Intel unveils Xeon Phi coprocessors for high performance computing

Micro Electronics

by CBR Staff Writer| 13 November 2012

The new coprocessors are combined with Intel Xeon processor E5 family is expected to increase the computational capabilities over Petascale

Chipmaker Intel has introduced the new Xeon Phi coprocessors, which are expected to cater to the demand for high-performance computing in manufacturing, life sciences, energy and other areas.

The new coprocessor is based on the Intel Many Integrated Core (Intel MIC) architecture and complements the existing Intel Xeon processor E5-2600/4600 product families.

Combination of the new coprocessor and Intel Xeon processor E5 family is expected to boost computing to Exascale level, which would increase the computational capabilities over Petascale.

By utilising programming languages, parallelism models, techniques and developer tools available for the Intel architecture, the new release will enable software companies and IT departments to use parallel code without retraining developers on proprietary and hardware specific programming models associated with accelerators, the company said.

In addition, Intel is also providing the software tools to help scientists and engineers optimise their code to take full advantage of Intel Xeon Phi coprocessors, including Intel Parallel Studio XE and Intel Cluster Studio XE.

Intel is introducing two new Intel Xeon Phi coprocessor families, which are built with Intel's advanced 22-nanometer, 3-D tri-gate transistors, that provide optimal performance and performance-per-watt for highly parallel HPC workloads.

The Xeon Phi coprocessor 3100 family will offer more than 1000 Gigaflops (1 TFlops) double-precision performance, support for up to 6GB memory at 240GB/sec bandwidth, a series of reliability features including memory error correction codes (ECC) and operate within a 300W thermal design point (TDP) envelope.

Intel Xeon Phi coprocessor 5110P will provide additional performance at a lower power envelope, reache 1,011 Gigaflops (1.01 TFlops)double-precision performance, operate within 225 watts TDP and support 8GB of GDDR5 memory at a higher 320 GB/sec memory bandwidth.

Comments
Post a comment

Comments may be moderated for spam, obscenities or defamation.
Privcy Policy

We have updated our privacy policy. In the latest update it explains what cookies are and how we use them on our site. To learn more about cookies and their benefits, please view our privacy policy. Please be aware that parts of this site will not function correctly if you disable cookies. By continuing to use this site, you consent to our use of cookies in accordance with our privacy policy unless you have disabled them.