TY - GEN
T1 - ProjecToR
T2 - 2016 ACM Conference on Special Interest Group on Data Communication, SIGCOMM 2016
AU - Ghobadi, Monia
AU - Mahajan, Ratul
AU - Phanishayee, Amar
AU - Devanur, Nikhil
AU - Kulkarni, Janardhan
AU - Ranade, Gireeja
AU - Blanche, Pierre Alexandre
AU - Rastegarfar, Houman
AU - Glick, Madeleine
AU - Kilper, Daniel
N1 - Publisher Copyright:
© 2016 ACM.
PY - 2016/8/22
Y1 - 2016/8/22
N2 - We explore a novel, free-space optics based approach for building data center interconnects. It uses a digital micromirror device (DMD) and mirror assembly combination as a transmitter and a photodetector on top of the rack as a receiver (Figure 1). Our approach enables all pairs of racks to establish direct links, and we can reconfigure such links (i.e., connect different rack pairs) within 12 μs. To carry traffic from a source to a destination rack, transmitters and receivers in our interconnect can be dynamically linked in millions of ways. We develop topology construction and routing methods to exploit this flexibility, including a flow scheduling algorithm that is a constant factor approximation to the offline optimal solution. Experiments with a small prototype point to the feasibility of our approach. Simulations using realistic data center workloads show that, compared to the conventional folded-Clos interconnect, our approach can improve mean flow completion time by 30-95% and reduce cost by 25-40%.
AB - We explore a novel, free-space optics based approach for building data center interconnects. It uses a digital micromirror device (DMD) and mirror assembly combination as a transmitter and a photodetector on top of the rack as a receiver (Figure 1). Our approach enables all pairs of racks to establish direct links, and we can reconfigure such links (i.e., connect different rack pairs) within 12 μs. To carry traffic from a source to a destination rack, transmitters and receivers in our interconnect can be dynamically linked in millions of ways. We develop topology construction and routing methods to exploit this flexibility, including a flow scheduling algorithm that is a constant factor approximation to the offline optimal solution. Experiments with a small prototype point to the feasibility of our approach. Simulations using realistic data center workloads show that, compared to the conventional folded-Clos interconnect, our approach can improve mean flow completion time by 30-95% and reduce cost by 25-40%.
KW - Data centers
KW - Free-space optics
KW - Reconfigurablility
UR - http://www.scopus.com/inward/record.url?scp=84986607730&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84986607730&partnerID=8YFLogxK
U2 - 10.1145/2934872.2934911
DO - 10.1145/2934872.2934911
M3 - Conference contribution
AN - SCOPUS:84986607730
T3 - SIGCOMM 2016 - Proceedings of the 2016 ACM Conference on Special Interest Group on Data Communication
SP - 216
EP - 229
BT - SIGCOMM 2016 - Proceedings of the 2016 ACM Conference on Special Interest Group on Data Communication
PB - Association for Computing Machinery, Inc
Y2 - 22 August 2016 through 26 August 2016
ER -