Intel Releases oneAPI 2022 Toolkits

Jan. 4, 2022 — Intel today released oneAPI 2022 toolkits, which the company said have expanded cross-architecture features to provide greater utility and architectural choice to accelerate computing. oneAPI is a cross-industry, open, standards-based unified programming model designed to improve the productivity of code development when building cross-architecture applications.

New capabilities in the 2022 toolkits include what Intel said is the first unified compiler implementing C++, SYCL and Fortran, data parallel Python for CPUs and GPUs, advanced accelerator performance modeling and tuning and performance acceleration for AI and ray tracing visualization workloads.

Intel said there are more than 900 new and enhanced features added over the past year now available to download or use in the Intel DevCloud for free. Highlights include:

• Intel created a unified compiler implementing C++, SYCL and Fortran for CPUs and GPUs utilizing a common LLVM backend.
• Accelerated compute on CPUs and GPUs for Python, today’s most popular programming language.
• The Intel DPC++ Compatibility Tool was improved to automatically migrate 90 percent to 95 percent of CUDA code to SYCL/DPC++.
• Deep learning framework performance is accelerated up to 10 times over earlier versions with the latest Intel® Optimization for TensorFlow and Intel Optimization for PyTorch.
• New Intel Extension for Scikit-learn speeds up machine learning algorithms more than 100 times on Intel CPUs over the stock open source version.
• Introduced Intel Neural Compressor to achieve increased inference performance through post-training optimization techniques across multiple deep learning frameworks.
• Performance analysis for CPUs and accelerators – Intel VTune Profiler’s flame graph display helps improve the ability to visualize performance hot spots. Intel Advisor’s accelerator performance modeling allows developers to estimate performance benefits of offloading to a GPU before making code changes.
• Advanced ray tracing – New features including cone telemetry, auxiliary feature denoising and FP16 support provide more robust shapes and shorten rendering times, improving overall rendering performance. Support for upcoming Intel X^e GPUs as well as real-time denoising further improve industry-leading, final frame, production-quality rendering.
• Expanded development environment support including deeper Microsoft Visual Studio Code integration, support for Microsoft Visual Studio 2022, and Microsoft WSL2 for Linux development on Windows.