Efficient Mapping of CDFG onto Coarse-Grained Reconfigurable Array Architectures

Satyajit Das 1 Kevin Martin 1 Philippe Coussy 1 Davide Rossi 2 Luca Benini 2
1 Lab-STICC_UBS_CACS_MOCS
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
Abstract : In the approaching era of IoT, flexible and low power accelerators have become essential to meet aggressive energy efficiency targets. During the last few decades, Coarse Grain Reconfigurable Arrays (CGRA) have demonstrated high energy efficiency as accelerators, especially for high-performance streaming applications. While existing CGRAs mostly rely on partial and full predication techniques to support conditional branches, inefficient architecture and mapping support for handling control flow limits the use of CGRAs in accelerating either only inner loop bodies, or transformed loops specifically adapted to the target CGRA. This paper proposes a novel CGRA architecture with support for jump and conditional jump instructions and a lightweight global synchronization mechanism to enable complete Control Data Flow Graph (CDFG) mapping in an ultra-low-power environment. The architecture is coupled with a complete design flow that efficiently maps applications with heavy control flow starting from a generic C language description. The proposed mapping approach reduces the impact of wasteful instruction issues in the conventional approaches of predication providing an average energy improvement of 1.44x and 1.6x when compared to the state of the art partial and full predication techniques. Moreover , the proposed method achieves an average speed-up up to 21x and an energy improvement up to 50.42x while executing applications with heavy control flow with respect to sequential execution on a low-power embedded CPU, demonstrating its suitability for next generation IoT applications.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01452277
Contributor : Kevin Martin <>
Submitted on : Friday, October 5, 2018 - 3:41:17 PM
Last modification on : Monday, February 25, 2019 - 3:14:12 PM
Document(s) archivé(s) le : Sunday, January 6, 2019 - 4:33:09 PM

File

ASPDAC17.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01452277, version 1

Citation

Satyajit Das, Kevin Martin, Philippe Coussy, Davide Rossi, Luca Benini. Efficient Mapping of CDFG onto Coarse-Grained Reconfigurable Array Architectures. ASP-DAC, Jan 2017, Tokyo, Japan. ⟨hal-01452277⟩

Share

Metrics

Record views

715

Files downloads

48