Distributed computing for signal processing: modeling of asynchronous parallel computation. Appendix D. Analysis of MIMD (Multiple Instruction Streams, Multiple Data streams) algorithms: features, measurements, and results. Master's thesis
Analysis of parallel algorithms for MIMD (Multiple Instruction streams, Multiple data streams) machines is often difficult. Much work in the past has focused on SISD (Single Instruction and Data Streams (conventional)) and SIMD(Single Instruction stream, Multiple Instruction system (vector)) algorithms. Most of this work applies in MIMD systems, yet there are several significant problems that arise. This thesis focuses on these problems and proposes solutions to them. An image-processing problem is analyzed for parallelism. Measures of parallelism are proposed. With these measures in mind, the image-processing problem is again analyzed and several common parallel languages are surveyed. With this background, a set of language and machine-independent MIMD constructs is proposed, and it is shown how these can be used on several forms of traditional analysis.
- Research Organization:
- Purdue Univ., Lafayette, IN (USA). School of Electrical Engineering
- OSTI ID:
- 5381031
- Report Number(s):
- AD-A-168550/2/XAB
- Country of Publication:
- United States
- Language:
- English
Similar Records
Computer architectures for artificial intelligence processing
Parallel processing for computer vision