Blog Posts

Why #HPCMatters

hpcmatters-sticker

Back in March, I posted the SC14 video introducing this year’s theme: #HPCMatters. Since then several different organizations have posted videos expressing why #HPCmatters to them and should to the rest of us. Today, I’d like to share a few of those videos with you (with their YouTube descriptions). NCSA: A world without supercomputers, #HPCMatters […]

What’s Missing For A Successful Big Data Implementation?

Optimization

My previous blog proposed an answer to the drivers for big data and why it’s happening now. To review they are: cloud computing, low cost, high performance hardware, network ubiquity, mobility, social networks/computing, and sensor/machines data. Ok, so what’s missing from this list? When several technology areas evolve in an overlapping fashion and at high […]

Game Changer for HPC Scale and Performance

Game Changer for HPC

The exascale wave in today’s HPC market is creating an inflection point, where familiar solutions are simply inadequate. Modern supercomputers have so many internal network interconnects and coordinate so many calculations at such a rate that traditional scheduling cannot keep up. Jobs sit idle when they should be running; policy constraints are lost in the […]

Benefits of OpenStack for HPC

Benefits of OpenStack for HPC

Join us on August 20th (2-3pm MDT) for the next Society of HPC Professionals (SHPCP) event, “Benefits of OpenStack for HPC” webinar featuring a panel of industry experts. The industry looks to OpenStack as an agnostic open source platform that can span multiple environments such as Cloud, HPC and Big Data. Adaptive Computing has compiled […]

Taking the Master Out of Puppet

pe_screen_700_2x

As we prepare for the Utah County Puppet Users Group to begin here Provo Utah, the DevOps team here at Adaptive has started to contemplate what topic we want to contribute to the community. One of the topics we have identified is our use of Puppet in a masterless state. The Adaptive blog touched lightly […]

Lincoln Ascent: Communicating Between Moab and TORQUE

Cedar-Wright-Matah-Pitch-11-660

One of the major development projects for TORQUE 5.0 and Moab 8.0 was the Ascent project. We were extremely pleased with the progress made during this effort, so we’re continuing the effort into the next release (codename: Lincoln), and I’d like to take this chance to introduce it. The purpose of Ascent is to rapidly […]

Perspectives and Personas

Rubin Face Vase

Right now I am in India, a land of beauty filled with wonderful people. It has been said India is an assault on all of your senses, I believe that is true. The colors, sounds, flavors and smells exude the essence of foreign and exotic entrancing the American mind. Have I mentioned, I’m loving it? […]

Now Is The Time for Big Data

iStock_000042872664Small (1)

Several people have asked me why? Why is big data happening now? Why is it important? Why should I care? Why should my company care? Sometimes things just happen. In the case of big data, it seems like it just happened, but in reality it is a natural occurrence, bubbling to the top of a […]

Best Practices for Allocations

Allocations

So, you’ve procured a supercomputer—a product of a consortium of stakeholders whose goal is to combine resources to fulfill one or more mission objectives. And you have a constant stream of applicants who would like to use its cycles. The stakeholders have appointed an allocation committee to periodically review applications for time on the computer […]

Scheduling the Middle Ground

2607065194_a5962d9a01_z

As more and more financial services firms make the jump to HPC, some consideration needs to be made in getting the most out of the cluster resources employed. Financial applications are typically embarrassingly parallel jobs that only account of a few seconds each of computing time. HPC scheduling engines typically rely on longer running jobs […]