The design and implementation of genesis
- 1 March 1994
- journal article
- Published by Wiley in Software: Practice and Experience
- Vol. 24 (3) , 307-325
- https://doi.org/10.1002/spe.4380240305
Abstract
Although code optimizations are necessary to parallelize code, few guidelines exist for determining when and where to apply optimizations to produce the most efficient code. The order of applying optimizations can also have an impact on the efficiency of the final target code. However, determining the appropriate optimizations is difficult due to the complex interactions among the optimizations, scheduler and architecture. To aid in selecting appropriate optimizations, an optimizer generator (Genesis) is presented that produces an optimizer from specifications of optimizations. This paper describes the design and implementation of Genesis and demonstrates how such a generator could be used by optimizer designers. Some experiences with the generator are also described.Keywords
This publication has 11 references indexed in Scilit:
- Automatic generation of global optimizersPublished by Association for Computing Machinery (ACM) ,1991
- An approach to ordering optimizing transformationsPublished by Association for Computing Machinery (ACM) ,1990
- PARAFRASE-2: AN ENVIRONMENT FOR PARALLELIZING, PARTITIONING, SYNCHRONIZING, AND SCHEDULING PROGRAMS ON MULTIPROCESSORSInternational Journal of High Speed Computing, 1989
- Automatic generation of fast optimizing code generatorsACM SIGPLAN Notices, 1988
- A framework for determining useful parallelismPublished by Association for Computing Machinery (ACM) ,1988
- Advanced compiler optimizations for supercomputersCommunications of the ACM, 1986
- PeepACM SIGPLAN Notices, 1984
- Automatic generation of peephole optimizationsPublished by Association for Computing Machinery (ACM) ,1984
- PeepPublished by Association for Computing Machinery (ACM) ,1984
- Automatic generation of machine specific code optimizersPublished by Association for Computing Machinery (ACM) ,1982