The Impact of Performance Asymmetry in Emerging Multicore Architectures

Performance asymmetry in multicore architectures arises when individual cores have different performance. Building such multicore processors is desirable because many simple cores together provide high parallel performance while a few complex cores ensure high serial performance. However, application developers typically assume computational cores provide equal performance, and performance asymmetry breaks this assumption. This paper is concerned with the behavior of commercial applications running on performance asymmetric systems. We present the first study investigating the impact of performance asymmetry on a wide range of commercial applications using a hardware prototype. We quantify the impact of asymmetry on an applicationýs performance variance when run multiple times, and the impact on the applicationýs scalability. Performance asymmetry adversely affects behavior of many workloads. We study ways to eliminate these effects. In addition to asymmetry-aware operating system kernels, the application often itself needs to be aware of performance asymmetry for stable and scalable performance.

[1]  Jack J. Purdum,et al.  C programming guide , 1983 .

[2]  John Paul Shen,et al.  Best of both latency and throughput , 2004, IEEE International Conference on Computer Design: VLSI in Computers and Processors, 2004. ICCD 2004. Proceedings..

[3]  Leslie Jill Miller.  A heterogeneous multiprocessor design and the distributed scheduling of its task group workload , 1982, ISCA.

[4]  Renato J. O. Figueiredo,et al.  Impact of heterogeneity on DSM performance , 2000, Proceedings Sixth International Symposium on High-Performance Computer Architecture. HPCA-6 (Cat. No.PR00550).

[5]  Virgílio A. F. Almeida,et al.  Cost-performance analysis of heterogeneity in supercomputer architectures , 1990, Proceedings SUPERCOMPUTING '90.

[6]  Yen-Kuang Chen,et al.  Implementation of H.264 encoder on general-purpose processors with hyper-threading technology , 2004, IS&T/SPIE Electronic Imaging.

[7]  Richard E. Overill,et al.  Heterogeneous Computing Machines and Amdahl's Law , 1996, Parallel Comput..

[8]  Norman P. Jouppi,et al.  Single-ISA heterogeneous multi-core architectures: the potential for processor power reduction , 2003, Proceedings. 36th Annual IEEE/ACM International Symposium on Microarchitecture, 2003. MICRO-36..

[9]  José A. B. Fortes,et al.  A heterogeneous hierarchical solution to cost-efficient high performance computing , 1996, Proceedings of SPDP '96: 8th IEEE Symposium on Parallel and Distributed Processing.

[10]  Michael A. Bender,et al.  Scheduling Cilk multithreaded parallel programs on processors of different speeds , 2000, SPAA.

[11]  Philip Enslow,et al.  Multiprocessor Organization—a Survey , 1977, CSUR.

[12]  Norman P. Jouppi,et al.  Single-ISA heterogeneous multi-core architectures for multithreaded workload performance , 2004, Proceedings. 31st Annual International Symposium on Computer Architecture, 2004..

[13]  Jane W.-S. Liu,et al.  Optimal scheduling of independent tasks on heterogeneous computing systems , 1974, ACM '74.

[14]  EnslowPhilip.  Multiprocessor Organizationa Survey , 1977 .

[15]  Milind Girkar,et al.  Towards efficient multi-level threading of H.264 encoder on Intel hyper-threading architectures , 2004, 18th International Parallel and Distributed Processing Symposium, 2004. Proceedings..

[16]  Frederic G Withington.  Technology forecast , 1985 .