Speed-up run-time reconfiguration implementation on FPGAs

International audienceReconfigurable computing is certainly one of the most important emerging research topics over the last few years, in the field of digital processing architectures. The introduction of run-time reconfiguration (RTR) on FPGAs requires appropriate design flows and methodologies to fully exploit this new functionality. For that purpose we present an automatic design generation methodology for heterogeneous architectures based on Network on Chip (NoC) and FPGAs that eases and speed-up RTR implementation. We focus on how to take into account specificities of partially reconfigurable components during the design generation steps. This method automatically generates designs for both fixed and partially reconfigurable parts of a FPGA with automaticmanagement of the reconfiguration process. Furthermore this automatic design generation enables reconfiguration pre-fetching techniques to minimize reconfiguration latency and buffer merging techniques to minimize memory requirements of the generated design. This concept has been applied to different wireless access schemes, based on a combination of OFDM and CDMA techniques. The implementation example illustrates the benefits of the proposed design methodology