The name of project has changed to oneDNN. Enable GPU engine to be built
by default which would need clang layer to be included.
Also include two minor fixes to install logic that have been submitted
for review upstream.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Added full text of third party licenses and copyright
notices to LICENSE
88d4573ed5
Release notes can be found here:
https://github.com/intel/mkl-dnn/releases/tag/v1.2
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Added third party license info:
CMake, 3-clause BSD licenseq
Copyright 2000-2019 Kitware, Inc. and Contributors
See full license text in cmake/Copyright.txt
MathJax, Apache License 2.0
Copyright (c) 2009-2018 The MathJax Consortium
See full license text in doc/assets/mathjax/LICENSE
Boost C++ Libraries, Boost Software License, Version 1.0
Copyright 2005-2014 Daniel James.
See full license text in src/common/LICENSE_1_0
Release highlights can be found here:
https://github.com/intel/mkl-dnn/releases/tag/v1.1
Note:
Starting with this release (version 1.1) the library is renamed to DNNL
https://intel.github.io/mkl-dnn/dev_guide_transition_to_dnnl.htmlhttps://intel.github.io/mkl-dnn/dev_guide_transition_to_v1.html
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Otherwise everything after underscore either gets ignored (in case of
devtool) or converted to a hyphen. This ensures that the version is
handled more consistently.
Also add a custom GITTAGREGEX check to check for upstream releases.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Added third party license info:
"ittnotify, 3-clause BSD license
Copyright (c) 2011, Intel Corporation
See full copyright notice and license text in
src/cpu/jit_utils/jitprofiling/LICENSE.BSD"
Release highlights can be found here:
https://github.com/intel/mkl-dnn/releases/tag/v1.0
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
It adds generic recipe for libXCam for extended camera feature, but not limited
in camera. It focuses on image quality improvement and video analysis.
Signed-off-by: Ankit Navik <ankit.tarot@gmail.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Added api-c & test_c_symbols testcases under ptest.
Shipping benchdnn, which is a standalone correctness and performance
benchmark for Intel(R) Math Kernel Library for Deep
Neural Networks (Intel(R) MKL-DNN).
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
The /dev/microcode interface and microcode-ctl utility has
been deprecated in favor of the new kernel
/sys/devices/system/cpu/microcode/reload interface as documented in:
https://github.com/torvalds/linux/blob/master/Documentation/x86/microcode.rst
It expects the microcode binaries to be split out and loaded from
/lib/firmware, eg:
/lib/firmware/intel-ucode/06-01-01
/lib/firmware/intel-ucode/06-01-02
/lib/firmware/intel-ucode/06-01-06
/lib/firmware/intel-ucode/06-01-07
/lib/firmware/intel-ucode/06-01-09
...
This change does not affect the earlyfw cpio generated by inte-ucode.
Signed-off-by: Yong, Jonathan <jonathan.yong@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
For GNU* Compiler Collection version 5 and newer
the default options are `-march=native -mtune=native`,
which should not happen in cross compilation environment.
ARCH_OPT_FLAGS=\"\" does not allow to use host machine
instructions.
For more information, please check:
http://intel.github.io/mkl-dnn/dev_guide_build_options.html
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Include the microcode from caveats as well since all kernels supported
have those patches. Also point to the new git repo and corrected
license.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
This fork of zlib has a number of IA-specific improvements and is
noticably faster when running on Intel hardware.
As this is a relatively minor fork of zlib, include the oe-core recipe
and override where appropriate. This ensures that we still generate
the ptest package for example.
Signed-off-by: Ross Burton <ross.burton@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
A list of third party components added to the LICENSE.
LICENSE changes:
"""
Intel MKL-DNN includes components with separate copyright
notices and license terms.
XByak, 3-clause BSD license
Copyright (c) 2007 MITSUNARI Shigeo
See full copyright notice and license text in src/cpu/xbyak/COPYRIGHT
gtest, 3-clause BSD license
Copyright 2008, Google Inc.
See full copyright notice and license text in tests/gtests/gtest/LICENSE
"""
This release contains performance optimizations, new functionality,
usability improvements and bug fixes.
For more details, please check:
https://github.com/intel/mkl-dnn/releases
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Add generic recipe for Intel(R) Math Kernel Library for Deep Neural
Networks. The library accelerates deep-learning applications and
frameworks on Intel architecture.
Signed-off-by: Ankit Navik <ankit.tarot@gmail.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
It's not being maintained anymore and the scripts have not been kept in
sync with upstream for quite some time.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Point to the the license from layer now that text .dat isn't supplied. And,
generate cpio from binary files.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
The LIC_FILES_CHKSUM also needed to be updated, as the copyright
added the year 2018.
Signed-off-by: California Sullivan <california.l.sullivan@intel.com>
Since Quark is getting depercated remove reference and WKS file
Signed-off-by: Saul Wold <sgw@linux.intel.com>
Signed-off-by: California Sullivan <california.l.sullivan@intel.com>
Remove the concept of the common directory and move all the recipes-* dirs
to the top level as a normal layer would be. layer.conf is updated appropriately
Signed-off-by: Saul Wold <sgw@linux.intel.com>
