BooleDozer: logic synthesis for ASICs
IBM Journal of Research and Development
A signature based approach to regularity extraction
ICCAD '97 Proceedings of the 1997 IEEE/ACM international conference on Computer-aided design
Regular layout generation of logically optimized datapaths
Proceedings of the 1997 international symposium on Physical design
M32: a constructive multilevel logic synthesis system
DAC '98 Proceedings of the 35th annual Design Automation Conference
A general approach for regularity extraction in datapath circuits
Proceedings of the 1998 IEEE/ACM international conference on Computer-aided design
DATAPATH: a CMOS data path silicon assembler
DAC '86 Proceedings of the 23rd ACM/IEEE Design Automation Conference
Static Profile-Driven Compilation for FPGAs
FPL '01 Proceedings of the 11th International Conference on Field-Programmable Logic and Applications
Pattern-based behavior synthesis for FPGA resource reduction
Proceedings of the 16th international ACM/SIGDA symposium on Field programmable gate arrays
Reconfigurable Computing: The Theory and Practice of FPGA-Based Computation
Reconfigurable Computing: The Theory and Practice of FPGA-Based Computation
Keep it straight: teaching placement how to better handle designs with datapaths
Proceedings of the 2012 ACM international symposium on International Symposium on Physical Design
Proceedings of the 49th Annual Design Automation Conference
Structure-aware placement for datapath-intensive circuit designs
Proceedings of the 49th Annual Design Automation Conference
Network flow based datapath bit slicing
Proceedings of the 2013 ACM international symposium on International symposium on physical design
LatchPlanner: latch placement algorithm for datapath-oriented high-performance VLSI designs
Proceedings of the International Conference on Computer-Aided Design
Hi-index | 0.00 |
We present a new and innovative logic synthesis approach using regularity information of a design to selectively apply transformations and globally guide the synthesis process.Since traditional logic synthesis applies transformations without consideration of global design characteristics such as regularity and dataflow, it destroys a substantial amount of regular structures. In addition, due to the non-incremental nature of most logic transformations, synthesis relies vastly on the computationally expensive concept of trial and error application of transformations, a time-consuming process in the synthesis of large designs.The proposed approach addresses both shortcomings of traditional logic synthesis and describes a mechanism to speed up logic synthesis and preserve regularity. It selectively applies transformations to places with similar characteristics and to the same stage of a regular structure, introducing a notion of dataflow-aware synthesis.Preservation of regular structures has tremendous advantages to the following physical design stages. It yields high-density layouts, shorter wiring length and improved delay. In addition, the layout becomes more predictable at an earlier design stage.