Efficient heap data management on software managed manycore architectures

Jinn Pean Lin, Jing Lu, Jian Cai, Aviral Shrivastava

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

Abstract

Software Managed Manycore (SMM) architectures have been proposed as a solution for scaling the memory architecture. In a typical SMM architecture, Scratch Pad Memories (SPM) are used instead of caches, and data must be explicitly managed in software. While all code and data need to be managed, heap management on SMMs is especially challenging due to the highly dynamic nature of heap data access. Existing techniques spend over 90% of execution time on heap data management, which largely compromised the power efficiency of SMM architectures. This paper presents compiler-based efficient techniques that reduce heap management overhead. Experimental results on benchmarks from MiBench [1] executing on an SMM processor modeled in Gem5 demonstrate that our approach implemented in LLVM 3.8 can improve execution time by an average of 80%, compared to the state-of-the-art [2].

Original languageEnglish (US)
Title of host publicationProceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages269-274
Number of pages6
ISBN (Electronic)9781728104096
DOIs
StatePublished - May 9 2019
Event32nd International Conference on VLSI Design, VLSID 2019 - New Delhi, India
Duration: Jan 5 2019Jan 9 2019

Publication series

NameProceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019

Conference

Conference32nd International Conference on VLSI Design, VLSID 2019
CountryIndia
CityNew Delhi
Period1/5/191/9/19

Fingerprint

Information management
Memory architecture
Data storage equipment

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Lin, J. P., Lu, J., Cai, J., & Shrivastava, A. (2019). Efficient heap data management on software managed manycore architectures. In Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019 (pp. 269-274). [8710801] (Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VLSID.2019.00065

Efficient heap data management on software managed manycore architectures. / Lin, Jinn Pean; Lu, Jing; Cai, Jian; Shrivastava, Aviral.

Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 269-274 8710801 (Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019).

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

Lin, JP, Lu, J, Cai, J & Shrivastava, A 2019, Efficient heap data management on software managed manycore architectures. in Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019., 8710801, Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019, Institute of Electrical and Electronics Engineers Inc., pp. 269-274, 32nd International Conference on VLSI Design, VLSID 2019, New Delhi, India, 1/5/19. https://doi.org/10.1109/VLSID.2019.00065
Lin JP, Lu J, Cai J, Shrivastava A. Efficient heap data management on software managed manycore architectures. In Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 269-274. 8710801. (Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019). https://doi.org/10.1109/VLSID.2019.00065
Lin, Jinn Pean ; Lu, Jing ; Cai, Jian ; Shrivastava, Aviral. / Efficient heap data management on software managed manycore architectures. Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 269-274 (Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019).
@inproceedings{d7bdbde5561a4d9087448661c6745678,
title = "Efficient heap data management on software managed manycore architectures",
abstract = "Software Managed Manycore (SMM) architectures have been proposed as a solution for scaling the memory architecture. In a typical SMM architecture, Scratch Pad Memories (SPM) are used instead of caches, and data must be explicitly managed in software. While all code and data need to be managed, heap management on SMMs is especially challenging due to the highly dynamic nature of heap data access. Existing techniques spend over 90{\%} of execution time on heap data management, which largely compromised the power efficiency of SMM architectures. This paper presents compiler-based efficient techniques that reduce heap management overhead. Experimental results on benchmarks from MiBench [1] executing on an SMM processor modeled in Gem5 demonstrate that our approach implemented in LLVM 3.8 can improve execution time by an average of 80{\%}, compared to the state-of-the-art [2].",
author = "Lin, {Jinn Pean} and Jing Lu and Jian Cai and Aviral Shrivastava",
year = "2019",
month = "5",
day = "9",
doi = "10.1109/VLSID.2019.00065",
language = "English (US)",
series = "Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "269--274",
booktitle = "Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019",

}

TY - GEN

T1 - Efficient heap data management on software managed manycore architectures

AU - Lin, Jinn Pean

AU - Lu, Jing

AU - Cai, Jian

AU - Shrivastava, Aviral

PY - 2019/5/9

Y1 - 2019/5/9

N2 - Software Managed Manycore (SMM) architectures have been proposed as a solution for scaling the memory architecture. In a typical SMM architecture, Scratch Pad Memories (SPM) are used instead of caches, and data must be explicitly managed in software. While all code and data need to be managed, heap management on SMMs is especially challenging due to the highly dynamic nature of heap data access. Existing techniques spend over 90% of execution time on heap data management, which largely compromised the power efficiency of SMM architectures. This paper presents compiler-based efficient techniques that reduce heap management overhead. Experimental results on benchmarks from MiBench [1] executing on an SMM processor modeled in Gem5 demonstrate that our approach implemented in LLVM 3.8 can improve execution time by an average of 80%, compared to the state-of-the-art [2].

AB - Software Managed Manycore (SMM) architectures have been proposed as a solution for scaling the memory architecture. In a typical SMM architecture, Scratch Pad Memories (SPM) are used instead of caches, and data must be explicitly managed in software. While all code and data need to be managed, heap management on SMMs is especially challenging due to the highly dynamic nature of heap data access. Existing techniques spend over 90% of execution time on heap data management, which largely compromised the power efficiency of SMM architectures. This paper presents compiler-based efficient techniques that reduce heap management overhead. Experimental results on benchmarks from MiBench [1] executing on an SMM processor modeled in Gem5 demonstrate that our approach implemented in LLVM 3.8 can improve execution time by an average of 80%, compared to the state-of-the-art [2].

UR - http://www.scopus.com/inward/record.url?scp=85066914338&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066914338&partnerID=8YFLogxK

U2 - 10.1109/VLSID.2019.00065

DO - 10.1109/VLSID.2019.00065

M3 - Conference contribution

T3 - Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019

SP - 269

EP - 274

BT - Proceedings - 32nd International Conference on VLSI Design, VLSID 2019 - Held concurrently with 18th International Conference on Embedded Systems, ES 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -