ABSTRACT
We consider a dynamic application running on a multiprocessor network-on-chip as a set of independent jobs, each job possibly running on multiple processors. To provide guaranteed quality and performance, the scheduling of jobs, jobs themselves and the hardware must be amenable to timing analysis. For a certain class of applications and multiprocessor architectures, we propose exact timing models that effectively co-model both the computation and communication of a job. The models are based on interprocessor communication (IPC) graphs [4]. Our main contribution is a precise model of network-on-chip communication, including buffer models. We use a JPEG-decoder job as an example to demonstrate that our models can be used in practice to derive upper bounds on the job execution time and to reason about optimal buffer sizes.
- Ackland, B., et al., A Single-Chip, 1.6-Billion, 16-b MAC/s Multiprocessor DSP. In IEEE Journal of Solid-State Circuits, vol. 35, no. 3, 412--424, March 2000.Google ScholarCross Ref
- http://www.arm.comGoogle Scholar
- Baccelli, F., Cohen, G., Olsder, G.J., and Quadrat, J.-P., Synchronization and Linearity. New York: Wiley, 1992.Google Scholar
- Bambha, N., Kianzad, V., Khandelia, M., and Bhattacharrya, S.S., Intermediate Representations for Design Automation of Multiprocessor DSP Systems. In Design Automation for Embedded Systems, vol. 7, 307--323, Kluwer Academic Publishers, 2002.Google ScholarDigital Library
- Culler, D.E., and Singh, J.P., Parallel Computer Architecture: A Hardware/Software Approach, Morgan Kaufmann Publishers, 1999. Google ScholarDigital Library
- Dasdan, A., and Gupta, R.K., Faster Maximum and Minimum Cycle Algorithms for System-Performance Analysis. In IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 17, no. 10, 889--899, Oct. 1998. Google ScholarDigital Library
- Goossens, K.G.W, et al., Guaranteeing the Quality of Services in Networks on Chip. In Networks on Chip, ed. by A. Jantsch and H. Tenhunen, 61--82, Kluwer Academic Publishers, 2003. Google ScholarDigital Library
- Govindarajan, R., Gao, G.R., and Desai, P., Minimizing Buffer Requirements under Rate-Optimal Schedule in Regular Dataflow Networks. In Journal of VLSI Signal Processing, vol. 31, 207--229, Kluwer Academic Publishers, 2002. Google ScholarDigital Library
- Govindarajan, R., and Gao, G.R., Rate-Optimal Schedule for Multi-Rate DSP Applications. In Journal of VLSI Signal Processing, vol. 9, no. 3, 211--232, 1995. Google ScholarDigital Library
- Hoang, P., and Rabaey, J., Scheduling of DSP Programs onto Multiprocessors for Maximum Throughput. In IEEE Transactions on Signal Processing, vol. 41, no.6, June 1993.Google Scholar
- Kock, E.A. de, Practical Experiences: Multiprocessor Mapping of Process Networks: a JPEG Decoding Case Study. In Proceedings 15th International Symposium on System Synthesis, 68--73, ACM, 2002. Google ScholarDigital Library
- Kock, E.A. de., et al., YAPI: Application Modeling for Signal Processing Systems. In Proceedings 37th Design Automation Conference, 402--405, 2000. Google ScholarDigital Library
- Lee, E.A., and Messerschmitt, D.G., Static Scheduling of Synchronous Data Flow Programs for Digital Signal Processing. In IEEE Transactions on Computers, vol. 36, no. 1, 24--35, 1987. Google ScholarDigital Library
- Lauwereins, R., Engels, M., Ade M., and Peperstraete, J.A., Grape-II: A System-Level Prototyping Environment for DSP Applications. In IEEE Computer, vol. 28, no. 2, 35--43, Feb. 1995. Google ScholarDigital Library
- Rijpkema, E., Goossens, K.G.W., and Radulescu, A., Trade Offs in the Design of a Router with Both Guaranteed and Best-Effort Services for Networks on Chip. In Proceedings of DATE'03, 350--355, ACM, 2003. Google ScholarDigital Library
- Rudack, M., Redeker, M., Hilgenstock, J., and Moch, S., A Large-Area Integrated Multiprocessor System for Video Applications. In IEEE Design & Test of Computers, vol. 19, no. 1, 6--17, 2002. Google ScholarDigital Library
- Sriram, S., and Bhattacharyya, S.S., Embedded Multiprocessors: Scheduling and Synchronization, Marcel Dekker, Inc., 2002. Google ScholarDigital Library
- Strik, M.T.J., Timmer, A.H., Meerbergen, J.L.van, and Rootselaar, G.-J. van, Heterogeneous Multiprocessor for the Management of Real-time Video and Graphics Streams. In IEEE Journal of Solid-State Circuits, vol. 35, no. 11, 1722 --1731, Nov. 2000.Google ScholarCross Ref
- Yang, M.-T., Kasturi, R., and Sivasubramaniam, A.A., Pipeline-Based Approach for Scheduling Video Processing Algorithms on NOW. In IEEE Transactions on Parallel and Distributed Systems, vol. 14, no. 2, 119--130, Feb. 2003. Google ScholarDigital Library
Index Terms
- Task-level timing models for guaranteed performance in multiprocessor networks-on-chip
Recommendations
P-NoC: Performance Evaluation and Design Space Exploration of NoCs for Chip Multiprocessor Architecture Using FPGA
AbstractThe network-on-chip (NoC) has emerged as an efficient and scalable communication fabric for chip multiprocessors (CMPs) and multiprocessor system on chips (MPSoCs). The NoC architecture, the routers micro-architecture and links influence the ...
A shortly connected mesh topology for high performance and energy efficient network-on-chip architectures
Network-on-chip-based communication schemes represent a promising solution to the increasing complexity of system-on-chip problems. In this paper, we propose a new mesh-like topology called the shortly connected mesh technology (ScMesh), which is based ...
Invited paper: Network-on-Chip design and synthesis outlook
With the growing complexity in consumer embedded products, new tendencies forecast heterogeneous Multi-Processor Systems-On-Chip (MPSoCs) consisting of complex integrated components communicating with each other at very high-speed rates. ...
Comments