Implementation and Analysis of AES Encryption on GPU

Li, Qinjian; Zhong, Chengwen; Zhao, Kaixuan; Mei, Xinxin; Chu, Xiaowen

doi:10.1109/hpcc.2012.119

Cited by 80 publications

(28 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…No related work for CIPHERUNICORN-A, Hierocrypt-3, SC2000, nor CLEFIA using GPGPU is described in the literature without our previous work. [19] CUDA AES GTX285 37.8 Nishikawa et al [19] CUDA Camellia GTX285 38.0 Osvik et al [25] CUDA AES GTX295 * 3 30.9 * 4 Li et al [23] CUDA AES C2050 60 Gilger et al [26] CUDA AES GTX295 * 3 29.6 Gilger et al [26] OpenCL AES GTX295 * 3 25.4 Gilger et al [26] CUDA Camellia GTX295 * 3 26.3 Gilger et al [26] OpenCL Camellia GTX295 * 3 26.3 * 3 They use only 1 of 2 chips of GPU (240 cores) * 4 Including data transfer time Qinjian Li et al [23] implemented AES on Nvidia C2050 using CUDA and achieved 60 Gb/sec throughput by reordering plaintext data. A quantitative cost of reordering was not shown.…”

Section: Performance Resultsmentioning

confidence: 99%

HiCrypt: A Specialized Translator for Symmetric Block Cipher and GPGPU

Iwai

Nishikawa

Kurokawa

2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYMany-core computer systems with GPUs are coming into mainstream use from high-end computing, including supercomputers, to embedded processors. Consequently, the implementation of cryptographic methods on GPGPU is also becoming popular because of such systems' performance. However, many factors affect the performance of GPUs. To cope with this problem, we developed a new translator, HiCrypt, which can generate an optimized GPGPU program written in both of CUDA and OpenCL from a cipher program written in standard C language with directives. Users must annotate only variables and an encoding/decoding function, which are characteristics of cipher programs, with directives. To evaluate the translator, five representative cipher programs are translated into CUDA and OpenCL programs by the translator. Generated programs perform high throughput almost identical to hand optimized programs for all five cipher programs. HiCrypt will contribute to development and evaluate of new and various symmetric block ciphers using GPGPU.

show abstract

Section: Performance Resultsmentioning

confidence: 99%

HiCrypt: A Specialized Translator for Symmetric Block Cipher and GPGPU

Iwai

Nishikawa

Kurokawa

2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Li et al also implemented AES-128 with TBox on Nvidia Tesla C2050 using CUDA, giving throughput of 60.0 Gbps ignoring data transfer [6]. However, they reordered the plaintext in host memory before loading it onto device memory to ingenerate coalesced access into global memory.…”

Section: Throughput Of Block Ciphers On Gpusmentioning

confidence: 99%

“…Instead, some works have been done for the evaluation of throughputs on GPUs with Nvidia Fermi and AMD VLIW architectures [6]- [8], [15].…”

Section: Throughput Of Block Ciphers On Gpusmentioning

confidence: 99%

“…Therefore, the performance evaluation of block ciphers on GPUs with Kepler and GCN architectures is an important research issue for understanding the potential of high-speed encryption processing on a GPU. However, regarding encryption technology on a GPU, performance only with Nvidia Fermi and AMD VLIW architectures have been reported in previous works [6]- [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Throughput and Power Efficiency Evaluation of Block Ciphers on Kepler and GCN GPUs Using Micro-Benchmark Analysis

Nishikawa

Iwai

Tanaka

et al. 2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYComputer systems with GPUs are expected to become a strong methodology for high-speed encryption processing. Moreover, power consumption has remained a primary deterrent for such processing on devices of all sizes. However, GPU vendors are currently announcing their future roadmaps of GPU architecture development: Nvidia Corp. promotes the Kepler architecture and AMD Corp. emphasizes the GCN architecture. Therefore, we evaluated throughput and power efficiency of three 128-bit block ciphers on GPUs with recent Nvidia Kepler and AMD GCN architectures. From our experiments, whereas the throughput and per-watt throughput of AES-128 on Radeon HD 7970 (2048 cores) with GCN architecture are 205.0 Gbps and 1.3 Gbps/Watt respectively, those on Geforce GTX 680 (1536 cores) with Kepler architecture are, respectively, 63.9 Gbps and 0.43 Gbps/W; an approximately 3.2 times throughput difference occurs between AES-128 on the two GPUs. Next, we investigate the reasons for the throughput difference using our micro-benchmark suites. According to the results, we speculate that to ameliorate Kepler GPUs as co-processor of block ciphers, the arithmetic and logical instructions must be improved in terms of software and hardware.

show abstract

“…Iwai et al achieved approximately a throughput of 35Gbps (Gigabits per second) on a NVIDIA Geforce GTX285 [12]. Li et al [17] achieved the highest performance, around 60Gbps throughput on a NVIDIA Tesla C2050 GPU, which runs up to 50 times faster than an Intel Core i7-920. More recent work accelerated asymmetric ciphers by exploiting the power of GPUs [31].…”

mentioning

confidence: 99%

Power Analysis Attack of an AES GPU Implementation

et al. 2018

View full text Add to dashboard Cite

In the past, Graphics Processing Units (GPUs) were mainly used for graphics rendering. In the past 10 years, they have been redesigned and are used to accelerate a wide range of applications, including deep neural networks, image reconstruction, and cryptographic algorithms. Despite being the accelerator of choice in a number of important application domains, today's GPUs receive little attention on their security, especially their vulnerability to realistic and practical threats, such as sidechannel attacks. In this work, we present our study of side-channel vulnerability targeting a general purpose GPU. We propose and implement a side-channel power analysis methodology to extract all the last round key bytes of an AES (Advanced Encryption Standard) implementation on an NVIDIA TESLA GPU. We first analyze the challenges of capturing GPU power traces due to the degree of concurrency and underlying architectural features of a GPU, and propose techniques to overcome these challenges. We then construct an appropriate power model for the GPU. We describe effective methods to process the GPU power traces and launch a correlation power attack (CPA) on the processed data. We carefully consider the scalability of the attack with increasing degrees of parallelism, a key challenge on the GPU. Both our empirical and theoretical results show that parallel computing hardware systems such as a GPU are vulnerable to power analysis side-channel attacks, and need to be hardened against such threats.

show abstract

Implementation and Analysis of AES Encryption on GPU

Cited by 80 publications

References 9 publications

HiCrypt: A Specialized Translator for Symmetric Block Cipher and GPGPU

HiCrypt: A Specialized Translator for Symmetric Block Cipher and GPGPU

Throughput and Power Efficiency Evaluation of Block Ciphers on Kepler and GCN GPUs Using Micro-Benchmark Analysis

Power Analysis Attack of an AES GPU Implementation

Contact Info

Product

Resources

About