a specific case: 1x1 filter and padding size >= filter size Signed-off-by: Tracy Narine <tracy.narine@arm.com> Change-Id: I46944e9f736df1ff60469b2d2852e1bba01ab8cd
2023-09-28IVGCVSW-7504 Create a backend specific optimization to fuse ↵Tracy Narine
ADD+MUL+Add+(Activation) in CpuAcc * Adding CpuAcc backend optimization to fuse add+mul+add into one layer * Tests added/enhanced * Also added optional extended parameter to Graph::Print() and throw macros that could be used in place of assert Signed-off-by: Tracy Narine <tracy.narine@arm.com> Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I5f8d094b969a130d8c2c7b4da07426313a9fea76
2023-08-31IVGCVSW-7525 Add broadcast_to operatorIdriss Chaouch
Signed-off-by: Idriss Chaouch <idriss.chaouch@arm.com> Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I94ec5f9120b2d736fdf98d00ec5137a4efd739b8
2023-08-02IVGCVSW-7880 Add check for FP16 backend supportRyan OShea
* Check if preferred backends have FP16 support before enable fp16-turbo-mode * Unit tests * Replaced global gpuAccCapabilities with getter method construction * Replaced deprecated function call in SL shim Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: If29b62b330ca8987de8acf6408db11daf25ca0b5
2023-07-12IVGCVSW-7783 Add check for FP16 infinity valuesNarumol Prangnawarat
* Check to round to closest finite FP16 value when convert FP32 to FP16 * Unit tests to be added Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: If3b982ff3030379ac33c47d4be13edb0bda679f6
2023-04-03IVGCVSW-3808 Deprecation notices for old ElementwiseBinary layersMike Kelly
* Added Deprecation notices for old ElementwiseBinary layers. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I5bd0f186aaed675885d667f47e1e210ee9ec84f8
2023-03-31Revert "IVGCVSW-3808 Deprecation notices for old ElementwiseBinary layers"Mike Kelly
This reverts commit 52e90bf59ecbe90d33368d8fc1fd120f07658aaf. Change-Id: I5a0d244593d8e760ee7ba0c9d38c02377e1bdc24 Signed-off-by: Mike Kelly <mike.kelly@arm.com>
2023-03-30IVGCVSW-3808 Deprecation notices for old ElementwiseBinary layersMike Kelly
* Added Deprecation notices for old ElementwiseBinary layers. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Iebbbaff38cc9c347b25eb2f9054c914a4f931c68
2023-03-14IVGCVSW-3808 Add ElementwiseBinaryLayerMike Kelly
!android-nn-driver:9329 * Added ElementwiseBinaryLayer that can represent all ElementwiseBinary operations including Add, Div, Sub, Maximum, Mul and Minimum. * Updated Delegate to use ElementwiseBinaryLayer instead of the Add, Div, Sub, Maximum, Mul and Minimum layers. * Updated Deserializer to use ElementwiseBinaryLayer instead of the Add, Div, Sub, Maximum, Mul and Minimum layers. * Updated OnnxParser to use ElementwiseBinaryLayer instead of the Add layer. * Updated TfLiteParser to use ElementwiseBinaryLayer instead of the Add, Div, Sub, Maximum, Mul and Minimum layers. * Updated CL and Neon tests to use ElementwiseBinaryLayer. * Updated CL and Neon Backend Specific Optimizations to accept ElementBinaryLayers as well as Add, Div, Mul, Sub, Maximum and Minimum layers. Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I7cbb96b60eb01f0e2b57b0541016d48a08b86c75
2023-01-18Github #700: Fix order of optimizations so dequantization works with foldingFrancis Murtagh
* Folding of pad into conv2d expected a Constant layer not Dequantisation * Fusing Dequantisation with Constant to a Constant ensures that. * Group Constant layer optimizations together where possible. * Add unit test. Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: Id0393313bf097595f2f13738b7513e427116ea4a
2022-12-12IVGCVSW-7209 Remove deprecated code due to be removed in 23.02Mike Kelly
* Removed weights and bias from Convolution, DepthwiseConv & FullyConnected layers * Removed the weight and bias ConstTensorHandles from the QueueDescriptors * Updated Workloads to take tensors from WorkloadInfo rather than the QueueDescriptors * Removed unused RedirectMembersToConstantInputs optimization and tests. Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I9ffcdc4a1c0dff725539dd69fc435b700bd98a56
2022-11-16IVGCVSW-7214 Disable BF16-Turbo-Mode and remove conversion layersRyan OShea
- Remove Bf16ToFp32 Conversion Layer - Remove Fp32ToBf16 Conversion Layer - Remove B16 Conversion tests * Throw exception if m_ReduceFp32ToBf16 optimzer option is set to true * Provide comments to enable fast math in order to use bf16 * Update docs to inform users to enable fast math for bf16 Execute Network Changes * Require bf16_turbo_mode to also have fast_math_enabled set to true - Remove setting m_ReduceFp32ToBf16 optimizer option Signed-off-by: Ryan OShea <ryan.oshea3@arm.com> Change-Id: Ibaa6da9d29c96a1ce32ff5196b0847fde9f04a1c
2022-08-05IVGCVSW-7149 FoldPadIntoQuantizedAvgPoolCpuRefTest test failing while ↵Cathal Corbett
running Arm NN Unittest Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I567452000287babad345e61ea85ea84f362f48e0
2022-08-05GitHub #667: Neon fold padding into average pool 2D quantization bug fix.Cathal Corbett
* Originated from a GitHub issue: https://github.com/ARM-software/armnn/issues/667 * Initially, Arm NN supports the pool 2D operation because there is no padding on the pool2d. Neon failure occurs when padding is followed by average pool 2D due to folding optimization. * Here we prevent the folding optimization from happening for the above special case and add it in as a backend specific optimization. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Ia0fd90c3a6b4b9d29c81106f154617d2e893e26b
2022-07-27IVGCVSW-6978: RedirectMembersToConstantInputs does not work with ↵Francis Murtagh
Fp32NetworkToBf16Converter * Fuse FP32ToBF16Layers with Constant Layer so Conv2d/FullyConnected can have their weights redirected. * If BF16 Unsupported in Conv2d || FullyConnected revert fused Constant Layer to FP32 Change-Id: If523c708a822659d64597d9ae39cca1c2f84b76f Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2022-06-29IVGCVSW-6962 Adding Const layer in the graph immediately after InputTeresa Charlin
instead of immediately before output Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I2d89a1efdabfdb4be24a8998a03fe1f502d26183
2022-05-24IVGCVSW-6967 Add Optimizer Test for FullyConnected in Fp32ToBf16experimental/serializationIssueKeith Davis
* Test already existed but bias was not enabled so yielded false positive * Updated Conv2d and FC to have const layers as inputs Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: Id4193adef2ac67b3a4681345e4dc01414cbbbad7
2022-05-23IVGCVSW-6123 ConstTensorsAsInputs: Conv2dKeith Davis
* Use new INetwork::AddConvolution2dLayer instead of deprecated version * Remove duplicated test in SerlializerTests * Fix some cosmetics Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I3407815bfdc1cdc01ca0a667b8e4d80d8621783f
2022-05-19IVGCVSW-6145 ConstTensorsAsInput: Optimizer Fix - GetConstantTensorsByRefFrancis Murtagh
* Add functionality to check for ConstantTensorsAsInputs to GetConstantTensorsByRef * Reorder optimizations so RedirectMembersToConstantInputs occurs after Conversion of Constants * Ensure graph is in topological order after loading in OptimizedNet * Fixed test to check release of m_LayerOutputs. Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I7cff50798d7217e8ea0d2f9b153eabd10174a566
2022-05-18IVGCVSW-6147 ConstTensorsAsInput: Optimizer - FusePermuteIntoConstLayerCathal Corbett
* No trailing permute layer after a constant layer * Unit test for optimization Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I0d098f5af41d2c55df7cef1ccfb848093320ddc1
2022-05-18IVGCVSW-6455 Support Const + Dequantize layer and optimize it.Teresa Charlin
* Support Float16 as input to Dequantize layer * Add Optimization to substitute Const+Dequantize layers with Const layer Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I58bb7e3871ca480c7b6fca93c4efb2de84e09e64 Signed-off-by: David <david.monahan@arm.com>
2022-05-17IVGCVSW-6126 ConstTensorsAsInput: Conv2d - BackendsCathal Corbett
!android-nn-driver:7477 Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Ibf633ccccc385bd980934ff829407d21981323ef
2022-05-16IVGCVSW-6124 ConstTensorsAsInput: Conv2d - FrontEndKeith Davis
* Update Front-end and Tools. * Updated Serializer, Deserializer and unit tests to reflect this. * Updated TfLiteDelegate, TfLiteParser and OnnxParser. * Updated Ref. * Fixed resulting Neon / CL tests * Unified optimizers for conv2d ops * Optimizer Fix - Fp32ToBf16 * Partial implementation for ACL backends to fix VTS failures !android-nn-driver:7477 Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I5fb18877f7ee32643e15a9818945356274bb401b
2022-05-12IVGCVSW-6940 ConstTensorsAsInput: DepthwiseConvolution2d - Complete ACLCathal Corbett
* Added backend specific optimization & test for CpuAcc and GpuAcc: PermuteDepthwiseConv2dWeights Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I600476b2e9c557a39818a574c1091c9d650b21b1
2022-05-05IVGCVSW-6127 ConstTensorsAsInput: DepthwiseConvolution2dCathal Corbett
!android-nn-driver:7418 * Update Front-end and Tools. * Updated Serializer, Deserializer and unit tests to reflect this. * Updated TfLiteDelegate, TfLiteParser and OnnxParser. * Change NNDriver to new API. * Updated Ref. * Neon and Cl backend partially completed (Backend.cpp files). * Added dynamic or constant input EndToEnd tests. * Added ConstantTensorAsInputMemeberVariableRedirect Optimization. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Ib18b6c10a093042e165e25237dc04a4c67ba82da
2022-02-07IVGCVSW-6635 Move MemCopyTestImpl from acl to armnnTestUtils.Colm Donelan
* Move MemCopyTestImpl.hpp from src/backends/aclCommon/test/ to include/armnnTestutils. * Refactor MemCopyTests in aclCommon, cl and Neon. * Introduce RefMemCopyTests to exercise this utility in x86 builds. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I8824f013d3656658ed0a2904bb79384e3af68641
2021-12-15IVGCVSW-6626 Promote backend headers in backendCommon to armnn/backendsColm Donelan
Move the following header files from backendsCommon to armnn/backends. * MemCopyWorkload.hpp * TensorHandle.hpp * Workload.hpp * WorkloadData.hpp * WorkloadFactory.hpp Replace them with forwarding headers and a pragma deprecation message. Resolve the deprecation messages in Arm NN code. Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I47f116b30f86e478c9057795bc518c391a8ae514
2021-12-14IVGCVSW-6453 'Move the ArmNN Test Utils code to a physically separate directory'Sadik Armagan
* Created include/armnnTestUtils directory * Moved Arm NN test utils files into armnnTestUtils directory Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I03ac54c645c41c52650c4c03b6a58fb1481fef5d
2021-11-08IVGCVSW-6420: Constant flag in tensor info is not set correctlyCathal Corbett
!android-nn-driver:6532 !armnn-internal-tests:372451 * Made fix to 2 out of 3 ConstTensor() constructors in Tensor.hpp to throw InvalidArgumentException when TensorInfo isConstant parameter is false. * Added new ConstTensor() constructor in Tensor.cpp to accept vector<>.data() using template<typename MemoryType>. * Fixed runtime->GetOutputTensorInfo()/GetInputTensorInfo() methods and called submethods to return TensorInfo& rather than TensorInfo. * Fixed all failing unit tests for CpuRef/CpuAcc/GpuAcc to ensure any ConstTensor created has it's TensorInfo isConstant set to true. * Added unit tests in TensorTest.cpp to ensure ConstTensor constructors throw InvalidArgumentException when TensorInfo isConstat parameter is false. * Added unit test to ensure an empty ConstTensor constructor will set TensorInfo isConatant to true. * Indentation fixes. * Fix to arm_tensor.i to add isConstant parameter to TensorInfo constructor. Added methods IsConstant() and SetConstant(). * Fix to const_tensor.py to throw ValueError when TensorInfo isConstant is set to false when constructing a ConstTensor. * Fixed PyArmnn unit tests to set TensorInfo isConstant to True when ConstTensor is used. * Added unit tests in test_const_tensor.py to ensure ConstTensor constructors throw ValueError when TensorInfo isConstat parameter is false. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I44e440dd0422c366d31bbdbc77ad2b4db0bde148
2021-08-06IVGCVSW-6119 ConstTensorsAsInput: FullyConnectedMatthew Sloyan
* Constant weights and biases are now stored as Constant layers. * Updated Serializer, Deserializer and unit tests to reflect this. * Updated TfLiteDelegate, TfLiteParser and OnnxParser. * Updated Schema with IsConstant and ConstantTensorsAsInputs. * Updated Ref backend to handle constant weights and bias as inputs rather than reading from member variables. * Added dynamic or constant input EndToEnd tests. !android-nn-driver:5959 Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ibf3cf437df1100e4b322b0d303c575c6339f9696
2021-07-16Avoid empty test suitesMatthew Bentham
Refactor code around conditionally-compiled tests to avoid declaring empty test suites, as this can cause unused function warnings to be issued under certain combinations of compiler, warning level, and doctest version. Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: Ib501aef80475538a725b857d9c31d1d2f96b124d
2021-06-30IVGCVSW-6161 ConstTensorsAsInput: Optimizer - Redirect ConstTensor layer membersMatthew Sloyan
* Optimization that searches for layers with ConstantLayers as inputs. * The layer member variables are then redirected to these ConstantLayers. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I24a2bf0e8575b808343e0bbe3897b344e94796ad
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
2021-06-11IVGCVSW-5963 'Move unit tests to new framework'Sadik Armagan
* Used doctest in ArmNN unit tests Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ia9cf5fc72775878885c5f864abf2c56b3a935f1a
2021-05-24IVGCVSW-6069 Add Unit Test for Pad + DepthwiseConv and Pad + ConvTeresa Charlin
*All fold pad test are now in a separate file Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ic0b0436f6b0194404f9a3f1553e2f69524b63580
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
2021-04-29IVGCVSW-5890 Prevent modification to const layers with multiple connectionsColm Donelan
* In AddBroadcastReshapeLayerImpl check if a constant layer has other connections before modifying its output tensor shape. * In ElementWiseBaseLayer replace an ARMNN_ASSERT with a proper error message. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: Id3f3796c260eede61f076660505257a8b65d93fc
2021-04-07Fix graph copy memory spikeFinn Williams
* Change layer storage of ConstTensors to std::shared_ptr<ConstCpuTensorHandle> * Change clone to share ConstTensor rather than copy * Remove uses of non-const GetTensor() call * Reduce scope of non-optimized network in ExeNet, so memory can be released after use Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: Ibb2c7309d12411d21405bd6024c76bcdf5404545
2021-03-16IVGCVSW-5754 Change the behaviour of the AddBroadcastReshapeLayer ↵Finn Williams
Optimisation when the input is a const tensor Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I8b1357bdefc45880d064d7e448af364ac8644c0d
2021-02-17IVGCVSW-5734 Building armnn failed in our Backends CI jobFrancis Murtagh
* CreateTestNetwork() and CreateTransposeTestNetwork should only be defined if Ref enabled; the same as the test its called in otherwise it's defined but not called. Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I7bc522a7884d216d1a8e51afd7cec7a66e4e2947
2021-02-15IVGCVSW-4873 Implement Pimpl Idiom for INetwork and IOptimizedNetworkFrancis Murtagh
!android-nn-driver:5042 Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Ia1ce8b839e81b46428ba0f78463e085e5906958d Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Signed-off-by: Finn Williams <Finn.Williams@arm.com>
2021-01-05adding BOOST_TEST to EnqueueWorkload in FuseActivation Unit TestTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I6a00045967fa48ec0913c8708ffc146a72ed2b87
2020-12-17IVGCVSW-5532 Adding UnitTest fusing activationTeresa Charlin
* QASymmS8 and BoundedReLU * Float16 and ReLU in GpuAcc * Remove layerName, not needed as 1 test per combination Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I930c7a04d8d904f370f1b40c62cf9311c172bbdf
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
2020-11-13IVGCVSW-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
2020-11-08IVGCVSW-5315 Create FuseBatchNorm classMike Kelly
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Id0625c58dbeea79874bf986b70d136ed9390bf83
2020-11-02IVGCVSW-5476 Fix Fuse_batchNorm_into_Conv2D_Float32_TestTeresa Charlin
* failing with no backends provided Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I55ebfc52268ad667e495831c64977338d003db99
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-17 14:41:12 +0000