Compiling Dynamical Systems for Efficient Simulation on Reconfigurable Analog Computers
Sara Achour
MIT
SWS Colloquium
Sara Achour is a PhD candidate at the Computer Science and Artificial Intelligence Laboratory at Massachusetts Institute of Technology (CSAIL MIT) and a NSF Fellowship recipient. Her current research focuses on compilation techniques for reconfigurable analog devices. Her broader research interests focus on developing automated techniques for nontraditional computational platforms and devices.
AG 1, AG 2, AG 3, INET, AG 4, AG 5, SWS, RG1, MMCI
Programmable analog devices are a powerful new computing substrate that are especially appropriate for performing computationally intensive simulations of dynamical systems. Until recently, the de-facto standard for programming these devices required hardware specialists to manually program the analog device to model the dynamical system of interest. In this talk, I will present Arco, a compiler that automatically configures analog devices to perform dynamical system simulation, and Jaunt, a compilation technique that that scales dynamical system parameters to change the speed of the simulation and render the resulting simulation physically realizable given the operating constraints of the analog hardware platform. These techniques capture the domain knowledge required to fully exploit the capabilities of reconfigurable analog devices, eliminating a key obstacle to the widespread adoption of these devices.