Superthreading: Integrating Compilation Technology and Processor Architecture for Cost-Effective Concurrent Multithreading

Abstract

As the number of transistors that can be integrated on a single chip continues to grow, it is important for computer architects to think beyond the traditional approaches of deeper pipelines and wider instruction issue units for improving performance. This single-threaded execution model limits these approaches to exploiting only the relatively small amount of instruction-level parallelism available in application programs. While integrating an entire multiprocessor onto a single chip is feasible, this architecture is limited to exploiting only relatively coarse-grained heavy-weight parallelism. We propose the superthreaded architecture as an excellent alternative for utilizing the large number of transistors that will become available on a single high-density chip. As a hybrid of a wideissue superscalar processor and a multiprocessor-on-a-chip, this new concurrent multithreading architecture can leverage the best of existing and future parallel hardware and software technologies. By incorporating speculation for control dependences and run-time checking of data dependences, the superthreaded architecture can exploit the multiple granularities of parallelism available in general-purpose application programs to reduce the execution time of a single program.