Department of Mechanical Engineering
Kenneth E. Goodson
Aly, M.M.S., Gao, M., Hills, G., Lee., C.-S., Pitner, G., Shulaker, M.M., Wu, T.F., Asheghi, M., Bokor, J., Franchetti., F., Goodson, K.E., Kozyrakis, C., Markov, I., Olukotin, K., Pileggi, L., Pop, E., Rabaey, J., Re, C., Wong, H.-S., Mitra, S., 2015, "Energy-Efficient Abundant-Data Computing: The N3XT 1,000X," IEEE Computer, Vol. 48, pp. 24-33.
Next-generation information technologies will process unprecedented amounts of loosely-structured data, including streaming video and audio, natural languages, real-time sensor readings, and contextual environments. These newly available data far exceed the processing capacity of known computing architectures and algorithms, thereby making coming generations of end-user applications infeasible.
Our N3XT approach overcomes these challenges through recent advances across the entire computing stack: (a) one-dimensional carbon nanotubes and two-dimensional layered nanomaterials for high performance and energy efficiency, (b) high-density non-volatile resistive and magnetic memories, (c) monolithic three-dimensional (3D) integration of logic and memory for ultra-dense and fine-grained connectivity, (d) new architectures and runtimes for computation immersed in memory, and (e) new materials technologies and their integration for efficient heat removal.
Compared to conventional approaches, N3XT architectures promise to improve the energy efficiency of abundant-data applications significantly, in the range of three orders of magnitude, thereby enabling new frontiers of applications for both mobile devices and the cloud.