Dataflow-driven execution control in a coarse-grained reconfigurable array (abstract only)

  • Authors:
  • Robin Panda;Scott Hauck

  • Affiliations:
  • University of Washington, Seattle, WA, USA;University of Washington, Seattle, WA, USA

  • Venue:
  • Proceedings of the ACM/SIGDA international symposium on Field Programmable Gate Arrays
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Coarse Grained Reconfigurable Arrays (CGRAs) are a promising class of architectures for accelerating applications using a large number of parallel execution units for high throughput. While they are typically very efficient for a single task, all functional units are required to perform in lock step; this makes some classes of applications more difficult to program and efficiently use resources. Other architectures like Massively Parallel Processor Arrays (MPPAs) are better suited for these applications and excel at executing unrelated tasks simultaneously, but the amount of resources dedicated to a single task is limited. We are developing a new architecture with the design flexibility of an MPPA and the throughput of a CGRA. A key to the flexibility of MPPAs is the ability for subtasks to execute independently instead of in lock step with all other tasks on the array. Adding this capability requires special control circuitry for architectural support in a CGRA. We decribe the modifications required and our solutions. Additionally, we also describe the CAD tool modification and application developer concerns for utilizing the resulting hybrid CGRA/MPPA architecture.