RECONFIGURABLE COPROCESSOR ARCHITECTURE TEMPLATE FOR NESTED LOOPS AND PROGRAMMING TOOL

摘要

The architectures derived from the proposed template are integrated in a generic System on Chip (SoC) and consist of reconfigurable coprocessors for executing nested program loops whose bodies are expressions of operations performed in a functional unit array in parallel. The data arrays are accessed from one or more system inputs and from an embedded memory array in parallel. The processed data arrays are sent back to the memory array or to system outputs. The architectures enable the acceleration of nested loops compared to execution on a standard processor, where only one operation or datum access can be performed at a time. The invention can be used in a number of applications especially those which involve digital signal processing, such as multimedia and communications. The architectures are used preferably in conjunction with von Neumann processors which are better at implementing control flow. The architectures can be scaled easily in the number of data stream inputs, outputs, embedded memories, functional units and configuration registers. A computational system may entail several general purpose processors and several coprocessors derived from this architectural template. The coprocessors are connected either synchronously or using asynchronous first in first out memories (FIFOs), forming a globally asynchronous locally synchronous system. Each coprocessor can be programmed by tagging and rewriting the nested loops in the original program. The programming tool produces a coprocessor configuration per each nested loop group, which is replaced in the original code with coprocessor input/output operations and control.