E. L. Miller, "Input/output behavior of supercomputing applications," Tech. Rep. UCB/CSD 91/616, University of California at Berkeley, 1991. 21  Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
The Architectural Implications of Pipeline and.. - Thain, Bent.. (2002) (1 citation) (Correct)
....works by studying the sharing behavior of an important new class of workload. Many of these studies demonstrate the drastic differences in I O behavior for parallel applications compared to general purpose workloads. For example, parallel scientific workloads often have high, bursty I O rates [21, 25] and relatively constant behavior across different runs and input parameters [25] further, parallel workloads tend to be dominated by the storage and retrieval costs of large files, particularly check point files[21, 16] finally, quick deletion is uncommon [16] As many have observed, ....
.... For example, parallel scientific workloads often have high, bursty I O rates [21, 25] and relatively constant behavior across different runs and input parameters [25] further, parallel workloads tend to be dominated by the storage and retrieval costs of large files, particularly check point files[21, 16]; finally, quick deletion is uncommon [16] As many have observed, improvements in processor and memory speed have far outstripped improvements in I O performance. Models of I O system behavior [2, 26] have relied on general rules such as Amdahl s law to guide system design. A more detailed ....
E. L. Miller and R. H. Katz. Input/output behavior of supercomputing applications. In Proceedings of the ACM/IEEE conference on Supercomputing, pages 567--576, 1991.
Pipeline and Batch Sharing in Grid Workloads - Thain, Bent, Arpaci-Dusseau.. (2003) (3 citations) (Correct)
....a discussion of the ramifications of these workloads for end to end scalability and overall system design. 1. Introduction For many years, researchers have understood the importance of studying workload characteristics in order to evaluate their impact on current and future systems architecture [5, 15, 17]. Most of these previous application studies have focused on the detailed behavior of single applications, whether sequential or parallel. For example, the caching behavior of the SPEC workloads has long been a topic of intense scrutiny [6] and the communication characteristics of parallel ....
....works by studying the sharing behavior of an important new class of workload. Many of these studies demonstrate the drastic differences in I O behavior for parallel applications compared to general purpose workloads. For example, parallel scientific workloads often have high, bursty I O rates [17] and relatively constant behavior across different runs and input parameters [19] further, parallel workloads tend to be dominated by the storage and retrieval costs of large files, particularly check point files [17] finally, quick deletion is uncommon [14] 7. Conclusions Applications are ....
[Article contains additional citation context not shown here]
E. L. Miller and R. H. Katz. Input/output behavior of supercomputing applications. In Proceedings of the ACM/IEEE conference on Supercomputing, pages 567--576, 1991.
Automatic Arima Time Series Modeling And Forecasting Adaptive.. - Tran (2002) (3 citations) (Correct)
....series when new observations are added. To cover a broader spectrum of temporal patterns, we modeled time series in its general form, encompassing stationary, non stationary, and seasonal processes. Based on findings that access patterns in scientific applications are often bursty and seasonal [38, 53], modeling this behavior is crucial to achieving a higher fraction of the theoretical performance peak. Specifically, we have expanded the recursive parameter estimation algorithm for modeling stationary processes [2, 36, 11] to include a recursive differencing integration algorithm for the large ....
MILLER, E. L., AND KATZ, R. H. Input Output Behaviors of Super Computing Applications. In Proceedings of SuperComputing '91 (Nov. 1991), pp. 567-576. 158
The Vesta Parallel File System - Corbett, Feitelson (2001) (8 citations) (Correct)
....di erent numbers of I O nodes. they are satis ed from memory. To summarize, our results indicate that the Vesta bu er cache management is an important contributor to performance. This corroborates independent studies that anticipated the advantages of caching based on analysis of applications [31, 25]. It also shows that with regular access patterns all processes bene t from the prefetching, thus refuting the anxiety raised in [26] regarding this issue. 5.6 Performance of Sorting Application Synthetic benchmarks that gauge a system s peak performance are important, but they do not provide a ....
E. L. Miller and R. H. Katz, \Input/output behavior of supercomputing applications". In Supercomputing '91, pp. 567-576, Nov 1991.
Unknown - Self-citation (California Berkeley) (Correct)
No context found.
Ethan L. Miller. Input/output behavior of supercomputing applications. Technical Report UCB/CSD 91/616, University of California at Berkeley, 1991.
Input/output Characterization Of Parallel Systems Based On Three .. - Treaster (2004) Self-citation (Input) (Correct)
No context found.
Ethan L. Miller and Randy H. Katz. Input/output behavior of supercomputing applications. In Proceedings of the 1991.
File System Workload Analysis for Large Scale.. - Wang, Xin, Hong.. (2004) (1 citation) Self-citation (Applications) (Correct)
No context found.
E. L. Miller and R. H. Katz. Input/output behavior of supercomputing applications. In Proceedings of Supercomputing '91, pages 567--576, Nov. 1991.
File System Workload Analysis for Large Scale.. - Wang, Xin, Hong.. (2004) (1 citation) Self-citation (Applications) (Correct)
No context found.
E. L. Miller and R. H. Katz. Input/output behavior of supercomputing applications. In Proceedings of Supercomputing '91, pages 567--576, Nov. 1991.
File System Workload Analysis for Large Scale.. - Wang, Xin, Hong.. (2004) (1 citation) Self-citation (Applications) (Correct)
No context found.
E. L. Miller and R. H. Katz. Input/output behavior of supercomputing applications. In Proceedings of Supercomputing '91, pages 567--576, Nov. 1991.
File System Workload Analysis for Large Scale.. - Wang, Xin, Hong.. (2004) (1 citation) Self-citation (Applications) (Correct)
No context found.
E. L. Miller and R. H. Katz. Input/output behavior of supercomputing applications. In Proceedings of Supercomputing '91, pages 567--576, Nov. 1991.
An Analytic Performance Model of Disk Arrays - And Its Application (Correct)
No context found.
E. L. Miller, "Input/output behavior of supercomputing applications," Tech. Rep. UCB/CSD 91/616, University of California at Berkeley, 1991. 21
A Static Analysis of I/O Characteristics - Of Broad Class (Correct)
No context found.
Miller, E. L. and Katz, R. H., "Input/Output Behavior of Supercomputing Applications," Proceedings of Supercomputing '91, November 1991.
The Rubicon workload characterization tool - Veitch, Keeton (2001) (2 citations) (Correct)
No context found.
E.L. Miller and R.H. Katz. Input/output behavior of supercomputing applications. Proc. Supercomputing 1991, pp. 567-576, November 1991
Using System-Level Models to Evaluate I/O Subsystem Designs - Ganger, Patt (1998) (5 citations) (Correct)
No context found.
# E. Miller and R. Katz, "Input/Output Behavior of Supercomputing Applications," Proc. Supercomputing '91, pp. 567-576, 1991.
RAMA: An easy-to-use, high-performance parallel file system - Miller, Katz (1997) (2 citations) (Correct)
No context found.
E.L. Miller, R.H. Katz, Input/output behavior of supercomputing applications, in: Proceedings of Supercomputing '91, Nov. 1991, pp. 567-576.
Parallel I/O Subsystems in Massively Parallel.. - Feitelson, Corbett.. (Correct)
No context found.
E.L Miller and R.H. Katz, "Input/Output Behavior of Supercomputing Applications," &'ot. Supercomputing '91, CS Press, 1991, pp. 567-576.
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