Citation
Reinhard von Hanxleden, Xin Li, Marian Boldt. "A Multi-Threaded Reactive Processor". Talk or presentation, 18, September, 2007.

Abstract
Many embedded systems belong to the class of reactive systems, which continuously react to inputs from the environment by generating corresponding outputs. The programming of reactive systems typically requires the use of non-standard control flow constructs, such as concurrency or exception handling. The synchronous language Esterel has been developed to express reactive control flow patterns in a concise manner, with a clear semantics that imposes deterministic program behavior under all circumstances. However, classical Esterel synthesis approaches suffer from the limitations of traditional processors, with their instruction set architectures geared towards the sequential von-Neumann execution model, or they are very inflexible if HW synthesis is involved.rnrn

Recently, another alternative for synthesizing Esterel has emerged, the reactive processing approach. This talk presents a multi-threaded reactive processor, the Kiel Esterel Processor (KEP). The KEP Instruction Set Architecture supports reactive control flow directly, and provides a very dense encoding; code size is typically an order of magnitude smaller than that of the MicroBlaze, a 32-bit COTS RISC processor core. The worst case reaction time is typically improved by 4x, and energy consumption is also typically reduced to a quarter. Apart from efficiency and determinism concerns, another advantage of reactive processors is that due to their comparatively simple structure (no caches, no pipelining) and their direct implementation of the synchronous model of computation it becomes feasible to precisely characterize their timing behavior.

Electronic downloads

• talk-trans.pdf · · 1674 kbytes

• HTML

  Reinhard von Hanxleden, Xin Li, Marian Boldt. <a
  href="http://chess.eecs.berkeley.edu/pubs/352.html"
  ><i>A Multi-Threaded Reactive
  Processor</i></a>, Talk or presentation,  18,
  September, 2007.

• Plain text

  Reinhard von Hanxleden, Xin Li, Marian Boldt. "A
  Multi-Threaded Reactive Processor". Talk or
  presentation,  18, September, 2007.

• BibTeX

  @presentation{vonHanxledenLiBoldt07_MultiThreadedReactiveProcessor,
      author = {Reinhard von Hanxleden and Xin Li and Marian Boldt},
      title = {A Multi-Threaded Reactive Processor},
      day = {18},
      month = {September},
      year = {2007},
      abstract = {Many embedded systems belong to the class of
                reactive systems, which continuously react to
                inputs from the environment by generating
                corresponding outputs. The programming of reactive
                systems typically requires the use of non-standard
                control flow constructs, such as concurrency or
                exception handling. The synchronous language
                Esterel has been developed to express reactive
                control flow patterns in a concise manner, with a
                clear semantics that imposes deterministic program
                behavior under all circumstances. However,
                classical Esterel synthesis approaches suffer from
                the limitations of traditional processors, with
                their instruction set architectures geared towards
                the sequential von-Neumann execution model, or
                they are very inflexible if HW synthesis is
                involved.rnrn<p>Recently, another alternative for
                synthesizing Esterel has emerged, the reactive
                processing approach. This talk presents a
                multi-threaded reactive processor, the Kiel
                Esterel Processor (KEP). The KEP Instruction Set
                Architecture supports reactive control flow
                directly, and provides a very dense encoding; code
                size is typically an order of magnitude smaller
                than that of the MicroBlaze, a 32-bit COTS RISC
                processor core. The worst case reaction time is
                typically improved by 4x, and energy consumption
                is also typically reduced to a quarter. Apart from
                efficiency and determinism concerns, another
                advantage of reactive processors is that due to
                their comparatively simple structure (no caches,
                no pipelining) and their direct implementation of
                the synchronous model of computation it becomes
                feasible to precisely characterize their timing
                behavior. },
      URL = {http://chess.eecs.berkeley.edu/pubs/352.html}
  }
  

Posted by Douglas Densmore on 10 Oct 2007.
Groups: chess
For additional information, see the Publications FAQ or contact webmaster at chess eecs berkeley edu.