skip to main content

Title: Neuromorphic Computing – From Materials Research to Systems Architecture Roundtable

Computation in its many forms is the engine that fuels our modern civilization. Modern computation—based on the von Neumann architecture—has allowed, until now, the development of continuous improvements, as predicted by Moore’s law. However, computation using current architectures and materials will inevitably—within the next 10 years—reach a limit because of fundamental scientific reasons. DOE convened a roundtable of experts in neuromorphic computing systems, materials science, and computer science in Washington on October 29-30, 2015 to address the following basic questions: Can brain-like (“neuromorphic”) computing devices based on new material concepts and systems be developed to dramatically outperform conventional CMOS based technology? If so, what are the basic research challenges for materials sicence and computing? The overarching answer that emerged was: The development of novel functional materials and devices incorporated into unique architectures will allow a revolutionary technological leap toward the implementation of a fully “neuromorphic” computer. To address this challenge, the following issues were considered: The main differences between neuromorphic and conventional computing as related to: signaling models, timing/clock, non-volatile memory, architecture, fault tolerance, integrated memory and compute, noise tolerance, analog vs. digital, and in situ learning New neuromorphic architectures needed to: produce lower energy consumption, potential novel nanostructured materials,more » and enhanced computation Device and materials properties needed to implement functions such as: hysteresis, stability, and fault tolerance Comparisons of different implementations: spin torque, memristors, resistive switching, phase change, and optical schemes for enhanced breakthroughs in performance, cost, fault tolerance, and/or manufacturability.« less
 [1] ;  [2] ;  [3] ;  [3]
  1. Univ. of California, San Diego, CA (United States)
  2. Argonne National Lab. (ANL), Argonne, IL (United States); Univ. of Chicago, IL (United States)
  3. Dept. of Energy (DOE) Office of Science, Washington, DC (United States)
Publication Date:
OSTI Identifier:
Resource Type:
Program Document
Research Org:
USDOE Office of Science (SC) (United States)
Sponsoring Org:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22)
Country of Publication:
United States