Now Available: Version 2022.1 of Intel® oneAPI Toolkits

/in /by

Highlights : The latest release is now available and offers new features, capabilities, and improvements (over 900 since the 2021 release last December) that deliver peak performance and accelerate heterogeneous computing.

Key highlights :

Compilers

  • Intel® oneAPI DPC++/C++ Compiler adds SYCL 2020 features to improve programming productivity plus OpenMP 5.0 & 5.1 features to improve multi-platform, shared-memory programming.
  • Intel® Fortran Compiler is production-ready for CPUs and GPUs and supports OpenMP 5.2 compute offload to GPUs, Fortran 2003, and the most common Fortran 2008 features.

Analysis Tools

  • Intel® VTune™ Profiler Flame Graph feature allows visualization of performance hotspots.
  • New GPU-to-GPU and CPU-to-GPU offload modeling enables performance projections before code changes are made.

High-Performance Computing

  • Intel® MPI Library includes new performance optimizations for Google Cloud Platform fabric (OFI/tcp).
  • Development and distribution platforms have expanded support, including VSCode integration, WSL 2 (Windows Subsystem for Linux), and Spack for HPC tools package management.

Rendering & Ray Tracing

  • Intel® oneAPI Rendering Toolkit adds support for the latest ray tracing techniques, including BVH traversal and intersection, FP16 data format support, Wilkie Sun Sky light sources, rolling shutter, quaternion motion blur, and VDB structure support.

Hardware Platforms

  • Cross-architecture development is supported for Python (via Data Parallel Python for CPUs and GPUs) and Fortran in addition to C++.
  • All toolkits are ready for the latest hardware, including Alder Lake, pre-release software development for Sapphire Rapids, and upcoming client and datacenter GPUs.

With oneAPI, you can realize your full hardware value, confidently develop high-performing cross-architecture code, and ensure your applications are future-ready.

Get started today.

Customer quotes :

What Customers are Saying

“Moving to a cross-architecture model for application development can save significant time and money—over 5 months and $300,000 each time a performance-sensitive application is moved to a new computing platform.” – J. Gold Associates research report

“We used Intel’s denoiser on every shot of The Addams Family 2 and were able to gain a 10% to 20%—and sometimes 25%—efficiency in rendering, saving thousands of hours in rendering production time. – Kenny Chang, Head of Lighting, Cinesite Studios

“Intel® Advisor—and specifically the Roofline Model—really allows us Customers to  understand what is possible and what the performance could be for our specific workloads.” – Ilias Katsardis, HPC Solution Lead, Google Cloud

Watch what customers are saying [3:45]

Subhead : Intel® oneAPI Priority Support

Priority Support tout :

Get professional answers from Intel engineers—technical questions, problems, issues, and more.  Your Intel oneAPI commercial toolkits come with:

  • Priority Support via our Online Service Center for at least one year from your date of purchase. You can extend/renew it at a highly discounted rate.
  • Direct and private interaction with Intel’s support engineers. Customers submit confidential support requests. 
  • Accelerated response time for technical questions and other product needs.  
  • Priority Support for escalated defects and feature requests. 
  • Free download access to all new product updates and continued access to older versions of the product.
  • Access to a vast library of self-help documentation, how-to articles, and videos that build off decades of experience with creating high-performance code. 
  • Access to Intel public community forums supported by community technical experts and monitored by Intel engineers. 
  • Optional Services at additional cost: Onsite/online training and consultation by Intel technical consulting engineers