armnn-21.05-bp153.2.3.1

- 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
- Add patch to fix include path:
  * armnn-fix-include.patch
- 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
- Drop upstream patch:
  * c5c40fe.diff

- Fix instalaltion of cmake files with an upstream patch:
  * c5c40fe.diff

- Backport patch to fix tflite parser when built against
  tensorflow 2.4:
  * 96beb97.diff

- Update to 20.11:
  * Changelog: https://github.com/ARM-software/armnn/releases/tag/v20.11
- Refresh patch to handle boost::variant to mapbox::util::variant update:
  * 0006-armnn-mobilenet-test-example.patch

- 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
- Refresh patch:
  * 0005-add-armnn-mobilenet-test-example.patch
- Drop upstream patch:
  * armnn-fix-catch.patch
- 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

- Unify Leap/SLE options
- Update to 20.05:
  * Changelog: https://github.com/ARM-software/armnn/releases/tag/v20.05
- Drop upstream patch:
  * armnn-enable-use-of-arm-compute-shared-library.patch
- Refresh patch:
  * 0003-add-more-test-command-line-arguments.patch
- Add new patch to fix build with gcc10:
  * armnn-fix-catch.patch
- 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

- Disable RPATH to fix build on Leap15.2/SLE15SP2

- Add '-Wno-error=deprecated-declarations' to fix build with latest
  protobuf 3.11.x (Tumbleweed)
  https://github.com/ARM-software/armnn/issues/366
- Use python-onnx package instead of python-onnx-devel, since it
  is now a single package.

- Fix build on Leap 15.2

- Update to 20.02:
  * Changelog: https://github.com/ARM-software/armnn/releases/tag/v20.02
  * Drop upstream patch:
  - armnn-fix_include.patch
  * Refresh patch:
  - 0006-armnn-mobilenet-test-example.patch
  * Replace downstream patch:
  - 0007-enable-use-of-arm-compute-shared-library.patch
    by upstream patch:
  - armnn-enable-use-of-arm-compute-shared-library.patch
  * Add 'vim' as BuildRequires since it needs 'xxd' tool
- Use TensorFlow 2 also on Leap 15.2 / SLE15SP2

- Use Tensorflow 2.x only for Tumbleweed, as TensorFlow2 is not
  available in Leap 15.2
- Skip some tests if TensorFlow < 1.14 is used

- Enable ONNX on Leap 15.2

- Use tensorflow2 as armnn 19.11 now requires TensorFlow >= 1.14

- Disable ArmnnConverter and ArmnnQuantizer packaging by default
  as it requires libQuantizer.so to be packaged, which is not yet

- Package ArmnnConverter and ArmnnQuantizer

- ExcludeArch %ix86: Parts of the build deps (tensorflow/bazel) are
  not supported on ix86.

- Update to 19.11:
  * Changelog: https://github.com/ARM-software/armnn/releases/tag/v19.11
- Remove upstreamed patches:
  * armnn-generate-versioned-library.patch
  * armnn-fix_boost.patch
  * armnn-fix_arm32_dep.patch
  * armnn-fix_arm32.patch
- Add patch to fix include:
  * armnn-fix_include.patch

- tensorflow-devel package now includes *.pb.* files, so
  remove TensorFlow parser build workaround:
  * armnn-fix_tensorflow_link.patch

- Add a conflict between armnn-extratests and armnn-opencl-extratests

- Add a conflict between armnn-devel and armnn-opencl-devel

- Enable ONNX for Tumbleweed

- Add downstream ArmnnExamples in a separate '-extratests' package
  with patches:
  * 0003-add-more-test-command-line-arguments.patch
  * 0005-add-armnn-mobilenet-test-example.patch
  * 0006-armnn-mobilenet-test-example.patch
  * 0007-enable-use-of-arm-compute-shared-library.patch
  * 0009-command-line-options-for-video-port-selection.patch
  * 0010-armnnexamples-update-for-19.08-modifications.patch
- Fix build when extratests are disabled
  * armnn-fix_find_opencv.patch

- Replace patch with an upstreamable version:
  * armnn-generate-versioned-library.patch

- Add ONNX Parser support (disabled by default as there is no
  official ONNX package yet)

- Re-enable Tensorflow on Tumbleweed as boo#1151150 is now fixed

- Update _constraints