An exact methodology for scheduling in a 3D design space

Abstract: This paper describes an exact solution methodology, implemented in Rensselaer's Voyager design space exploration system, for solving the scheduling problem in a 3-dimensional (3D) design space: the usual 2D design space (which trades off area and schedule length), plus a third dimension representing clock length. Unlike design space exploration methodologies which rely on bounds or estimates, this methodology is guaranteed to find the globally optimal solution to the 3D scheduling problem. Furthermore, this methodology efficiently prunes the search space, eliminating provably inferior design points through: a careful selection of candidate clock lengths; and tight bounds on the number of functional units of each type or on the schedule length.

[1]  Jacek Blazewicz,et al.  Simple Algorithms for Multiprocessor Scheduling to Meet Deadlines , 1977, Inf. Process. Lett..

[2]  Liang-Gee Chen,et al.  Optimal module set and clock cycle selection for DSP synthesis , 1991, 1991., IEEE International Sympoisum on Circuits and Systems.

[3]  Rajiv Jain,et al.  Module selection for pipelined synthesis , 1988, 25th ACM/IEEE, Design Automation Conference.Proceedings 1988..

[4]  Daniel Gajski,et al.  System clock estimation based on clock slack minimization , 1992, Proceedings EURO-DAC '92: European Design Automation Conference.

[5]  Eduardo B. Fernández,et al.  Bounds on the Number of Processors and Time for Multiprocessor Optimal Schedules , 1973, IEEE Transactions on Computers.

[6]  Viraphol Chaiyakul,et al.  Timing models for high-level synthesis , 1992, Proceedings EURO-DAC '92: European Design Automation Conference.

[7]  Miodrag Potkonjak,et al.  Estimating implementation bounds for real time DSP application specific circuits , 1994, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[8]  Robert A. Walker,et al.  Computing lower bounds on functional units before scheduling , 1994, ISSS '94.

[9]  Yuan Hu,et al.  Lower bounds on the iteration time and the number of resources for functional pipelined data flow graphs , 1993, Proceedings of 1993 IEEE International Conference on Computer Design ICCD'93.

[10]  Yuan Hu,et al.  Improved lower bounds for the scheduling optimization problem , 1994, Proceedings of IEEE International Symposium on Circuits and Systems - ISCAS '94.

[11]  Minjoong Rim,et al.  Lower-bound performance estimation for the high-level synthesis scheduling problem , 1994, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[12]  Eduard Cerny,et al.  A recursive technique for computing lower-bound performance of schedules , 1996, TODE.

[13]  Alice C. Parker,et al.  Predicting system-level area and delay for pipelined and nonpipelined designs , 1992, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[14]  Alok Sharma,et al.  Estimating Architectural Resources and Performance for High-Level Synthesis Applications , 1993, 30th ACM/IEEE Design Automation Conference.

[15]  Nikil D. Dutt,et al.  Comprehensive Lower Bound Estimation From Behavioral Descriptions , 1994, IEEE/ACM International Conference on Computer-Aided Design.

[16]  Donald E. Thomas,et al.  Algorithmic and Register-Transfer Level Synthesis: The System Architect's Workbench , 1989 .

[17]  Alice C. Parker,et al.  Synthesis of Optimal Clocking Schemes , 1985, 22nd ACM/IEEE Design Automation Conference.

[18]  J. E. Mitchell,et al.  Analyzing and exploiting the structure of the constraints in the ILP approach to the scheduling problem , 1994, IEEE Trans. Very Large Scale Integr. Syst..

[19]  Miodrag Potkonjak,et al.  Instruction set mapping for performance optimization , 1993, ICCAD.

[20]  H. B. Bakoglu,et al.  Circuits, interconnections, and packaging for VLSI , 1990 .

[21]  John A. Nestor,et al.  SALSA: a new approach to scheduling with timing constraints , 1993, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..