Operating system support for overlapping-ISA heterogeneous multi-core architectures
作者： Tong Li , Paul Brett , Rob Knauerhase , David Koufaty , Dheeraj Reddy
DOI: 10.1109/HPCA.2010.5416660
关键词:
摘要: A heterogeneous processor consists of cores that are asymmetric in performance and functionality. Such a design provides cost-effective solution for manufacturers to continuously improve both single-thread multi-thread throughput. This design, however, faces significant challenges the operating system, which traditionally assumes only homogeneous hardware. paper presents comprehensive study OS support architectures have overlapping, but non-identical instruction sets. Our algorithms allow applications transparently execute fairly share different types cores. We implemented these Linux 2.6.24 kernel evaluated them on an actual platform. Evaluation results demonstrate our designs efficiently manage hardware enable improvements range applications.
happyli.org 
researchgate.net 参考文章(28)
Muthu Venkatachalam, Prashant Chandra, Raj Yavatkar, A highly flexible, distributed multiprocessor architecture for network processing Computer Networks. ,vol. 41, pp. 563- 586 ,(2003) , 10.1016/S1389-1286(02)00450-4
Fred A. Bower, Daniel J. Sorin, Landon P. Cox, The Impact of Dynamically Heterogeneous Multicore Processors on Thread Scheduling IEEE Micro. ,vol. 28, pp. 17- 25 ,(2008) , 10.1109/MM.2008.46
Virgílio Almeida, Daniel Menascé, Cost-performance analysis of heterogeneity in supercomputer architectures conference on high performance computing (supercomputing). pp. 169- 177 ,(1990) , 10.5555/110382.110430
Daniel Shelepov, Juan Carlos Saez Alcaide, Stacey Jeffery, Alexandra Fedorova, Nestor Perez, Zhi Feng Huang, Sergey Blagodurov, Viren Kumar, HASS ACM SIGOPS Operating Systems Review. ,vol. 43, pp. 66- 75 ,(2009) , 10.1145/1531793.1531804
Tong Li, Dan Baumberger, David A. Koufaty, Scott Hahn, Efficient operating system scheduling for performance-asymmetric multi-core architectures Proceedings of the 2007 ACM/IEEE conference on Supercomputing - SC '07. pp. 53- ,(2007) , 10.1145/1362622.1362694
John B. Andrews, Constantine D. Polychronopoulos, An analytical approach to performance/cost modeling of parallel computers Journal of Parallel and Distributed Computing. ,vol. 12, pp. 343- 356 ,(1991) , 10.1016/0743-7315(91)90005-T
Jeffrey C Mogul, Jayaram Mudigonda, Nathan Binkert, Parthasarathy Ranganathan, Vanish Talwar, None, Using Asymmetric Single-ISA CMPs to Save Energy on Operating Systems IEEE Micro. ,vol. 28, pp. 26- 41 ,(2008) , 10.1109/MM.2008.47
Soraya Ghiasi, Tom Keller, Freeman Rawson, Scheduling for heterogeneous processors in server systems computing frontiers. pp. 199- 210 ,(2005) , 10.1145/1062261.1062295
Michael Gschwind, The cell broadband engine: exploiting multiple levels of parallelism in a chip multiprocessor International Journal of Parallel Programming. ,vol. 35, pp. 233- 262 ,(2007) , 10.1007/S10766-007-0035-4
R.J.O. Figueiredo, J.A.B. Fortes, Impact of heterogeneity on DSM performance high performance computer architecture. pp. 26- 35 ,(2000) , 10.1109/HPCA.2000.824336