ABSTRACT
The primary objective of the Warp programming environment (WPE) is to simplify the use of Warp, a high-performance programmable linear systolic array connected to a general-purpose workstation host. WPE permits the development of distributed applications that access Warp either locally from the host or remotely from a large number of workstations connected to a local area network. Its audience includes the user who calls routines from a library, the programmer who develops new algorithms for Warp, as well as the implementor who writes support software. Since the linear arrangement of the cells in the array restricts direct input and output with the host to the boundary cells, a source language debugger is important for program development on Warp. This paper presents the Warp debugger and its relation to the other components of the Warp programming environment.
- 1.Annaratone, M., Bitz, F., Deutch, J., Hamey, L., Kung, H. T., Maulik P. C., Tseng, P., and Webb, J. A. Applications Experience on Warp. Proceedings of the 1987 National Computer Conference, AFIPS, Chicago, June, 1987, pp. 149-158.Google Scholar
- 2.Annaratone, M., Amould, E., Gross, T., Kung, H. T., l.am, M. S., Menzilcioglu, O., and Webb, J.A. "i'he Warp Machine: Architecture. Implementation and Performance". IEEE Trans. on Computers C-36, 12 (Dec. 1987), 1523-1538. Google ScholarDigital Library
- 3.Annaratone, M., Amould, E., Colin, R., Gross, T., Kung, H. T., Lain, M., Menzilcioglu, O., S arocky, K., Senko, J., and Webb, J. Warp Architecture: From Prototype to Production. Proce~ings of the 1987 National Computer Conference, AFIPS, Chicago, June, 1987, pp. 133-140.Google Scholar
- 4.Bruegge, B. Warp Programming Environment: User Manual. Tech. Rept. CMU-CS-88-105, Carnegie Mellon University, Dept. of Computer Science, 1988.Google Scholar
- 5.Bruegge, B. Adaptability and Portability of Symbolic Debuggers. Ph.D. Th., Carnegie-Mellon University, September 1985. Google ScholarDigital Library
- 6.Bruegge, B., Gross, T. An Integrated Environment for Development and Execution of Real-Time Programs. International Conference on Supercomputing, S aint-Malo, France, July, 1988. Google ScholarDigital Library
- 7.Bruegge, B. and Hibbard, P. "Generalized Path Expressions -- A High Level Debugging Mechanism". Journal of Systems and Software 3, (1983), 265-276.Google ScholarDigital Library
- 8.Gross, T. and Lain, M. Compilation for a Highperformance Systolic Array. Proceedings of the ACM SIGPLAN '86 Symposium on Compiler Construction, ACM SIGPLAN, June, 1986, pp. 27-38. Google ScholarDigital Library
- 9.Hamey, L. A User's Guide to the Generalized Image Library. In Warp Programming Environment: Documentation, Carnegie Mellon University, Dept. of Computer Science, 1988.Google Scholar
- 10.Hanson, D. "Event Associations in SNOBOLA for Program Debugging". Software--Practice and Experience 8, 2 (1978), 115-129.Google ScholarCross Ref
- 11.Hennessy, J.L. "Symbolic Debugging of Optimized Code". ACM Trwts. on Programming Languages and Systems 4, 3 (July 1982), 323 - 344. Google ScholarDigital Library
- 12.Kanade, T. and Webb, J. End of Year Report for Parallel Vision Algorithm Design & Implementation. CMU, Robotics Institute, 1987.Google Scholar
- 13.Lain, M. S. A Systolic Array Optimizing Compiler. Ph.D. Th., Carnegie Mellon University, May 1987.Google Scholar
- 14.Pomerleau, D. A., Gusciora, G. L., Touretzlcy, D. S. and Kung, H. T. Neural Network Simulation at Warp Speed: How We Got 17 Million Connections Per Second. Submitted to the IEEE Second International Conference on Neural Networks, April, 1988.Google Scholar
- 15.Scheifler, R. and Oettys, J, "The X Window System". ACM Trans. on Graphics 5, 2 (April 1986). Google ScholarDigital Library
- 16.Stallmart, R. GNU Emacs Manual, 4th edition. Cambridge, Mass, 1988. Google ScholarDigital Library
- 17.Wall, D., Srivastava, A., and Templin, F. "A Note on Hennessy' s 'Symbolic Debugging of Optimized Code'". ACM Transactions on Programming Languages and Systems 7, 1 (January 1985), 176-181. Google ScholarDigital Library
Index Terms
- Program development for a systolic array
Recommendations
HMMer acceleration using systolic array based reconfigurable architecture
FPGA '09: Proceedings of the ACM/SIGDA international symposium on Field programmable gate arraysHMMer is a widely-used bioinformatics software package that uses profile Hidden Markov Models (HMMs) to model the primary structure consensus of a family of protein or nucleic acid sequences. However, with the rapid growth of both sequence and model ...
Program Optimization of Array-Intensive SPEC2k Benchmarks on Multithreaded GPU Using CUDA and Brook+
ICPADS '09: Proceedings of the 2009 15th International Conference on Parallel and Distributed SystemsGraphic Processing Unit (GPU), with many light-weight data-parallel cores, can provide substantial parallel computing power to accelerate several general purpose applications. Both the AMD and NVIDIA corps provide their specific high performance GPUs ...
Program development for a systolic array
Proceedings of the ACM/SIGPLAN PPEALS 1988The primary objective of the Warp programming environment (WPE) is to simplify the use of Warp, a high-performance programmable linear systolic array connected to a general-purpose workstation host. WPE permits the development of distributed ...
Comments