First International Workshop on Massively Parallel Processing Using Optical Interconnections
DOI: 10.1109/mppoi.1994.336641
|View full text |Cite
|
Sign up to set email alerts
|

A fine-grain, high-throughput architecture using through-wafer optical interconnect

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 8 publications
(1 citation statement)
references
References 15 publications
0
1
0
Order By: Relevance
“…Each node occupies a square area of 1 cm 2 and is separated by 0.5 cm from its neighbors for a minimum connection path of 1.5 cm (die only). Recent studies confirm that packaging of multiprocessor free-space optical interconnects at this level of compaction is feasible [28,29]. The VCSEL and P-I-N detector arrays are integrated on top of the CMOS circuits via flip chip bonding [30].…”
Section: Latency Comparisonmentioning
confidence: 99%
“…Each node occupies a square area of 1 cm 2 and is separated by 0.5 cm from its neighbors for a minimum connection path of 1.5 cm (die only). Recent studies confirm that packaging of multiprocessor free-space optical interconnects at this level of compaction is feasible [28,29]. The VCSEL and P-I-N detector arrays are integrated on top of the CMOS circuits via flip chip bonding [30].…”
Section: Latency Comparisonmentioning
confidence: 99%