LASER: A hardware/software approach to accelerate complicated loops on CGRAs

Mahesh Balasubramanian, Shail Dave, Aviral Shrivastava, Reiley Jeyapaul

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Coarse-Grained Reconfigurable Arrays (CGRAs) are popular accelerators predominantly used in streaming, filtering, and decoding applications. Due to their high performance and high power-efficiency, CGRAs can be a promising solution to accelerate the loops of general purpose applications also. However, the loops in general purpose applications are often complicated, like loops with perfect and imperfect nests and loops with nested if-then-else's (conditionals). We argue that the existing hardware-software solutions to execute branches and conditions are inefficient. In order to efficiently execute complicated loops on CGRAs, we present a hardware-software hybrid solution: LASER - a comprehensive technique to accelerate compute-intensive loops of applications. In LASER, compiler transforms complex loops, maps them to the CGRA, and lays them out in the memory in a specific manner, such that the hardware can fetch and execute the instructions from the right path at runtime. LASER achieves a geomean performance improvement of 40.91% and utilization of 43.43% with 46% lower energy consumption.

Original languageEnglish (US)
Title of host publicationProceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1069-1074
Number of pages6
Volume2018-January
ISBN (Electronic)9783981926316
DOIs
StatePublished - Apr 19 2018
Event2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018 - Dresden, Germany
Duration: Mar 19 2018Mar 23 2018

Other

Other2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018
CountryGermany
CityDresden
Period3/19/183/23/18

Fingerprint

Hardware
Computer hardware
Particle accelerators
Decoding
Energy utilization
Data storage equipment
Laser
Software

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality
  • Hardware and Architecture
  • Software
  • Information Systems and Management

Cite this

Balasubramanian, M., Dave, S., Shrivastava, A., & Jeyapaul, R. (2018). LASER: A hardware/software approach to accelerate complicated loops on CGRAs. In Proceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018 (Vol. 2018-January, pp. 1069-1074). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/DATE.2018.8342170

LASER : A hardware/software approach to accelerate complicated loops on CGRAs. / Balasubramanian, Mahesh; Dave, Shail; Shrivastava, Aviral; Jeyapaul, Reiley.

Proceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 1069-1074.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Balasubramanian, M, Dave, S, Shrivastava, A & Jeyapaul, R 2018, LASER: A hardware/software approach to accelerate complicated loops on CGRAs. in Proceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1069-1074, 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018, Dresden, Germany, 3/19/18. https://doi.org/10.23919/DATE.2018.8342170
Balasubramanian M, Dave S, Shrivastava A, Jeyapaul R. LASER: A hardware/software approach to accelerate complicated loops on CGRAs. In Proceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1069-1074 https://doi.org/10.23919/DATE.2018.8342170
Balasubramanian, Mahesh ; Dave, Shail ; Shrivastava, Aviral ; Jeyapaul, Reiley. / LASER : A hardware/software approach to accelerate complicated loops on CGRAs. Proceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1069-1074
@inproceedings{a42f16461a9f4c2ba09c0c6e4fcb3f8c,
title = "LASER: A hardware/software approach to accelerate complicated loops on CGRAs",
abstract = "Coarse-Grained Reconfigurable Arrays (CGRAs) are popular accelerators predominantly used in streaming, filtering, and decoding applications. Due to their high performance and high power-efficiency, CGRAs can be a promising solution to accelerate the loops of general purpose applications also. However, the loops in general purpose applications are often complicated, like loops with perfect and imperfect nests and loops with nested if-then-else's (conditionals). We argue that the existing hardware-software solutions to execute branches and conditions are inefficient. In order to efficiently execute complicated loops on CGRAs, we present a hardware-software hybrid solution: LASER - a comprehensive technique to accelerate compute-intensive loops of applications. In LASER, compiler transforms complex loops, maps them to the CGRA, and lays them out in the memory in a specific manner, such that the hardware can fetch and execute the instructions from the right path at runtime. LASER achieves a geomean performance improvement of 40.91{\%} and utilization of 43.43{\%} with 46{\%} lower energy consumption.",
author = "Mahesh Balasubramanian and Shail Dave and Aviral Shrivastava and Reiley Jeyapaul",
year = "2018",
month = "4",
day = "19",
doi = "10.23919/DATE.2018.8342170",
language = "English (US)",
volume = "2018-January",
pages = "1069--1074",
booktitle = "Proceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - LASER

T2 - A hardware/software approach to accelerate complicated loops on CGRAs

AU - Balasubramanian, Mahesh

AU - Dave, Shail

AU - Shrivastava, Aviral

AU - Jeyapaul, Reiley

PY - 2018/4/19

Y1 - 2018/4/19

N2 - Coarse-Grained Reconfigurable Arrays (CGRAs) are popular accelerators predominantly used in streaming, filtering, and decoding applications. Due to their high performance and high power-efficiency, CGRAs can be a promising solution to accelerate the loops of general purpose applications also. However, the loops in general purpose applications are often complicated, like loops with perfect and imperfect nests and loops with nested if-then-else's (conditionals). We argue that the existing hardware-software solutions to execute branches and conditions are inefficient. In order to efficiently execute complicated loops on CGRAs, we present a hardware-software hybrid solution: LASER - a comprehensive technique to accelerate compute-intensive loops of applications. In LASER, compiler transforms complex loops, maps them to the CGRA, and lays them out in the memory in a specific manner, such that the hardware can fetch and execute the instructions from the right path at runtime. LASER achieves a geomean performance improvement of 40.91% and utilization of 43.43% with 46% lower energy consumption.

AB - Coarse-Grained Reconfigurable Arrays (CGRAs) are popular accelerators predominantly used in streaming, filtering, and decoding applications. Due to their high performance and high power-efficiency, CGRAs can be a promising solution to accelerate the loops of general purpose applications also. However, the loops in general purpose applications are often complicated, like loops with perfect and imperfect nests and loops with nested if-then-else's (conditionals). We argue that the existing hardware-software solutions to execute branches and conditions are inefficient. In order to efficiently execute complicated loops on CGRAs, we present a hardware-software hybrid solution: LASER - a comprehensive technique to accelerate compute-intensive loops of applications. In LASER, compiler transforms complex loops, maps them to the CGRA, and lays them out in the memory in a specific manner, such that the hardware can fetch and execute the instructions from the right path at runtime. LASER achieves a geomean performance improvement of 40.91% and utilization of 43.43% with 46% lower energy consumption.

UR - http://www.scopus.com/inward/record.url?scp=85048793392&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048793392&partnerID=8YFLogxK

U2 - 10.23919/DATE.2018.8342170

DO - 10.23919/DATE.2018.8342170

M3 - Conference contribution

AN - SCOPUS:85048793392

VL - 2018-January

SP - 1069

EP - 1074

BT - Proceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -