October 08, 2013
SEATTLE, Wash., Oct. 8 -- Global supercomputer leader Cray Inc. today introduced new OpenACC 2.0 support for directives-based programming of accelerators and coprocessors in Cray supercomputers. Leveraging years of successful production accelerator experience and supercomputing domain knowledge, the Cray OpenACC programming implementation now supports NVIDIA Tesla GPU accelerators and Intel Xeon Phi coprocessors on the Cray XC30 series of supercomputers.
In an ongoing effort to make it easier for programmers to take advantage of parallel computing, the OpenACC parallel programming standard is a simple, directives-based approach enabling the acceleration of applications on hybrid many-core and multi-core processing systems. The OpenACC approach provides simplified programming of accelerators and coprocessors, wide application support, and flexible and standards-compliant results. OpenACC 2.0 support is delivered for the Cray compiler through the latest release of the Cray Programming Environment.
“Congratulations to Cray for releasing the first compiler with complete support for OpenACC 2.0,” said Duncan Poole, president of OpenACC. “The objective of OpenACC is to provide a programming API that performs well on all types of accelerators and CPUs. The OpenACC organization is responding quickly to create an open standard that is architected to ensure developer code is portable, with good performance on all types of accelerators and CPUs. This rapid pace of leadership further distances the OpenACC specification from similar efforts.”
“Software tools that are optimized for supercomputers are an imperative for programmers to get every ounce of power and performance efficiency out of a supercomputing system,” said Peg Williams, Cray’s senior vice president of high performance computing systems. “Cray’s support for version 2.0 of the OpenACC Application Programming Interface demonstrates our commitment to providing the OpenACC user community with the ability to develop applications that are easily portable across platforms while eliminating the need for multiple versions of source code.”
Established in 2011, OpenACC is a non-profit organization founded with the purpose of advancing directives-based programming methodology for enabling high performance accelerators and coprocessors in hybrid supercomputing systems. By exposing parallelism to the compiler, directives allow the compiler to do the detailed work of mapping the computation onto the accelerator. Offloading specific loops and regions of code from the CPU to an attached accelerator can greatly improve performance while simultaneously significantly reducing power consumption.
Cray is a co-founding member, and the OpenACC organization has been joined by numerous high performance computing (HPC) organizations since, including users, computing centers and educational institutions, as well as silicon and software vendors.
The Cray implementation of OpenACC 2.0 delivers on user productivity requests and optimization requirements, including dozens of new construct updates, enhancements and improvements. More information on OpenACC and the 2.0 specification can be found at www.openacc-standard.org.
To learn more about the OpenACC 2.0 enhancements for the Cray XC30 supercomputers, please register for an upcoming webinar, which will be held on Wednesday, Oct. 30, 2013 at 10:00 a.m. PDT.
About Cray Inc.
Global supercomputing leader Cray Inc. provides innovative systems and solutions enabling scientists and engineers in industry, academia and government to meet existing and future simulation and analytics challenges. Leveraging 40 years of experience in developing and servicing the world’s most advanced supercomputers, Cray offers a comprehensive portfolio of supercomputers and Big Data storage and analytics solutions delivering unrivaled performance, efficiency and scalability. Cray’s Adaptive Supercomputing vision is focused on delivering innovative next-generation products that integrate diverse processing technologies into a unified architecture, allowing customers to meet the market’s continued demand for realized performance. Go to www.cray.com for more information.
Source: Cray Inc.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?