Abstract
Modern FPGA synthesis tools typically apply a predetermined sequence of logic optimizations on the input logic network before carrying out technology mapping. While the “known recipes” of logic transformations often lead to improved mapping results, there remains a nontrivial gap between the quality metrics driving the pre-mapping logic optimizations and those targeted by the actual technology mapping. Needless to mention, such miscorrelations would eventually result in suboptimal quality of results.
In this article, we propose PIMap, which couples logic transformations and technology mapping under an iterative improvement framework for LUT-based FPGAs. In each iteration, PIMap randomly proposes a transformation on the given logic network from an ensemble of candidate optimizations; it then invokes technology mapping and makes use of the mapping result to determine the likelihood of accepting the proposed transformation. By adjusting the optimization objective and incorporating required time constraints during the iterative process, PIMap can flexibly optimize for different objectives including area minimization, delay optimization, and delay-constrained area reduction. To mitigate the runtime overhead, we further introduce parallelization techniques to decompose a large design into multiple smaller sub-netlists that can be optimized simultaneously. Experimental results show that PIMap achieves promising quality improvement over a set of commonly used benchmarks, including improving the majority of the best-known area and delay records for the EPFL benchmark suite.
- Luca Amarú, Pierre-Emmanuel Gaillardon, and Giovanni De Micheli. 2014. Majority-inverter graph: A novel data-structure and algorithms for efficient logic optimization. In Proceedings of the Design Automation Conference (DAC’14). Google Scholar
Digital Library
- Luca Amarú, Pierre-Emmanuel Gaillardon, and Giovanni De Micheli. 2015. The EPFL combinational benchmark suite. In Proceedings of the International Workshop on Logic 8 Synthesis (IWLS’15).Google Scholar
- Luca Amarú, Pierre-Emmanuel Gaillardon, and Giovanni De Micheli. 2016. Majority-inverter graph: A new paradigm for logic optimization. IEEE Trans. Comput.-Aid. Des. Integr. Circ. Syst. 35, 5 (2016), 806--819. Google Scholar
Digital Library
- Luca Amarú, Mathias Soeken, Patrick Vuillod, Jiong Luo, Alan Mishchenko, Pierre-Emmanuel Gaillardon, Janet Olson, Robert Brayton, and Giovanni De Micheli. 2017. Enabling exact delay synthesis. In Proceedings of the International Conference on Computer-Aided Design (ICCAD’17). Google Scholar
Digital Library
- Berkeley Logic Synthesis and Verification Group, ABC: A System for Sequential Synthesis and Verification, Release 60413. 2017. Retrieved from http://www.eecs.berkeley.edu/∼alanmi/abc/.Google Scholar
- Andrea Casotto, Fabio Romeo, and Alberto Sangiovanni-Vincentelli. 1987. A parallel simulated annealing algorithm for the placement of macro-cells. IEEE Trans. Comput.-Aid. Des. Integr. Circ. Syst. 6, 5 (1987), 838--847. Google Scholar
Digital Library
- Deming Chen, Jason Cong, and Peichen Pan. 2006. FPGA design automation: A survey. Found. Trends Electron. Des. Autom. 1, 3 (2006), 139--169. Google Scholar
Digital Library
- Doris Chen and Deshanand Singh. 2010. Parallelizing FPGA technology mapping using graphics processing units (GPUs). In Proceedings of the International Conference on Field Programmable Logic and Applications (FPL’10). Google Scholar
Digital Library
- Jordi Cortadella. 2003. Timing-driven logic bi-decomposition. IEEE Trans. Comput.-Aid. Des. Integr. Circ. Syst. 22, 6 (2003), 675--685. Google Scholar
Digital Library
- Giovanni De Micheli. 1991. Synchronous logic synthesis: Algorithms for cycle-time minimization. IEEE Trans. Comput.-Aid. Des. Integr. Circ. Syst. 10, 1 (1991), 63--73. Google Scholar
Digital Library
- Amir H. Farrahi and Majid Sarrafzadeh. 1994. Complexity of the lookup-table minimization problem for FPGA technology mapping. IEEE Trans. Comput.-Aid. Des. Integr. Circ. Syst. 13, 11 (1994). Google Scholar
Digital Library
- Petr Fišer and Jan Schmidt. 2010. It is better to run iterative resynthesis on parts of the circuit. In Proceedings of the International Workshop on Logic 8 Synthesis (IWLS’10).Google Scholar
- Petr Fišer and Jan Schmidt. 2012. Improving the iterative power of resynthesis. In Proceedings of the International Symposium on Design and Diagnostics of Electronic Circuits and Systems (DDECS'12).Google Scholar
Cross Ref
- Petr Fišer, Jan Schmidt, Zdenĕk Vašíč, Lukáš Sekanina, et al. 2010. On logic synthesis of conventionally hard to synthesize circuits using genetic programming. In Proceedings of the IEEE International Symposium on Design and Diagnostics of Electronic Circuits and Systems. 346--351.Google Scholar
Cross Ref
- Charles J. Geyer. 1992. Practical Markov chain Monte Carlo. Statist. Sci. 7, 4 (1992), 473--483.Google Scholar
Cross Ref
- W. Keith Hastings. 1970. Monte Carlo sampling methods using Markov chains and their applications. Biometrika 57, 1 (1970), 97--109.Google Scholar
Cross Ref
- Yu Hu, Victor Shih, Rupak Majumdar, and Lei He. 2008. FPGA area reduction by multi-output function based sequential resynthesis. In Proceedings of the Design Automation Conference (DAC’08). Google Scholar
Digital Library
- Andrew Kennings and Chirag Ravishankar. 2011. Parallel FPGA technology mapping using multi-core architectures. In Proceedings of the Canadian Conference on Electrical and Computer Engineering (CCECE’11).Google Scholar
Cross Ref
- Scott Kirkpatrick, C. Daniel Gelatt, and Mario P. Vecchi. 1983. Optimization by simmulated annealing. Science 220, 4598 (1983), 671--680.Google Scholar
- Laurent Lemarchand. 1999. Parallel performance directed technology mapping for FPGA. In Proceedings of the Southwest Symposium on Mixed-Signal Design.Google Scholar
Cross Ref
- Gai Liu and Zhiru Zhang. 2017. A parallelized iterative improvement approach to area optimization for LUT-based technology mapping. In Proceedings of the International Symposium on Field-Programmable Gate Arrays (FPGA’17). Google Scholar
Digital Library
- A. Mishchenko and R. K. Brayton. 2006. Scalable logic synthesis using a simple circuit structure. In Proceedings of the International Workshop on Logic 8 Synthesis (IWLS’06). 15--22.Google Scholar
- Alan Mishchenko, Robert Brayton, and Satrajit Chatterjee. 2008. Boolean factoring and decomposition of logic networks. In Proceedings of the International Conference on Computer-Aided Design (ICCAD’08). Google Scholar
Digital Library
- Alan Mishchenko, Satrajit Chatterjee, and Robert Brayton. 2006. DAG-aware AIG rewriting a fresh look at combinational logic synthesis. In Proceedings of the Design Automation Conference (DAC’06). Google Scholar
Digital Library
- Alan Mishchenko, Satrajit Chatterjee, and Robert K. Brayton. 2007. Improvements to technology mapping for LUT-based FPGAs. IEEE Trans. Comput.-Aid. Des. Integr. Circ. Syst. 26, 2 (2007), 240--253. Google Scholar
Digital Library
- Peichen Pan, Arvind K. Karandikar, and C. L. Liu. 1998. Optimal clock period clustering for sequential circuits with retiming. IEEE Trans. Comput.-Aid. Des. Integr. Circ. Syst. 17, 6 (1998), 489--498. Google Scholar
Digital Library
- Eric Schkufza, Rahul Sharma, and Alex Aiken. 2013. Stochastic superoptimization. In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS’13). Google Scholar
Digital Library
- Bruno Schmitt, Alan Mishchenko, and Robert Brayton. 2018. SAT-based area recovery in structural technology mapping. In Proceedings of the Asia and South Pacific Design Automation Conference (ASP-DAC’18). Google Scholar
Digital Library
- Carl Sechen. 1988. Chip-planning, placement, and global routing of macro/custom cell integrated circuits using simulated annealing. In Proceedings of the Design Automation Conference (DAC’88). Google Scholar
Digital Library
- Chuyu Shen, Zili Lin, Ping Fan, Xianglong Meng, and Weikang Qian. 2016. Parallelizing FPGA technology mapping through partitioning. In Proceedings of the IEEE Symposium on Field Programmable Custom Computing Machines (FCCM’16).Google Scholar
Cross Ref
- Mathias Soeken, Luca Gaetano Amaru, Pierre-Emmanuel Gaillardon, and Giovanni De Micheli. 2017. Exact synthesis of majority-inverter graphs and its applications. IEEE Trans. Comput.-Aid. Des. Integr. Circ. Syst. 36, 11 (2017), 1842--1855.Google Scholar
Cross Ref
- Mathias Soeken, Giovanni De Micheli, and Alan Mishchenko. 2017. Busy man’s synthesis: Combinational delay optimization with SAT. In Proceedings of the Design, Automation, and Test in Europe Conference (DATE’17). Google Scholar
Digital Library
- Simon Szykman and Jonathan Cagan. 1995. A simulated annealing-based approach to three-dimensional component packing. J. Mech. Des. 117, 2A (1995), 308--314.Google Scholar
Cross Ref
- Zdenek Vasicek and Lukas Sekanina. 2011. A global postsynthesis optimization method for combinational circuits. In Proceedings of the Design, Automation, and Test in Europe Conference (DATE’11).Google Scholar
Cross Ref
- Saeyang Yang. 1991. Logic Synthesis and Optimization Benchmarks. Microelectronics Center of North Carolina (MCNC).Google Scholar
- Wenlong Yang, Lingli Wang, and Alan Mishchenko. 2012. Lazy man’s logic synthesis. In Proceedings of the International Conference on Computer-Aided Design (ICCAD’13).Google Scholar
Digital Library
Index Terms
PIMap: A Flexible Framework for Improving LUT-Based Technology Mapping via Parallelized Iterative Optimization
Recommendations
A Parallelized Iterative Improvement Approach to Area Optimization for LUT-Based Technology Mapping
FPGA '17: Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate ArraysModern FPGA synthesis tools typically apply a predetermined sequence of logic optimizations on the input logic network before carrying out technology mapping. While the "known recipes" of logic transformations often lead to improved mapping results, ...
Improvements to technology mapping for LUT-based FPGAs
FPGA '06: Proceedings of the 2006 ACM/SIGDA 14th international symposium on Field programmable gate arraysThe paper presents several improvements to state-of-the-art in FPGA technology mapping exemplified by a recent advanced technology mapper DAOmap [Chen and Cong, ICCAD '04]. Improved cut enumeration computes all K-feasible cuts without pruning for up to ...
Semi-individual wire-length prediction with application to logic synthesis
A new concept for wire-length prediction, the semi-individual wire-length prediction, is introduced. Structural metrics, such as mutual contraction and net range, are used to predict which interconnects have a tendency to be long or short in the final ...






Comments