PIV and WPIV: Performance Index For Heterogeneous Systems Evaluation

This article presents two new performance indices (PIV - performance index vector and WPIV - weighted performance index vector), to evaluate heterogeneous computing systems, based on a Euclidian metric. Aiming to maximize the use of the machines, the proposed indices are a combination of several usual indices and the results of their evaluation through a simulator show an appropriate behavior for different kinds of applications

[1]  C. Petri.  Kommunikation mit Automaten , 1962 .

[2]  Veljko Milutinovic,et al.  A survey of heterogeneous computing: concepts and systems , 1996, Proc. IEEE.

[3]  Kalinka Regina Lucas Jaquie Castelo Branco.  Load and Performance Index for Parallel/Distributed System - Modelling and Metrics (Índices de carga e desempenho em ambientes paralelos/distribuídos - modelagem e métricas) , 2004 .

[4]  Paul Roe,et al.  Optimising heterogeneous task migration in the Gardens virtual cluster computer , 2000, Proceedings 9th Heterogeneous Computing Workshop (HCW 2000) (Cat. No.PR00556).

[5]  M. H. MacDougall.  Simulating computer systems: techniques and tools , 1989 .

[6]  Marcos José Santana,et al.  A novel metric for checking levels of heterogeneity in distributed computer systems , 2003 .

[7]  Baruch Awerbuch,et al.  An Opportunity Cost Approach for Job Assignment in a Scalable Computing Cluster , 2000, IEEE Trans. Parallel Distributed Syst..

[8]  Kang G. Shin,et al.  Period-Based Load Partitioning and Assignment for Large Real-Time Applications , 2000, IEEE Trans. Computers.

[9]  Stephen L. Scott,et al.  Work-based performance measurement and analysis of virtual heterogeneous machines , 1997, Int. J. Syst. Sci..

[10]  Viktor K. Prasanna,et al.  Heterogeneous computing: challenges and opportunities , 1993, Computer.

[11]  Helen D. Karatza,et al.  Parallel Job Scheduling in Homogeneous Distributed Systems , 2003, Simul..

[12]  Sarita Mazzini Bruschi,et al.  Extensão do ASiA para simulação de arquiteturas de computadores. , 1997 .

[13]  Thomas Kunz,et al.  The Influence of Different Workload Descriptions on a Heuristic Load Balancing Scheme , 1991, IEEE Trans. Software Eng..

[14]  Bin Yao,et al.  A taxonomy for describing matching and scheduling heuristics for mixed-machine heterogeneous computing systems , 1998, Proceedings Seventeenth IEEE Symposium on Reliable Distributed Systems (Cat. No.98CB36281).

[15]  Yves Robert,et al.  Optimal algorithms for scheduling divisible workloads on heterogeneous systems , 2003, Proceedings International Parallel and Distributed Processing Symposium.

[16]  G. N. Higginbottom,et al.  Performance Evaluation of Communication Networks , 1998 .

[17]  Robert G. Sargent,et al.  Validation and verification of simulation models , 1999, Proceedings of the 2004 Winter Simulation Conference, 2004..

[18]  Seyed Hossein Hosseini,et al.  An Experimental Study of Workload Indices for Non-dedicated, Heterogeneous Systems , 1997, PDPTA.

[19]  Domenico Ferrari,et al.  An Empirical Investigation of Load Indices for Load Balancing Applications , 1987, Performance.

[20]  Cyril Fonlupt,et al.  Data-Parallel Load Balancing Strategies , 1998, Parallel Comput..