Community
cancel
Showing results for 
Search instead for 
Did you mean: 
Highlighted
Moderator
36 Views

oneAPI 2021.1 Beta09 release is now available!

Release 9 of Intel® oneAPI(Beta) is now live.

Highlights include
* Improved performance and stability across all compilers, libraries, and tools in preparation for the gold product release coming up later this year.


Additional details
* Intel® AI Analytics Toolkit introduces Intel Low Precision Optimization Tool, an unified low-precision inference interface that supports multiple deep learning frameworks. Easily convert FP32 models to int8 or Bfloat16 and take advantage of accuracy-driven tuning strategies, along with optimizations for performance, model size and memory footprint.

* Intel® Optimization for PyTorch now adds bindings to Intel® oneAPI Collective Communications Library (oneCCL) for efficient distributed training on CPUs. It also now supports automatic mixed precision for model data types.

* New Technical Preview capabilities in Intel® Advisor including user interface workflows and toolbars, incorporating Roofline analysis for GPUs and Offload Advisor, as well as data transfer optimization recommendations in Offload Advisor.

* Find the module causing performance killing I/O writes using Intel® VTune™ Profiler’s improved I/O analysis that identifies where slow MMIO writes are made.

* Less guessing is needed when optimizing FPGA software performance as developers can now get stall and data transfer data for each compute unit in the FPGA using Intel® VTune™ Profiler.

* Intel® MPI Library introduces initial GPU programming support, as well as, enabling connecting of independent MPI jobs on Mellanox fabric.

* Intel® oneAPI Math Kernel Library (oneMKL) adds DPC++ functions for CPU and GPU including RNG move operators and LAPACK buffer and pointer based (Unified Shared Memory) interfaces.

* Intel® oneAPI Video Processing Library (oneVPL) adds H.264 & MJPEG SW decode and encode, video pre-processing including resize, color conversion, and crop functions, and support for internally allocated buffers

* Intel® Distribution for Python adds initial Windows support for automatic GPU offload of data parallel kernels inside Numba functions and multi-threading for scikit-image transform functions and filters optimizations.

Download Intel® oneAPI Toolkits(Beta) TODAY!

Labels (2)
0 Kudos
0 Replies