An overview of high-level synthesis of multiprocessors for logic programming

This paper introduces a language and framework for designing multiprocessor architectures in the logic programming domain. Our goal is to enable application developers in areas such as machine learning and cognitive robotics to produce high-performance designs without detailed knowledge of hardware development. This framework provides a high level of abstraction, enabling rapid system generation and design space exploration while supporting high performance. We present an overview of the Archlog language and its library-based compilation framework, which makes use of a customisable logic programming processor. An example implementation of a multiprocessor for the machine learning system Progol on a 35MHz XC2V6000 FPGA achieves 43 times faster execution than a 2GHz Pentium 4 processor