Performance of On-Chip Multiprocessors for Vision Tasks (Summary)
Computer vision is a challenging data intensive application. Currently, superscalar architectures dominate the processor marketplace. As more transistors become available on a single chip, the “on-chip multiprocessor” has been proposed as a promising alternative to processors based on the superscalar architecture. This paper examines the performance of vision benchmark tasks on an on-chip multiprocessor. To evaluate the performance, a program-driven simulator and its programming environment were developed. DARPA IU benchmarks were used for evaluation purposes. The benchmark includes integer, floating point, and extensive data movement operations. The simulation results show that the proposed on-chip multiprocessor can exploit thread-level parallelism effectively.
Unable to display preview. Download preview PDF.
- 1.Prasanna Kumar, V.: Parallel Architectures and Algorithms for Image Understanding. Academic Press (1991)Google Scholar
- 4.Weems, C., Riseman, E., and Hanson, A.: Image Understanding Architecture: Exploiting Potential Parallelism in Machine Vision. IEEE Computer, Vol. 25, No. 2 (1992) 65–68Google Scholar
- 5.Wilson, J.: Challenges and Trends in Processor Design. IEEE Computer, Vol. 30, No. 1 (1997) 39–50Google Scholar
- 6.Wall, D.: Limits of Instruction Level Parallelism. WRL Research Report, Digital Western Research Laboratory (1993)Google Scholar
- 7.Hammond, L., et al.: A Single-Chip Multiprocessor. IEEE Computer, Vol. 30, No. 9 (1997) 79–85Google Scholar
- 10.Park, K., et al.: On-Chip Multiprocessing with Simultaneous Multithreading. Technical Report, ETRI (1999)Google Scholar
- 11.POSIX P1003.4a: Threads Extension for Portable Operating Systems, IEEE (1994)Google Scholar
- 12.Burger, D. and Austin, T.: The SimpleScalar Tool Set, Version 2.0. Technical Report, University of Wisconsin (1997)Google Scholar
- 13.Bondalapati, K., Dutta, D., Narayanan, S., Prasanna, V. K., Ragahavendra, C, and Seshadri, A.: Optimizing DRAM-based Memory System Performance. Submitted to the 27th Annual International Symposium on Computer ArchitectureGoogle Scholar
- 14.Musmanno, J. F.: DARPA DIS Benchmarks. Atlantic Aerospace Electronics Corp. (1999)Google Scholar