TY - GEN
T1 - QoS-Aware stochastic power management for many-cores
AU - Pathania, Anuj
AU - Khdr, Heba
AU - Shafique, Muhammad
AU - Mitra, Tulika
AU - Henkel, Jörg
N1 - Funding Information:
This work was supported in parts by the German Research Foundation (DFG) as part of the Transregional Collaborative Research Centre “Invasive Computing" (SFB/TR 89), and in parts by National Research Foundation, Prime Minister’s O ce, Singapore under its Industry-IHL Partnership Grant and Huawei International Pte. Ltd. NRF2015-IIP003.
Publisher Copyright:
© 2018 Association for Computing Machinery.
Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2018/6/24
Y1 - 2018/6/24
N2 - A many-core processor can execute hundreds of multi-threaded tasks in parallel on its 100s-1000s of processing cores. When deployed in a Quality of Service (QoS)-based system, the many-core must execute a task at a target QoS. The amount of processing required by the task for the QoS varies over the task's lifetime. Accordingly, Dynamic Voltage and Frequency Scaling (DVFS) allows the many-core to deliver precise amount of processing required to meet the task QoS guarantee while conserving power. Still, a global control is necessitated to ensure that the many-core overall does not exceed its power budget. Previously, only non-stochastic controls have been proposed for the problem of QoS-aware power budgeting in many-cores. We propose the first stochastic control for the problem, which has a computational complexity less than the non-stochastic control by a factor of O (lnn) but with equivalent performance. The proposed stochastic control can operate with 6.4x less overhead than the non-stochastic control for a 256-task workload.
AB - A many-core processor can execute hundreds of multi-threaded tasks in parallel on its 100s-1000s of processing cores. When deployed in a Quality of Service (QoS)-based system, the many-core must execute a task at a target QoS. The amount of processing required by the task for the QoS varies over the task's lifetime. Accordingly, Dynamic Voltage and Frequency Scaling (DVFS) allows the many-core to deliver precise amount of processing required to meet the task QoS guarantee while conserving power. Still, a global control is necessitated to ensure that the many-core overall does not exceed its power budget. Previously, only non-stochastic controls have been proposed for the problem of QoS-aware power budgeting in many-cores. We propose the first stochastic control for the problem, which has a computational complexity less than the non-stochastic control by a factor of O (lnn) but with equivalent performance. The proposed stochastic control can operate with 6.4x less overhead than the non-stochastic control for a 256-task workload.
KW - Many-Core
KW - Power Budgeting
KW - Probabilistic Control
UR - http://www.scopus.com/inward/record.url?scp=85053660573&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85053660573&partnerID=8YFLogxK
U2 - 10.1145/3195970.3196097
DO - 10.1145/3195970.3196097
M3 - Conference contribution
AN - SCOPUS:85053660573
SN - 9781450357005
T3 - Proceedings - Design Automation Conference
BT - Proceedings of the 55th Annual Design Automation Conference, DAC 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 55th Annual Design Automation Conference, DAC 2018
Y2 - 24 June 2018 through 29 June 2018
ER -