Optical linear algebra processors - Architectures and algorithmsAttention is given to the component design and optical configuration features of a generic optical linear algebra processor (OLAP) architecture, as well as the large number of OLAP architectures, number representations, algorithms and applications encountered in current literature. Number-representation issues associated with bipolar and complex-valued data representations, high-accuracy (including floating point) performance, and the base or radix to be employed, are discussed, together with case studies on a space-integrating frequency-multiplexed architecture and a hybrid space-integrating and time-integrating multichannel architecture.
Document ID
19870039334
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Casasent, David (Carnegie-Mellon University Pittsburgh, PA, United States)