\u201cOurs is for anyone who has the need to examine data in a deep way.”<\/p><\/blockquote>\n
While many colleges have high-performance computing clusters, it\u2019s not uncommon for them to be appropriated by a few faculty members (superheroes, as it were).<\/p>\n
Bates’ HPCC, however, is designed as a “community-based resource as opposed to one that would just benefit specific faculty members,\u201d explains Andrew White, director of academic and client services for Information and Library Services. \u201cOurs is for anyone who has the need to examine data in a deep way.”<\/p>\n
![\"Jeffrey](\"https:\/\/www.bates.edu\/news\/files\/2016\/10\/web-161004_high_performance_computing_cluster_9271.jpg\")
<\/a>Jeffrey Oishi, the college’s new computational astrophysicist, visits the HPCC where it lives: in a ground-floor hub room in Kalperis Hall at 65 Campus Ave. (Jay Burns\/Bates College)<\/p><\/div>\n
One of those people is Jeff Oishi, the college’s new computational astrophysicist. He’ll be a power user, and some of his research funds helped to purchase the HPCC, which sits in a 15-by-17 hub room in the basement of Kalperis Hall, one of the college’s two new residences on Campus Avenue.<\/p>\n
Oishi calls the HPCC “the once and future” of computing. “Once” because sharing was once the way to access powerful computing, and “future” because it anticipates how Bates will use and expand the HPCC.<\/p>\n
When it comes to an HPCC, “high performance” has the same meaning as it does for a 1971 Plymouth Hemi Cuda muscle car. It means extraordinary power.<\/p>\n
For Oishi and his student researchers, this computing power will run models that explain how gases flow inside the atmospheres of giant planets like Jupiter. In one project, they will use an approximation known as linearization to model how gases go from stable to unstable. In a second project, Oishi\u2019s team will do 3D simulations of these transitions.<\/p>\n
When a big job comes to the HPCC from Oishi\u2019s lab in Carnegie Science, the job goes first to one of the 12 computers, each of which are known as “nodes.” The receiving node, called the “head node,” is the traffic cop that manages requests and draws on the other 11 nodes\u2019 computing power as needed.<\/p>\n
In computer parlance, this gabfest is called \u201call-to-all\u201d communication and it\u2019s a hallmark of high-performance computing.<\/p><\/blockquote>\n
\u201cThe head node splits up the job, with pieces going to everybody else,\u201d explains Jim Bauer, director of network and infrastructure services for ILS. \u00a0\u201cThe nodes all communicate with each other, assemble the results, and send it back to the head node.\u201d<\/p>\n
As the job gets crunched and all the processors inside all the nodes swing into action, each processor is \u201ctalking with every other processor all the time,\u201d Oishi says. It’s an overlapping conversation, like a Robert Altman movie. In computer parlance, this gabfest is called \u201call-to-all\u201d communication and it\u2019s a hallmark of high-performance computing.<\/p>\n
The speed of this conversation depends on a dazzling array of pricey cables that connect the head node to the other nodes and each node to one another. So while you can use $2 HDMI cables for your home theater, in this case, \u201ccables do matter,\u201d says Bauer. Collectively called \u201cfabric,\u201d all this high-speed networking allows data to whip around at 100 gigabytes per second, the gold standard of high-speed computing.<\/p>\n