Conference proceeding
Efficient masking techniques for large-scale SIMD architectures
[1990 Proceedings] The Third Symposium on the Frontiers of Massively Parallel Computation, pp.259-264
The Third Symposium on the Frontiers of Massively Parallel Computation, 3 (College Park, Maryland, 10/08/1990–10/10/1990)
1990
DOI: 10.1109/FMPC.1990.89469
Abstract
SIMD (single-instruction-stream, multiple-data-stream) architectures require mechanisms that efficiently enable and disable mask processors to support flexible programming. Most current SIMD architectures use local masking. Global processor masks, specified by the control unit, are more efficient for tasks where the masking is data independent. An efficient hybrid masking technique that supports global masking, as well as local masking, for SIMD architectures constructed from standard microprocessors is proposed. A design for the hybrid mechanism is described, and its experimental performance using the existing PASM prototype is examined. It is shown that the hybrid masking technique can increase the utilization of PEs and thus increase performance, the degree of improvement being algorithm dependent.< >
Details
- Title: Subtitle
- Efficient masking techniques for large-scale SIMD architectures
- Creators
- Wayne G Nation - Purdue University West LafayetteSamuel A FinebergMark D AllemangThomas SchwederskiThomas L CasavantHoward Jay Siegel
- Resource Type
- Conference proceeding
- Publication Details
- [1990 Proceedings] The Third Symposium on the Frontiers of Massively Parallel Computation, pp.259-264
- Conference
- The Third Symposium on the Frontiers of Massively Parallel Computation, 3 (College Park, Maryland, 10/08/1990–10/10/1990)
- DOI
- 10.1109/FMPC.1990.89469
- Publisher
- IEEE Comput. Soc. Press
- Language
- English
- Date published
- 1990
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering
- Record Identifier
- 9984197915702771
Metrics
11 Record Views