MIT Upgrades AI Research with Satori Supercomputer

By Andy Morris, IBM Cognitive Infrastructure

September 26, 2019

[Connect with Spectrum users and learn new skills in the IBM Spectrum LSF User Community.]

Supercomputers are powering the artificial intelligence (AI) revolution, and MIT is poised to receive a boost to lead the charge.

Sometime this fall, MIT will fire up Satori – an $11.6 million compute cluster donated by IBM – coinciding with the opening of the MIT Stephen A. Schwarzman College of Computing. The new system is modeled on the heterogeneous architecture used for Summit built by IBM for DOE and now the fastest computer in the world.

Named Satori for the Zen Buddhism term for “sudden enlightenment,” the new system will deliver 2 petaflops of peak computational power, “the equivalent of each person on Earth performing more than 10 million multiplication problems each second for an entire year, making Satori nimble enough to join the middle ranks of the world’s 500 fastest computers,” according to an article posted on the MIT website.1 Satori will be housed at a silk mill-turned data center, the Massachusetts Green High Performance Computing Center (MGHPCC) in Holyoke, Massachusetts, and connect to MIT via dedicated, high-speed fiber optic cables.2

[Also read: IBM-Powered Supercomputers Lead Semi-Annual Rankings]

MIT reported rapid progress in AI has fueled a relentless demand for computing power to train more elaborate models on ever-larger datasets while at the same time federal funding for academic computing facilities has been on a three-decade decline. Christopher Hill, director of MIT’s Research Computing Project, puts the current demand at MIT at five times what the Institute can offer.

“The cloud alone wasn’t giving us all that we needed for challenging AI training tasks,” says John Cohn, chief scientist at the MIT-IBM Watson AI Lab. “The expense and long run times made us ask, could we bring more compute power here, to MIT?”

Like Summit, Satori’s architecture is well suited for both traditional modeling & simulation tasks as well as AI and hybrid AI plus traditional workloads. Here’s a snapshot of Satori’s specs:

  • 64 IBM Power 9 Nodes
  • 256 Nvidia V100 GPUs
  • EDR Infiniband
  • 2PB storage
  • 8TB GPU memory
  • 64 TB main memory
  • IBM Power AI Software
  • Cloud Integration

[Also read: 5 Benefits Artificial Intelligence Brings to HPC]

Satori should put a dent in the computing capacity shortfall. “IBM’s gift couldn’t come at a better time,” says Maria Zuber, a geophysics professor and MIT’s vice president of research. “The opening of the new college will only increase demand for computing power. Satori will go a long way in helping to ease the crunch.”

IBM’s gift follows a history of collaborations with MIT that have paved the way for computing breakthroughs. In 1956, IBM helped launch the MIT Computation Center with the donation of an IBM 704, the first mass-produced computer to handle complex math. Nearly three decades later, IBM helped fund Project Athena, an initiative that brought networked computing to campus. Together, these initiatives spawned time-share operating systems, foundational programming languages, instant messaging, and the network-security protocol, Kerberos, among other technologies.

More recently, IBM agreed to invest $240 million over 10 years to establish the MIT-IBM Watson AI Lab, a founding sponsor of MIT’s Quest for Intelligence.3 In addition to filling the computing gap at MIT, Satori will be configured to allow researchers to exchange data with all major commercial cloud providers, as well as prepare their code to run on IBM’s Summit supercomputer.


Resources

1 http://news.mit.edu/2019/ibm-gives-lift-artificial-intelligence-computing-mit-0826

2 https://www.mghpcc.org

3 https://quest.mit.edu

 

Return to Solution Channel Homepage

IBM Resources

Follow @IBMSystems

IBM Systems on Facebook

Do NOT follow this link or you will be banned from the site!
Share This