A two-stage solution approach to multidimensional periodicscheduling

We present a two-stage solution approach to the multidimensional periodic scheduling (MPS) problem. This problem originates from the design of high-throughput digital-signal-processor systems, where highly parallel execution of loops is of utmost importance. We introduce the concept of multidimensional periodic operations in order to cope with problems originating from loop hierarchies and explicit timing requirements. In the first stage of the approach, we assign periods to the multidimensional periodic operations such that storage costs are minimized. This is done by means of branch-and-bound, based on a linear programming and constraint-generation technique. In the second stage, we assign start times to the operations and determine on which processing units (PUs) they are executed. This is done by means of an iterative approach. The two major subproblems of MPS concerning checking data dependency constraints and PU constraints are solved by means of an all-integer integer-linear-programming technique. This technique is used as a subroutine in the above two stages. The effectiveness and efficiency of the approach are good, which is illustrated by means of some practical examples.

[1]  W.F.J. Verhaegh,et al.  Relative location assignment for repetitive schedules , 1993, 1993 European Conference on Design Automation with the European Event in ASIC Design.

[2]  W.F.J. Verhaegh,et al.  Allocation of multiport memories for hierarchical data streams , 1993, Proceedings of 1993 International Conference on Computer Aided Design (ICCAD).

[3]  J. Kettenis,et al.  A video signal processor for motion-compensated field-rate upconversion in consumer television , 1996, 1996 IEEE International Solid-State Circuits Conference. Digest of TEchnical Papers, ISSCC.

[4]  W.F.J. Verhaegh,et al.  Design of a 30 MHz, 32/16/8-points DCT processor with Phideo , 1994, Proceedings of 1994 IEEE Workshop on VLSI Signal Processing.

[5]  Ed F. Deprettere,et al.  Systolic array implementation of nested loop programs , 1990, [1990] Proceedings of the International Conference on Application Specific Array Processors.

[6]  Wim F. J. Verhaegh,et al.  PHIDEO: High-level synthesis for high throughput applications , 1995, J. VLSI Signal Process..

[7]  Richard P. Kleihorst,et al.  MPEG2 video encoding in consumer electronics , 1999 .

[8]  H.J. De Man,et al.  Modeling data flow and control flow for high level memory management , 1992, [1992] Proceedings The European Conference on Design Automation.

[9]  Jos Huisken,et al.  PHIDEO: a silicon compiler for high speed algorithms , 1991, Proceedings of the European Conference on Design Automation..

[10]  William Pugh,et al.  The Omega test: A fast and practical integer programming algorithm for dependence analysis , 1991, Proceedings of the 1991 ACM/IEEE Conference on Supercomputing (Supercomputing '91).

[11]  W.F.J. Verhaegh,et al.  Memory synthesis for high speed DSP applications , 1991, Proceedings of the IEEE 1991 Custom Integrated Circuits Conference.

[12]  Emile H. L. Aarts,et al.  Multidimensional periodic scheduling: a solution approach , 1997, Proceedings European Design and Test Conference. ED & TC 97.

[13]  Wfj Wim Verhaegh,et al.  Multidimensional periodic scheduling , 1995 .

[14]  Miodrag Potkonjak,et al.  A Scheduling and Resource Allocation Algorithm for Hierarchical Signal Flow Graphs , 1989, 26th ACM/IEEE Design Automation Conference.

[15]  Jan Karel Lenstra,et al.  Periodic Multiprocessor Scheduling , 1991, PARLE.

[16]  Emile H. L. Aarts,et al.  Improved force-directed scheduling in high-throughput digital signal processing , 1995, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[17]  Fred W. Glover,et al.  A New Foundation for a Simplified Primal Integer Programming Algorithm , 1968, Oper. Res..

[18]  Hugo De Man,et al.  Control flow optimization for fast system simulation and storage minimization [real-time multidimens , 1994 .

[19]  H.J. De Man,et al.  Automating High Level Control F'low Transformations For Dsp Memory Management , 1992, Workshop on VLSI Signal Processing.

[20]  Alice C. Parker,et al.  Sehwa: a software package for synthesis of pipelines from behavioral specifications , 1988, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[21]  Edwin Hsing-Mean Sha,et al.  Loop Pipelining for Scheduling Multi-Dimensional Systems via Rotation , 1994, 31st Design Automation Conference.

[22]  de Ea Erwin Kock,et al.  Video signal processor mapping , 1999 .

[23]  Hugo De Man,et al.  Control flow optimization for fast system simulation and storage minimization /spl lsqb/real-time multidimensional signal processing/spl rsqb/ , 1994, Proceedings of European Design and Test Conference EDAC-ETC-EUROASIC.

[24]  Edward A. Lee,et al.  Static Scheduling of Synchronous Data Flow Programs for Digital Signal Processing , 1989, IEEE Transactions on Computers.

[25]  R. Haupt,et al.  A survey of priority rule-based scheduling , 1989 .

[26]  Emile H. L. Aarts,et al.  Multidimensional Periodic Scheduling Model and Complexity , 1996, Euro-Par, Vol. II.

[27]  Kenneth Steiglitz,et al.  Combinatorial Optimization: Algorithms and Complexity , 1981 .

[28]  R. Woudsma,et al.  Consumer applications: a driving force for high-level synthesis of signal-processing architectures , 1992, IEEE Micro.