An optical highway for parallel interconnection of processors has previously been presented. Several matrix-vector multiplication algorithms are mapped onto the highway, and these are compared with traditional results. The practicalities of implementing such a design are then discussed with attention to possible fabrication routes and the polarization losses involved. This specifically involves mapping the parameter space of the angle of polarizing elements by a Monte Carlo method. © 2006 Society of Photo-Optical Instrumentation Engineers.
|Publication status||Published - Sept 2006|
- Liquid crystals
- Optical computing
- Optical interconnects