Skip to content

Releases: ARM-software/armnn

Release list

Release 26.07

Release 26.07 Latest
Latest

Choose a tag to compare

View all tags
@ArmDude ArmDude released this 06 Jul 13:55
v26.07
944dced

Arm NN SDK

Features & Improvements

  • Add CpuAcc SME/SVE shape policy
  • Update Compute Library pin/version to v53.2.0

Bug Fixes

  • Adjust Android™ binary page size to 16 KB

ABI/API Changes:

There are no API/ABI changes. 

Build Dependencies

Tools Supported Version
Git 2.17.1 or later
SCons 2.4.1 (Ubuntu) and 2.5.1 (Debian)
CMake 3.22.1
Tensorflow 2.19.0
Onnx 1.6.0
Flatbuffer 24.3.25
Protobuf 3.19.4
Android NDK r26b
cxxopts 3.1.1
doctest 2.4.6
fmt 8.30
ghc 1.3.2
half 1.12.0
mapbox/variant 1.1.3
stb 2.16
Gemmlowp 16e8662c34917be0065110bfcd9cc27d30f52fdf
Assets 27

Release 26.01

Release 26.01

Choose a tag to compare

View all tags
@gunes-arm gunes-arm released this 23 Jan 10:50
v26.01
600c000

Arm NN SDK

Features & Improvements

  • Updated Compute Library pin/version to v52.7.0.

Bug Fixes

  • Fixed error handling in build_android_ndk_guide.sh
  • Fetch correct reference for Compute Library in script/get_compute_library.sh

ABI/API Changes:

There are no API/ABI changes. 

Build Dependencies

Tools Supported Version
Git 2.17.1 or later
SCons 2.4.1 (Ubuntu) and 2.5.1 (Debian)
CMake 3.22.1
Tensorflow 2.19.0
Onnx 1.6.0
Flatbuffer 24.3.25
Protobuf 3.19.4
Android NDK r26b
cxxopts 3.1.1
doctest 2.4.6
fmt 8.30
ghc 1.3.2
half 1.12.0
mapbox/variant 1.1.3
stb 2.16
Gemmlowp 16e8662c34917be0065110bfcd9cc27d30f52fdf
Loading

Release 25.11

Release 25.11

Choose a tag to compare

View all tags
@walidbr walidbr released this 10 Nov 11:01
v25.11
0d0be76

Arm NN SDK

Features & Improvements:

  • Updated ABI version for v25.11 release.
  • Integrated ArmNN Parser with LiteRT FlatBuffer schema.
  • Added validation of buffer pointers for safer memory operations in the parser.
  • Added PRELU operator support and BOOL type for GREATER_EQUAL.
  • Added bias support for TRANSPOSE_CONV operator in delegates.
  • Updated TensorFlow dependencies and build scripts for TensorFlow 2.19 migration.
  • Added profiling headers and tracepoint setup.
  • Added QNX platform port.
  • Improved compatibility for Bare Metal targets and NEReorderLayer backward compatibility.
  • Added support for building against libtensorflow-lite.so.
  • Updated protobuf dependency in build-tools.
  • Added unit tests for Rescale, DepthwiseConv2d, Shift/Multiplier operators.
  • Refactored reorder kernel and layer.

Bug Fixes:

  • Fixed missing includes to resolve GCC 15 build errors.
  • Fixed GCC compilation issues on armv7.
  • Fixed heap buffer overflow in ArmNN TFLite parser (SpaceToBatchND input type validation).
  • Fixed range validation in Shift operations (added Op_Minimum).
  • Fixed over-eager operand reads in a64_hgemm_8x24.
  • Fixed CpuGemmAssembly bf16 tests.
  • Fixed SME softmax FP32 kernel for large inputs.
  • Fixed INT8 Softmax reserved register issue in SME2 kernels.
  • Fixed SUB, MUL and ADD operators output to be closer to TFLite reference output

Documentation:

  • Updated documentation to reflect GitHub migration.
  • Updated README to note legacy project status.
  • Updated copyright years in contribution guidelines.

ABI/API Changes

The following front-end API changes have occurred during the implementation of 25.11, which users should be aware of before upgrading.
Due to these, changes we have bumped our ARMNN_VERSION to 36.0.0, following Semantic Versioning guidelines.
markdown

Feature SHA Gerrit Review Resultant ABI/API Changes
Subgraph in Opaque Delegate ac9607f https://review.mlplatform.org/c/ml/armnn/+/9389 ArmnnSubgraph::VisitNode method has been updated. tfLiteRegistration argument updated from TfLiteRegistrationExternal* type to TfLiteOperator*

Build Dependencies

Tools Supported Version
Git 2.17.1 or later
SCons 2.4.1 (Ubuntu) and 2.5.1 (Debian)
CMake 3.22.1
Tensorflow 2.19.0
Onnx 1.6.0
Flatbuffer 24.3.25
Protobuf 3.19.4
Android NDK r26b
cxxopts 3.1.1
doctest 2.4.6
fmt 8.30
ghc 1.3.2
half 1.12.0
mapbox/variant 1.1.3
stb 2.16
Gemmlowp 16e8662c34917be0065110bfcd9cc27d30f52fdf
Loading

Release 25.02

Release 25.02

Choose a tag to compare

View all tags
@JonathanC-ARM JonathanC-ARM released this 19 Feb 18:03
v25.02
e1ec5b8

Arm NN SDK

Bug Fixes:

  • TosaRef mapping bug fixes for Operators LeakyRelu, Quantize, Stack, Dequantize
  • TosaRef refactorisation and bug fixes for a range of different Operators.
  • TosaRef Strided Slice Error.
  • TfLite Turbo Model Detection Fix.
  • Added a check to ensure activation is within the current subgraph before fusion in Neon and CL backends.

Removed Features:

  • Removed Async API.
  • Removed PyArmNN.
  • Removed Shim and support library.
  • Removed RangeTracker class.

ABI/API Changes:

The following front-end API changes have occurred during the implementation of 25.02, which users should be aware of before upgrading.

Due to these, changes we have bumped our ARMNN_VERSION to 35.0.0, following Semantic Versioning guidelines.

Feature

SHA

Gerrit Review

Resultant ABI/API Changes
Remove Async API 4483b24 https://review.mlplatform.org/c/ml/armnn/+/12979

The IWorkingMemHandle class has been removed.

The IAsyncExecutionCallback class has been removed.


INetworkProperties structure has had the following fields removed:

  • m_AsyncEnabled

4 functions have been removed from the IRuntime class:

  • IRuntime::ClearImportedInputs ( NetworkId networkId, std::vector<unsigned int>const inputIds )
  • IRuntime::ClearImportedOutputs ( NetworkId networkId, std::vector<unsigned int>const outputIds )
  • IRuntime::CreateWorkingMemHandle ( NetworkId networkId )
  • IRuntime::Execute ( experimental::IWorkingMemHandle& workingMemHandle, InputTensors const& inputTensors, OutputTensors const& outputTensors, std::vector<unsigned int> preImportedInputs, std::vector<unsigned int> preImportedOutputs )


The Threadpool class along with its functions have been removed:

  • Threadpool::LoadMemHandles ( std::vector<std::shared_ptr<IWorkingMemHandle> > memHandles )
  • Threadpool::Schedule ( armnn::NetworkId networkId, armnn::InputTensors const& inputTensors, armnn::OutputTensors const& outputTensors, enum armnn::QosExecPriority const priority, std::shared_ptr<IAsyncExecutionCallback> cb )
  • Threadpool::TerminateThreadPool ( )
  • Threadpool::Threadpool [C1] ( std::size_t numThreads, armnn::IRuntime* runtimePtr, std::vector<std::shared_ptr<IWorkingMemHandle> > memHandles )
  • Threadpool::Threadpool [C2] ( std::size_t numThreads, armnn::IRuntime* runtimePtr, std::vector<std::shared_ptr<IWorkingMemHandle> > memHandles )
  • Threadpool::UnloadMemHandles ( armnn::NetworkId networkId ) 

Build Dependencies

Tools

Supported Version
Git 2.17.1 or later
SCons 2.4.1 (Ubuntu) and 2.5.1 (Debian)
CMake

3.22.1
Tensorflow

2.15.0
Onnx

1.6.0
Flatbuffer 23.5.26
Protobuf

3.12.0

Android NDK

r26b
cxxopts

3.1.1
doctest 2.4.6
fmt 7.0.1
ghc 1.3.2
half 1.12.0
mapbox/variant 1.1.0
stb 2.16
Gemmlowp 16e8662c34917be0065110bfcd9cc27d30f52fdf
Loading

Release 24.11

Release 24.11

Choose a tag to compare

View all tags
@CianMcGriskinARM CianMcGriskinARM released this 29 Nov 16:33
v24.11
3ed70c0

Arm NN SDK

New Features:

  • Implemented "All or Nothing" logic in assign backends.
  • Added Signed64 support for Constant and Tile workloads.
  • Added Int8 and Uint8 support for LogSoftMax to run on CpuAcc and GpuAcc backends.
  • Added automatic backend selection of GPU to ExecuteNetwork.
  • Added TfLite Turbo Model recognition and enable Turbo Mode.

TosaCommon & TosaRef:

  • Added "Convolution3d" support.
  • Added support for activation functions "Sigmoid" and "TanH".
  • Added support for activation function "HardSwish".
  • Added "StridedSlice" support.
  • Added "ElementwiseBinary:SqDiff" support.
  • Added "Stack" support.
  • Added "Dequantize" support.
  • Added "DepthToSpace" support.
  • Added "Gather" support.

Bug Fixes:

  • Fixed the ReduceProdOp Int8 CpuAcc and GpuAcc backend failures in the delegate test suite.
  • Fixed Mean operator in TosaCommon and TosaRef.
  • Fixed ExecuteNetwork logic error when using -N parameter.
  • Fixed convolution delegate test suite failures.
  • Fixed UnpackOpTest Acc backend failures in the delegate test suite.
  • Fixed layer name error on classic delegate DepthwiseConvolution2d.
  • Fixed GatherNd Acc backend failures in the delegate test suite.
  • Fixed FloorDiv Acc backend failures in the delegate test suite.
  • StridedSliceOp Acc backend failures in the delegate test suite.
  • Fixed Pad tests incorrectly reporting unsupported in the delegate test suite.

Removed Features:

  • Removed the Arm NN Converter
  • Removed the GpuFsa backend.

Other Changes:

  • Updated ExecuteNetwork comparison options to return a result value.
  • Added Debugging macros to LoadedNetwork.


ABI/API Changes:

The following front-end API changes have occurred during the implementation of 24.11, which users should be aware of before upgrading.

Due to these, changes we have bumped our ARMNN_VERSION to 34.0.0, following Semantic Versioning guidelines.

Feature SHA Gerrit Review Resultant ABI/API Changes
Make ExecuteNetwork handle automatic selection of GPU backends. b670f11 https://review.mlplatform.org/c/ml/armnn/+/12662 The size of the BackendRegistry class has changed from 192 bytes to 216 bytes. Field m_MappedGpuBackends has been added.
FixFloorDiv Acc DTS Failures. 88a149f https://review.mlplatform.org/c/ml/armnn/+/12411 BinaryOperatory enum has a new member FloorDiv. The member FloorDiv with a value of 8 has been added.

Build Dependencies

Tools Supported Version
Git 2.17.1 or later
SCons 2.4.1 (Ubuntu) and 2.5.1 (Debian)
CMake 3.22.1
Tensorflow 2.15.0
Onnx 1.6.0
Flatbuffer 23.5.26
Protobuf 3.12.0
Android NDK r26b
cxxopts 3.1.1
doctest 2.4.6
fmt 7.0.1
ghc 1.3.2
half 1.12.0
mapbox/variant 1.1.0
stb 2.16
Gemmlowp 16e8662c34917be0065110bfcd9cc27d30f52fdf


Loading

Release 24.08

Release 24.08

Choose a tag to compare

View all tags
@orlmon01 orlmon01 released this 28 Aug 09:58
v24.08
c47f050

Summary

New Features

  • Softmax implemented in TosaCommon and TosaRef.
  • MEAN implemented in TosaCommon and TosaRef.
  • REDUCE_SUM implemented in TosaCommon and TosaRef.
  • Activation:Gelu implemented in TosaRef.
  • ElementwiseUnary:Log implemented in TosaRef.
  • Pad implemented in TosaCommon and TosaRef.
  • ElementwiseUnary:Exp implemented in TosaRef.
  • BatchMatMul implemented in TosaCommon and TosaRef.
  • FullyConnected implemented in TosaCommon and TosaRef.
  • Activation:BoundedReLu implemented in TosaCommon and TosaRef.
  • Activation:ReLu implemented in TosaCommon and TosaRef.
  • DepthwiseConvolution2d Implemented in TosaCommon and TosaRef.
  • Implemented quantized ElementwiseBinary Add, Max, Mul and Sub support in TosaCommon and TosaRef.

Bug Fixes

  • Fix floating point exception in PerAxisIterator.
  • Fix TFLite Parser & Opaque Delegate ExecuteNetwork incorrectly unloading runtime.
  • Fix StridedSliceOp out of bounds errors.
  • Fix not specified dimensionality errors in classic and opaque delegates.
  • Fix warnings when building ArmNN Delegate with GCC-14.1.0.
  • Fix ReshapeOp DTS Test Failures.
  • Fix ConstFloat DTS Test Failures.
  • Fix Broadcast DTS test failures.
  • Fix BatchMatMul DTS test failures.

Other Changes

  • Update to Arm NN documentation for 24.08 release.
  • Review and update documentation for the 24.08 release.
  • Android support for evaluate_network.sh.
  • Added Gemmlowp for fixed point arithmetic on small values.
  • Moved Arm NN repository to use CMake 3.22.
  • Added Numpy Support to Execute Network.

ABI/API Changes

No ABI breaking change occurred in ArmNN Core (libarmnn.so) and so the Major version has not changed, only a bump in minor version (33.1.0 → 33.2.0).

No API breaking back-end changes have occurred during the implementation of 24.08.

Build Dependencies

Tools Supported Version
Git 2.17.1 or later
SCons 2.4.1 (Ubuntu) 2.5.1 (Debian)
Cmake 3.22.1
Tensorflow 2.15.0
Onnx 1.6.0
Flatbuffer 23.5.26
Protobuf 3.12.0
Android NDK r26b
mapbox/variant 1.2.0
cxxopts 3.1.1
doctest 2.4.6
fmt 7.0.1
ghc 1.3.2
half 1.12.0
mapbox/variant 1.1.0
stb 2.16
Gemmlowp 16e8662c34917be0065110bfcd9cc27d30f52fdf
Loading

Release 24.05

Release 24.05

Choose a tag to compare

View all tags
@KevinARM KevinARM released this 30 May 15:20
v24.05
1f3eb73

Summary

New Features

  • ScatterNd Operator Implementation.
    • Added support to delegate and opaque delegate.
    • Added support to Serializer and Deserializer.
    • Added support to TFLite parser.
    • End to End tests added.
    • Added support for CpuRef and GpuAcc.
  • Adding options to serialize networks in ExecuteNetwork.
  • Add a build option to enable the OpenMP scheduler in ACL and made it the default scheduler for ACL builds.
  • Add Boolean data type to Debug layer support.
  • Update TOSA Common and TosaRef to use TOSA v0.80.
  • Update build-tool README to include macOS support.

Bug Fixes

  • ExecuteNetwork fix for abort after inference.
  • Fix for failing CTS Float16 tests.
  • Enable serialize-to-armnn only when ARMNN_SERIALIZER is on.
  • TosaCommon backend
    • In TosaCommon, modify the way the unique names for the inputs are generated.
    • CreateRescaleTosaOperator() modified.
    • Move ComputeSplitAxis() to backendsCommon/WorkloadUtils.
    • For LeakyRelu, add TosaRefEndToEndTests and enable FP16 in TOSA mapping.
    • Fix quantized Conv2d TOSA mapping.
  • Broadcast handling for Comparison layer is inconsistent.
  • Remove limitations on zero scale value in quantization.
  • Fix failing fsrcnn test.
  • Fix broken link in the delegate README.
  • Fix runtime memory handling in delegate and Arm NN executor.
  • Remove use of std::clamp.
  • Syntax change to allow building on older compilers.
  • Assert audit and removal.

Other Changes

  • Deprecation notices for items to be removed in 24.08 release.
  • Review and update documentation for operators added in 24.05 release.
  • Update to Arm NN documentation for 24.05 release.
  • Update python pillow version.
  • Remove reference to 22.08 release in docker README.
  • Minor change to the printouts in ExecuteNetwork.
  • Enable build of execute network in build tool.
  • Arm NN build tool script update for delegate header and so files.

ABI/API Changes

No API breaking front-end changes have occurred during the implementation of 24.05.

No API breaking back-end changes have occurred during the implementation of 24.05.

Build Dependencies

Tools Supported Version
Git 2.17.1 or later
SCons 2.4.1 (Ubuntu) 2.5.1 (Debian)
Cmake 3.19.0 (Ubuntu) and 3.19.0 (Debian)
Tensorflow 2.15.0
Onnx 1.6.0
Flatbuffer 23.5.26
Protobuf 3.12.0
Android NDK r26b
mapbox/variant 1.2.0
cxxopts 3.1.1
doctest 2.4.6
fmt 8.3.0
ghc 1.3.2
half 1.12.0
mapbox/variant 1.2.0
stb 2.16
xxd 1.10
Loading

Release 24.02

Release 24.02

Choose a tag to compare

View all tags
@KevinARM KevinARM released this 22 Feb 13:27
v24.02
2431f76

Summary

New Features

  • ArmNN to TOSA backend:
    • LeakyRelu Activation support added
    • Quantize support added
    • Maximum support added
    • Split support added
    • Resize Nearest Neighbour support added
  • GpuFsa Backend (Dynamic Fusion)
    • RESIZE/SCALE support added
    • CAST support added
    • POOL2d support added
    • SUB support added
    • ADD support added
    • DEPTHWISE CONVOLUTION 2D support added
    • CONVOLUTION 2D support added
  • Updated to Android NDK r26b.
  • Updated to TensorFlow 2.15.
  • Added optimization to remove reshape operators where possible to CL, Neon and Ref backends.

Bug Fixes

  • Removed implicit sign conversion which could cause compile errors.
  • Fixed memory leak which only happens during profiling and reference Resize workload's align corners is true.
  • Fixed build failures on C++ 14 compilers.
  • Fixed build tool errors when building for Android target.

Other Changes

  • Delegate Unit Tests are now only built for the backends which are being built.
  • Increased end to end testing for two layer and three layer MaxPool2d.
  • In ExecuteNetwork added support to serialize to dot graph for the Arm NN Delegates.

ABI/API Changes

No API breaking front-end changes have occurred during the implementation of 24.02.

No API breaking back-end changes have occurred during the implementation of 24.02.

Note: The minimum API level supported by Arm NN AAR file is 27.

Build Dependencies

Tools Supported Version
Git 2.17.1 or later
SCons 2.4.1 (Ubuntu) 2.5.1 (Debian)
Cmake 3.19.0 (Ubuntu) and 3.19.0 (Debian)
Tensorflow 2.15.0
Onnx 1.6.0
Flatbuffer 23.5.26
Protobuf 3.12.0
Android NDK r26b
mapbox/variant 1.2.0
cxxopts 3.1.1
doctest 2.4.6
fmt 8.3.0
ghc 1.3.2
half 1.12.0
mapbox/variant 1.2.0
stb 2.16
xxd 1.10
Loading

Release 23.11

Release 23.11

Choose a tag to compare

View all tags
@nikraj01 nikraj01 released this 23 Nov 12:08
v23.11
3ba1ff4

Summary

New Features

  • Add support for BROADCAST_TO layer in CpuRef, and remove it when it is followed by ElementWise layer.
  • Add an optimization that fuses Add+Mul+Add+(Optional Relu) layers in CpuAcc.
  • Add support for GELU activation layer in CpuRef, CpuAcc, GpuAcc.
  • Upgrade Arm NN to Tensorflow 2.14
  • Add Signed64 support
  • Add support for Signed64 data type in Cast layer
  • Add a script that evaluates the performance of a network
  • Add ReverseV2 CL and Neon Workloads

TfLite Parser

  • Add support for BROADCAST_TO layer.
  • Add support for GELU activation layer.
  • Updating TfLite parser to ignore VALIDATION: subgraphs

Arm NN Serializer/Deserializer:

  • Add support for GELU activation layer.

Bug Fixes

  • Fix UnidirectionalSequenceLstm
  • Fix weights checking when converting in Support Library
  • Fix unsafe Usages of Memcpy in Armnn
  • Fix for -Wno-sign-conversion in profiling test in gcc9
  • Fix ElementwiseBinary missing from NeonBackend activation fusion optimization
  • Fix Reshape and concat invalid results
  • Remove unnecessary Prelu restriction in quantization
  • Remove unnecessary Square Difference restriction in quantization

Other Changes

  • Update the Arm NN Execute Network app --help
  • Introduce clang-format scripts to ArmNN
  • Remove profiling detail for ConstTensorAsInputs Layers
  • Install missing profiling headers
  • Remove ASSERTs from deserializer code
  • Remove ASSERTs from armnnUtils code
  • Remove ASSERTs from shim code
  • Update documentation to correct C++ version: C++ 17
  • Removing explicit block on non constant bias in NEON CONV2D, allowing Arm Compute Library to handle this.

ABI/API Changes

The following front-end API changes have occurred during the implementation of 23.11 that users should be aware of before upgrading. Due to these changes we have bumped our ARMNN_VERSION to 33.1.0 and our OPAQUE_DELEGATE_VERSION to 2.0.0, following Semantic Versioning guidelines.

Feature SHA Gerrit Review Resultant ABI/API changes
Add ArmNNSettings to Opaque Delegate 3e4b608 https://review.mlplatform.org/c/ml/armnn/+/10493 2 changes have occurred:
  • TfLiteArmnnOpaqueDelegateCreate function has a different signature: Previously: TfLiteOpaqueDelegate* TfLiteArmnnOpaqueDelegateCreate(const void* settings); Now: TfLiteOpaqueDelegate* TfLiteArmnnOpaqueDelegateCreate(armnnDelegate::DelegateOptions options);

  • Size of struct ArmnnDelegatePlugin has increased as a new private member has been added: armnnDelegate::DelegateOptions m_delegateOptions;

No API breaking back-end changes have occurred during the implementation of 23.11

TfLite Delegate

  • Add support for BROADCAST_TO layer to Classic and opaque delegate.
  • Add support for GELU activation layer to classic and opaque delegate.
  • Add ArmNNSettings parser function for Opaque Delegate.
  • Improve logging in the delegate

Bug Fixes

  • Reduce Sum uint8 failing. The fix was to only treat Reduce Prod Uint8 as a special case, as opposite of treating all reduce operations in uint8 as special case (kTfLiteAffineQuantization → kTfLiteNoQuantization)
  • Fix Issue with delegate supporting FP16 models
  • Delegate Test Suite: Fix reshape floating point exception
  • Delegate Test Suite: Fix default scale/offset issue
  • Delegate Test Suite: Fix ElementWise isnan assert
  • Delegate Test Suite: Fix Unspecified dimension while using ShapeInferenceMethod::ValidateOnly
  • Delegate Test Suite: Fix QuantizePerChannel tests
  • Delegate Test Suite: Fix Gather and GatherNd Tests in CpuRef

PyArmNN

  • Update requests version in PyArm NN
  • Bump Pillow version from 9.3.0 to 10.0.1

Build Dependencies

Tools Supported Version
Git 2.17.1 or later
SCons 2.4.1 (Ubuntu) 2.5.1 (Debian)
Cmake 3.19.0 (Ubuntu) and 3.19.0 (Debian)
Tensorflow 2.14.0
Onnx 1.6.0
Flatbuffer 23.5.26
Protobuf 3.12.0
Android NDK r25
mapbox/variant 1.2.0
cxxopts 3.1.1
doctest 2.4.6
fmt 8.3.0
ghc 1.3.2
half 1.12.0
mapbox/variant 1.2.0
stb 2.16
xxd 1.10
Loading

Release 23.08

Release 23.08

Choose a tag to compare

View all tags
@nikraj01 nikraj01 released this 24 Aug 14:03
v23.08
ef0f3e7

Summary

New Features

  • Added support for tile operator in CpuRef, CpuAcc, GpuAcc.
  • Added support for reverse_v2 operator in CpuRef.
  • Added pow and squared_difference as ElementWiseBinary layers in CpuRef, CpuAcc, and GpuAcc.
  • Added squared_difference, power and ceil to TypeUtils.hpp.
  • Enabled dynamic / non-constant bias for:
    • Fully-Connected layers in CpuAcc and GpuAcc
    • 3-D Convolutional layers in CpuAcc and GpuAcc
    • Depthwise Convolutional layers in GpuAcc
  • Added DataType to .dot files for constant layers.
  • Added BinaryElementwiseOperation to .dot files.
  • Added a FileComparisonExecutor to ExecuteNetwork.
  • Added an optional TensorInfo to InputSlot.
  • Added 3D tensors to batch_to_space and space_to_batch for CpuAcc and GpuAcc.
  • Added check for half-precision floating-point infinity values and backend support (FP16).
  • Added backend optimisations to remove reshape layers where possible.
  • Added data layout to tensors in NeonStridedSliceWorkload.
  • Added names to workloads.
  • Enabled slice end-to-end tests in all backends and Signed32 in CpuRef.
  • Added axis to ViewsDescriptor.
  • Refactored ElementBinaryOps to use ElementBinaryLayer.

TfLite Parser

  • Added reverse_v2 support to TFLite Parser.
  • Added tile to TFLite Parser.
  • Added square as mul in the TFLite Parser.
  • Check for options != null before adding fused activation in TFLite Parser.
  • Fixed segfault with some models in the TFLite Parser.

Arm NN Serializer/Deserializer:

  • Added tile to Serialiser/Deserialiser.
  • Added reverse_v2 to Serialiser/Deserialiser.

Support library

  • Added reverse_v2 to Support Library.
  • Added tile to Support Library.
  • Added cache-size check to Support Library.

Bug Fixes

  • Fixed incorrect validation of unidirectional_sequence_lstm on CL and Neon.
  • Fixed issue with ExecuteNetwork when running with TFLite Executor.
  • Replaced asserts with exceptions in Gather reference workload.
  • Introduced fix to explicitly state the correct header to be included (following prior deprecation warning).
  • Fixed XML parsing error in Arm NN Doxygen.
  • Fixed -Werror=unused-result error.
  • Introduced fix for ExecuteNetwork where --output-network-details-only was not working with -T delegate flag.
  • Introduced fix for duplicate definitions in cross-compilation build.
  • Fixed incorrect Concat permutation parameters in Support Library.
  • Removed unnecessary warnings for certain models.
  • Introduced fix to allow SplitterLayer to use overridden TensorInfos correctly.
  • Introduced fix for some cases where the use of sub-tensors was causing an error.
  • Fixed read memory access caused by missing printf arguments.
  • Introduced fix for failing dynamic backend build.
  • Fixed issue where the dimension's specificity didn't match the number of dimensions.
  • Fixed ambiguous method name in BackendHelper.
  • Introduced fix for segmentation fault when an input was directly connected to an output.
  • Fixed uninitialised variable error found during static analysis.
  • Fixed fault in ExecuteNetwork when a model file was passed without an extension.
  • Fixed GitHub issue where search bar was not working in Doxygen documentation.

Other Changes

  • Replaced use of std::filesystem with ghc::filesystem.
  • Refactored ConnectedToSplitterWithMoreThan4Dims function to a more generally useful ConnectedToLayerType function.
  • Customised Doxygen output.
  • Removal of deprecated code due to be removed in 23.08 or earlier:
    • INetworkProperties
    • SubgraphView
    • ILayerSupport
    • WorkloadFactory
  • Updated documentation with new operators in 23.08.
  • Audited the use of armnn_assert.

Known Issues

  • Intermittent issue on Dma Buf memory import on GPU. This is fix in Mali Driver r30p0.
  • There might be performance regressions against v20.08 in Inception v3 using int8 data types on Arm Mali-G77 GPUs. Currently under investigation.

ABI/API Changes

The following front-end API changes have occurred during the implementation of 23.08 that users should be aware of before upgrading. Due to these changes we have bumped our ARMNN_VERSION to 33.0.0, following Semantic Versioning guidelines.

Feature SHA Gerrit Review Resultant ABI/API changes
Removal of Reshape 4cc341c https://review.mlplatform.org/c/ml/armnn/+/9885 4 additional virtual methods added to class IInputSlot:
SetTensorInfo ( TensorInfo ),
GetTensorInfo ( ) const,
IsTensorInfoSet ( ) const,
IsTensorInfoOverridden ( ) const
Front end and reference implementation for TILE 79a06a5 https://review.mlplatform.org/c/ml/armnn/+/9920 LayerType enum has had the LastLayer member value changed from 72 to 74 The member Tile with value 74 has been added
Remove deprecated code 09e4d05 https://review.mlplatform.org/c/ml/armnn/+/9266 2 functions have been removed from the BatchMatMulDescriptor class:
  • BatchMatMulDescriptor::GetAxesNotMul ( struct BatchMatMulDescriptor const& desc, TensorShape const& inputXShape, TensorShape const& inputYShape ) [static]
  • BatchMatMulDescriptor::GetAxesToMul ( struct BatchMatMulDescriptor const& desc, TensorShape const& tensorXShape, TensorShape const& tensorYShape ) [static]
Remove deprecated code (INetworkProperties) b179382 https://review.mlplatform.org/c/ml/armnn/+/10001 INetworkProperties structure has had the following fields removed: m_ExportEnabled m_ImportEnabled
Remove deprecated code (ILayerSupport) 6627703 https://review.mlplatform.org/c/ml/armnn/+/10005 In ArmNN individual virtual IsXXXSupported() functions in the ILayerSupport class have been removed. This functionality has been replaced by a more ABI compliant model whereby an IsLayerSupported() function now accepts a LayerType argument.
In ArmNNTestUtils, removal of 4 virtual methods from class MockLayerSupport:
  • IsAdditionSupported ( TensorInfo const&, TensorInfo const&, TensorInfo const&, Optional<std::__cxx11::basic_string&> ) const
  • IsConvolution2dSupported ( TensorInfo const&, TensorInfo const&, struct Convolution2dDescriptor const&, TensorInfo const&, Optionalconst&, Optional<std::__cxx11::basic_string&> ) const
  • IsInputSupported ( TensorInfo const&, Optional<std::__cxx11::basic_string&> ) const
  • IsOutputSupported ( TensorInfo const&, Optional<std::__cxx11::basic_string&> ) const
Remove deprecated code (WorkloadFactory) 7894ef9 https://review.mlplatform.org/c/ml/armnn/+/10006 In ArmNNTestUtils the MockWorkloadFactory class has had the following virtual method removed: CreateInput ( InputQueueDescriptor const&, struct WorkloadInfo const& ) const
Added Axis to ViewsDescriptor fca5916 https://review.mlplatform.org/c/ml/armnn/+/10073 The size of thte ViewsDescriptor structure has changed from 48 bytes to 56 bytes Field m_IsAxisSet has been added

The following back-end API changes have occurred during the implementation of 23.08 that users should be aware of before upgrading.

Feature SHA Gerrit Review Resultant ABI/API changes
Add names to workloads 7cbe781 https://review.mlplatform.org/c/ml/armnn/+/9983 Pure virtual method GetName ( ) const has been added to IWorkload class. Size of CopyMemGenericWorkload class has been changed from 152 bytes to 184 bytes.
Remove deprecated code (SubgraphView) 0f3e9a0 https://review.mlplatform.org/c/ml/armnn/+/10009 Removed the following methods from SubgraphView:
GetInputSlot, GetIputSlots, GetLayers, GetOutputSlot, GetOutputtSlots.
Resulted in a change to return types for the following methods in SubgraphView as follows:
begin() returns SubgraphView::IConnectableLayerIterator,
begin() const returns SubgraphView::ConstIConnectableIterator,
cbegin() const returns, SubgraphView::ConstIConnectableIterator,
cend() const returns SubgraphView::ConstIConnectableIterator ,
end () returns SubgraphView::IConnectableLayerIterator,
end() const returns SubgraphView::ConstIConnectableIterator
Remove deprecated code (ILayerSupport) a504834 https://review.mlplatform.org/c/ml/armnn/+/10071 Made IWorkloadFactory::CreateWorkload a pure virtual function to force client to write its own implementation.
Fix coverity error on variable initialize b9b9792 https://review.mlplatform.org/c/ml/armnn/+/10075 Adjusted sequence of variable initialization in struct WorkloadInfo:
m_Name
m_WeightsTensorInfo
m_BiasTensorInfo
m_ConvolutionMethod

TfLite Delegate

  • Extended support for 3D tensors (`bat...
Read more
Loading