Exploitation of optical interconnects in future server architectures
By A. Benner, Mike Ignatowski, J. Kash, D. Kuchta, M. Ritter. IBM Journal of Research and Development, 2005
443 citations recorded by the source corpus.
View Paper: https://www.semanticscholar.org/paper/20f6ca246af84f0ccb105249d02197f92354cd6d
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Di Liang
- Martijn J. R. Heck
- Steven J. Koester
- J. Schaub
- A. Fang
- Nevin Kirman
- J. Chu
- Hui-wen Chen
Citations in the corpus
- Leveraging Optical Technology in Future Bus-based Chip Multiprocessors (2006, methodology): “We reasonably assume that the use of chip-to-chip optical technology will precede its on-chip application [6], and set off-chip pin bandwidth to 256GB/s and 128GB/s to L3 and memory, respectively.”
- 160 Gb/s Bidirectional Polymer-Waveguide Board-Level Optical Interconnects Using CMOS-Based Transceivers (2009, background): “2014877 steadily increasing aggregate bandwidth, channel (ch) data rate, and density requirements that are progressively more difficult to meet using electrical interconnect technology [1].”
- Hybrid Silicon Photonics for Optical Interconnects (2011, background): “ing the 10-m length over the past 30 years [2].”
- Germanium-on-SOI Infrared Detectors for Integrated Photonic Applications (2006, background): “A S bandwidth requirements for high-performance servers continue to rise, the incorporation of optical components to replace conventional copper interconnects for local I/O functions is being emphasized greatly [1].”