A framework for determining useful parallelism
Frances E. Allen, Michael Burke, Ron K. Cytron et al. · ACM International Conference on Supercomputing (ICS) · 1988
An approach to finding and forming parallel processes for both sequential and parallel programs is presented. The approach is presented in a framework that can create useful parallelism for a variety of parallel architectures. The framework makes use of a control dependence graph to capture maximal parallelism, a process tree to expose useful parallelism, renaming and storage segregation to reduce data dependencies, and an architecture-specific cost analyzer to evaluate the effectiveness of the potential processes. The framework is currently being implemented.
Cited by 66 works. doi:10.1145/55364.55385
Authors
References
- Compilers: Principles, Techniques, and Tools
- Bounds on Multiprocessing Timing Anomalies
- The program dependence graph and its use in optimization
- The Structure of Computers and Computations
- Optimizing supercompilers for supercomputers
- Dependence analysis for subscripted variables and its application to program transformations
- Speedup of ordinary programs
- Interprocedural dependence analysis and parallelization
- Partitioning and scheduling parallel programs for execution on multiprocessors
- An overview of the PTRAN analysis system for multiprocessing