ABSTRACT
Determining feasible application mappings for Design Space Exploration (DSE) and run-time embedding is a challenge for modern many-core systems. The underlying NP-complete system-synthesis problem faces tremendously complex problem instances due to the hundreds of heterogeneous processing elements, their communication infrastructure, and the resulting number of mapping possibilities. Thus, we propose to employ a search-space splitting (SSS) technique using architecture decomposition to increase the performance of existing design-time and run-time synthesis approaches. The technique first restricts the search for application embeddings to selected sub-architectures at substantially reduced complexity; therefore, the complete architecture needs to be searched only in case no embedding is found on any sub-system. Furthermore, we introduce a basic learning mechanism to detect promising sub-architectures and subsequently restrict the search to those. We exemplify the SSS for a SAT-based and a problem-specific backtracking-based system synthesis as part of DSE for NoC-based many-core systems. Experimental results show drastically reduced execution times (≈ 15--50 x on a 24×24 architecture) and an enhanced quality of the embedding, since less mappings (≈20--40 x, compared to the non-decomposing procedures) need to be discarded due to a timeout.
- A. K. Singh, M. Shafique, A. Kumar and J. Henkel. 2013. Mapping on Multi/Many-core Systems: Survey of Current and Emerging Trends. In 2013 50th ACM/EDAC/IEEE Design Automation Conference (DAC). 1--10. Google ScholarDigital Library
- M. K. Benhaoua and A. K. Singh. 2014. Heuristic for Accelerating Run-time Task Mapping in NoC-based Heterogeneous MPSoCs. Journal of Digital Information Management 12, 5 (2014), 293.Google Scholar
- R. Dick. 2018. Embedded System Synthesis Benchmarks Suite (E3S). (2018). http://ziyang.eecs.umich.edu/~dickrp/e3s/.Google Scholar
- A. Emeretlis, G. Theodoridis, P. Alefragis, and N. Voros. 2016. A Logic-Based Benders Decomposition Approach for Mapping Applications on Heterogeneous Multicore Platforms. ACM Trans. Embed. Comput. Syst. 15, 1, Article 19 (2016). Google ScholarDigital Library
- M. A. Al Faruque, R. Krist, and J. Henkel. 2008. ADAM: Run-time Agent-based Distributed Application Mapping for On-Chip Communication. In 2008 45th ACM/IEEE Design Automation Conference. 760--765. Google ScholarDigital Library
- A. Goens, S. Siccha, and J. Castrillon. 2017. Symmetry in Software Synthesis. ACM Transactions on Architecture and Code Opt. 14, 2, Article 20 (2017). Google ScholarDigital Library
- L. Benini, M. Lombardi, M. Milano and M. Ruggiero. 2011. Optimal Resource Allocation and Scheduling for the CELL BE Platform. Annals of Operations Research 184, 1 (2011), 51--77.Google ScholarCross Ref
- M. Lukasiewycz, M. Glaß, F. Reimann, and J. Teich. 2011. Opt4J: A Modular Framework for Meta-heuristic Optimization. In Proc. of the 13th Annual Conf. on Genetic and Evol. Comp. (GECCO '11). ACM, New York, NY, USA, 1723--1730. Google ScholarDigital Library
- M. Laumanns, L. Thiele, K. Deb and E. Zitzler. 2002. Combining Convergence and Diversity in Evolutionary Multiobjective Optimization. Evolutionary Computing 10, 3 (2002), 263--282. Google ScholarDigital Library
- M. Ruggiero, A. Guerri, D. Bertozzi, M. Milano and L. Benini. 2008. A Fast and Accurate Technique for Mapping Parallel Applications on Stream-Oriented MPSoC Platforms with Communication Awareness. International Journal of Parallel Programming 36, 1 (2008), 3--36. Google ScholarDigital Library
- P. K. Sahu and S. Chattopadhyay. 2013. Survey on Application Mapping Strategies for Network-on-Chip Design. Journal of Systems Arch. 59, 1 (2013), 60 -- 76. Google ScholarDigital Library
- T. Schwarzer, A. Weichslgartner, M. Glaß, S. Wildermann, P. Brand, and J. Teich. 2018. Symmetry-Eliminating Design Space Exploration for Hybrid Application Mapping on Many-Core Architectures. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 37, 2 (Feb 2018), 297--310. Google ScholarDigital Library
- A. K. Singh, P. Dziurzanski, H. R. Mendis, and L. S. Indrusiak. 2017. A Survey and Comp. Study of Hard and Soft Real-Time Dynamic Resource Allocation Strategies for Multi-/Many-Core Systems. ACM Comput. Surv. 50, 2, Article 24 (2017). Google ScholarDigital Library
- T. Blickle, J. Teich and L. Thiele. 1998. System-Level Synthesis Using Evolutionary Algorithms. Design Automation for Embedded Systems 3, 1 (1998), 23--58. Google ScholarDigital Library
- J. Teich. 2012. Hardware/Software Codesign: The Past, the Present, and Predicting the Future. Proc. IEEE 100, Special Centennial Issue (2012), 1411--1430.Google ScholarCross Ref
- A. Weichslgartner, D. Gangadharan, S. Wildermann, M. Glaß, and J. Teich. 2014. DAARM: Design-Time Application Analysis and Run-Time Mapping for Predictable Execution in Many-Core Systems. In Proc. of CODES+ISSS 2014. Google ScholarDigital Library
- E. Zitzler and L. Thiele. 1998. Multiobjective Optimization Using Evolutionary Algorithms --- A Comparative Case Study. In In Proceedings of PPSN. 292--301. Google ScholarDigital Library
Index Terms
- Architecture decomposition in system synthesis of heterogeneous many-core systems
Recommendations
Architecture Decomposition in System Synthesis of Heterogeneous Many-Core Systems
2018 55th ACM/ESDA/IEEE Design Automation Conference (DAC)Determining feasible application mappings for Design Space Exploration (DSE) and run-time embedding is a challenge for modern many-core systems. The underlying NP-complete system-synthesis problem faces tremendously complex problem instances due to the ...
Engineering change protocols for behavioral and system synthesis
Rapid prototyping and development of in-circuit and FPGA-based emulators as key accelerators for fast time-to-market has resulted in a need for efficient error correction mechanisms. Fabricated or emulated prototypes upon error diagnosis require an ...
Comments