Sign up for our newsletter and get the latest HPC news and analysis.

HSA Heterogeneous System Architecture Overview

vinod

The HSA Foundation seeks to create applications that seamlessly blend scalar processing on the CPU, parallel processing on the GPU, and optimized processing on the DSP via high bandwidth shared memory access enabling greater application performance at low power consumption.

How Allinea MAP helps Programmers Speed the Intel Xeon Phi

reindersAllinea

In this video from SC13, Intel Software Evangelist James Reinders describes how Allinea MAP helps programmers get the highest possible application performance from the Intel Xeon Phi.

Intel Knights Landing to Take Xeon Phi to the Next Level in 2015

Intel has taken the wraps off Knights Landing, its next-generation, 72-core Xeon Phi supercomputing chip.

Allinea Seamless Development Platform Steps Up to Intel Xeon Phi

This week Allinea Software announced fully integrated development tools for applications running on the Intel Xeon Phi coprocessor.

Slidecast: OpenACC Gains New Members and GCC Support

openacc2

In this slidecast, OpenACC President Duncan Poole leads a panel of speakers describing the latest additions to OpenACC.

Round-Up: Ancillary Events & Special Booth Sessions at SC13

SC13Logo-150x150

SC13 in Denver is loading up with loads of special events. Here’s the roundup of ancillary events and special programs not to miss on the show floor. Be sure to send us your news!

Cray Enhances Coprocessor and Accelerator Support for OpenACC 2.0

Today Cray introduced new OpenACC 2.0 support for directives-based programming of accelerators and coprocessors in the company’s 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. Congratulations to Cray […]

Cray Adds Intel Xeon Phi Coprocessor Support to XC30 Supercomputers

With support for both Nvidia Tesla K20X GPU accelerators and Intel Xeon Phi coprocessors, the Cray XC30 architecture combines multi-core and many-core.

UPDATE: Glenn Lockwood Looks at Intel’s Xeon Phi Uptake Measured from Real Users

photo

Despite having over 6,000 Intel Xeon Phi coprocessors, TACC’s Stampede system is seeing extremely low utilization of these coprocessors.

Benchmarks: Intel Xeon Phi vs. NVIDIA Tesla GPU

2

Which is better, Intel Xeon Phi or NVIDIA Kepler? The general answer has to be “it depends,” as this is heavily application-dependent.