Page 286 - 2024-Vol20-Issue2
P. 286
282 | Alrudainy, Marzook, Hussein & Shafik
[2] H. Esmaeilzadeh, E. Blem, R. S. Amant, K. Sankar- ment of concurrent workloads for energy-efficient multi-
alingam, and D. Burger, “Dark silicon and the end of core systems,” Journal of Low Power Electronics and
multicore scaling,” IEEE micro, vol. 32, no. 3, pp. 122– Applications, vol. 10, no. 3, p. 25, 2020.
134, 2012.
[12] S. Tzilis, P. Trancoso, and I. Sourdis, “Energy-efficient
[3] A. Shafaei Bejestan, Y. Wang, S. Ramadurgam, Y. Xue, runtime management of heterogeneous multicores using
P. Bogdan, and M. Pedram, “Analyzing the dark silicon online projection,” ACM Transactions on Architecture
phenomenon in a many-core chip multi-processor under and Code Optimization (TACO), vol. 15, no. 4, pp. 1–26,
deeply-scaled process technologies,” in Proceedings of 2019.
the 25th edition on Great Lakes Symposium on VLSI,
pp. 127–132, 2015. [13] A. K. Singh, A. Prakash, K. R. Basireddy, G. V. Mer-
rett, and B. M. Al-Hashimi, “Energy-efficient run-time
[4] J. Henkel, H. Bukhari, S. Garg, M. U. K. Khan, H. Khdr, mapping and thread partitioning of concurrent opencl
F. Kriebel, U. Ogras, S. Parameswaran, and M. Shafique, applications on cpu-gpu mpsocs,” ACM Transactions on
“Dark silicon: From computation to communication,” Embedded Computing Systems (TECS), vol. 16, no. 5s,
in Proceedings of the 9th International Symposium on pp. 1–22, 2017.
Networks-on-Chip, pp. 1–8, 2015.
[14] C. Hankendi and A. K. Coskun, “Adaptive power and re-
[5] X. Wang, A. K. Singh, B. Li, Y. Yang, H. Li, and T. Mak, source management techniques for multi-threaded work-
“Bubble budgeting: Throughput optimization for dy- loads,” in 2013 IEEE International Symposium on Paral-
namic workloads by exploiting dark cores in many core lel & Distributed Processing, Workshops and Phd Forum,
systems,” IEEE Transactions on Computers, vol. 67, pp. 2302–2305, IEEE, 2013.
no. 2, pp. 178–192, 2017.
[15] R. A. Shafik, S. Yang, A. Das, L. A. Maeda-Nunez,
[6] X. Wang, B. Zhao, L. Wang, T. Mak, M. Yang, Y. Jiang, G. V. Merrett, and B. M. Al-Hashimi, “Learning transfer-
and M. Daneshtalab, “A pareto-optimal runtime power based adaptive energy minimization in embedded sys-
budgeting scheme for many-core systems,” Micropro- tems,” IEEE Transactions on Computer-Aided Design of
cessors and Microsystems, vol. 46, pp. 136–148, 2016. Integrated Circuits and Systems, vol. 35, no. 6, pp. 877–
890, 2015.
[7] E. Musoll, “Hardware-based load balancing for mas-
sive multicore architectures implementing power gating,” [16] A. Das, A. Kumar, B. Veeravalli, R. Shafik, G. Mer-
IEEE Transactions on Computer-Aided Design of Inte- rett, and B. Al-Hashimi, “Workload uncertainty char-
grated Circuits and Systems, vol. 29, no. 3, pp. 493–497, acterization and adaptive frequency scaling for energy
2010. minimization of embedded systems,” in 2015 Design,
Automation & Test in Europe Conference & Exhibition
[8] J. N. Mistry, B. M. Al-Hashimi, D. Flynn, and S. Hill, (DATE), pp. 43–48, IEEE, 2015.
“Sub-clock power-gating technique for minimising leak-
age power during active mode,” in 2011 Design, Automa- [17] B. K. Reddy, M. J. Walker, D. Balsamo, S. Diestelhorst,
tion & Test in Europe, pp. 1–6, IEEE, 2011. B. M. Al-Hashimi, and G. V. Merrett, “Empirical cpu
power modelling and estimation in the gem5 simulator,”
[9] J. Charles, P. Jassi, N. S. Ananth, A. Sadat, and A. Fe- in 2017 27th International Symposium on Power and
dorova, “Evaluation of the intel® core™ i7 turbo boost Timing Modeling, Optimization and Simulation (PAT-
feature,” in 2009 IEEE International Symposium on MOS), pp. 1–8, IEEE, 2017.
Workload Characterization (IISWC), pp. 188–197, IEEE,
2009. [18] A. Aalsaud, A. Rafiev, F. Xia, R. Shafik, and
A. Yakovlev, “Model-free runtime management of con-
[10] K. Ma and X. Wang, “Pgcapping: Exploiting power current workloads for energy-efficient many-core het-
gating for power capping and core lifetime balancing erogeneous systems,” in 2018 28th International Sympo-
in cmps,” in Proceedings of the 21st international con- sium on Power and Timing Modeling, Optimization and
ference on Parallel architectures and compilation tech- Simulation (PATMOS), pp. 206–213, IEEE, 2018.
niques, pp. 13–22, 2012.
[11] A. Aalsaud, F. Xia, A. Rafiev, R. Shafik, A. Romanovsky, [19] A. Aalsaud, R. Shafik, A. Rafiev, F. Xia, S. Yang, and
and A. Yakovlev, “Low-complexity run-time manage- A. Yakovlev, “Power–aware performance adaptation of
