| An architectural research facility: ISP descriptions, simulation, data collection |
| Full text |
Pdf
(1.24 MB)
|
| Source
|
AFIPS Joint Computer Conferences
archive
Proceedings of the June 13-16, 1977, national computer conference
table of contents
Dallas, Texas
SESSION: Selection methods for a family of computer architectures
table of contents
Pages 161-173
Year of Publication: 1977
|
|
Authors
|
|
Mario Barbacci
|
Carnegie-Mellon University, Pittsburgh, Pennsylvania
|
|
Daniel Siewiorek
|
Carnegie Mellon University, Pittsburgh, Pennsylvania
|
|
Robert Gordon
|
Naval Underwater Systems Center, New London, Connecticut
|
|
Rosemary Howbrigg
|
Naval Underwater Systems Center, New London, Connecticut
|
|
Susan Zuckerman
|
Naval Research Laboratory, Washington, DC
|
|
| Sponsor |
|
| Publisher |
|
| Bibliometrics |
Downloads (6 Weeks): 3, Downloads (12 Months): 8, Citation Count: 0
|
|
|
ABSTRACT
The objectives of this paper are twofold. In the first place we discuss some issues related to the formal description of computer systems and how these issues were handled in a specific project, the selection of a standard computer architecture for the Army/Navy Computer Family Architecture (CFA) project. The second purpose is to present a methodology for automatically gathering architectural data which can be used for evaluation and comparison purposes. We will not discuss the rationale behind the selection of specific test programs and the statisical experiment set up to ascertain the influence of the programmers, the test programs, and the machine architecture on the results. These issues and the actual results of the experiment belong in a companion paper. Formal descriptions of three candidate architectures (IBM S/370, Interdata 8/32 and DEC PDP-11) were written in ISP, a computer description language. The ISP descriptions of the three architectures were used to simulate the execution of assembly language test programs. The measurements collected during the program simulations were stored into a data base for post-processing. Automating the data collection process not only eliminated tedious and potentially error prone hand calculations, but also provided the means to gather information about dynamic program behavior, information that would be almost impossible to calculate manually.
REFERENCES
Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.
| |
1
|
Amdahl, G. M., G. A. Blaauw, and F. P. Brooks, "Architecture of the IBM System/360", IBM Journal of Research and Development, Vol. 8, No. 2, April 1964, pp. 87--101.
|
| |
2
|
Barbacci, M. R. and D. P. Siewiorek, Some Aspects of the Symbolic Manipulation of Computer Descriptions, Department of Computer Science, Carnegie-Mellon University, July 1974.
|
| |
3
|
|
| |
4
|
Barbacci, M. R., The Symbolic Manipulation of Computer Descriptions: ISPL Compiler and Simulator, Technical Report, Department of Computer Science, Carnegie-Mellon University, 1976.
|
| |
5
|
Barbacci, M. R., S. H. Fuller, and D. P. Siewiorek, A Methodology for Comparative Computer Architecture, Department of Computer Science, Carnegie-Mellon University, 1977.
|
| |
6
|
|
| |
7
|
Computer Family Architecture Selection Committee Final Report, Naval Research Laboratory, Washington, D.C., December 1976. A collection of volumes describing each aspect of the CFA project.
|
| |
8
|
Elovitz, H. S. and R. A. Parker, The Architecture Research Facility (ARF) User's Guide, Technical Memorandum 5403--472, Naval Research Laboratory, Washington, D.C., October 1976.
|
 |
9
|
Samuel H. Fuller , Paul Shaman , David Lamb , William E. Burr, Evaluation of computer architectures via test programs, Proceedings of the June 13-16, 1977, national computer conference, June 13-16, 1977, Dallas, Texas
[doi> 10.1145/1499402.1499434]
|
| |
10
|
|
|