Communication Challenges for Extreme-Scale, Real-Time Neural Network Simulation

Add to your list(s) Download to your calendar using vCal

• Paul Fox and Steve Marsh, University of Cambridge
• Wednesday 16 November 2011, 11:00-12:00
• SC04, Computer Laboratory, William Gates Building.

If you have a question about this talk, please contact Prof Simon Moore.

Neural network simulation is an example of an embarrassingly-parallel problem with complex communication patterns. The neurons being simulated are inherently parallel but the spike messages between them exhibit complex patterns. We consider GPUs as a possible simulation platform, but discover that their methods of processing and communication make them unsuited to the task. As an alternative we propose a simulation platform consisting of a network of Field Programmable Gate Arrays (FPGAs), connected using integrated high-speed serial transceivers. This system is much more suited to the complex communication patterns and real-time requirements of an extreme-scale neural network simulation.

This talk is part of the Computer Laboratory Computer Architecture Group Meeting series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge talks
• Computer Laboratory Computer Architecture Group Meeting
• Department of Computer Science and Technology talks and seminars
• Interested Talks
• SC04, Computer Laboratory, William Gates Building
• School of Technology
• Trust & Technology Initiative - interesting events
• bld31

Note that ex-directory lists are not shown.