Uri Lublin and Dror G. Feitelson. The workload on parallel supercomputers: Modeling the characteristics of rigid jobs. Journal of Parallel and Distributed Computing, 63(20):1105--1122, 2003. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Workload Flurries - Dan Tsafrir Dror (2003) Self-citation (Feitelson) (Correct)
No context found.
U. Lublin and D. G. Feitelson, "The workload on parallel supercomputers: modeling the characteristics of rigid jobs ". J. Parallel & Distributed Comput. 63(11), pp. 1105--1122, Nov 2003.
Parallel Job Scheduling Under Dynamic Workloads - Eitan Frachtenberg Dror (2003) (1 citation) Self-citation (Feitelson) (Correct)
No context found.
Uri Lublin and Dror G. Feitelson. The workload on parallel supercomputers: Modeling the characteristics of rigid jobs. Journal of Parallel and Distributed Computing, 2003. (to appear).
Paired Gang Scheduling - Wiseman, Feitelson (2001) Self-citation (Feitelson) (Correct)
....detailed behavior of the system, it was not very realistic. In this subsection we turn to more realistic workloads. The experiments reported here were run on the full 16 nodes of the ParPar cluster. Each experiment consisted of running 1000 jobs generated according to the Lublin workload model [12]. The model specifies the arrival time, number of nodes, and running time of each job. As the model is based on long running jobs from production supercomputer installations, we divided the arrival times and running times by 40 to reduce the overall time to run the experiments. The arrival times ....
Lublin U. and Feitelson D. G., The Workload on Parallel Supercomputers: Modeling the Characteristics of Rigid Jobs. Technical Report 2001-12, School of Computer Science and Engineering, The Hebrew University of Jerusalem, Oct 2001.
Paired Gang Scheduling - Wiseman, Feitelson (2001) Self-citation (Feitelson) (Correct)
....the detailed behavior of the system, it was not very realistic. In this subsection we turn to more realistic workloads. The experiments reported here were run on the full 16 nodes of the ParPar cluster. Each experiment consisted of running 1000 jobs generated according to the Lublin workload model [14]. The model specifies the arrival time, number of nodes, and running time of each job. As the model is based on long running jobs from production supercomputer installations, we divided the arrival times and running times by 40 to reduce the overall time to run the experiments. The arrival times ....
U. Lublin and D. G. Feitelson, The Workload on Parallel Supercomputers: Modeling the Characteristics of Rigid Jobs. Technical Report 2001-12, School of Computer Science and Engineering, The Hebrew University of Jerusalem, Oct 2001.
Workload Modeling for Performance Evaluation - Feitelson (2002) (4 citations) Self-citation (Feitelson) (Correct)
.... 18, 6] Other examples include studies of process arrivals and runtimes [12, 37] le systems [36] and video streams [48] In the area of parallel systems, descriptive studies of workloads have only started to appear in recent years [29, 76, 58, 27, 14] There are also some attempts at modeling [10, 28, 21, 41, 23, 54, 15] and on line characterization [34] But where does the data come from There are two main options: use data that is available anyway, or collect data speci cally for the workload model. The latter can be done in two ways: active or passive instrumentation. Importantly, collected data can and ....
....by a small number of unrepresentative samples. Finding a distribution that matches given moments is relatively easy, because it can be done based on inverting equations that relate a distribution s parameters to its moments. Finding a distribution that ts a given shape is typically harder [54]. One possibility is to use a maximum likelihood method, which nds the parameters that most likely gave rise to the observed data. Another option is to use an iterative method, in which the goodness of t at each stage is quanti ed using the Chi square test, the Kolmogorov Smirnov test, or the ....
[Article contains additional citation context not shown here]
U. Lublin and D. G. Feitelson, The Workload on Parallel Supercomputers: Modeling the Characteristics of Rigid Jobs. Technical Report 2001-12, Hebrew University, Oct 2001.
The Effect of Metrics and Workloads on the Evaluation of.. - Feitelson Self-citation (Feitelson) (Correct)
....[5] which uses a buddy system to allocate processors in blocks that are powers of 2. Seven different workloads were used, of which four were models and three were actual workloads from production systems. The models used were those proposed by Feitelson [4] Jann [7] Downey [2] and Lublin [10]. The Feitelson workload, when generated with the default random seed, caused problems when trying to modify the load; using a different seed produced a workload that was more manageable. The Downey workload caused severe problems for the gang scheduler simulation. These problematic simulations ....
U. Lublin and D. G. Feitelson, The Workload on Parallel Supercomputers: Modeling the Characteristics of Rigid Jobs. Technical Report 2001-12, Hebrew University, Oct 2001.
The Forgotten Factor: Facts on Performance Evaluation and its.. - Feitelson (2002) (2 citations) Self-citation (Feitelson) (Correct)
....on the same or on di erent numbers of nodes. The dispersion of runtimes when the same application is executed many times. Practically all of this empirical data was unprecedented at the time. Since then, several other datasets have been studied, typically emphasizing job sizes and runtimes [27, 14, 15, 6, 2, 1, 18]. However, some new attributes have also been considered, such as speedup characteristics, memory usage, user estimates of runtime, and the probability that a job be cancelled [20, 10, 19, 2] 7 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 1 10 100 1000 10000 100000 runtime [s] 1 2 nodes ....
U. Lublin and D. G. Feitelson, The Workload on Parallel Supercomputers: Modeling the Characteristics of Rigid Jobs. Technical Report 2001-12, Hebrew University, Oct 2001.
On Grid Performance Evaluation - Using Synthetic Workloads (2006) (Correct)
No context found.
Uri Lublin and Dror G. Feitelson. The workload on parallel supercomputers: Modeling the characteristics of rigid jobs. Journal of Parallel and Distributed Computing, 63(20):1105--1122, 2003.
Loosely Coordinated Coscheduling In The Context Of . . . - Sodan (2005) (Correct)
No context found.
Lublin U, Feitelson DG. The workload on parallel Supercomputers: Modeling the characteristics of rigid jobs. Journal of Parallel and Distributed Computing 2003; 63(11):1105--1122.
Synthetic Grid Workloads With Ibis, Koala, And Grenchmark - Alexandru Iosup And (Correct)
No context found.
Uri Lublin and Dror G. Feitelson. The workload on parallel supercomputers: Modeling the characteristics of rigid jobs. Journal of Parallel & Distributed Computing, 63(11):1105--1122, Nov 2003.
Scheduling Task Parallel Applications For Rapid Turnaround on.. - Kondo (2005) (Correct)
No context found.
U. Lublin and D. G. Feitelson. The workload on parallel supercomputers: modeling the characteristics of rigid jobs. J. Parallel & Distributed Comput., 11(63), 2003.
Parallel Computer Workload Modeling with Markov Chains - Song, Ernemann, Yahyapour (2004) (Correct)
No context found.
Uri Lublin and Dror G. Feitelson. The workload on parallel supercomputers: Modeling the characteristics of rigid jobs. J. Parallel & Distributed Comput., 63(11):1105--1122, Nov 2003.
Scaling of Workload Traces - Ernemann, Song, Yahyapour (2003) (2 citations) (Correct)
No context found.
Uri Lublin and Dror G. Feitelson. The workload on parallel supercomputers: Modeling the characteristics of rigid jobs. J. Parallel & Distributed Comput., (to appear).
Workload Characteristics of a Multi-cluster Supercomputer - Li, Groep, Wolters (2004) (2 citations) (Correct)
No context found.
U. Lublin and D. G. Feitelson. The workload on parallel supercomputers: modeling the characteristics of rigid jobs. J. Parallel and Distributed Comput., 63(11): 1105--1122, 2003.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC