Abstract
Manual tuning techniques are widely applied but are generally slow, costly and require a great deal of expertise. This paper addresses the problem of automatically tuning the virtual architecture of a microprogrammed computer by microprogramming techniques. Two algorithms are presented to automate the tuning process. The algorithms are implemented on the same dynamic microprogrammed computer that executes the given application. After execution of the program the algorithms are invoked and a tuning iteration performed on the architecture and the program. Several tuning iterations are performed with different data sets over a period of time to select the optimized architecture. It is demonstrated that individual code segments experience a 2-8 speed improvement over their corresponding non-tuned versions, while the overall execution time of the program is reduced by 30-45%. The computational requirements of the algorithms are shown to be very modest.
- 1 M.V. Wilkes, "The best way to design an automated calculating machine," Manchester University Computer Inaugural Conference, pp. 16-18, 1951.]]Google Scholar
- 2 S.H. Husson, Microprogramming Principles and Practices, Prentice-Hall Inc., 1970.]]Google Scholar
- 3 A.K. Agrawala and T.G. Rauscher, Foundations of Microprogramming, Academic Press Inc., 1976]]Google Scholar
- 4 A.K. Agrawala and T.G. Rauscher, "Microprogramming: perspective and status," IEEE Trans. on Comp., Vol. C-23, No. 8, pp. 817-837, Aug. 1974.]]Google Scholar
- 5 E.W. Reigel et al, "The interpreter a microprogrammable building block system," Spring Joint Comp. Conf., pp. 705-723, 1972.]]Google Scholar
- 6 D.C. Snyder, "Computer performance improvement by measurement and microprogramming," SIGMICRO newsletter, pp. 7-14, Sep. 1975.]] Google Scholar
Digital Library
- 7 A.B. Tucker and M.J. Flynn, "Dynamic microprogramming: Processor organization and programming," Comm. ACM, Vol. 14, No. 4, pp. 240-250, April 1971.]] Google Scholar
Digital Library
- 8 G.M. Stabler, "The Brown University graphics system," Cent. Comp. Inform. Sci., Brown University, Providence, R.I., Feb. 1973.]]Google Scholar
- 9 A.M. Abd-Alla and D.C. Karlgaard, "Heuristic synthesis of microprogrammed computer architecture," IEEE Trans. on Comp., Vol. C-23, No. 8, pp. 802-807, Aug. 1974.]]Google Scholar
- 10 D.C. Karlgaard, "Heuristic tuning of virtual architectures for global system optimization," D.Sc. thesis, George Washington University, Washington D.C., 1974.]] Google Scholar
Digital Library
- 11 T.G. Rauscher and A.K. Agrawala, "Developing application oriented computer architectures on general purpose microprogrammable machines," Proc. 1976 National Computer Conference, pp. 715-722.]]Google Scholar
- 12 T.G. Rauscher, "Dynamic problem oriented redefinition of computer architecture via microprogramming," Ph.d. thesis, University of Maryland, Maryland, 1975.]] Google Scholar
Digital Library
- 13 K.A. El-Ayat, "A self tuning microprogrammed computer," Ph.d. dissertation, University of California, Santa Barbara, Ca 1977.]] Google Scholar
Digital Library
- 14 R.L. Kleir and C.V. Ramamoorthy, "Optimization strategies for microprograms," IEEE Trans. on Comp., Vol. C-20, pp. 783-794, July 1971.]]Google Scholar
- 15 M. Tsuchiya and M.J. Gonzalez Jr., "An approach to optimization of horizontal microprograms," MICRO 7 Preprints, pp. 85-90, 1974.]] Google Scholar
Digital Library
- 16 D. Gries, Compiler Construction for Digital Computers, John Wiley, Inc., 1971.]] Google Scholar
Digital Library
Index Terms
Algorithms for a self-tuning microprogrammed computer
Recommendations
Algorithms for a self-tuning microprogrammed computer
MICRO 10: Proceedings of the 10th annual workshop on MicroprogrammingManual tuning techniques are widely applied but are generally slow, costly and require a great deal of expertise. This paper addresses the problem of automatically tuning the virtual architecture of a microprogrammed computer by microprogramming ...
Heuristic Synthesis of Microprogrammed Computer Architecture
This paper describes an algorithm for the synthesis of applications-oriented microcode for a dynamically microprogrammable computer. The synthesis algorithm provides an iterative method for generating specialized architectures. Current attempts at ...
Too many knobs to tune? towards faster database tuning by pre-selecting important knobs
HotStorage'20: Proceedings of the 12th USENIX Conference on Hot Topics in Storage and File SystemsTo achieve high performance, recent research has shown that it is important to automatically tune the configuration knobs present in database systems. However, as database systems usually have 100s of knobs, auto-tuning frameworks spend a significant ...






Comments