linux/meta-intel.git/recipes-core, branch 2.8_M2

intel-microcode: fix upstream check

2019-07-04T09:39:29+00:00

There could be zero or more characaters at the end of version string. Signed-off-by: Anuj Mittal

mkl-dnn: add ptest

2019-07-04T02:17:36+00:00

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 Signed-off-by: Anuj Mittal

intel-microcode: fix microcode loading on newer kernels

2019-07-04T02:16:09+00:00

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 Signed-off-by: Anuj Mittal

mkl-dnn: do not use host machine instructions

2019-07-01T02:15:20+00:00

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 Signed-off-by: Anuj Mittal

intel-microcode: upgrade 20190514a -> 20190618

2019-06-19T11:53:43+00:00

For changes in this version, see: https://github.com/intel/Intel-Linux-Processor-Microcode-Data-Files/blob/940d904b7272edd689a5f0eef9dee09c13746748/releasenote Signed-off-by: Anuj Mittal

mkl-dnn: update SRCREV to fix GCC9 build failure

2019-06-07T03:02:18+00:00

Fix for GCC9 build error is backported from master branch to release branch rls-v0.19. Patch Link: https://github.com/intel/mkl-dnn/commit/027de7603662a569366e15132ac80298902b96b8 Signed-off-by: Naveen Saini Signed-off-by: Anuj Mittal

mkl-dnn: upgrade 0.18.1 -> 0.19

2019-06-01T08:00:44+00:00

For more details, please check: https://github.com/intel/mkl-dnn/releases Signed-off-by: Naveen Saini Signed-off-by: Anuj Mittal

intel-microcode: fix upstream release checking

2019-05-24T02:09:39+00:00

There could be a character to signify minor changes for the same microcode at the end. Signed-off-by: Anuj Mittal

intel-microcode: upgrade to 20190514a

2019-05-21T09:31:51+00:00

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

zlib-intel: add zlib fork with IA-specific optimisations

2019-05-06T04:03:14+00:00

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 Signed-off-by: Anuj Mittal