Skip to Main Content
Multi-level electronic integration of massively parallel computers leads to latency effects and I/O bottlenecks. A new implementation scheme using MCM-to-MCM free-space optical interconnects is discussed in terms of architecture enhancement, system modeling and technical challenges. Building blocks of an experimental demonstrator including zero-biased-VCSEL with hybridized microlenses are also presented.
Date of Conference: 22-24 June 1997