Input/output speed-up in tightly-coupled multiprocessors
Previous models of program speed-up on parallel architectures tend to ignore I/O activity and other important issues. In this paper we derive analytic speed-up models including I/O activities. We show that ignoring I/O yields conservative speed-up results. We explore the effectiveness of using hardware format conversion units in multiprocessors. We prove that hardware parallel format conversion loses its edge over software parallel format conversion if the ratio of the number of processors to I/O bandwidth increases. For a given number of processors, program speed-up is more sensitive to the available I/O bandwidth rather than the format conversion speed. Ninety-one Fortran programs are used in various experiments to verify our models and conclusions. 35 refs., 5 figs., 8 tabs.
- Research Organization:
- Illinois Univ., Urbana (USA). Center for Supercomputing Research and Development
- DOE Contract Number:
- FG02-85ER25001
- OSTI ID:
- 7249673
- Report Number(s):
- DOE/ER/25001-28; ON: DE87002106
- Resource Relation:
- Other Information: Portions of this document are illegible in microfiche products
- Country of Publication:
- United States
- Language:
- English
Similar Records
Parallel input/output architectures for multiprocessors
Nonpreemptive run-time scheduling issues on a multitasked, multiprogrammed multiprocessor with dependencies, bidimensional tasks, folding and dynamic graphs
Related Subjects
PARALLEL PROCESSING
COMPUTERIZED SIMULATION
PERFORMANCE TESTING
CDC COMPUTERS
EXPERIMENTAL DATA
FORTRAN
IBM COMPUTERS
THEORETICAL DATA
COMPUTERS
DATA
INFORMATION
NUMERICAL DATA
PROGRAMMING
PROGRAMMING LANGUAGES
SIMULATION
TESTING
990200* - Mathematics & Computers