Optimizing Reconfigurable Hardware Resource Usage in System-on-a-Programmable-Chip with Location Aware Genetic Algorithm

This paper presents static !ask scheduling using localiollaware genetic algorithm techniques 10 schedule task systems to fi nite amounts of rcconfigurable hardware. This researc h optimi:tcs the use of limited rcconfigurablc resources. This scheduling algorithm is built upon our previotls work 11 214]. In Ihis paper, the genetic algorithm has been expanded 10 include a fealure 10 assign selected task s to specific fUllctional units, tn this reconfigurable hardware environment, llmlliple sequential proccss ing elements (soft core processors such as Xilinx MicroBlazc [22] or Altera NiosII II]), task-specific corc (application specific hardware), and communicat ion network within the rcconfigurablc hardware can be used (such a system is called system-on-a-programmable-ch ip, SoPC). This paper shows that by prc-assigning (manually or r93 percent, with twO processors configuration).