Mentor Graphics and the University of Basel joined the OpenMP Architecture Review Board (ARB), a group of leading hardware vendors, software vendors and research organizations, in creating the standard for the most popular shared-memory parallel programming model in use today.
Mentor Graphics Corporation, a Siemens business, is a world leader in electronic hardware and software design solutions, providing products, consulting services, and award-winning support for the world’s most successful electronic, semiconductor, and systems companies. Mentor’s Embedded Platform Solutions group provides software solutions that enable embedded device manufacturers to quickly design and build high quality connected devices, including those with rich user interfaces, cloud-based remote management, or requiring safety certification. Mentor also offers development services for its embedded software products and high performance compilers including open source compiler commercialization, customization and support.
“Mentor provides services to high performance computing customers to extend open source compiler support for OpenMP accelerator offload capabilities”, says Pete Decher, Director Sourcery Tools, Mentor, a Siemens Business.
The University of Basel is the oldest university in Switzerland (est. 1460). “The increase in node-level parallelism and heterogeneity render scheduling and load balancing critical for ensuring high performance in OpenMP applications”, says Florina Ciorba, Assistant Professor for High Performance Computing in the High Performance Computing Group. “We are very excited to join the OpenMP effort and work together to provide user-defined scheduling and load balancing interfaces and policies.”
“We are delighted to welcome Mentor and the University of Basel as our newest members”, says Michael Klemm, CEO of the OpenMP ARB, “Both are very active in the open source and scientific community, and underline the relevance of the OpenMP API in the HPC community.”
The OpenMP ARB’s mission is to standardize directive-based, multi-language, high-level parallelism that is performant, productive, and portable. Jointly defined by a group of major computer hardware and software vendors, the OpenMP API is a portable, scalable model that provides parallel programmers with a simple and flexible interface for developing parallel applications for platforms ranging from embedded systems and accelerator devices to multi-core and shared-memory systems.