by Emilia Rosti, Evgenia Smirni, Mark S. Squillante
http://www.cs.wm.edu/~esmirni/docs/chario.ps.gz
Add To MetaCart
Abstract:
Characterizing the I/O requirements of parallel applications that manipulate huge amounts of data, such as scientific codes, is critical to the achievement of good application performance and to the effective use of parallel systems. In this paper we formulate a compositional stochastic model of the behavior of I/O intensive scientific applications, which can be applied at various granularity levels of characterization. Based on the observation of the interaction of CPU and I/O activity in a set of scientific codes, we exercise the stochastic model. The model is in excellent agreement with experimental data in the set of the examined codes. For the model to be used for performance prediction, we also propose a set of functional forms for forecasting the scalability of computation and I/O components of an application. The complexity of the functional form adopted affects the accuracy of performance prediction. 1
Citations
|
269
|
Validity of the Single Processor Approach to Achieving Large-Scale Computing Capabilities
– Amdahl
- 1967
|
|
200
|
The HP AutoRAID hierarchical storage system
– Wilkes, Golding, et al.
- 1996
|
|
130
|
Speedup versus efficiency in parallel systems
– Eager, Zahorjan, et al.
- 1989
|
|
127
|
B.: Scalable Performance Analysis: the Pablo Performance Analysis Environment
– Reed, Roth, et al.
- 1993
|
|
99
|
Input/output behavior of supercomputer applications
– Miller, Katz
- 1991
|
|
83
|
File-Access Characteristics of Parallel Scientific Workloads
– Nieuwejaar, Kotz, et al.
- 1996
|
|
82
|
Tuning the performance of I/O intensive parallel applications
– Acharya, Uysal, et al.
- 1996
|
|
65
|
The processor working set and its use in scheduling multiprocessor systems
– Ghosal, Serazzi, et al.
- 1991
|
|
55
|
The Design and Implementation of SOLAR, a Portable Library for Scalable Out-of-Core Linear Algebra Computations
– Toledo, Gustavson
- 1996
|
|
49
|
Performance of the iPSC/860 Concurrent File System
– Nitzberg
- 1992
|
|
38
|
I/O Requirements of Scientific Applications: An Evolutionary View
– Smirni, Aydt, et al.
- 1996
|
|
36
|
Intelligent, adaptive file system policy selection
– Madhyastha, Reed
- 1996
|
|
34
|
Preliminary survey of I/O intensive applications, Technical Report CCSF-38, Scalable I/O initiative, Caltech Concurrent supercomputing facilities
– Poole
- 1995
|
|
23
|
Dynamic I/O Characterization of I/O Intensive Scientific Applications
– Pasquale, Polyzos
- 1994
|
|
22
|
Lessons from Characterizing the Input/Output Behavior of Parallel Scientific Applications. Performance Evaluation: An
– Smirni, Reed
- 1998
|
|
22
|
Requirements of I/O Systems for Parallel Machines: An Application-driven Study
– Uysal, Acharya, et al.
- 1997
|
|
14
|
The impact of I/O on program behavior and parallel scheduling
– Rosti, Serazzi, et al.
- 1998
|
|
9
|
Quantum chemical reaction dynamics on a highly parallel supercomputer. Theoretica Chimica Acta 79
– Wu, Cuccaro, et al.
- 1991
|
|
8
|
Scalable I/O Initiative. California Institute of Technology, Available at http://www.ccsf.caltech.edu/SIO
– Poole
- 1996
|
|
5
|
Input/Output Characterization of Scalable Parallel Applications
– Crandall, Aydt, et al.
- 1995
|
|
2
|
On Some Associative, Parallel and Analog Computations, Associative Information Technologies
– Minsky, Papert
- 1971
|
|
2
|
Algorithmic influences on i/o access patterns and parallel file system performance
– Smirni, Elford, et al.
- 1997
|
