github ARM-software/armnn v22.05
Release 22.05
on GitHub

latest releases: v24.08, v24.05, v24.02...
2 years ago

Summary

New Features

  • ArmnnTestUtils is now versioned and under ABI compliance checker
  • Added support for Int32 CONCATENATION layer for CpuRef
  • Added support for Float32 Unidirectional Sequence LSTM layer for CpuAcc and GpuAcc
  • Added support for GatherNd for CpuRef, CpuAcc and GpuAcc
  • Added support for SQRT for CpuAcc and GpuAcc
  • Added support for Depthwise Convolution2d ConstTensorsAsInput for CpuRef, CpuAcc and GpuAcc
  • Added support for Conv2d ConstTensorsAsInput for CpuRef, CpuAcc and GpuAcc
  • Added support for Fully Connected ConstTensorsAsInput for CpuAcc and GpuAcc
  • Added support for MaxPool3D and AveragePool3D for CpuAcc and GpuAcc
  • Added support for L2Pooling3D for GpuAcc
  • Added support for UnidirectionalLSTM for CpuAcc
  • ConstTensorsAsInput: Optimizer Fix - FuseBatchNorm
  • ConstTensorsAsInput: Optimizer Fix - FoldPadIntoConvolution2d
  • ConstTensorsAsInput: Optimizer Fix - Fp32ToBf16 optimization

TfLite Parser

  • Added support for GatherNd
  • Added support for FloorDiv
  • Added support for UnidirectionalLSTM
  • Do not create Floor for FloorDiv layer when the data type is int32

ArmNN Serializer/Deserializer

  • Added support for GatherNd

ExecuteNetwork App Changes:

  • Added Reuse IO Buffers mode
  • Profiling details weights and bias JSON keys deprecated. Will be removed for 22.08

Bug Fixes

  • Fixed crashing in profiling
  • Fixed the issue with running SimpleSample app in Raspi
  • Removed MockBackend.hpp from armnn/src/backends/backendsCommon/test/ to solve problems when using Visual Studio in Windows
  • Fixed segfault in RefDepthwiseConvolution2d workload

Other Changes

  • ArmNN Baremetal
    • Change the namespace from armnn::profiling to arm::pipe

ABI/API Changes

The following front-end API changes have occurred during the implementation of 22.05 that users should be aware of before upgrading.

.

Feature SHA Gerrit Review Resultant ABI/API changes
Change the namespace from armnn::profiling to arm::pipe 5aa9fd7 https://review.mlplatform.org/c/ml/armnn/+/7222
  • Pure virtual method GetOwningIConnectableLayer( ) const has been added to class IOutputSlot. Applications will not provide the implementation for this pure virtual method and therefore cause a crash in the library trying to call this method.
  • The layout of v-table has been changed. Call of any virtual method at higher position in this class or its subclasses may result in crash or incorrect behavior of applications.
  • The following functions has had a change in signature meaning it will not be recognized by old applications: BackendRegistry::SetProfilingService
    IRuntime::RegisterDebugCallback
  • Type of field m_LocalPacketHandlers has been changed from std::vector<std::shared_ptrprofiling::ILocalPacketHandler > to std::vector<std::shared_ptrarm::pipe::ILocalPacketHandler > in Runtime::CreateOptions::ExternalProfilingOptions
  • Type of return value has been changed from profiling::ProfilingGuid to arm::pipe::ProfilingGuid in OptimizedNetwork::GetGuid
    • Replace ProfilingService includes with IProfilingService. af94772 https://review.mlplatform.org/c/ml/armnn/+/7240 The following function has had a change in signature meaning it will not be recognized by old applications.
    BackendRegistry::SetProfilingService
    Remove dependency on armnn::Exception classes from the Profiling code f9db3ef https://review.mlplatform.org/c/ml/armnn/+/7280 Class armnn::BackendProfilingException has been moved to namespace arm::pipe; this will result in older applications not being able to find it.
    Replace armnn:Optional with arm::pipe::Optional in profiling code decd08b https://review.mlplatform.org/c/ml/armnn/+/7295 Class armnn::TimeoutException has been moved to namespace arm::pipe; this will result in older applications not being able to find it.
    Add Unidirectional Sequence Lstm support to TFLite 5880b91 https://review.mlplatform.org/c/ml/armnn/+/7023 Following fields have been added to struct LstmDescriptor:
    m_CellIntermediateScale
    m_ForgetIntermediateScale
    m_HiddenStateScale
    m_HiddenStateZeroPoint
    m_InputIntermediateScale
    m_OutputIntermediateScale
    As a result of this size of the struct has been changed
    ConstTensorsAsInput: DepthwiseConvolution2d 0690265 https://review.mlplatform.org/c/ml/armnn/+/7417 Pure virtual method VisitDepthwiseConvolution2dLayer ( IConnectableLayer const*, struct DepthwiseConvolution2dDescriptor const&, char const* ) has been added to this class..
  • Applications will not provide the implementation for this pure virtual method and therefore cause a crash in the library trying to call this method..
  • The layout of v-table has been changed. Call of any virtual method at higher position in this class or its subclasses may result in crash or incorrect behavior of applications.
    • ConstTensorsAsInput: Conv2d - FrontEnd b4dd5cc https://review.mlplatform.org/c/ml/armnn/+/7382 Pure virtual method VisitConvolution2dLayer ( IConnectableLayer const*, struct Convolution2dDescriptor const&, char const* ) has been added to this class.
  • Applications will not provide the implementation for this pure virtual method and therefore cause a crash in the library trying to call this method.
  • The layout of v-table has been changed. Call of any virtual method at higher position in this class or its subclasses may result in crash or incorrect behavior of applications.

    • The following back-end API changes have occurred during the implementation of 22.02 that users should be aware of before upgrading.

    Feature SHA Gerrit Review Resultant ABI/API changes
    Move headers to profiling/client/include 2776183 https://review.mlplatform.org/c/ml/armnn/+/7327 Headers have been moved to profiling/client/include.
    Change the namespace from armnn::profiling to arm::pipe 5aa9fd7 https://review.mlplatform.org/c/ml/armnn/+/7222
  • Namespace changed from armnn: profiling to armnn: pipe:: profiling

    • TfLite Delegate

    New features

    • Added support for GatherNd

    Bug Fixes

    Note: Arm NN is aware of an issue where converting a model to .armnn will yield unpredictable results when reading back in through the deserializer. This is due to the serializer being dependent on graph topology and the graph being out of order. The graph becomes out of order because of the additional constant layers as inputs that are created through the parsers

    PyArmNN

    • Added support for GatherNd
    • Added Pooling3D

    Build Dependencies

    Tools Supported Version
    Git 2.17.1 or later
    SCons 2.4.1 (Ubuntu) 2.5.1 (Debian)
    Cmake 3.5.1 (Ubuntu) and 3.7.2 (Debian)
    Tensorflow 2.5.0
    Onnx 1.6.0
    Flatbuffer 1.12.0
    Protobuf 3.12.0
    Android NDK r20b
    mapbox/variant 1.2.0
    cxxopts SHA 12e496da3d486b87fa9df43edea65232ed852510
    doctest 2.4.6
    fmt 7.0.1
    ghc 1.3.2
    half 1.12.0
    stb 2.16

    Android 12 Compatibility Testing was performed using the following:

    Android Tag Android Build ID Mali Driver Android Compatibility Test Suite Android Vendor Test Suite
    android-12.0.0_r1 SP1A.210812.015 r36p0_01eac0-rc0 12_r2 (7987736) 12_r2 (7973604)

    Android 11 Compatibility Testing was performed using the following:

    Android Tag Android Build ID Mali Driver Android Compatibility Test Suite Android Vendor Test Suite
    android-11.0.0_r6 RPM1.210413.002 r33p0_01eac0 11_r5 (7640833) 11_r5 (7599184)

    Android 10 Compatibility Testing was performed using the following:

    Androidtag Android Build ID Mali Driver
    android-10.0.0_r39 QQ3A.200605.002.A1 R23P0_01REL0
    Check out latest releases or
    releases around ARM-software/armnn v22.05

    Don't miss a new armnn release

    NewReleases is sending notifications on new releases.

    Get notifications