TY - GEN
T1 - Modelling DVFS and UFS for region-based energy aware tuning of HPC applications
AU - Chadha, Mohak
AU - Gerndt, Michael
N1 - Publisher Copyright:
© 2019 IEEE
PY - 2019/5
Y1 - 2019/5
N2 - Energy efficiency and energy conservation are one of the most crucial constraints for meeting the 20MW power envelope desired for exascale systems. Towards this, most of the research in this area has been focused on the utilization of user-controllable hardware switches such as per-core dynamic voltage frequency scaling (DVFS) and software controlled clock modulation at the application level. In this paper, we present a tuning plugin for the Periscope Tuning Framework which integrates fine-grained autotuning at the region level with DVFS and uncore frequency scaling (UFS). The tuning is based on a feed-forward neural network which is formulated using Performance Monitoring Counters (PMC) supported by x86 systems and trained using standardized benchmarks. Experiments on five standardized hybrid benchmarks show an energy improvement of 16.1% on average when the applications are tuned according to our methodology as compared to 7.8% for static tuning.
AB - Energy efficiency and energy conservation are one of the most crucial constraints for meeting the 20MW power envelope desired for exascale systems. Towards this, most of the research in this area has been focused on the utilization of user-controllable hardware switches such as per-core dynamic voltage frequency scaling (DVFS) and software controlled clock modulation at the application level. In this paper, we present a tuning plugin for the Periscope Tuning Framework which integrates fine-grained autotuning at the region level with DVFS and uncore frequency scaling (UFS). The tuning is based on a feed-forward neural network which is formulated using Performance Monitoring Counters (PMC) supported by x86 systems and trained using standardized benchmarks. Experiments on five standardized hybrid benchmarks show an energy improvement of 16.1% on average when the applications are tuned according to our methodology as compared to 7.8% for static tuning.
KW - Autotuning
KW - Dynamic tuning
KW - Dynamic voltage and frequency scaling
KW - Energy-efficiency
KW - Uncore frequency scaling
UR - http://www.scopus.com/inward/record.url?scp=85072834573&partnerID=8YFLogxK
U2 - 10.1109/IPDPS.2019.00089
DO - 10.1109/IPDPS.2019.00089
M3 - Conference contribution
AN - SCOPUS:85072834573
T3 - Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium, IPDPS 2019
SP - 805
EP - 814
BT - Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium, IPDPS 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 33rd IEEE International Parallel and Distributed Processing Symposium, IPDPS 2019
Y2 - 20 May 2019 through 24 May 2019
ER -