A fast routability-driven router for FPGAs

@inproceedings{Swartz1998AFR,
  title={A fast routability-driven router for FPGAs},
  author={Jordan S. Swartz and Vaughn Betz and Jonathan Rose},
  booktitle={FPGA '98},
  year={1998}
}
Three factors are driving the demand for rapid FPGA compilation. First, as FPGAs have grown in logic capacity, the compile computation has grown more quickly than the compute power of the available computers. Second, there exists a subset of users who are willing to pay for very high speed compile with a decrease in quality of result, and accordingly being required to use a larger FPGA or use more real-estate on a given FPGA than is otherwise necessary. Third, very high speed compile has been a… 
Trading quality for compile time: ultra-fast placement for FPGAs
TLDR
An ultra-fast placement algorithm targeted to FPGAs that can generate a placement for a 100,000-gate circuit in 10 seconds on a 300 MHz Sun UltraSPARC workstation that is only 33% worse than a high-quality placement that takes 524 seconds using a pure simulated annealing implementation.
A High-Speed Timing-Aware Router for FPGAs
TLDR
This thesis focuses on the routing phase and proposes a new high-speed timing-aware routing algorithm that is able to predict if the routing task is difficult and will take a long time to complete, or impossible to complete.
Trading Quality f or Compile Time : Ultra-F ast Placement f or FPGAs
TLDR
An ultra-fast placement algorithm targeted to FPGAs is presented, based on a combination of multiple-level, bottom-up clustering and hierarchical simulated annealing, that provides superior area results over a known high-quality placement tool on a set of large benchmark circuits, when both are restricted to a short run time.
CRoute: A Fast High-Quality Timing-Driven Connection-Based FPGA Router
TLDR
The concept of the connection-based routing principle is elaborated on, the algorithm is improved and a timing-driven version is introduced and high-quality results are obtained in 3.4x less routing runtime.
Ultra-fast automatic placement for FPGAs
TLDR
This thesis presents an ultra-fast placement algorithm for FPGAs based on a combination of multiple-level, bottom-up clustering and simulated annealing, which provides superior area results over a known high-quality placement tool on a set of large benchmark circuits.
Negotiated A* Routing for FPGAs ∗
TLDR
This paper addresses the compilation time issue for routing array FPGAs with segmented routing architectures by treating the routing problem as an A∗ search, and shows that it is possible to trade additional device routing resources for decreased router run-time by converting an exhaustive breadth-first maze route into a shorter depth-first route.
A connection-based router for FPGAs
TLDR
The connection router is introduced, capable of partially ripping up and rerouting the routing trees of nets, and it is able to find routing solutions with 5.8% less tracks per channel than the VPR directed search router.
Fast place and route approaches for fpgas
TLDR
This thesis describes an new integrated floorplanning and routing system for FPGAs, called Frontier, which has been designed to optimize FPGA layout time at the cost of modest increases in device logic and routing resources.
Routing algorithms for field-programmable gate arrays
TLDR
This dissertation addresses issues on routing algorithms to optimize area and timing of an FPGA system by presenting a new timing-driven routing algorithm for FPGAs based on an iterative refinement scheme based on the Lagrangian relaxation technique.
Stochastic spatial routing for reconfigurable networks
...
...

References

SHOWING 1-10 OF 32 REFERENCES
Placement and routing tools for the Triptych FPGA
TLDR
Automatic mapping tools for Triptych, an FPGA architecture with improved logic density and performance over commercial FPGAs, and extensions to these algorithms for mapping asynchronous circuits to Montage, the first FGPA architecture to completely support asynchronous and synchronous interface applications are described.
VPR: A new packing, placement and routing tool for FPGA research
TLDR
In terms of minimizing routing area, VPR outperforms all published FPGA place and route tools to which the authors can compare and presents placement and routing results on a new set of circuits more typical of today's industrial designs.
A detailed router for field-programmable gate arrays
TLDR
The results show that C GE is able to route relatively large FPGAs in the absolute minimum number of tracks as determined by global routing, and that CGE has a linear run-time over circuit size.
Generation of synthetic sequential benchmark circuits
TLDR
Comparing the post-lay out properties of the generated circuits with already existing circuits, it is demonstrated that the synthetic circuits are much more realistic than random graphs with the same number of nodes, edges and I/Os.
The RAW benchmark suite: computation structures for general purpose computing
  • J. BabbM. Frank A. Agarwal
  • Computer Science
    Proceedings. The 5th Annual IEEE Symposium on Field-Programmable Custom Computing Machines Cat. No.97TB100186)
  • 1997
TLDR
The RAW benchmark suite consists of twelve programs designed to facilitate comparing, validating, and improving reconfigurable computing systems, and includes an architecture-independent compilation framework, Raw Computation Structures (RawCS), to express each algorithm's dependencies and to support automatic synthesis, partitioning, and mapping to a reconfigured computer.
Risa: Accurate And Efficient Placement Routability Modeling
TLDR
An accurate and efficient placement routability modeling technique is proposed and incorporated into the prevailing simulated annealing approach based on the supply versus demand analysis of routing resource over an array of regions on a chip.
The Transmogrifier-2: a 1 million gate rapid prototyping system
TLDR
The Transmogrifier-2 is a second generation multi-FPGA system that is modular and scalable, meaning that various sized systems can be constructed from the same board, while maintaining routability and the constant delay feature.
A Simple Yet Effective Technique for Global Wiring
  • R. Nair
  • Computer Science
    IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
  • 1987
TLDR
An implementation for global wiring of a structured custom chip design style is described along with results, and various parameters can be set to give preference to short routes or to reduce the time taken by the algorithm.
An Algorithm for Path Connections and Its Applications
  • C. Y. Lee
  • Computer Science, Mathematics
    IRE Trans. Electron. Comput.
  • 1961
The algorithm described in this paper is the outcome of an endeavor to answer the following question: Is it possible to find procedures which would enable a computer to solve efficiently
Plane parallel A* maze router and its application to FPGAs
  • M. Palczewski
  • Computer Science
    [1992] Proceedings 29th ACM/IEEE Design Automation Conference
  • 1992
TLDR
A framework is established for unified code to support traditional wire routing, timing driven routing, and plane parallel and global routing for field programmable gate arrays.
...
...