Look-Ahead Processors
Robert Keller · ACM Computing Surveys · 1975
Methods of achieving look-ahead in processing units are discussed.An optimality criterion is proposed, and several schemes are compared against the optimum under varying assumptions.These schemes include existing and proposed machine organizations, and theoretical treatments not mentioned before in this context.The problems of eliminating associative searches in the processor control and the handling of loop-forming decisions are also considered.The inherent limitations of such processors are discussed.Finally, a number of enhancements to look-ahead processors is qualitatively surveyed.
Cited by 144 works. doi:10.1145/356654.356657 Open-access PDF
Authors
References
- Bounds on Multiprocessing Timing Anomalies
- A Theorem on Boolean Matrices
- Parallel program schemata
- Some Computer Organizations and Their Effectiveness
- The IBM System/360 Model 91: Machine Philosophy and Instruction-Handling
- Planning a Computer System: Project Stretch
- An Efficient Algorithm for Exploiting Multiple Arithmetic Units
- Bounds on multiprocessing anomalies and related packing algorithms
- The Inhibition of Potential Parallelism by Conditional Jumps
- On the Number of Operations Simultaneously Executable in Fortran-Like Programs and Their Resulting Speedup