Blog Posts

TORQUE Protocol 4: Inter-Server Communication

Screen Shot 2014-10-21 at 11.58.09 AM
This entry is part 4 of 4 in the series TORQUE Protocols

The TORQUE inter-server or IS protocol is for inter-server communication. “What do you mean by inter-server?” you might say. “Isn’t there only one server in the TORQUE cluster?” Like so many other things in the computer art the term server can have an ambiguous meaning. In the case of the IS Protocol a server is […]

TORQUE BoF 2014: Past, Present and Future

3817086937_ea62e3d28d_z

Supercomputing 2014 is almost here. And for the fifth time in the last six years that means it is also time for the Supercomputing TORQUE Birds of a Feather. Aside from the stress of preparing for the meeting I really love this event. My first TORQUE BoF was at Supercomputing 2009 in Portland, Oregon. This […]

PuppetConf 2014 – A New Breed of Developer

puppetconf-2014-promo-video-1024x576

The DevOps team here at Adaptive Computing recently attended PuppetConf 2014 in beautiful downtown San Francisco. Being able to work for a company and with a team that is passionate about DevOps practices, it was an absolute blast to be among fellow Puppet community members soaking in all that PuppetLabs had to offer this year. […]

Visualizing TORQUE

TORQUEView - Heat Map with tooltip

For many months now, I’ve noticed that TORQUE users needed help graphically visualizing what was happening inside a TORQUE system.  A GUI tool was needed to visually monitor the health of an entire cluster at a glance and have the ability to quickly move to any trouble spots and drill in to find more information. […]

Convergence of High-Throughput Computing (HTC) with HPC

underthehood

While HPC workloads are compute- and data-intensive and can sometimes take several months to complete, High-throughput computing (HTC) jobs have by nature extremely short runtimes, usually in the millisecond range. Nearly all HTC jobs can be classified as “embarrassingly parallel,” which means the workload can be divided up into multiple, autonomous pieces, each of which […]

Big Data Challenge: Data Wrangling

Cowboy Data

One of the well-known difficulties for data analytics is data wrangling. Essentially, the process of “data wrangling”—sometimes lovingly referred to as janitor work—is transforming raw data into something that can actually be analyzed by algorithms and data scientists. When you have totally raw data it is very difficult to process, especially with natural language. Think […]

#HPCMatters in Art

Giant Floating Jellyfish
This entry is part 4 of 4 in the series #HPCMatters

Janet Echelman is probably not a name many would recognize in HPC circles. She isn’t a research scientist or a HPC advocate. She doesn’t work for one of the industry vendors, nor is she a university professor leading one of the competitive student teams. Janet Echelman is an artist. More specifically, she is a sculptor. […]

#HPCMatters: We’ll See You at SC14

Screen Shot 2014-10-09 at 2.43.12 PM

We’re counting down the days until one of our favorite conferences of the year (besides MoabCon) Supercomputing! This year’s Supercomputing conference highlights why #HPCMatters, and we’ve enjoyed diving deeper into why HPC matters for individuals in our community. The Adaptive Computing team is in preparation mode getting ready for the big event. Here’s the key […]

A Culture of Healthy Peer Review

Culture of Healthy Peer Review

The editors of Nature, the “international weekly journal of science,” receive 10,000 submitted papers per year, but 60% are rejected without being reviewed. The surviving 40% of submissions run a gauntlet of peer review in which two or more anonymous referees are chosen to read and comment confidentially on the proposed paper. The editors consider […]

Tune into the Society of HPC Professionals (SHPCP) Webinar Series

Screen Shot 2014-10-07 at 6.18.00 PM

Adaptive Computing is proud to sponsor the monthly Society of HPC Professionals (SHPCP) monthly webinar series. The SHPCP is a Texas non-profit corporation established in 2009 to provide HPC professionals with an organization that will organize and conduct open forum meetings that address the use, availability and evaluation of existing technology and introduce emerging technology […]