Seeds of SEED: H-CRAM: In-memory Homomorphic Search Accelerator using Spintronic Computational RAM

Husrev Cilasun; Salonik Resch; Zamshed I. Chowdhury; Masoud Zabihi; Zhengyang Zhao; Thomas Peterson; Jian Ping Wang; Sachin S. Sapatnekar; Ulya R. Karpuzcu

doi:10.1109/SEED51797.2021.00018

Seeds of SEED: H-CRAM: In-memory Homomorphic Search Accelerator using Spintronic Computational RAM

Husrev Cilasun, Salonik Resch, Zamshed I. Chowdhury, Masoud Zabihi, Zhengyang Zhao, Thomas Peterson, Jian Ping Wang, Sachin S. Sapatnekar, Ulya R. Karpuzcu

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

Growing use of cloud raises privacy concerns for search in sensitive databases such as bioinformatics, where homomorphic encryption can help through direct computation -hence search/pattern matching-on the encrypted data. The recently proposed homomorphic secure content-addressable memory (SCAM) exploits this principle. Data dependencies in SCAM, however, lead to a memory bottleneck which has been addressed by various near-memory computing solutions. In this paper we demonstrate a more efficient alternative based on the true in-memory computing substrate spintronic Computational RAM (CRAM). The resulting SCAM accelerator, H-CRAM, achieves significant speedup and energy reduction.

Original language	English (US)
Title of host publication	Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	70-75
Number of pages	6
ISBN (Electronic)	9781665420259
DOIs	https://doi.org/10.1109/SEED51797.2021.00018
State	Published - 2021
Event	1st International Symposium on Secure and Private Execution Environment Design, SEED 2021 - Virtual, Online, United States Duration: Sep 20 2021 → Sep 21 2021

Publication series

Name	Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021

Conference

Conference	1st International Symposium on Secure and Private Execution Environment Design, SEED 2021
Country/Territory	United States
City	Virtual, Online
Period	9/20/21 → 9/21/21

Bibliographical note

Funding Information:
This work was supportedACKNOWinLEDGMENTpart by NSF grant no. SPX-1725420.

Publisher Copyright:
© 2021 IEEE.

Keywords

Computational RAM
Homomorphic
Processing in Memory

Access

10.1109/SEED51797.2021.00018

OpenUrl availability

Full text

Cite this

Cilasun, H., Resch, S., Chowdhury, Z. I., Zabihi, M., Zhao, Z., Peterson, T., Wang, J. P., Sapatnekar, S. S., & Karpuzcu, U. R. (2021). Seeds of SEED: H-CRAM: In-memory Homomorphic Search Accelerator using Spintronic Computational RAM. In Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021 (pp. 70-75). (Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SEED51797.2021.00018

Seeds of SEED: H-CRAM: In-memory Homomorphic Search Accelerator using Spintronic Computational RAM. / Cilasun, Husrev; Resch, Salonik; Chowdhury, Zamshed I. et al.
Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 70-75 (Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Cilasun, H, Resch, S, Chowdhury, ZI, Zabihi, M, Zhao, Z, Peterson, T, Wang, JP , Sapatnekar, SS & Karpuzcu, UR 2021, Seeds of SEED: H-CRAM: In-memory Homomorphic Search Accelerator using Spintronic Computational RAM. in Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021. Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021, Institute of Electrical and Electronics Engineers Inc., pp. 70-75, 1st International Symposium on Secure and Private Execution Environment Design, SEED 2021, Virtual, Online, United States, 9/20/21. https://doi.org/10.1109/SEED51797.2021.00018

Cilasun H, Resch S, Chowdhury ZI, Zabihi M, Zhao Z, Peterson T et al. Seeds of SEED: H-CRAM: In-memory Homomorphic Search Accelerator using Spintronic Computational RAM. In Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 70-75. (Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021). doi: 10.1109/SEED51797.2021.00018

Cilasun, Husrev ; Resch, Salonik ; Chowdhury, Zamshed I. et al. / Seeds of SEED : H-CRAM: In-memory Homomorphic Search Accelerator using Spintronic Computational RAM. Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 70-75 (Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021).

@inproceedings{540a7cda619c468db1497a73e956ff2f,

title = "Seeds of SEED: H-CRAM: In-memory Homomorphic Search Accelerator using Spintronic Computational RAM",

abstract = "Growing use of cloud raises privacy concerns for search in sensitive databases such as bioinformatics, where homomorphic encryption can help through direct computation -hence search/pattern matching-on the encrypted data. The recently proposed homomorphic secure content-addressable memory (SCAM) exploits this principle. Data dependencies in SCAM, however, lead to a memory bottleneck which has been addressed by various near-memory computing solutions. In this paper we demonstrate a more efficient alternative based on the true in-memory computing substrate spintronic Computational RAM (CRAM). The resulting SCAM accelerator, H-CRAM, achieves significant speedup and energy reduction.",

keywords = "Computational RAM, Homomorphic, Processing in Memory",

author = "Husrev Cilasun and Salonik Resch and Chowdhury, {Zamshed I.} and Masoud Zabihi and Zhengyang Zhao and Thomas Peterson and Wang, {Jian Ping} and Sapatnekar, {Sachin S.} and Karpuzcu, {Ulya R.}",

note = "Funding Information: This work was supportedACKNOWinLEDGMENTpart by NSF grant no. SPX-1725420. Publisher Copyright: {\textcopyright} 2021 IEEE.; 1st International Symposium on Secure and Private Execution Environment Design, SEED 2021 ; Conference date: 20-09-2021 Through 21-09-2021",

year = "2021",

doi = "10.1109/SEED51797.2021.00018",

language = "English (US)",

series = "Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "70--75",

booktitle = "Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021",

}

TY - GEN

T1 - Seeds of SEED

T2 - 1st International Symposium on Secure and Private Execution Environment Design, SEED 2021

AU - Cilasun, Husrev

AU - Resch, Salonik

AU - Chowdhury, Zamshed I.

AU - Zabihi, Masoud

AU - Zhao, Zhengyang

AU - Peterson, Thomas

AU - Wang, Jian Ping

AU - Sapatnekar, Sachin S.

AU - Karpuzcu, Ulya R.

PY - 2021

Y1 - 2021

N2 - Growing use of cloud raises privacy concerns for search in sensitive databases such as bioinformatics, where homomorphic encryption can help through direct computation -hence search/pattern matching-on the encrypted data. The recently proposed homomorphic secure content-addressable memory (SCAM) exploits this principle. Data dependencies in SCAM, however, lead to a memory bottleneck which has been addressed by various near-memory computing solutions. In this paper we demonstrate a more efficient alternative based on the true in-memory computing substrate spintronic Computational RAM (CRAM). The resulting SCAM accelerator, H-CRAM, achieves significant speedup and energy reduction.

AB - Growing use of cloud raises privacy concerns for search in sensitive databases such as bioinformatics, where homomorphic encryption can help through direct computation -hence search/pattern matching-on the encrypted data. The recently proposed homomorphic secure content-addressable memory (SCAM) exploits this principle. Data dependencies in SCAM, however, lead to a memory bottleneck which has been addressed by various near-memory computing solutions. In this paper we demonstrate a more efficient alternative based on the true in-memory computing substrate spintronic Computational RAM (CRAM). The resulting SCAM accelerator, H-CRAM, achieves significant speedup and energy reduction.

KW - Computational RAM

KW - Homomorphic

KW - Processing in Memory

UR - http://www.scopus.com/inward/record.url?scp=85123303708&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85123303708&partnerID=8YFLogxK

U2 - 10.1109/SEED51797.2021.00018

DO - 10.1109/SEED51797.2021.00018

M3 - Conference contribution

AN - SCOPUS:85123303708

T3 - Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021

SP - 70

EP - 75

BT - Proceedings - 2021 International Symposium on Secure and Private Execution Environment Design, SEED 2021

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 20 September 2021 through 21 September 2021

ER -

Seeds of SEED: H-CRAM: In-memory Homomorphic Search Accelerator using Spintronic Computational RAM

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this