openSUSE Recommended Update: Recommended update for ComputeLibrary, armnn ______________________________________________________________________________ Announcement ID: openSUSE-RU-2022:10110-1 Rating: moderate References: Affected Products: openSUSE Backports SLE-15-SP3 ______________________________________________________________________________ An update that has 0 recommended fixes can now be installed. Description: This update for ComputeLibrary, armnn fixes the following issues: ComputeLibrary was updated to 21.05: * Public major release * Documentation (API, changelogs, build guide, contribution guide, errata, etc.) available here: https://arm-software.github.io/ComputeLibrary/v21.05/ - Package separately libarm_compute_core and libarm_compute_graph - Update to 21.02: * Public major release * Documentation (API, changelogs, build guide, contribution guide, errata, etc.) available here: https://arm-software.github.io/ComputeLibrary/v21.02/ - Update to 20.11: * Public major release * Deprecation notice: Deprecated GLES functions and kernels Deprecated Neon and OpenCL Computer Vision functions * Documentation (API, changelogs, build guide, contribution guide, errata, etc.) available here: https://arm-software.github.io/ComputeLibrary/v20.11/ - Update to 20.08: * Public major release * Documentation (API, changelogs, build guide, contribution guide, errata, etc.) available here: https://arm-software.github.io/ComputeLibrary/v20.08/ - Update to 20.05: * Public major release * Documentation (API, changelogs, build guide, contribution guide, errata, etc.) available here: https://arm-software.github.io/ComputeLibrary/v20.05/ - Fix libarmnnOnnxParser version - Update to 21.05: * Changelog: https://github.com/ARM-software/armnn/releases/tag/v21.05 * Main changes: - new capabilities to allow users attain higher performance by: * Making the Arm NN Core thread safe opening the possibility of running multiple inferences on the same model in parallel software threads. * Allowing graphs on the GPU backend import their input and output buffers either from correctly aligned main memory or from kernel memory exposed as a dma_buf, thus reducing memory usage and saving the time involved in copying data into and out of the GPU memory space. - In addition to this, support was added to allow the MobileBERT network to be parsed and run. - Finally three deprecated components: the Tensorflow Parser, the Caffe Parser and the Arm NN Quantizer tool, were removed - Disable armnn-extratests as it fails to build with current version - Update to 21.02: * Changelog: https://github.com/ARM-software/armnn/releases/tag/v21.02 - Update to 20.11: * Changelog: https://github.com/ARM-software/armnn/releases/tag/v20.11 - Add python support, disabled for now as it does not install files atm - Package libtimelineDecoderJson - Update to 20.08: * Changelog: https://github.com/ARM-software/armnn/releases/tag/v20.08 - Disable ONNX on Tumbleweed since there is a compatibility issue with ONNX 1.7.0, see: https://github.com/ARM-software/armnn/issues/419 - Build only where ComputeLibrary is built: aarch64 armv7 and x86_64 - Update to 20.05: * Changelog: https://github.com/ARM-software/armnn/releases/tag/v20.05 - Package new libtimelineDecode and libarmnnBasePipeServer - Apply boost link fixes only for armnn_extra_tests - Apply patches for armnn_extra_tests only when armnn_extra_tests is built Patch Instructions: To install this openSUSE Recommended Update use the SUSE recommended installation methods like YaST online_update or "zypper patch". Alternatively you can run the command listed for your product: - openSUSE Backports SLE-15-SP3: zypper in -t patch openSUSE-2022-10110=1 Package List: - openSUSE Backports SLE-15-SP3 (aarch64 x86_64): ComputeLibrary-21.05-bp153.2.3.5 ComputeLibrary-devel-21.05-bp153.2.3.5 ComputeLibrary-sample-data-21.05-bp153.2.3.5 armnn-21.05-bp153.2.3.1 armnn-debuginfo-21.05-bp153.2.3.1 armnn-debugsource-21.05-bp153.2.3.1 armnn-devel-21.05-bp153.2.3.1 armnn-opencl-21.05-bp153.2.3.10 armnn-opencl-debuginfo-21.05-bp153.2.3.10 armnn-opencl-debugsource-21.05-bp153.2.3.10 armnn-opencl-devel-21.05-bp153.2.3.10 libarm_compute23-21.05-bp153.2.3.5 libarm_compute_core23-21.05-bp153.2.3.5 libarm_compute_graph23-21.05-bp153.2.3.5 libarmnn25-21.05-bp153.2.3.1 libarmnn25-debuginfo-21.05-bp153.2.3.1 libarmnn25-opencl-21.05-bp153.2.3.10 libarmnn25-opencl-debuginfo-21.05-bp153.2.3.10 libarmnnBasePipeServer25-21.05-bp153.2.3.1 libarmnnBasePipeServer25-debuginfo-21.05-bp153.2.3.1 libarmnnBasePipeServer25-opencl-21.05-bp153.2.3.10 libarmnnBasePipeServer25-opencl-debuginfo-21.05-bp153.2.3.10 libarmnnOnnxParser24-21.05-bp153.2.3.1 libarmnnOnnxParser24-debuginfo-21.05-bp153.2.3.1 libarmnnOnnxParser24-opencl-21.05-bp153.2.3.10 libarmnnOnnxParser24-opencl-debuginfo-21.05-bp153.2.3.10 libarmnnSerializer25-21.05-bp153.2.3.1 libarmnnSerializer25-debuginfo-21.05-bp153.2.3.1 libarmnnSerializer25-opencl-21.05-bp153.2.3.10 libarmnnSerializer25-opencl-debuginfo-21.05-bp153.2.3.10 libarmnnTfLiteParser24-21.05-bp153.2.3.1 libarmnnTfLiteParser24-debuginfo-21.05-bp153.2.3.1 libarmnnTfLiteParser24-opencl-21.05-bp153.2.3.10 libarmnnTfLiteParser24-opencl-debuginfo-21.05-bp153.2.3.10 libtimelineDecoder25-21.05-bp153.2.3.1 libtimelineDecoder25-debuginfo-21.05-bp153.2.3.1 libtimelineDecoder25-opencl-21.05-bp153.2.3.10 libtimelineDecoder25-opencl-debuginfo-21.05-bp153.2.3.10 libtimelineDecoderJson25-21.05-bp153.2.3.1 libtimelineDecoderJson25-debuginfo-21.05-bp153.2.3.1 libtimelineDecoderJson25-opencl-21.05-bp153.2.3.10 libtimelineDecoderJson25-opencl-debuginfo-21.05-bp153.2.3.10 References: