Understanding the Performance of Multi-core Platforms
Recent advancements in multi-core systems have created interest among many research groups to develop efficient algorithms for multi-core platforms. The performance evaluation of such multi-core architectures becomes essential before the design of such high end, cutting edge systems. One important question is how to evaluate the performance of such multi-core systems? In this paper, the authors have made a preliminary study of simulating the various architectural components of a typical multi-core environment using Super ESCalar (SESC) simulator and evaluated their performance using lmbench.
Keywordsmulti-core performance simulator SESC lmbench
Unable to display preview. Download preview PDF.
- 1.Calandrino, J.M., Anderson, J.H.: On the Design and Implementation of a Cache Aware Multicore Real-Time Scheduler. In: Proceedings of 21st Euromicro Conference on Real-Time Systems, pp. 194–204 (2009)Google Scholar
- 2.Calandrino, J.M., Anderson, J.H.: Cache-Aware Real-Time Scheduling on Multi-core Platforms: Heuristics and a Case Study. In: Proceedings of 20th Euromicro Conference on Real-Time Systems, pp. 299–308 (2008)Google Scholar
- 3.Bui, J., Xu, C., Gurumurthy, S.: Understanding Performance Issues on both Single Core and multicore Architecture. In: Technical Report, University of Virginia, Department of Computer Science, Charlottesville (2007)Google Scholar
- 6.Ortego, P.M., Sack, P.: Super ESCalar simulator. In: Proceedings of 17th Euromicro Conference on Real-Time Systems, pp. 1–4 (2004)Google Scholar
- 10.McVoy, L., Staelin, C.: lmbench: Portable tools for performance analysis. In: Proceedings of the 1996 Annual Conference on USENIX Annual Technical Conference, pp. 23–39 (1996)Google Scholar