Download:
|
by X. Shen, G. Thiruvathukal, W. Liao, A. Choudhary, A. Singh
http://www.ece.nwu.edu/~wkliao/MDMS/publications/hpc_asia.ps.gz
Add To MetaCart
Abstract:
Large-scale scientific applications have presented great challenges to computational scientists in terms of high performance and easy-to-manage. These simulations may employ multiple techniques and resources in a heterogeneously distributed environment. Effectively working in such an environment with high performance is crucial for modern large-scale simulations. In this paper, we present an integrated Java graphical user interface (IJ-GUI) that makes the entire environment virtually an easy-to-use control platform for managing complex programs and their large datasets. As far as performance is concerned, we also present and evaluate our initial implementation of two optimization schemes, i.e. data replica and data prediction, in such an environment when the user carries out visualization. Data replica can take advantage of `temporal locality' by caching the remote datasets on local disks; Data prediction, on the other hand, provides prefetch hints based on datasets ' past activities that are kept in databases. We also first introduce the data contiguity concept in such an environment that guides data prediction. The relationship of the two approaches are also discussed. 1
Citations
|
365
|
The implementation of POSTGRES
– Stonebraker, Rowe, et al.
- 1990
|
|
222
|
Disk-directed I/O for MIMD Multiprocessors
– Kotz
- 1994
|
|
154
|
The SDSC Storage Resource Broker
– Baru, Moore, et al.
- 1998
|
|
113
|
Improved parallel I/O via a two-phase run-time access strategy
– Rosario, Bordawekar, et al.
- 1993
|
|
101
|
Input-Output Characteristics of Scalable Parallel Applications
– Crandall, Aydt, et al.
- 1995
|
|
84
|
Prefetching in File Systems for MIMD Multiprocessors
– Kotz, Ellis
- 1990
|
|
79
|
PASSION: Parallel and scalable software for input-output
– Choudhary, Bordawekar, et al.
- 1994
|
|
76
|
Application-Controlled File Caching Policies
– Cao, Felten, et al.
- 1994
|
|
55
|
The Design and Implementation of SOLAR, a Portable Library for Scalable Out-of-Core Linear Algebra Computations
– Toledo, Gustavson
- 1996
|
|
49
|
Data sieving and collective I/O in ROMIO
– Thakur, Gropp, et al.
- 1999
|
|
44
|
Object-Relational DBMSs - Tracking the Next Great Wave
– Stonebraker, Brown
- 1999
|
|
31
|
The high performance storage system
– Coyne, Hulen, et al.
- 1993
|
|
11
|
Data Management for Large-Scale Scientific Computations in High Performance Distributed Systems
– Choudhary, Kandemir, et al.
- 1999
|
|
11
|
A novel application development environment for large-scale scientific computations
– Shen, Liao, et al.
- 2000
|
|
10
|
APRIL: A Run-Time Library for Tape Resident Data
– Memik, Kandemir, et al.
- 2000
|
|
8
|
Meta-data sharing for balanced performance
– Brown, Troy, et al.
- 1996
|
|
7
|
Database Management Systems, The McGraw-Hill Companies
– Ramakrishnan
- 1998
|
|
5
|
A portable and efficient parallel code for astrophysical fluid dynamics
– Malagoli, Dubey, et al.
|
