Power Efficiency Evaluation of Block Ciphers on GPU-Integrated Multicore Processor

Nishikawa, Naoki; Iwai, Keisuke; Kurokawa, Takakazu

doi:10.1007/978-3-642-33078-0_25

Cited by 4 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For implementation of block ciphers on a GPU, we take advantage of achievements of previous works [3], [16], [17]. First, round keys are generated in the host.…”

Section: Methodsmentioning

confidence: 99%

“…We previously evaluated the throughput and power efficiency of three 128-bit block ciphers (AES, Camellia, and SC2000) on AMD GPUs with VLIW architecture [3]. Results show that the power efficiency on Radeon HD 5450 with VLIW architecture and 80 cores is about nine times higher than that on AMD Phenom II X6 1100T CPU with 6 cores.…”

Section: Power Efficiency Of Block Ciphers On Gpusmentioning

confidence: 99%

“…6.2, we cite the power efficiency on AMD Phenom II X6 1100T from our previous work [3]. Implementation methodology and measurement environment are the same as the one described in Sect.…”

Section: Evaluation Of Power Efficiencymentioning

confidence: 99%

“…7. Moreover, as the reference of measurement result on a multicore CPU, we cite the encryption throughput on AMD Phenom II X6 1100T with six cores from our previous work [3], whose machine specification is the same as the one used in this paper. These programs are parallelized and implemented using OpenMP programming interface [18].…”

Section: Evaluation Of Throughputmentioning

confidence: 99%

“…However, the evaluation of power efficiency against encryption processing on a GPU is insufficient. For example, only our previous work [3] suggests that the power efficiency of encryption processing on a GPU is excellent compared to that on multicore CPUs. Recently, Nvidia Corp. and AMD Corp. have respectively released Kepler and Graphics Core Next (GCN) as recent GPU architectures.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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.

Self Cite

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

“…For implementation of block ciphers on a GPU, we take advantage of achievements of previous works [3], [16], [17]. First, round keys are generated in the host.…”

Section: Methodsmentioning

confidence: 99%

Section: Power Efficiency Of Block Ciphers On Gpusmentioning

confidence: 99%

“…6.2, we cite the power efficiency on AMD Phenom II X6 1100T from our previous work [3]. Implementation methodology and measurement environment are the same as the one described in Sect.…”

Section: Evaluation Of Power Efficiencymentioning

confidence: 99%

Section: Evaluation Of Throughputmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations