Splitting functions in code management on scratchpad memories

Youngbin Kim, Jian Cai, Yooseong Kim, Kyoungwoo Lee, Aviral Shrivastava

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

3 Citations (Scopus)

Abstract

As the number of cores increases, cache-based memory hierarchy is becoming a major problem in terms of the scalability and energy consumption. Software-managed scratchpad memories (SPM) is a scalable alternative to caches, but the benefit comes at the cost of explicit management of data. For instance, an instruction SPM needs a code management techniques to load code blocks to the SPM. This paper presents a technique to split functions into smaller functions, to break away with the fundamental limitations of function-level code management. Our function-splitting technique is able to generate more efficient mappings by modifying the characteristics of functions to be more suitable for function-level code management. We propose two optimization policies to improve performance and reduce size respectively. The performance optimization policy improves performance by 16% on average, which can only be achieved by using 20% more SPM space if without function-splitting The size optimization policy can reduce the minimum SPM size requirement by 31% while increasing only 7% execution time.

Original languageEnglish
Title of host publication2016 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781450344661
DOIs
Publication statusPublished - 2016 Nov 7
Event35th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2016 - Austin, United States
Duration: 2016 Nov 72016 Nov 10

Publication series

NameIEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
Volume07-10-November-2016
ISSN (Print)1092-3152

Other

Other35th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2016
CountryUnited States
CityAustin
Period16/11/716/11/10

Fingerprint

Data storage equipment
Block codes
Scalability
Energy utilization

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Cite this

Kim, Y., Cai, J., Kim, Y., Lee, K., & Shrivastava, A. (2016). Splitting functions in code management on scratchpad memories. In 2016 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2016 [2967075] (IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD; Vol. 07-10-November-2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1145/2966986.2967075
Kim, Youngbin ; Cai, Jian ; Kim, Yooseong ; Lee, Kyoungwoo ; Shrivastava, Aviral. / Splitting functions in code management on scratchpad memories. 2016 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2016. Institute of Electrical and Electronics Engineers Inc., 2016. (IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD).
@inproceedings{94fb1057deca4624ab7faf8e780ac14e,
title = "Splitting functions in code management on scratchpad memories",
abstract = "As the number of cores increases, cache-based memory hierarchy is becoming a major problem in terms of the scalability and energy consumption. Software-managed scratchpad memories (SPM) is a scalable alternative to caches, but the benefit comes at the cost of explicit management of data. For instance, an instruction SPM needs a code management techniques to load code blocks to the SPM. This paper presents a technique to split functions into smaller functions, to break away with the fundamental limitations of function-level code management. Our function-splitting technique is able to generate more efficient mappings by modifying the characteristics of functions to be more suitable for function-level code management. We propose two optimization policies to improve performance and reduce size respectively. The performance optimization policy improves performance by 16{\%} on average, which can only be achieved by using 20{\%} more SPM space if without function-splitting The size optimization policy can reduce the minimum SPM size requirement by 31{\%} while increasing only 7{\%} execution time.",
author = "Youngbin Kim and Jian Cai and Yooseong Kim and Kyoungwoo Lee and Aviral Shrivastava",
year = "2016",
month = "11",
day = "7",
doi = "10.1145/2966986.2967075",
language = "English",
series = "IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2016 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2016",
address = "United States",

}

Kim, Y, Cai, J, Kim, Y, Lee, K & Shrivastava, A 2016, Splitting functions in code management on scratchpad memories. in 2016 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2016., 2967075, IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD, vol. 07-10-November-2016, Institute of Electrical and Electronics Engineers Inc., 35th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2016, Austin, United States, 16/11/7. https://doi.org/10.1145/2966986.2967075

Splitting functions in code management on scratchpad memories. / Kim, Youngbin; Cai, Jian; Kim, Yooseong; Lee, Kyoungwoo; Shrivastava, Aviral.

2016 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2016. Institute of Electrical and Electronics Engineers Inc., 2016. 2967075 (IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD; Vol. 07-10-November-2016).

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

TY - GEN

T1 - Splitting functions in code management on scratchpad memories

AU - Kim, Youngbin

AU - Cai, Jian

AU - Kim, Yooseong

AU - Lee, Kyoungwoo

AU - Shrivastava, Aviral

PY - 2016/11/7

Y1 - 2016/11/7

N2 - As the number of cores increases, cache-based memory hierarchy is becoming a major problem in terms of the scalability and energy consumption. Software-managed scratchpad memories (SPM) is a scalable alternative to caches, but the benefit comes at the cost of explicit management of data. For instance, an instruction SPM needs a code management techniques to load code blocks to the SPM. This paper presents a technique to split functions into smaller functions, to break away with the fundamental limitations of function-level code management. Our function-splitting technique is able to generate more efficient mappings by modifying the characteristics of functions to be more suitable for function-level code management. We propose two optimization policies to improve performance and reduce size respectively. The performance optimization policy improves performance by 16% on average, which can only be achieved by using 20% more SPM space if without function-splitting The size optimization policy can reduce the minimum SPM size requirement by 31% while increasing only 7% execution time.

AB - As the number of cores increases, cache-based memory hierarchy is becoming a major problem in terms of the scalability and energy consumption. Software-managed scratchpad memories (SPM) is a scalable alternative to caches, but the benefit comes at the cost of explicit management of data. For instance, an instruction SPM needs a code management techniques to load code blocks to the SPM. This paper presents a technique to split functions into smaller functions, to break away with the fundamental limitations of function-level code management. Our function-splitting technique is able to generate more efficient mappings by modifying the characteristics of functions to be more suitable for function-level code management. We propose two optimization policies to improve performance and reduce size respectively. The performance optimization policy improves performance by 16% on average, which can only be achieved by using 20% more SPM space if without function-splitting The size optimization policy can reduce the minimum SPM size requirement by 31% while increasing only 7% execution time.

UR - http://www.scopus.com/inward/record.url?scp=85001055691&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85001055691&partnerID=8YFLogxK

U2 - 10.1145/2966986.2967075

DO - 10.1145/2966986.2967075

M3 - Conference contribution

AN - SCOPUS:85001055691

T3 - IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD

BT - 2016 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kim Y, Cai J, Kim Y, Lee K, Shrivastava A. Splitting functions in code management on scratchpad memories. In 2016 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2016. Institute of Electrical and Electronics Engineers Inc. 2016. 2967075. (IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD). https://doi.org/10.1145/2966986.2967075