*Fixed performance regression in binary primitive with broadcast (b972174, ff75122).
*Fixed issue with SYCL device properties initialization (cabc5ca, 095f13e).
*Fixed issue in matmul primitive with zero points (3157354).
*Fixed segmentation fault in depthwise convolution primitive for shapes with huge spatial size for processors with Intel AVX-512 support (6834764, 1d2addc).
*Fixed issue in forward convolution primitive for processors with Intel AVX2 support (d691137).
*Fixed performance regression on GPUs with SYCL runtime (d8364e5).
Signed-off-by: ezhilarasan s <ezhilarasanx.s@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
*Fixed compilation errors with C++20.
*Fixed CL_OUT_OF_RESOURCES issue for Radix sort algorithm executed on CPU devices.
*Fixed crashes in exclusive_scan_by_segment, inclusive_scan_by_segment, reduce_by_segment algorithms applied to
device-allocated USM.
Signed-off-by: ezhilarasan s <ezhilarasax.s@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Backport a patch to fix issues while building with gcc 11.2.
Signed-off-by: Yew, Chang Ching <chang.ching.yew@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
New in This Release
===================
* Updated mfxvideo++.h to remove deprecation warnings
* Sample* tools select oneVPL 2.x APIs by default
* Sample* tool update to support new GPU features
* Updates to C++ & Python previews:
* AV1 extension buffer support
* new property interface
* Targets Python 3.7
* Updated documentation and build for OpenVINO interop sample
* The libmfx.dll and libmfx.so.2021.1.11 libraries, that had been renamed to libvpl.* have been removed
Release notes:
https://github.com/oneapi-src/oneVPL/releases/tag/v2022.0.0
Signed-off-by: Yew, Chang Ching <chang.ching.yew@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Commit cba66dfb7b ("intel-microcode: fix microcode loading on newer
kernels") effectively disabled microcode filtering for intel-microcode
package.
Add the missing filter parameter to iucode_tool command to install only
necessary files. Do not generate microcode bin file in compile step as
it is no longer needed.
Signed-off-by: Tomasz Moń <tomasz.mon@camlingroup.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
The recipe for Intel OneAPI IPP library version 2021.5.1.
IPP is an extensive library of ready-to-use, domain-specific functions
that are highly optimized for diverse Intel architectures.
Signed-off-by: Mariia Vtiurina <mariia.vtiurina@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Slim Bootloader is an open-source boot firmware running on Intel x86
architecture.
Currently it supports qemu, apl(Apollo Lake), cfl(Coffee Lake),
cml(Comet Lake), tgl(Tiger Lake), and ehl(Elkhart Lake). You can set
"SLIMBOOT_TARGET" in .bb file or .bbappend file to specify or add the
target firmware you want, for example: SLIMBOOT_TARGET = "qemu apl".
The default target is qemu.
Generated firmware and security keys are installed in build directory:
image
`-- usr
`-- libexec
`-- slimboot
|-- Outputs
| |-- qemu
| |-- apl
| `-- cfl
`-- keys
Boot firmware for qemu can be used by command:
"qemu-system-x86_64 -machine q35 -nographic -serial mon:stdio -pflash
SlimBootloader.bin"
Other boot firmware for real hardware cannot be programmed directly to
flash, please refer to https://slimbootloader.github.io/index.html for
more instructions.
Signed-off-by: Yongxin Liu <yongxin.liu@windriver.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Update kernel config as well.
Backported patch to fix 32-bit compilation failure.
32-bit compilation failure log:
build/tmp/work-shared/intel-core2-32/kernel-source/include/linux/io-mapping.h:88:16: error: implicit declaration of function '__iomap_local_pfn_prot'; did you mean '__kmap_local_pfn_prot'? [-Werror=implicit-function-declaration]
| 88 | return __iomap_local_pfn_prot(PHYS_PFN(phys_addr), mapping->prot);
| | ^~~~~~~~~~~~~~~~~~~~~~
| | __kmap_local_pfn_prot
| build/tmp/work-shared/intel-core2-32/kernel-source/include/linux/io-mapping.h:88:16: warning: returning 'int' from a function with return type 'void *' makes pointer from integer without a cast [-Wint-conversion]
| 88 | return __iomap_local_pfn_prot(PHYS_PFN(phys_addr), mapping->prot);
| | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
The patch fixes the build when OpenSSL 3.0 is used. We also disable
errors on deprecations as the code uses a good amount of them that look
to be harmless.
Signed-off-by: Andrei Gherzan <andrei.gherzan@huawei.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
It is not required to disable bsp config audit with 5.15 as
warning causing patch is already part ot it.
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Default kernel is 5.15 now and this doesn't build with 5.15 so exclude
from world to prevent builds from failing.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Intel® Integrated Performance Primitives (Intel® IPP) Cryptography
is a secure, fast and lightweight library of building blocks for cryptography,
highly-optimized for various Intel® CPUs.
Signed-off by: Andrey Latyshev <andrey.latyshev@intel.com>
Signed-off-by: Mariia Vtiurina <mariia.vtiurina@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
New LTS 5.15 is already added, so time to drop 5.4 support
Drop linux-intel-rt/5.4 too.
Drop cfg which is not required for LTS 5.10 & 5.15.
Ref:
eb83479e18
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Build 5.10 with poky-altcfg as kenrel 5.4 support is going to drop
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Release notes:
Lights can be now part of OSPGroup and thus instanced like
geometries and volumes and thus lights also support motion blur
(with the path tracer)
Add cylinder light (with solid area sampling)
Add support for rolling shutter of cameras
Add support for quaternion motion blur for instance and camera to
allow for smoothly interpolated rotations
Fix illumination from emissive quad meshes
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Release notes:
vklExamples improvements: asynchronous rendering, multiple viewports, docking, and more
Fixed bug in openvkl_utility_vdb which could lead to crashes when creating VDB volumes with temporally constant tiles
Superbuild updates to latest versions of dependencies
Minimum rkcommon version is now 1.8.0
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
