Since 1986 - Covering the Fastest Computers in the World and the People Who Run Them

Language Flags

Tag: I/O

Numascale Delivers Shared Memory Systems at Cluster Price with Virtually Unlimited Number of Cores and Memory

Aug 19, 2013 |

Numascale’s Numaconnect is now applied in servers form IBM and Supermicro to create versatile and scaleable systems with large headroom for cores and memory. The systems run standard Linux operating systems and do not rely upon any complicated virtualization layers. The ccNuma approach is based on well established experience in computer architecture.

The Week in HPC Research

Apr 11, 2013 |

The top research stories of the week include an evaluation of multi-stage programming with Terra; a look at parallel I/O for multicore architectures; a survey of on-chip monitoring approaches used in multicore SoCs; a review of grid security protocols and architectures; and a discussion of the finer distinctions between HPC and cloud computing.

HPC in the Cloud Research Roundup

Mar 15, 2013 |

<img src=”http://media2.hpcwire.com/hpccloud/Network_optimization_225x.jpg” alt=”” width=”95″ height=”64″ />The top HPC cloud research story this week addresses the question: What if it were possible to cheaply and easily test the suitability of moving to a cloud platform – a virtual “try it before you buy it”? In other items, researchers explore the reliability of HPC cloud, take another pass at GPU virtualization, and evaluate I/O performance in Amazon’s EC2 cloud.

The Future of Workload Management

Oct 12, 2012 |

<img style=”float: left;” src=”http://media2.hpcwire.com/hpcwire/venn_diagram_colors_200x.jpg” alt=”” width=”98″ height=”78″ />In this era of heterogeneous architectures and hybrid infrastructures, workload managers are necessarily becoming more and more sophisticated. Looking toward the future of workload management, there are three major trends: application insight, big data awareness, and HPC clouds. While inter-related, each has something important to contribute to the advancement of HPC.

The Future of Workload Management

Oct 12, 2012 |

<img style=”float: left;” src=”http://media2.hpcwire.com/hpcwire/venn_diagram_colors_200x.jpg” alt=”” width=”92″ height=”69″ />In this era of heterogeneous architectures and hybrid infrastructures, workload managers are necessarily becoming more and more sophisticated. Looking toward the future of workload management, there are three major trends: application insight, big data awareness, and HPC clouds. While inter-related, each has something important to contribute to the advancement of HPC.

When Is Cloud the Right Choice for HPC?

Aug 9, 2012 |

Cloud technologies have become integral to a number of services including video streaming, file sharing and social media to name a few. But when it comes to HPC applications, the benefits don’t always translate.

When Time Is of the Egress: Optimizing Your Transfers

Jul 31, 2012 |

Traditionally running scientific workloads in AWS provides a diverse toolkit that allows researchers to easily sling data around different time zones, regions, or even globally once the data is inside of the infrastructure sandbox. However, getting data in and out of AWS has historically been more of a challenge. Cycle Computing’s Andrew Kaczorek and Dan Harris offer some helpful tips on optimizing ingress and egress transfers.

Exascale Storage Group Aims to Bring I/O Up to Speed

Apr 5, 2012 |

<img style=”float: left;” src=”http://media2.hpcwire.com/hpcwire/server_storage.jpg” alt=”” width=”114″ height=”90″ />The first meeting of the Exascale IO Workgroup (EIOW) brought together stakeholders looking to develop open source middleware for exascale file systems. Peter Braam, who heads up the File Systems group at Xyratex and is one of the principle drivers behind EIOW, helped facilitate much of the initial discussion. We asked Braam about the outcome of the first workshop gathering, the significance of the EIOW effort, and why exascale I/O needs special attention.

HPC Center Traces Storage Selection Experience

Jul 8, 2011 |

We often hear about national labs and universities settling on a particular vendor for server and storage solutions, but details about the full evaluation process behind that selection are often sparse. The Utah Center for High Performance Computing’s storage lead explains how his team whittled down the list — and evaluated options against a tricky application.

Say Hello to the New ADIOS

Sep 12, 2010 |

Last week marked the release of ADIOS 1.2, the latest incarnation of one of computational science’s most effective I/O tools. So far ADIOS has helped researchers make huge strides in fusion, astrophysics and combustion. The new version features some interesting improvements that will doubtless aid researchers in taking full advantage of leading supercomputing platforms.