TY - GEN
T1 - Routing Keys
AU - Samuel, Asaf
AU - Zahavi, Eitan
AU - Keslassy, Isaac
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/10/17
Y1 - 2017/10/17
N2 - The network plays a key role in High-Performance Computing (HPC) system efficiency. Unfortunately, current HPC routing solutions are not application-aware, and therefore cannot deal with the sudden HPC traffic bursts and their resulting congestion peaks.To address this problem, we introduce Routing Keys, a scalable routing paradigm for HPC networks that decouples intra- and inter-application flow contention. Our Application Routing Key (ARK) algorithm proactively allows each self-aware application to route its flows according to a predetermined routing key, i.e., its own intra-application contention-free routing. In addition, in our Network Routing Key (NRK) algorithm, a centralized scheduler chooses between several routing keys for the communication phases of each application, and therefore reduces inter-application contention while maintaining intra-application contention-free routing and avoiding scalability issues. Using extensive evaluations, we show that both ARK and NRK significantly improve the communication runtime by up to 2.7x.
AB - The network plays a key role in High-Performance Computing (HPC) system efficiency. Unfortunately, current HPC routing solutions are not application-aware, and therefore cannot deal with the sudden HPC traffic bursts and their resulting congestion peaks.To address this problem, we introduce Routing Keys, a scalable routing paradigm for HPC networks that decouples intra- and inter-application flow contention. Our Application Routing Key (ARK) algorithm proactively allows each self-aware application to route its flows according to a predetermined routing key, i.e., its own intra-application contention-free routing. In addition, in our Network Routing Key (NRK) algorithm, a centralized scheduler chooses between several routing keys for the communication phases of each application, and therefore reduces inter-application contention while maintaining intra-application contention-free routing and avoiding scalability issues. Using extensive evaluations, we show that both ARK and NRK significantly improve the communication runtime by up to 2.7x.
KW - HPC
KW - contention-free routing
KW - routing keys
UR - http://www.scopus.com/inward/record.url?scp=85039930561&partnerID=8YFLogxK
U2 - 10.1109/HOTI.2017.14
DO - 10.1109/HOTI.2017.14
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85039930561
T3 - Proceedings - 2017 IEEE 25th Annual Symposium on High-Performance Interconnects, HOTI 2017
SP - 9
EP - 16
BT - Proceedings - 2017 IEEE 25th Annual Symposium on High-Performance Interconnects, HOTI 2017
T2 - 25th IEEE Annual Symposium on High-Performance Interconnects, HOTI 2017
Y2 - 28 August 2017 through 30 August 2017
ER -