Dynamic Loop Pipelining in Data-Driven Architectures

Data-driven array architectures seem to be important alternatives for coarse-grained reconfigurable computing platforms. Their use has provided performance improvements over microprocessors and shorter programming cycles than FPGA-based platforms. As with other architectures, in data-driven architectures loop pipelining plays an important role to improve performance. Usually this kind of pipelining can be achieved using the dataflow software pipelining technique or other software pipelining approaches. Although performance improvements are achieved, those techniques heavily depend on the insertion of pipelining stages and thus require complex balancing efforts. Furthermore, those techniques statically define the pipelining and do not take fully advantage of the dynamic scheduling attainable by the data-driven concept. This paper presents a novel scheme to pipeline loops in data-driven architectures, orchestrated by a handshaking protocol. Using the new approach, self loop pipelining is naturally achieved. The scheme is based on duplicating cyclic hardware structures, in order they are autonomously executed, with synchronization being achieved by the data flow. It can be applied to nested loops, requires less aggressive pipeline balancing efforts than usual software pipelining techniques, and innermost loops with conditional structures can be pipelined without conservative pipelining implementations. We show results of using the proposed technique when mapping algorithms in imperative programming languages to the PACT eXtreme Processing Platform (XPP). The results confirm improvements over the use of conventional loop pipelining techniques. Better performance and fewer resources are achieved in a number of cases