Cost-performance analysis of heterogeneity in supercomputer architectures
Proceedings of the 1990 ACM/IEEE conference on Supercomputing
Using random task graphs to investigate the potential benefits of heterogeneity in parallel systems
Proceedings of the 1992 ACM/IEEE conference on Supercomputing
SODA '97 Proceedings of the eighth annual ACM-SIAM symposium on Discrete algorithms
Computers and Intractability: A Guide to the Theory of NP-Completeness
Computers and Intractability: A Guide to the Theory of NP-Completeness
Routing Algorithms for DHTs: Some Open Questions
IPTPS '01 Revised Papers from the First International Workshop on Peer-to-Peer Systems
Making gnutella-like P2P systems scalable
Proceedings of the 2003 conference on Applications, technologies, architectures, and protocols for computer communications
Selfish load balancing and atomic congestion games
Proceedings of the sixteenth annual ACM symposium on Parallelism in algorithms and architectures
Coordination mechanisms for congestion games
ACM SIGACT News
How many servers are best in a dual-priority M/PH/k system?
Performance Evaluation
Hi-index | 0.00 |
Suppose we have a parallel or distributed system whose nodes have limited capacities, such as processing speed, bandwidth, memory, or disk space. How does the performance of the system depend on the amount of heterogeneity of its capacity distribution? We propose a general framework to quantify the worst-case effect of increasing heterogeneity in models of parallel systems. Given a cost function g(C,W) representing the system's performance as a function of its nodes' capacities C and workload W (such as the completion time of an optimum schedule of jobs W on machines C), we say that g has price of heterogeneity α when for any workload, cost cannot increase by more than a factor α if node capacities become arbitrarily more heterogeneous. We give constant bounds on the price of heterogeneity of several well-known job scheduling and graph degree/diameter problems, indicating that increasing heterogeneity can never be much of a disadvantage. On the other hand, with the introduction of timing constraints such as release times or precedence constraints on the jobs, the dependence on node capacities becomes more complex, so that increasing heterogeneity may be quite detrimental.