Acceleration of differential power analysis through the parallel use of GPU and CPU

Sung Jae Lee; Seog Chung Seo; Dong Guk Han; Seokhie Hong; Sangjin Lee

doi:10.1587/transfun.E93.A.1688

Acceleration of differential power analysis through the parallel use of GPU and CPU

Sung Jae Lee, Seog Chung Seo, Dong Guk Han, Seokhie Hong, Sangjin Lee

Research output: Contribution to journal › Article › peer-review

4 Citations (Scopus)

Abstract

This paper proposes methods for accelerating DPA by using the CPU and the GPU in a parallel manner. The overhead of naive DPA evaluation software increases excessively as the number of points in a trace or the number of traces is enlarged due to the rapid increase of file I/O overhead. This paper presents some techniques, with respect to DPA-arithmetic and file handling, which can make the overhead of DPA software become not extreme but gradual as the increase of the amount of trace data to be processed. Through generic experiments, we show that the software, equipped with the proposed methods, using both CPU and GPU can shorten the time for evaluating the DPA resistance of devices by almost half.

Original language	English
Pages (from-to)	1688-1692
Number of pages	5
Journal	IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Volume	E93-A
Issue number	9
DOIs	https://doi.org/10.1587/transfun.E93.A.1688
Publication status	Published - 2010 Sept

Keywords

Compute unified device architecture (CUDA)
Differential power analysis (DPA)
Graphic processing unit (GPU)

ASJC Scopus subject areas

Signal Processing
Computer Graphics and Computer-Aided Design
Electrical and Electronic Engineering
Applied Mathematics

Access to Document

10.1587/transfun.E93.A.1688

Cite this

@article{b525e61280c44d30a5acdb5f515d8a29,

title = "Acceleration of differential power analysis through the parallel use of GPU and CPU",

abstract = "This paper proposes methods for accelerating DPA by using the CPU and the GPU in a parallel manner. The overhead of naive DPA evaluation software increases excessively as the number of points in a trace or the number of traces is enlarged due to the rapid increase of file I/O overhead. This paper presents some techniques, with respect to DPA-arithmetic and file handling, which can make the overhead of DPA software become not extreme but gradual as the increase of the amount of trace data to be processed. Through generic experiments, we show that the software, equipped with the proposed methods, using both CPU and GPU can shorten the time for evaluating the DPA resistance of devices by almost half.",

keywords = "Compute unified device architecture (CUDA), Differential power analysis (DPA), Graphic processing unit (GPU)",

author = "Lee, {Sung Jae} and Seo, {Seog Chung} and Han, {Dong Guk} and Seokhie Hong and Sangjin Lee",

year = "2010",

month = sep,

doi = "10.1587/transfun.E93.A.1688",

language = "English",

volume = "E93-A",

pages = "1688--1692",

journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",

issn = "0916-8508",

publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",

number = "9",

}

TY - JOUR

T1 - Acceleration of differential power analysis through the parallel use of GPU and CPU

AU - Lee, Sung Jae

AU - Seo, Seog Chung

AU - Han, Dong Guk

AU - Hong, Seokhie

AU - Lee, Sangjin

PY - 2010/9

Y1 - 2010/9

N2 - This paper proposes methods for accelerating DPA by using the CPU and the GPU in a parallel manner. The overhead of naive DPA evaluation software increases excessively as the number of points in a trace or the number of traces is enlarged due to the rapid increase of file I/O overhead. This paper presents some techniques, with respect to DPA-arithmetic and file handling, which can make the overhead of DPA software become not extreme but gradual as the increase of the amount of trace data to be processed. Through generic experiments, we show that the software, equipped with the proposed methods, using both CPU and GPU can shorten the time for evaluating the DPA resistance of devices by almost half.

AB - This paper proposes methods for accelerating DPA by using the CPU and the GPU in a parallel manner. The overhead of naive DPA evaluation software increases excessively as the number of points in a trace or the number of traces is enlarged due to the rapid increase of file I/O overhead. This paper presents some techniques, with respect to DPA-arithmetic and file handling, which can make the overhead of DPA software become not extreme but gradual as the increase of the amount of trace data to be processed. Through generic experiments, we show that the software, equipped with the proposed methods, using both CPU and GPU can shorten the time for evaluating the DPA resistance of devices by almost half.

KW - Compute unified device architecture (CUDA)

KW - Differential power analysis (DPA)

KW - Graphic processing unit (GPU)

UR - http://www.scopus.com/inward/record.url?scp=77956481953&partnerID=8YFLogxK

U2 - 10.1587/transfun.E93.A.1688

DO - 10.1587/transfun.E93.A.1688

M3 - Article

AN - SCOPUS:77956481953

SN - 0916-8508

VL - E93-A

SP - 1688

EP - 1692

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

IS - 9

ER -

Acceleration of differential power analysis through the parallel use of GPU and CPU

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this