Short Takes

Weekly Twitter Roundup (Sept. 22, 2016)

Sep 22, 2016 |

Here at HPCwire, we aim to keep the HPC community apprised of the most relevant and interesting news items that get tweeted throughout the week. The tweets that caught our eye this past week are presented below. Check back in next Thursday for an entirely updated list.

The Tweet of the Week goes to @InspurServer for their informative pic from the HPC User Forum. Read more…

CCC Weighs in on Need for Industry-Academic Collaboration

Sep 22, 2016 |

How best to foster academic-industry collaboration is a hot topic. The National Strategic Computing Initiative calls it out as one of five imperatives. The Department of Energy’s HPC4Mfg program has been liberally doling project grants. Now, Community Computing Consortium has issued a report, The Future of Computing Research: Industry-Academic Collaborations, which likewise underscores the success of past efforts and the need for more. Read more…

DOE Invests $16M in Supercomputer Technology to Advance Material Sciences

Sep 22, 2016 |

The Department of Energy (DOE) plans to invest $16 million over the next four years in supercomputer technology that will accelerate the design of new materials by combining “theoretical and experimental efforts to create new validated codes.” The new program will focus on software development that eventually may run on exascale machines.

Luke Shulenburger of Sandia National Laboratories will lead a team to improve algorithms that predict and show how to modify materials properties, a key element of the DOE project. Read more…

Energy Giant Vestas Harnesses HPC and Analytics for Renewables

Sep 21, 2016 |

The energy industry was an early adopter of supercomputing; in fact, energy companies have the most powerful supercomputers in the commercial world. And although HPC in the energy sector is almost exclusively associated with seismic workloads, it also plays a critical role with renewables as well, reflecting the growing maturity of that vertical.

The largest wind turbine company in the world, Vestas Wind Systems of Denmark (2015 revenues: Read more…

Weekly Twitter Roundup (Sept. 15, 2016)

Sep 15, 2016 |

Here at HPCwire, we aim to keep the HPC community apprised of the most relevant and interesting news items that get tweeted throughout the week. The tweets that caught our eye this past week are presented below. Check back in next Thursday for an entirely updated list.

The Tweet of the Week goes to @StefanHabel for his cool Cray-1 photo. Read more…

MIT Programmers Attack Big Data Memory Gap

Sep 15, 2016 |

Among the computing challenges presented by big data is the scattering of unstructured items across huge datasets. Pulling together that data from arbitrary locations in main memory is therefore emerging as a major performance bottleneck in CPUs.

Researchers at MIT’s Computer Science and Artificial Intelligence Laboratory have proposed a solution to the memory “locality” problem with a new programming language called “Milk.” The approach is designed to allow application developers to more efficiently manage memory when crunching scattered data in ever-larger datasets. Read more…

In Search of the Next Circuit Building Method – ORNL has Ideas

Sep 14, 2016 |

No one knows what the next, best way to build electronic circuits will be. That said there’s no shortage of efforts to invent something beyond current lithography. Oak Ridge National Laboratory, perhaps not surprisingly, is in the thick of the race and two recent studies from ORNL researchers showcase promising but very different approaches.

One method suggests phase change in a single complex oxide material may allow “creating” circuit elements much smaller than in today’s CMOS process while a second study puts STEM (scanning transmission electron microscopy) to work directly writing tiny patterns in metallic “ink,” forming features in liquid that are finer than half the width of a human hair. Read more…

On-Chip Device Accelerates Core-to-Core Communication

Sep 13, 2016 |

A team of engineers from North Carolina State University and Intel have joined forces to address on-chip communications bottlenecks that hamper performance scaling for workloads that share data frequently. Their paper, “CAF: Core to Core Communication Acceleration Framework,” describes a novel core-to-core Communication Acceleration Framework (CAF).

The technique could provide relief for many HPC applications and other communications-depending workloads such as pipelined packet processing, widely used in software-based networking. Read more…

New Approach to Computationally Designing Drugs for GPCRs

Sep 8, 2016 | Modeling protein interactions with drugs has long been computationally challenging. One obstacle is these interactions often take relatively long to occur and conventional molecular dynamics simulation is insufficient. This week a group of researchers, using several EXSEDE supercomputers, report a hybrid in silico-experimental approach that shows promise as a drug design tool for use with G protein-coupled receptors (GPCRs) Read more…

Weekly Twitter Roundup (Sept. 8, 2016)

Sep 8, 2016 |

Here at HPCwire, we aim to keep the HPC community apprised of the most relevant and interesting news items that get tweeted throughout the week. The tweets that caught our eye this past week are presented below. Check back in next Thursday for an entirely updated list.

The Tweet of the Week goes to @hpcnotes for his HPC User Forum Twitter coverage. Read more…