Parallel Implementations of LEA

Seo, Hwajeong; Liu, Zhe; Park, Tae Hwan; Kim, Hyun‐Jin; Lee, Yeoncheol; Choi, Jongseok; Kim, Howon

doi:10.1007/978-3-319-12160-4_16

Cited by 10 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we have presented the first implementation of Chaskey, SIMECK, SIMON, and SPECK in GPU platforms, which can be useful in server environments. For LEA, our implementation is better (24.5% faster) than the previous best performance achieved by Seo et al The best throughput achieved by LEA, Chaskey, SPECK, and SIMECK is faster than 1 Tb/s, which proves that GPUs can be utilized as an efficient cryptographic accelerator when the implementation is carefully designed.…”

Section: Resultsmentioning

confidence: 62%

Section: Resultsmentioning

confidence: 99%

“…The GTX680 used by Seo et al and the K40c used in this paper are GPUs produced from the same generation (Kepler architecture), but K40c has more SMs (15) compared to GTX680 (8). In order to have a fair comparison, we scale the result from the work of Seo et al by a factor of 15/8 = 1.875; hence, the scaled throughput for implementation in the work of Seo et al becomes 138.82 × 15/8 = 260.28 Gb/s. The best throughput we can achieve in K40c for the LEA implementation (324 Gb/s) is 24.5% better than the scaled throughput (260.28 Gb/s) from the work of Seo et al This shows that storing the round keys in registers can improve the performance of LEA computation.…”

Section: Resultsmentioning

confidence: 99%

“…The implementation proposed by Seo et al 24 does not use warp shuffle to exchange the round keys among different threads, which is the main difference with our work. Besides that, we do not implement LEA in PTX code as proposed by them.…”

Section: Leamentioning

confidence: 88%

“…The selected GPUs represent the state‐of‐the‐art GPU architectures, which can be used as accelerators in data centers to handle massive computational tasks including encryption and decryption. Our implementation for LEA is also 24.5% faster than the state‐of‐the‐art work by Seo et al…”

Section: Introductionmentioning

confidence: 89%

See 4 more Smart Citations

Terabit encryption in a second: Performance evaluation of block ciphers in GPU with Kepler, Maxwell, and Pascal architectures

Lee

Goi

Phan

2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary With the emergence of IoT and cloud computing technologies, massive data are generated from various applications everyday and communicated through the Internet. Secure communication is essential to protect these data from malicious attacks. Block ciphers are one mechanism to offer such protection but unfortunately involve intensive computations that can be performance bottlenecks to the servers, especially when the data center needs to handle thousands of concurrent transactions. In this paper, we investigate the feasibility of the GPU as an accelerator to perform high‐speed encryption in server environments. We present optimized implementations of a conventional block cipher (AES) and new lightweight block ciphers (LEA, Chaskey, SIMON, SPECK, and SIMECK) across three new GPU architectures (Kepler, Maxwell, and Pascal). For AES, we improve the fine‐grain implementation by utilizing the warp shuffle instruction available in these three new GPU architectures, which yield a 6%‐16% improvement over the previous implementations. For LEA, Chaskey, SIMON, SPECK, and SIMECK, we first analyze why they cannot have efficient fine‐grain implementations in the GPU and then present our optimization techniques, which are able to achieve impressive encryption speeds of 1.912, 637, 1.485, 2.291, and 1.478 Tb/s, respectively, in GTX1080.

show abstract

Section: Resultsmentioning

confidence: 62%

Section: Resultsmentioning

confidence: 99%