File armnn.changes of Package armnn.16481
-------------------------------------------------------------------
Tue May 25 06:49:01 UTC 2021 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Fix libarmnnOnnxParser version
-------------------------------------------------------------------
Fri May 21 06:55:48 UTC 2021 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- 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
-------------------------------------------------------------------
Mon Mar 29 12:17:08 UTC 2021 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Update to 21.02:
* Changelog: https://github.com/ARM-software/armnn/releases/tag/v21.02
- Drop upstream patch:
* c5c40fe.diff
-------------------------------------------------------------------
Mon Feb 15 09:48:06 UTC 2021 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Fix instalaltion of cmake files with an upstream patch:
* c5c40fe.diff
-------------------------------------------------------------------
Mon Jan 25 08:21:39 UTC 2021 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Backport patch to fix tflite parser when built against
tensorflow 2.4:
* 96beb97.diff
-------------------------------------------------------------------
Wed Dec 9 14:33:19 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- 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
-------------------------------------------------------------------
Fri Sep 4 16:07:09 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Add python support, disabled for now as it does not install
files atm
-------------------------------------------------------------------
Fri Sep 4 14:56:36 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Package libtimelineDecoderJson
-------------------------------------------------------------------
Thu Sep 3 11:18:40 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- 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
-------------------------------------------------------------------
Wed Jun 17 07:19:10 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Build only where ComputeLibrary is built:
aarch64 armv7 and x86_64
-------------------------------------------------------------------
Thu Jun 4 09:51:23 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- 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
-------------------------------------------------------------------
Thu May 28 15:10:11 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Apply boost link fixes only for armnn_extra_tests
- Apply patches for armnn_extra_tests only when
armnn_extra_tests is built
-------------------------------------------------------------------
Tue Mar 31 15:23:29 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Disable RPATH to fix build on Leap15.2/SLE15SP2
-------------------------------------------------------------------
Tue Mar 24 14:01:29 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- 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.
-------------------------------------------------------------------
Wed Mar 11 08:41:20 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Fix build on Leap 15.2
-------------------------------------------------------------------
Mon Mar 9 17:47:42 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- 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
-------------------------------------------------------------------
Mon Feb 10 13:01:53 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- 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
-------------------------------------------------------------------
Tue Jan 28 12:33:19 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Enable ONNX on Leap 15.2
-------------------------------------------------------------------
Tue Jan 28 09:48:55 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Use tensorflow2 as armnn 19.11 now requires TensorFlow >= 1.14
-------------------------------------------------------------------
Mon Jan 20 15:21:09 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Disable ArmnnConverter and ArmnnQuantizer packaging by default
as it requires libQuantizer.so to be packaged, which is not yet
-------------------------------------------------------------------
Tue Jan 14 13:07:58 UTC 2020 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Package ArmnnConverter and ArmnnQuantizer
-------------------------------------------------------------------
Tue Jan 14 11:59:14 UTC 2020 - Dominique Leuenberger <dimstar@opensuse.org>
- ExcludeArch %ix86: Parts of the build deps (tensorflow/bazel) are
not supported on ix86.
-------------------------------------------------------------------
Fri Dec 6 13:45:57 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- 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
-------------------------------------------------------------------
Mon Nov 25 14:16:29 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- tensorflow-devel package now includes *.pb.* files, so
remove TensorFlow parser build workaround:
* armnn-fix_tensorflow_link.patch
-------------------------------------------------------------------
Mon Oct 28 15:38:27 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Add a conflict between armnn-extratests and armnn-opencl-extratests
-------------------------------------------------------------------
Mon Oct 28 13:06:56 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Add a conflict between armnn-devel and armnn-opencl-devel
-------------------------------------------------------------------
Mon Oct 28 09:56:16 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Enable ONNX for Tumbleweed
-------------------------------------------------------------------
Thu Oct 17 06:57:00 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- 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
-------------------------------------------------------------------
Mon Oct 7 13:00:59 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Replace patch with an upstreamable version:
* armnn-generate-versioned-library.patch
-------------------------------------------------------------------
Tue Oct 1 19:04:50 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Add ONNX Parser support (disabled by default as there is no
official ONNX package yet)
-------------------------------------------------------------------
Tue Oct 1 14:30:13 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Re-enable Tensorflow on Tumbleweed as boo#1151150 is now fixed
-------------------------------------------------------------------
Thu Sep 19 07:21:48 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Update _constraints
-------------------------------------------------------------------
Wed Sep 18 12:26:55 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Enable openCL only on a separate flavor as runtime requires
libOpenCL.so, libGLES_mali.so, or libmali.so
-------------------------------------------------------------------
Wed Sep 18 11:53:30 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Enable openCL support
- Disable UnitTests when openCL support is enabled as it fails
on OBS workers
-------------------------------------------------------------------
Wed Sep 18 09:57:39 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Add patches to make UnitTests to pass on armv7:
* armnn-fix_arm32.patch
* armnn-fix_arm32_dep.patch
-------------------------------------------------------------------
Thu Sep 5 11:22:41 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Disable TensorFlow as on 15.1 only x86_64 succeed and on TW we
have incompatibility with protobuf (3.8.0 in TW and
Tensorflow uses 3.6.1 internally) - boo#1151150
-------------------------------------------------------------------
Thu Sep 5 07:25:16 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Update to 19.08:
- Changelog: https://github.com/ARM-software/armnn/releases/tag/v19.08
- Remove upstreamed patch:
* armnn-fix_quantizer_link.patch
* armnn-fix_caffe_parser_with_new_protobuf.patch
- Refresh patch:
* armnn-generate-versioned-library.patch
- Drop patches not needed anymore:
* armnn-remove_broken_std_move.patch
* armnn-fix_build_with_gcc9.patch
-------------------------------------------------------------------
Wed Sep 4 16:15:58 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Disable LTO until lto link is fixed
https://github.com/ARM-software/armnn/issues/251
-------------------------------------------------------------------
Tue Jun 18 11:54:48 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Fix build in Tumbleweed, with latest protobuf:
* armnn-fix_caffe_parser_with_new_protobuf.patch
-------------------------------------------------------------------
Tue Jun 11 14:17:34 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Enable Tensorflow parser
- Fix link with Tensorflow:
* armnn-fix_tensorflow_link.patch
-------------------------------------------------------------------
Wed Jun 5 09:07:12 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Build and package libarmnnTfLiteParser
- Fix libarmnnQuantizer build with:
* armnn-fix_quantizer_link.patch
-------------------------------------------------------------------
Tue Jun 4 09:22:24 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Add _constraints to avoid OOM errors
-------------------------------------------------------------------
Mon Jun 3 11:40:47 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Update to 19.05:
- Changelog: https://github.com/ARM-software/armnn/releases/tag/v19.05
- Remove upstreamed patch:
* armnn-fix_stb_include.patch
- Rebase patch:
* armnn-generate-versioned-library.patch
- Update patch:
* armnn-remove_broken_std_move.patch
-------------------------------------------------------------------
Mon Jun 3 09:15:25 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Fix build on Tumbleweed with:
* armnn-fix_build_with_gcc9.patch
-------------------------------------------------------------------
Wed May 29 15:19:15 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Fix build on Tumbleweed with:
* armnn-remove_broken_std_move.patch
-------------------------------------------------------------------
Wed May 29 08:12:43 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Call ldconfig in post/postun for libarmnnCaffeParser
-------------------------------------------------------------------
Mon May 27 05:42:06 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Enable and fix Caffe parser
- Use %cmake_build macro
-------------------------------------------------------------------
Fri Apr 19 10:11:29 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Add compute_cl option, disabled by default since check fails as
no openCL are enabled in OBS
-------------------------------------------------------------------
Thu Apr 11 09:35:54 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Split libarmnn and libarmnnSerializer to separate packages
-------------------------------------------------------------------
Thu Apr 11 07:38:23 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Add patch to have versionned libs:
* armnn-generate-versioned-library.patch
- Package versionned libs
-------------------------------------------------------------------
Tue Apr 9 16:18:55 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Enable NEON backend on AArch64
- Add patch to enable use of shared lib for ComputeLibrary:
* 0007-enable-use-of-arm-compute-shared-library.patch
-------------------------------------------------------------------
Tue Mar 26 14:29:39 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Update to 19.02
- Remove upstreamed patch:
* armnn-fix_catching_polymorphic_type.patch
-------------------------------------------------------------------
Thu Jan 17 12:51:41 UTC 2019 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Update to 18.11
- Add patch to fix build:
* armnn-fix_catching_polymorphic_type.patch
* armnn-fix_boost.patch
* armnn-fix_stb_include.patch
-------------------------------------------------------------------
Thu Sep 13 12:51:53 UTC 2018 - Guillaume GARDET <guillaume.gardet@opensuse.org>
- Initial version 18.08
