Intel have released the latest version of oneAPI, 2022.1.
The new toolkits have over 900 new features, capabilities, and improvements, helping your customers deliver high-performance, cross-architecture applications, and solutions.
Key highlights of the update are:
- Intel® oneAPI DPC++/C++ Compiler becomes the world’s first LLVM-based, unified compiler; it implements C++, SYCL, and Fortran to improve programming productivity for CPUs and GPUs.
- Data-parallel Python technologies enable accelerated computing on CPUs and GPUs.
- Intel® DPC++ Compatibility Tool now automatically migrates 90%-95% of CUDA cde to SYCL/DPC++.1
Advanced Development Productivity
- Intel® VTune™ Profiler flame graph display improves the ability to visualise performance hotspots.
- Intel® Advisor’s accelerator performance modeling estimates the benefits of offloading to a GPU before making code changes.
- New Intel® oneAPI Rendering Toolkit features including cone telemetry, auxiliary feature denoising, and FP16 support provide more robust shapes and shorten rendering times. Additional support for upcoming Intel® Xe GPU plus real-time denoising further improve final-frame, production-quality rendering.
- Expanded development environment support include deeper Microsoft VSCode integration, VS 2022 support, and WSL 2 for Linux development on Windows.
AI Training & Inference Performance Optimizations
- Intel® Optimisation for TensorFlow is now 10x faster compared to the stock version on 3rd Gen Intel® Xeon® Scalable processors.2
- New Intel® Extension for Scikit-learn speeds machine learning algorithms over 100x on Intel CPUs compared to the stock open-source version.3
- Intel® Neural Compressor is introduced to increase inference performance through post-training optimisation techniques across multiple deep-learning frameworks.
- All toolkits are optimised to enable advanced features of the latest (and upcoming) hardware, including 12th Gen Intel® Core™ processors (codenamed Alder Lake) with AVX-VNNI, Sapphire Rapids with Intel® AMX, and upcoming Xe client and datacenter GPUs.
For more information on the latest update, get in touch with our Intel Business Development Manager, Nicolas Rannou.
Canonical announced the release of Charmed Spark – an advanced solution for Apache Spark® that provides everything users need to run Apache Spark on Kubernetes. Apache Spark is suitable for use in diverse data processing applications including predictive analytics, data warehousing,...