Age | Commit message (Collapse) | Author |
|
Signed-off-by: John Mcloughlin <john.mcloughlin@arm.com>
Change-Id: Id4bdc31e3e6f18ccaef232c29a2d2825c915b21c
|
|
* Resolves MLCE-1040
Change-Id: I32878ed70af356832403e83dcb63b0b89a8a84e3
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
|
|
Remove deprecated GetGraph() from OptimizationViews. This method has
been deprecated for a long time and no backends still need it. Remove
include of Graph.hpp from the public headers.
Add includes elsewhere to deal with the header fallout.
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
Change-Id: I8dae275a8a446d9d0e19be62684e9b3cd2fa493d
|
|
* Added Deprecation notices for old ElementwiseBinary layers.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I5bd0f186aaed675885d667f47e1e210ee9ec84f8
|
|
This reverts commit 52e90bf59ecbe90d33368d8fc1fd120f07658aaf.
Change-Id: I5a0d244593d8e760ee7ba0c9d38c02377e1bdc24
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
|
|
* Added Deprecation notices for old ElementwiseBinary layers.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Iebbbaff38cc9c347b25eb2f9054c914a4f931c68
|
|
!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
|
|
aync execution
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I6f921feaf591f0a1e27c373bb708c7ec8dfcbe43
|
|
This makes it easier to use, particularly in backends where it
is common to pass around const pointers to IConnectableLayer.
The non-constant version is rewritten to use the constant version.
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
Change-Id: Id3a8384447e93c213299a85ade9a667df5960534
|
|
Previously we were adding a reshape layer to "broadcast" tensors
for elementwise operations. This broadcast was happening too late
and was really just an expand dims. This was breaking the constant
attributes of tensors and layer support of certain backends.
* Remove addition of reshape layer when expanding dimensions
* Replace broadcast function with expand dims to equal rank function
* Fix some error status checks in various layers
* Add new TensorUtil function that expands dims to a defined rank
* Add unit tests to new TensorUtil function
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: I31aca47c98075fef4f86864a15470f5faa55ab8d
|
|
* The test cases that use DebugTestImpl were creating temporary files
but not cleaning them up after running.
* Refactored FileSystem to extract a common RemoveDirectoryAndContents
function.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I35b8d2eeed286742358a9abccbc078493d033902
|
|
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I971ea25b3380329aa1ad3936e7f5db1f5039805a
|
|
* Added ability to reduce dimension sizes when calling BuildArmComputeTensorInfo or
BuildArmComputeTensorShapes, this will attempt to remove leading 1s in order to
squeeze the number of dimensions but retain the size.
* Changed ClBatchMatMulWorkload to attempt to squeeze the number of dimensions to 3
as the CL Gemm Kernel can only support up to 3 dimensions.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I6b3d0886c5b97fdb686838fc3dc292833ddc4643
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I55c1020dbfe13af439236fa72057f114e78e8bd3
|
|
* API to remove need for workaround so backend users can get slots
* OutputSlots outside the SubgraphView needed to obtain TensorInfo
* Fix a few Copyright headers
* Add shared_ptr back to original subgraph view using
std::enable_shared_from_this
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I033a00d6fc4020619d406ac06a156b7e380a426a
|
|
OptimizationViews::GetINetwork()
* Also provide API to return reference via GetINetworkRef().
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I80f4912cb7e22a2023e9bb880182ad4610c219e9
|
|
* Fixed bug when converting Constants with Per-Axis Quantization
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ifbea23e60483746ec987da491dae96e74cb33af4
|
|
* Added CreateNetworkFromBinary to the ONNX parser
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I5ca72ee49c7b098f9fb4aaf55a8bc077230cb30e
|
|
* 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
|
|
* Done as part of 22.11/23.02 innovation days.
* IsLayerSupported() is called in model prepare (delegate, android-nn-driver and shim/support_library)
and again in ArmNN once model otimization is performed.
* From calling IsLayerSupported() the first time, we should know that the layers are supported
and what backend they are supported on.
* Solution is to set the BackendId of the IConnectableLayer when IsLayerSupported() is called the first time,
* In the Optimize() function we then check if the backend is set. If so, we do not call IsLayerSupported() again.
* In the case a layer that is supported gets optimized, then the BackendId of that layer get set to "Unknown"
for the new optimized layer and IsLayerSupported() will get called on the newly optimized layer.
* Includes bug fix IVGCVSW-7213 for Android Mean FP16 CpuAcc tests. Also related to bug IVGCVSW-7211.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I7a7820d0cdb079ffb5a3a2e0c44e252f652df53b
|
|
This tool forces explicit includes of all dependencies and
highlights unused dependencies.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I92e449245246452a0227cbd13f9c082e2088bf8c
|
|
* Some pemutation vectors were not converted correctly.
* Add Transpose end to end test.
* Comments added with an example to clarify the differences betweeen
Transpose and Permute
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6c0954ca6ce00ef5f2a6f3625abe6f4fd27b5cdf
|
|
* Extended deprecation time of SubgraphView interface to 23.08
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Ic0a729ea31402f0b39724da47212ae5cc04465c4
|
|
- 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
|
|
* Add functionality to print output tensors to file in tempdir
* UnitTests
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Idfb4c186544187db1fecdfca11c662540f645439
|
|
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
Change-Id: I3573078206272c3a72a2b3acf8781ab458ea6c90
|
|
* IRuntime.hpp includes one file from the profiling interface and it's
causing some build problems for some users. Replace the include with
a forward declaration of arm::pipe::ILocalPacketHandlerSharedPtr.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I6064e02db4ca056423bb448ddc0d712b50a704cb
|
|
* Add a breakdown of the runtime options to the documentation.
* Exclude test classes from Doxygen generation.
* Limit the file extension selection for Doxygen generation.
* Add the support library to be generated.
* Fix some broken markups.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I81896f2d7fff503a1d51d6d4ac3876aa8b84118e
|
|
* Added files based on RefBackend
* Added PreCompiled Workload skeleton
* Increment ABI version of armnnTestUtils for CreateInput which had
been left as pure virtual, added base implementation for it.
* Add IsTosaLayerSupported() for Addition
Change-Id: I4c963adf3f50593d17ecdf21554502a64ad3bd76
|
|
overridden
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: If594e291951a5f9ed1957a19a971c498f6e7843f
|
|
* AddConv and AddDWConv with weights and bias
* ResizeBilinearDescriptor
* b,blacklist option in accuracy tool
!android-nn-driver:8172
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ibbc04fd18be7f938b11590bf67cd7af103cb4d99
|
|
* Added transpose parameters to pre-transpose each input tensor's slices
* Added adjoint parameters to pre-adjoint each input tensor's slices
* Small refactoring (BatchMatMulDescriptor static helpers and BatchMatMulImpl constructor)
* Updated input validation and output shape inference for parameters
* Additional layer unit tests for parameters added
* Versionings incremented
Signed-off-by: Samuel Yap <samuel.yap@arm.com>
Change-Id: Ibe5242a8a5bf604c13de0dc65844fd6c421cc667
|
|
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
Change-Id: I3a3aab7b5042349cb2df8517678306665e037610
|
|
This reverts commit 1a7f033768acb27da11503bd29abb468d2e77f9e.
List of fixes to be able to add this code again:
* "emplacing_back" the vector inputTensors into the vector m_InputTensorsVec outside the for loop
* GetIOInfo() uses IOptimizedNetwork instead of INetwork, where the infered shapes are not saved
* Add missing data type Signed32 to SetupInputsAndOutputs()
* PrintOutputTensors() prints the actual output without dequantizing
* Add profilingDetailsMethod as input in networkProperties in ArmNNExecutor constructor
* Fix typos
Change-Id: I91de166f87228282db3efa27431fe91458834442
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ic6634d48892d11e5f146cdf285e1e333e93e9937
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
* Descriptors added for BatchMatMul
* Layer definition added
* Input validation added (will likely change when opt. param support comes in)
* Ref workload implementation for BatchMatMul added (will also change with opt. param support)
* Ref layer tests made for BatchMatMul
* CMake and other build files updated
Signed-off-by: Samuel Yap <samuel.yap@arm.com>
Change-Id: Ic885301da543ee0fbe7922b85e7f9658c4efc617
|
|
* Refactor backend capability checks in LoadedNetwork.
* ImportInputs should check the number of tensors does not exceed the
number of inputs.
* In EnqueueWorkload the check for for the count of input tensors
was ignoring pre-imported inputs.
* Added checks to verify ImportInputs/ImportOutputs worked as expected
in EndToEndTestImpl.
* Improve documentation on ImportInputs/ImportOutputs in IRuntime.hpp.
* Disabled import tests in CL and Neon EndToEndTests that cannot work.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Iae4b2644a1c9f01ee72bce1afb211661cc9ae2e3
|
|
* ExecutionData holds a void* which can be assigned to data required
for execution in a backend. WorkingMemDescriptors are used in the Ref
backend which hold TensorHandles for inputs and outputs.
* Updated ExecuteAsync functions to take ExecutionData.
* Added CreateExecutionData and UpdateExectutionData to IBackendInternal.
* Streamlined experimental IWorkingMemHandle API by removing map related
function and unused m_workingMemDescriptorMap from WorkingMemHandle.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I54b0aab12872011743a141eb42dae200227769af
|
|
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I8c59f1feb9c44351427715b08d762b5a73320af5
|
|
* Add virtual GetSlotIndex to IInputSlot
* Fix logic in GetWorkingCopy to use index of slots; so as not
to add slots to cloned subgraphView if not in original subgraphView
* Add test to cover cases when not all inputSlots to subgraphView layer
are part of the original subgraphView
* Mark SubgraphView::GetWorkingCopy() as const
Change-Id: I1d540f84c57f97f6c834ec06ca13393ffa55d379
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I9ccaefbe28ea572e9e2b4a2168574804667f7460
|
|
* Added non-const variants of existing const member functions in
IInputSlot and IOutputSlot to retrieve non-const IConnectableLayer
Signed-off-by: Nabeel Ahmad <nabeel.ahmad@arm.com>
Change-Id: Ic3388b578324edb4d2cca36acce6560ad1ce83c5
|
|
This reverts commit a0f8b15d4ddb5075f380003ff31b271d389d3b66.
Reason for revert: <Test ClDmaBufInternalTests review >
Change-Id: Ibc4a77fa008643849da7330391942e4c87b941e2
|
|
This reverts commit 03bf98a8bc51ad20eef4b9ca5fbf6ce15e063721.
Reason for revert: Caused failures in tests located in internal repo.
Change-Id: If35cb0ede349b270e4e7827324382e09455d8cfa
|
|
Only one bool is used to indicate whether inputs should be imported.
However, its possible for the user to want to import inputs but not
export outputs. In addition it's possible for a user to enabled import
during optimize but then pass a memory source that does not require
import.
* Add m_ExportEnabled to INetwork.hpp.
* Modify Network::dNetwork to consider both m_ImportEnabled
and m_ExportEnabled.
* Add ValidateSourcesMatchOptimizedNetwork to LoadedNetwork to validate
import options between optimize and network load.
* Update the TfLite delegate consider exportEnabled flag in the
optimizer.
!armnn-internal-tests:425350
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I776eab81595898e43f91ab40306962eae61329f4
|
|
dimensions
* Added allow-expanded-dims to TFLite parser and ArmNN delegate
* If true ArmNN will disregard dimensions with a size of 1 when
validating tensor shapes. Tensor sizes must still match.
* This allows us to support models where tensors have expanded
dimensions (i.e. extra dimensions with a size of 1).
* Fixed bug in Network where it assumed that only the first option
could be ShapeInferenceMethod.
* Fixed bug where m_ShapeInferenceMethod was lost when copying or
moving Graphs.
* Changed Delegate to pass "infer-output-shape", "allow-expanded-dims"
and other BackendOptions through to the Network during construction.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ibe7c5ae6597796fc9164cb07bd372bd7f8f8cacf
|
|
* Resolves: IVGCVSW-6952
Signed-off-by: Finn Williams <finn.williams@arm.com>
Change-Id: Ic85bd5267cf94e0ee8461ff4e62b9db3cb80877a
|
|
* Signature change is ABI/API break, overloaded and forwarded to new function.
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I8590a6fd65986b5aeff905c1e761cb5c51042e99
|
|
* 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
|
|
!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
|
|
* Corrected TensorInfo order for IsUnidirectionalSequenceLstmSupported
* outputStateOut TensorInfo is not optional.
* cellStateOut TensorInfo is not optional.
* TensorInfo Order matches other QLSTM/LSTM layers.
* Added missing parameters to UnidirectionalSequenceLstmOperator for
delegate.
* Added quantized UnidirectionalSequenceLstm support to Neon
!android-nn-driver:7457
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I26dde1bb96793dd25eb9081ca5ae5f63752288c4
|