TY - GEN
T1 - Exploiting last idle periods of links for network power management
AU - Li, F.
AU - Chen, G.
AU - Kandemir, M.
AU - Karakoy, M.
PY - 2005
Y1 - 2005
N2 - Network power optimization is becoming increasingly important as the sizes of the data manipulated by parallel applications and the complexity of inter-processor data communications are continuously increasing. Several hardware-based schemes have been proposed in the past for reducing network power consumption, either by turning off unused communication links or by lowering voltage/frequency in links with low usage. While the prior research shows that these schemes can be effective in certain cases, they share the common drawback of not being able to predict the link active and idle times very accurately. This paper, instead, proposes a compiler-based scheme that determines the last use of communication links at each loop nest and inserts explicit link turn-off calls in the application source. Specifically, for each loop nest, the compiler inserts a turn-off call per communication link. Each turned-off link is reactivated upon the next access to it. We automated this approach within a parallelizing compiler and applied it to eight array-intensive embedded applications.
AB - Network power optimization is becoming increasingly important as the sizes of the data manipulated by parallel applications and the complexity of inter-processor data communications are continuously increasing. Several hardware-based schemes have been proposed in the past for reducing network power consumption, either by turning off unused communication links or by lowering voltage/frequency in links with low usage. While the prior research shows that these schemes can be effective in certain cases, they share the common drawback of not being able to predict the link active and idle times very accurately. This paper, instead, proposes a compiler-based scheme that determines the last use of communication links at each loop nest and inserts explicit link turn-off calls in the application source. Specifically, for each loop nest, the compiler inserts a turn-off call per communication link. Each turned-off link is reactivated upon the next access to it. We automated this approach within a parallelizing compiler and applied it to eight array-intensive embedded applications.
UR - http://www.scopus.com/inward/record.url?scp=29244478908&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=29244478908&partnerID=8YFLogxK
U2 - 10.1145/1086228.1086253
DO - 10.1145/1086228.1086253
M3 - Conference contribution
AN - SCOPUS:29244478908
SN - 1595930914
SN - 9781595930910
T3 - Proceedings of the 5th ACM International Conference on Embedded Software, EMSOFT 2005
SP - 134
EP - 137
BT - Proceedings of the 5th ACM International Conference on Embedded Software, EMSOFT 2005
PB - Association for Computing Machinery (ACM)
T2 - 5th ACM International Conference on Embedded Software, EMSOFT 2005
Y2 - 19 September 2005 through 22 September 2005
ER -