Language changes:
- Added support for non-type template parameters. Uniform integers
and enums can be used now as template parameters.
- Added dot product functions for unsigned and signed int8 and int16
types. They leverage AVX-VNNI and AVX512-VNNI instructions if
supported by targets (docs).
- Added macro definitions for numeric limits.
New targets:
- avx2vnni-i32x4, avx2vnni-i32x8, avx2vnni-i32x16 with AVX-VNNI
instruction support,
- avx512icl-x4, avx512icl-x8, avx512icl-x16, avx512icl-x32 and
avx512icl-x64 with AVX512-VNNI instruction support.
Code generation:
- Fixed generation of code for GPU when unnecessary vectorized
instruction are used during address arithmetic, e.g., for
accessing fields of varying structures (#2846).
- Improved generated code for cases when foreach loop iteration
domain is less than the target width (#2836 ).
Compiler switches behavior:
- --pic command line flag now corresponds to the -fpic flag of Clang
and GCC, whereas the newly introduced --PIC corresponds to -fPIC.
Bug fixes:
- The implementation of round standard library function was aligned
across all targets. It may potentially affect the results of the
code that uses this function for the following targets: avx2-i16x16,
avx2-i8x32 and all avx512 targets (#2793).
- Fixed cases when unwind info were not generated for functions.
This impacted debugging and profiling on Windows (#2842).
- Fixed broken targets sse4-i8xN and avx2-i8xN (#2800).
More details:
https://github.com/ispc/ispc/releases/tag/v1.24.0
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
This recipe enables User Mode Driver for Intel® NPU device.
Intel® NPU device is an AI inference accelerator integrated
with Intel client CPUs, starting from Intel® Core™ Ultra generation
of CPUs (formerly known as Meteor Lake).
It enables energy-efficient execution of artificial neural network tasks.
https://github.com/intel/linux-npu-driver
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
* Allows compilation with LLVM16.
* ISPC_NO_DUMPS is no longer an option and ISPC_PS4_TARGET has been
renamed.
* Libraries now have proper so versions so packaging tweaks are no
longer required.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
* Release Notes:
https://github.com/ispc/ispc/releases/tag/v1.20.0
* Drop already merged patches:
0001-CMakeLists.txt-allow-to-pick-llvm-config-from-usr-bi.patch
0001-CMakeLists.txt-link-with-libclang-cpp-library-instea.patch
ffc75e464ff2b8fce7dbf74f1846ebd0852bc6f9.patch
* Fix packaging to ensure libispcrt is packaged correctly.
* ISPC runtime with CPU support can either be enabled with OpenMP or
TBB. TBB is enabled by default that needs meta-oe to be included.
Signed-off-by: Teoh Suh Haw <suh.haw.teoh@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Currently empty level-zero-dev package is being generated, which
has dependency on level-zero package.
On enabling 'dev-pkgs' in IMAGE_FEATURES, install level-zero-dev package, which throws
dependency conflict error.
Problem: conflicting requests
- nothing provides level-zero = 1.5.4-r0 needed by level-zero-dev-1.5.4-r0.corei7_64
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Add branch name explicitly to SRC_URI where it's not defined and switch
to using https protocol for Github projects.
The change was made using convert_srcuri script for OE-Core.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Release notes:
https://github.com/oneapi-src/level-zero/releases
Highlights:
- Added support for Level Zero Specification v1.2
- Fixed a bug that resulted in zeInit failing when multiple drivers
are discovered and one of them fails to load.
- Note: API's introduced in v1.2 spec can only be traced with the new
tracing layer implementation. Driver tracing APIs are deprecated.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
The oneAPI Level-Zero Application Programming Interface (API) is to
provide direct-to-metal interfaces to offload accelerator devices.
Its programming interface can be tailored to any device needs and
can be adapted to support broader set of languages features such as
function pointers, virtual functions, unified memory, and I/O capabilities.
It contains following components of oneAPI:
-> Copies of the Level Zero Specification API C/C++ header files
-> Level Zero Loader
-> Level Zero Validation Layer
It should be installed using:
IMAGE_INSTALL_append = " level-zero-headers level-zero-loader"
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
