Modeling performance of heterogeneous parallel computing systems

Clematis, Andrea; Corana, Angelo

doi:10.1016/s0167-8191(99)00044-7

Cited by 22 publications

(13 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It maps taskheterogeneity to system-heterogeneity using a hierarchical model. In [3], the authors suggest a scheme which uses a relative computational speed for each processing element in the system against a "gold standard", which is independent of workloads. In [25], each node in a system is described relative to the fastest processing element in the system, and the system modeled is reliant upon variances of the processing elements.…”

Section: Previous Workmentioning

confidence: 99%

“…In a one round algorithm for workload distribution onto the cluster, the time it takes to complete the task is the maximum time the slowest resource takes to complete its workload, B i : t total = max(P T i · B i ) (III.5) The adaptability of this framework is based on an analysis of the measurement of performance of the cluster derived 3 from individual resource profiles. This is accomplished by lessening the resource-to-resource capability variance; in essence, homogenizing the cluster for better control and predictability.…”

Section: B Workload Vectormentioning

confidence: 99%

See 1 more Smart Citation

Resource selection and allocation for dynamic adaptive computing in heterogeneous clusters

Duselis

Cauich

Wang

et al. 2009

2009 IEEE International Conference on Cluster Computing and Workshops

View full text Add to dashboard Cite

This paper provides a framework for dynamic adaptive computing in heterogeneous clusters for computationally intensive applications. The framework considers a set of discoverable interconnected computational resources and either a parallel or sequential workload needing to be executed. An adaptive inclusion/exclusion algorithm is used to select the resources by using novel performance measurements and profiling techniques. Furthermore, contrary to a greedy approach where all the resources are seized for the workload application, our framework only harnesses the best fit resources measured against system-wide performance characterization, and is contingent upon the current workload definition. The intelligent selection of a subset of resources has proven to achieve better performance; especially in environments with a high level of heterogeneity where the characteristics of some resources may not achieve the best performance the cluster can provide. Additionally, this paper provides a novel analysis of the workload and cluster characteristics, exhibiting analytical starting points to be used in the resource selection.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: B Workload Vectormentioning

confidence: 99%

Resource selection and allocation for dynamic adaptive computing in heterogeneous clusters

Duselis

Cauich

Wang

et al. 2009

2009 IEEE International Conference on Cluster Computing and Workshops

View full text Add to dashboard Cite

show abstract

“…It maps taskheterogeneity to system-heterogeneity using a hierarchical model. In [16], the authors suggest a scheme which uses a relative computational speed for each processing element in the system against a "gold standard", which is independent of workloads. In [17], each node in a system is described relative to the fastest processing element in the system, and the system modeled is reliant upon variances of the processing elements.…”

Section: A Prior Workmentioning

confidence: 99%

Concurrent adaptive computing in heterogeneous environments (CACHE)

Duselis

Scherson

2009

2009 IEEE International Symposium on Parallel &Amp; Distributed Processing

View full text Add to dashboard Cite

We introduce a computational framework for concurrent adaptive computing in heterogeneous environments for computationally intensive applications. This framework considers the presence of inter-connected computational resources which are discoverable and a workload which needs to be executed either by concurrent means or on a singular resource. The selection of resources, using a novel measurement of performance, leads to the adaptive inclusion/exclusion of resources to be used in the efficient execution of workload computations. The adaptive approach is that it makes a determination to include a proper subset of resources for system inclusion to execute a workload, which is contrary (except when the subset is allinclusive) to a greedy approach where all the resources are seized for the workload application. The selection of a subset of resources may be more efficient due to the high level of heterogeneity of the resources, where, for some resources, certain resource selections may be detrimental or have no value to send work there. Furthermore, this framework aims to lessen the unpredictability and uncontrollability of heterogeneous systems by using this analysis for resource selection.

show abstract

“…Most of the existing researches are based on homogeneous cluster systems and the evaluations are confined to a single cluster [12][13][14][15]. Also, a performance model for Network of Workstations with processor heterogeneity is discussed in [16]. A general model based on queuing networks was proposed for a single cluster computing in [12].…”

mentioning

confidence: 99%

Analytical modeling of interconnection networks in heterogeneous multi-cluster systems

2007

View full text Add to dashboard Cite

The study of interconnection networks is important because the overall performance of a distributed system is often critically hinged on the effectiveness of its interconnection network. This paper addresses the problem of interconnection networks performance modeling of large-scale distributed systems with emphases on heterogeneous multi-cluster computing systems. We present an analytical model to predict message latency in multi-cluster systems in the presence of node, network and system organization heterogeneity. The model is validated through comprehensive simulation, which demonstrates that the proposed model exhibits a good degree of accuracy for various system organizations and under different working conditions.

show abstract

Modeling performance of heterogeneous parallel computing systems

Cited by 22 publications

References 12 publications

Resource selection and allocation for dynamic adaptive computing in heterogeneous clusters

Resource selection and allocation for dynamic adaptive computing in heterogeneous clusters

Concurrent adaptive computing in heterogeneous environments (CACHE)

Analytical modeling of interconnection networks in heterogeneous multi-cluster systems

Contact Info

Product

Resources

About