Integrated range comparison for data-parallel compilation systems
- 1 May 1999
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 10 (5) , 448-458
- https://doi.org/10.1109/71.770134
Abstract
A major difficulty in restructuring compilation, and in parallel programming in general, is how to compare parallel performance over a range of system and problem sizes. Execution time varies with system and problem size and an initially fast implementation may become slow when system and problem size scale up. This paper introduces the concept of range comparison. Unlike conventional execution time comparison in which performance is compared for a particular system and problem size, range comparison compares the performance of programs over a range of ensemble and problem sizes via scalability and performance crossing point analysis. A novel algorithm is developed to predict the crossing point automatically. The correctness of the algorithm is proven and a methodology is developed to integrate range comparison into restructuring compilations for data-parallel programming. A preliminary prototype of the methodology is implemented and tested under Vienna Fortran Compilation System. Experimental results demonstrate that range comparison is feasible and effective. It is an important asset for program evaluation, restructuring compilation, and parallel programming.Keywords
This publication has 17 references indexed in Scilit:
- The relation of scalability and execution timePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Buffer-safe communication optimization based on data flow analysis and performance predictionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Scalability versus Execution Time in Scalable SystemsJournal of Parallel and Distributed Computing, 2002
- Tau Pathology in a Family with Dementia and a P301L Mutation in TauJournal of Neuropathology and Experimental Neurology, 1999
- Performance range comparison via crossing point analysisPublished by Springer Nature ,1998
- The next 10,000/sub 2/ years. IComputer, 1996
- Performance metrics: keeping the focus on runtimeIEEE Parallel & Distributed Technology: Systems & Applications, 1996
- Parallel architectures: Performance prediction: A case study using a scalable shared-virtual-memory machineIEEE Parallel & Distributed Technology: Systems & Applications, 1996
- Performance considerations of shared virtual memory machinesIEEE Transactions on Parallel and Distributed Systems, 1995
- A static parameter based performance prediction tool for parallel programsPublished by Association for Computing Machinery (ACM) ,1993