Automated Floorplanning for Partially Reconfigurable Designs on Heterogenrous FPGAs

Pingakshya Goswami, Dinesh Bhatia

Floorplanning problem has been extensively explored for homogeneous FPGAs. Most modern FPGAs consist of heterogeneous resources in the form of configurable logic blocks, DSP blocks, BRAMs and more. Very little work has been done for heterogeneous FPGAs. In addition, features like partial reconfigurability allow on-the-fly changes to the executable design that can result in enhanced performance and very efficient utilization of resources. In this paper, we have designed a floorplanner for Partially Reconfigurable (PR) designs in FPGA that smartly decides one of the three proposed resource allocation schemes to floorplan a particular type of reconfigurable region. We also propose a White Space Detection algorithm for efficient management of white space inside an FPGA in order to reduce the area and the wire length. The floorplanner is demonstrated on Xilinx Virtex 5 and Artix 7 FPGA architectures and can be easily integrated with existing vendor-supplied Place and Route tools. The main objective of the floorplanner is to reduce the wire length, minimize wasted resources and the area. The performance of our floorplanner is evaluated using MCNC benchmarks. We have compared our proposed floorplanner with other previously published results reported in the literature. We observe a substantial improvement in the overall wire length as well as the execution time. Also, the floorplanner was integrated with vendor supplied place and route tools (Xilinx Vivado) to automate the floorplanning flow. The automation process was tested on a partially reconfigurable median filter used in image processing applications.

Knowledge Graph

arrow_drop_up

Comments

Sign up or login to leave a comment