Designing a Coarse-Grained Reconfigurable Architecture Using Loop Self-Pipelining
This paper introduces LEAP(Loop Engine on Array Processor), a novel coarse-grained reconfigurable architecture which accelerates applications through Loop Self-Pipelining (LSP) technique. The LSP can provide effective execution mode for application pipelining. By mapping and distributing the expression statements of high level programming languages onto processing elements array, the LEAP can step the loop iteration automatically. The LEAP architecture has no centralized control, no centralized multi-port registers and no centralized data memory. The LEAP has the ability to exploit loop-level, instruction-level, and task-level parallelism, and it is suitable choice for stream-based application domains, such as multimedia, DSP and graphics application.
KeywordsData Memory Array Processor Execution Mode High Level Programming Language Interface Controller
Unable to display preview. Download preview PDF.
- 1.Lee, M.H., Singh, H., Lu, G., et al.: Design and Implementation of the MorphoSys Reconfigurable Computing Processor. Journal of VLSI and Signal Processing Systems for Signal, Image and Video Technology 24, 147–164 (2000)Google Scholar
- 4.Miyamori, T., Olukotun, K.: REMARC: Reconfigurable multimedia array coprocessor. In: The ACM/SIGDA Sixth International Symposium on Field Programmable Gate Arrays (FPGA 1998) (1998)Google Scholar
- 6.Cardoso, J.M.P.: Dynamic Loop Pipelining in Data-Driven Architectures. In: Proc. of the 2nd Conference on Computing Frontiers(CF 2005), pp. 106–115 (2005)Google Scholar