Proceedings of the 6th international workshop on Hardware/software codesign
HSRA: high-speed, hierarchical synchronous reconfigurable array
FPGA '99 Proceedings of the 1999 ACM/SIGDA seventh international symposium on Field programmable gate arrays
An FPGA for Implementing Asynchronous Circuits
IEEE Design & Test
Architecture and synthesis for multi-cycle communication
Proceedings of the 2003 international symposium on Physical design
Automatic Production of Globally Asynchronous Locally Synchronous Systems
EMSOFT '02 Proceedings of the Second International Conference on Embedded Software
FPL '95 Proceedings of the 5th International Workshop on Field-Programmable Logic and Applications
PCA-1: A Fully Asynchronous, Self-Reconfigurable LSI
ASYNC '01 Proceedings of the 7th International Symposium on Asynchronous Circuits and Systems
A solution to line-routing problems on the continuous plane
DAC '69 Proceedings of the 6th annual Design Automation Conference
Exploration of pipelined FPGA interconnect structures
FPGA '04 Proceedings of the 2004 ACM/SIGDA 12th international symposium on Field programmable gate arrays
Highly pipelined asynchronous FPGAs
FPGA '04 Proceedings of the 2004 ACM/SIGDA 12th international symposium on Field programmable gate arrays
CAD Tools for a Globally Asynchronous Locally Synchronous FPGA Architecture
VLSID '06 Proceedings of the 19th International Conference on VLSI Design held jointly with 5th International Conference on Embedded Systems Design
FPGA Architecture: Survey and Challenges
Foundations and Trends in Electronic Design Automation
Hi-index | 0.00 |
Routing delays dominate other delays in current FPGA designs. We have proposed a novel Globally Asynchronous Locally Synchronous (GALS) FPGA architecture called the GAPLA to deal with this problem. In the GAPLA architecture, The FPGA area is divided into locally synchronous blocks and the communications between them are through asynchronous I/O interfaces. An automatic design flow is developed for the GAPLA architecture. Starting from behavioral description, a design is partitioned into smaller modules and fit to GAPLA synchronous blocks. The asynchronous communications between modules are then sytthesized. The CAD flow is parameterized in modeling the GAPLA architecture. By manipulating the parameters, we could study different factors of the designed GAPLA arcitecturc. Our experimental results show an average of 20% performance improvement could be achieved by the GAPLA architecture.