Topics » Applications

Features

Application Readiness at the DOE, Part II: NERSC Preps for Cori

Apr 17, 2015 |

In our second video feature from the HPC User Forum panel, “The Who-What-When of Getting Applications Ready to Run On, And Across, Office of Science Next-Gen Leadership Computing Systems,” we learn more about the goals and challenges associated with getting science applications ready for the coming crop of Department of Energy (DOE) supercomputers, which in addition to being five-to-seven times faster than Read more…

Application Readiness at the DOE, Part I: Oak Ridge Advances Toward Summit

Apr 16, 2015 |

At the 56th HPC User Forum, hosted by IDC in Norfolk, Va., this week, three panelists from major government labs discussed how they are getting science applications ready for the coming crop of Department of Energy (DOE) supercomputers, which in addition to being five-to-seven times faster than today’s fastest big iron machines, constitute significant architectural changes. Titled “The Who-What-When of Getting Applications Ready to Read more…

Last But Not Least: Argonne’s $200 Million Supercomputing Award

Apr 9, 2015 |

A supercomputer named Aurora is on track to become the fastest system in the United States and possibly the world. Just a few hours ago, DOE Undersecretary Franklin “Lynn” Orr, announced that Intel Corp. and Cray Inc. had been selected to supply Argonne National Laboratory with a 180 petaflops system, Aurora, and a secondary system of about Read more…

Something for Everyone at GPU Technology Conference

Mar 23, 2015 |

Once relegated to the category of specialized gaming hardware, today’s graphics processors are solving some of the world’s toughest computing problems. During GTC15 last week in San Jose, the full breadth and depth of session topics provided even more evidence of how far graphics processors have come from their gaming roots. And while this year deep Read more…

FPGA-Accelerated Search Heads for Mainstream

Mar 10, 2015 |

With data volumes now outpacing Moore’s Law, there is a move to look beyond conventional hardware and software tools. Accelerators like GPUs and the Intel MIC architecture have extended performance goals for many HPC-class workloads. Although field-programmable gate arrays (FPGAs) have not seen the same level of adoption for traditional HPC workloads, a subset of big data Read more…

Short Takes

Supercomputing Sheds Light on Party Polarization

Apr 7, 2015 |

What can supercomputers tell us about the way that government operates, or in some cases doesn’t operate? Quite a bit, actually. In a new feature piece on the Texas Advanced Computing Center website, science writer Makeda Easter shares how one TACC researcher is using the center’s Stampede supercomputer to analyze the link between federal spending priorities Read more…

Haswell’s New Instructions Benefit FEA Performance

Apr 2, 2015 |

Intel recently published a case study that demonstrates the advantages of the Intel Xeon E5-2600 v3 product family for running engineering workloads, using Dassault Systèmes’ SIMULIA-branded Abaqus/Standard software. Abaqus/Standard is general purpose finite element analysis (FEA) software, which works by sectioning an object into a large number of finite elements, each represented by an equation. As the individual equations are solved and Read more…

India Greenlights $730 Million Supercomputing Grid

Mar 26, 2015 |

The Indian government has approved a seven-year supercomputing program worth $730 million (Rs. 4,500-crore) intended to restore the nation’s status as a world-class computing power. The prime mandate of the National Supercomputing Mission, first revealed last October, is the construction of a vast supercomputing grid connecting academic and R&D institutions and select departments and ministries. The Read more…

Visualization Software Makes Leap from Science to Industry

Feb 24, 2015 |

For three years now, CFD software specialist Intelligent Light has been working to bring the open source visualization program VisIt into its family of industrial grade software products. Designed by Lawrence Livermore National Laboratory scientists to visualize data coming off Department of Energy (DOE) supercomputers, VisIt scales well and is well-suited for in situ processing. Read more…

Gordon Supercomputer Advances Fight Against Deadly Brain Cancer

Feb 23, 2015 |

A collaboration between San Diego Supercomputer Center (SDSC), Moores Cancer Center, and Department of Neurosciences at the University of California, San Diego, is shedding light on the underlying genetic mechanisms responsible for glioblastomas (GBM), highly aggressive and infiltrative brain tumors. Using SDSC’s data-intensive Gordon supercomputer, the partners were able to identify a pyramid hierarchical network of “coherent Read more…

Off the Wire

Intersect360 Research Releases New Report on HPC Applications

Sep 19, 2014 |

SUNNYVALE, Calif., Sept. 19 — Newly segmented market research reveals a stable and mature technical computing segment with opportunities to expand, as well as a plethora of new HPC opportunities in business computing, according to Intersect360 Research’s 2014 HPC User Site Census: Applications. The research firm segmented their research into High Performance Business Computing (HPBC) Read more…

ZIH Becomes Intel Parallel Computing Center

Sep 19, 2014 |

Sept. 19 — The Center for Information Services and High Performance Computing (ZIH) has been established as an Intel Parallel Computing Center (IPCC). The collaboration between ZIH and Intel focuses on increasing the parallelism of existing scientific applications on future supercomputers consisting of many-core processors. Led by ZIH scientists, the new IPCC carries out two Read more…

Altair Unveils HyperWorks 13.0

Sep 16, 2014 |

TROY, Mich., Sept. 16 – Altair today announced a new release of HyperWorks, the most comprehensive version to date of its computer-aided engineering (CAE) software platform, which has set the global standard for enabling its users to create more durable and efficient products. HyperWorks 13.0 increases engineering productivity in four distinct areas: Performance optimization. Through a wide array of solvers and multiphysics Read more…

Praesum Communications is Now Praesum Supercomputing

Sep 10, 2014 |

PETALUMA, Calif., Sept. 10 — Praesum Communications announced today that will now be doing business as Praesum Supercomputing and will provide advanced OpenCL-based computational acceleration products for a wide range of applications. This marks an important shift in the business direction of Praesum, which is known for being a leader in smart switching technologies in Read more…

Altera Showcasing FPGA-Based Products at IDF

Sep 9, 2014 |

SAN JOSE, Calif., Sept. 9 — Altera Corporation is demonstrating several advanced reconfigurable logic technologies at the Intel Developers Forum (IDF) 2014 that showcase how its FPGA-based solutions are advancing the capabilities of software-defined data centers and high-performance computing applications. Altera’s FPGA-based solutions on display showcase the capabilities of its hardware and software solutions, including advanced optical Read more…