Abstract
Recent advances in multi- and many-core architectures include increased hardware-level parallelism (i.e., core counts) and the emergence of platform-level heterogeneity. System software managing these platforms is typically comprised of multiple independent resource managers (e.g., drivers and specialized runtimes) customized for heterogeneous vs. general purpose platform elements. This independence, however, can cause performance degradation for an application that spans diverse cores and resource managers, unless managers coordinate with each other to better service application needs. This paper first presents examples that demonstrate the need for coordination among multiple resource managers on heterogeneous multicore platforms. It then presents useful coordination schemes for a platform coupling an IXP network processor with x86 cores and running web and multimedia applications. Experimental evidence of performance gains achieved through coordinated management motivates a case for standard coordination mechanisms and interfaces for future heterogeneous many-core systems.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Chapin, J., Rosenblum, M., Devine, S.: Hive: fault containment for shared-memory multiprocessors. SIGOPS Oper. Syst. Rev. (1995)
Krieger, O., Auslander, M., et al.: K42: building a complete operating system. In: Eurosys (2006)
Agarwala, S., Alegre, F., Schwan, K.: E2EProf: Automated End-to-End Performance Management for Enterprise Systems. In: DSN (2007)
Kumar, V., Schwan, K.: A state-space approach to SLA based management. In: NOMS (2008)
Stewart, C., Kelly, T., Zhang, A., Shen, K.: A dollar from 15 cents: cross-platform management for internet services. In: USENIX Annual Technical Conference (2008)
Zhu, X., Young, D.: 1000 Islands: Integrated Capacity and Workload Management for the Next Generation Data Center. In: ICAC (2008)
Kumar, S., Talwar, V., Schwan, K.: vManage: loosely coupled platform and virtualization management in data centers. In: ICAC (2009)
Gupta, V., Gavrilovska, A., Schwan, K., et al.: GViM: GPU-accelerated virtual machines. In: HPCVirt (2009)
Barham, P., Dragovic, B., Fraser, K., et al.: Xen and the art of virtualization. In: SOSP (2003)
Hong, S., Kim, H.: An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness. In: ISCA (2009)
AMD Opteron six-core rocessors, http://bit.ly/8oe8uU
AMD Fusion Processors, http://bit.ly/7fA5sb
Darwin: The Streaming Server, http://bit.ly/f4EWU
Intel QuickPath Interconnect, http://bit.ly/5OYmVP
Intel Nehalem Processors, http://bit.ly/5eNDKy
Larrabee: An x86 many-core architecture for visual computing, http://bit.ly/5sgX8T
Howard, J., Dighe, S., et al.: A 48-Core IA-32 Message-Passing Processor with DVFS in 45nm CMOS. In: International Solid State Circuits Conference (2010)
IBM Corporation: A Wire-speed Power processor: 2.3 GHz 45 nm SOI with 16 cores and 64 threads. In: International Solid State Circuits Conference (2010)
Adiletta, M., Rosenbluth, M., et al.: The Next Generation of Intel IXP Network Processors. Intel Technology Journal (2002)
Govil, K., Teodosiu, D., et al.: Cellular disco: resource management using virtual clusters on shared-memory multiprocessors. ACM Trans. Comput. Syst. (2000)
Nightingale, E.B., Hodson, O., et al.: Helios: heterogeneous multiprocessing with satellite kernels. In: SOSP (2009)
Nathuji., R., Schwan., K., et al.: VPM tokens: virtual machine-aware power budgeting in datacenters. In: Cluster Computing (2009)
Wickizer, S.B., Chen, H., et al.: Corey: An Operating system for Many Cores. In: OSDI (2008)
Baumann, A., Barham, P., et al.: The multikernel: a new OS architecture for scalable multicore systems. In: SOSP (2009)
Barham, P., Donnelly, A., Isaacs, R., Mortier, R.: Using Magpie for Request Extraction and Workload Modelling. In: OSDI (2004)
Cherkasova, L., Gupta, D., Vahdat, A.: Comparison of the three CPU schedulers in Xen. SIGMETRICS Perform. Eval. Rev. (2007)
Lee, M., Krishnakumar., A.S., Krishna., P., Singh, N., Yajnik, S.: Supporting soft real-time tasks in the xen hypervisor. In: VEE (2010)
Butrico, M., Da Silva, D., Krieger, O., et al.: Specialized execution environments. SIGOPS Oper. Syst. Rev. (2008)
Bala, V., Bruck, J., et al.: CCL: A Portable and Tunable Collective Communication Library for Scalable Parallel Computers. IEEE Transactions on Parallel and Distributed Systems (1995)
Frey, J., Tannenbaum, T., et al.: Condor-G: A Computation Management Agent for Multi-Institutional Grids. In: Cluster Computing (2002)
Govindan, S., Choi, J., Nath, A.R., et al.: Xen and Co.: Communication-Aware CPU Management in Consolidated Xen-Based Hosting Platforms. IEEE Transactions on Computers (2009)
Ongaro, D., Cox, A.L., Rixner, S.: Scheduling I/O in virtual machine monitors. In: VEE (2008)
Anderson, T.E., Bershad, B.N., et al.: Scheduler Activations: Effective Kernel Support for the User-level Management of Parallelism. ACM Transactions on Computer Systems (1992)
Rosu, M.-C., Schwan, K., Fujimoto, R.: Supporting Parallel Applications on Clusters of Workstations: The
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tembey, P., Gavrilovska, A., Schwan, K. (2011). A Case for Coordinated Resource Management in Heterogeneous Multicore Platforms. In: Varbanescu, A.L., Molnos, A., van Nieuwpoort, R. (eds) Computer Architecture. ISCA 2010. Lecture Notes in Computer Science, vol 6161. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24322-6_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-24322-6_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24321-9
Online ISBN: 978-3-642-24322-6
eBook Packages: Computer ScienceComputer Science (R0)