Evaluation of a Methodology for the Reverse Engineering and Parallelization of Sequential Code
Abstract:
A general methodology based on software engineering principles is proposed for the parallelization of existing sequential code. The utility of the proposed methodology is evaluated through a case study involving a numerically intensive application in the domain of petrochemical exploration. The methodology does not assume the existence of detail design documentation for the sequential code. The methodology involves three basic phases: (1) reverse engineering; (2) parallel design; and (3) parallel implementation. The process iterates between phases two and three until the values of the performance metrics satisfy project requirements. In addition to the methodology itself, considerable detail related to the experiences and lessons learned in
Citations
| 797 | Software Engineering. A Practitioners Approach – Pressman - 1997 |
| 274 | A Discipline For Software Engineering – Humphrey - 1995 |
| 176 | Parallel Programming with MPI – Pacheco - 1997 |
| 14 | et al. The SP2 high-performance switch – Stunkel - 1995 |
| 6 | SEMPA: Software Engineering Methods for Parallel Scientific Applications – Luksch, Maier, et al. - 1996 |
| 3 | Using the XL compiler options to improve application performance – Stewart - 1998 |
| 1 | Introduction to Performance Issues in Using – Gropp, Lusk, et al. - 1998 |
| 1 | The PARSE Project,” Software Engineering for Parallel and Distributed Systems, edited by – Jelly, Gorton - 1996 |
| 1 | Single-Processor Performance Considerations for the SP2,” Cornell Theory Center, http://www.tc.cornell.edu/Edu/Talks/Performance/SingleP rocPerf – Lantz - 1998 |
| 1 | 77: Automatic and Efficient Parallelizer for FORTRAN,” http://www.plogic.com/bert.html – “BERT - 1998 |
| 1 | document reference: D/LEWX/MA/000/740, http://www.verilogusa.com – VERILOG, Dallas - 1997 |
