Enabling Parallelization via a Reconfigurable Chip Multiprocessor - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2010

Enabling Parallelization via a Reconfigurable Chip Multiprocessor


While reconfigurable computing has traditionally involved attaching a reconfigurable fabric to a single processor core, the prospect of large-scale CMPs calls for a reevaluation of reconfigurable computing from the perspective of multicore architectures. We present ReMAPP, a reconfigurable architecture geared towards application acceleration and parallelization. In ReMAPP, parallel threads share a common reconfigurable fabric which can be configured for individual thread computation or fine-grained communication with integrated computation. The architecture supports both fine-grained barrier synchronization and fine-grained point-to-point communication for pipeline parallelization. The combination of communication and configurable computation within ReMAPP provides the unique ability to perform customized computation while data is transferred between cores, and to execute custom global functions after barrier synchronization. We demonstrate that ReMAPP achieves significantly higher performance and energy efficiency compared to hard-wired communication- only mechanisms, and over what can ideally be achieved by allocating the fabric area to more cores.
Fichier principal
Vignette du fichier
PESPMA-watkins.pdf (1.19 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00494289 , version 1 (22-06-2010)


  • HAL Id : inria-00494289 , version 1


Matthew A. Watkins, David H. Albonesi. Enabling Parallelization via a Reconfigurable Chip Multiprocessor. Pespma 2010 - Workshop on Parallel Execution of Sequential Programs on Multi-core Architecture, Jun 2010, Saint Malo, France. ⟨inria-00494289⟩
42 View
79 Download


Gmail Facebook Twitter LinkedIn More