Hardware design and performance analysis for cryptographic sponge BlaMka.

• Ano de defesa: 2017
• Autor(a) principal: Rossetti, Jônatas Faria
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: eng
• Instituição de defesa: Biblioteca Digitais de Teses e Dissertações da USP
• Palavras-chave em Português: Análise de desempenho; Criptologia; Cryptography; Hardware; Performance analysis
• Link de acesso: http://www.teses.usp.br/teses/disponiveis/3/3141/tde-10082017-134824/

To evaluate the performance of a hardware design, it is necessary to select the met- rics of interest. Several metrics can be chosen, but in general three of them are considered basic: area, latency, and power. From these, other metrics of practical interest such as throughput and energy consumption can be obtained. These metrics relate to one another by creating trade-offs that designers need to know to execute the best design decisions. Some works address optimized hardware design for improving one of these metrics. In other works, optimizations are made for two of them. Others analyze the trade-off between two of these metrics. However, the literature lacks of works that analyze the behavior of three metrics together. In this work, we intend to contribute to bridge this gap, proposing a method that allow analyzing trade-offs among area, power, and throughput. To verify the proposed method, the permutation function of crypto- graphic sponge BlaMka was chosen as a case study. No hardware implementation has been found for this algorithm yet. Therefore, an additional contribution is to provide its first hardware design. Combinational and sequential circuits were designed and synthesized for ASIC and FPGA. With the synthesis results, a detailed performance analysis was performed for each platform, starting from a one-dimensional analysis, going through a two-dimensional analysis, and culminating in a three-dimensional analysis. Two techniques were presented for such analysis, namely projections approach and planes approach. Although there is room for improvement, the proposed method is a initial step showing that, in fact, a trade-off between three metrics can be analyzed, and that it is also possible to find balanced performance points. From the two approaches presented, it was possible to derive a criterion to select optimizations when we have restrictions, such as a desired throughput range or a maximum physical size, and when we do not have restrictions, in which case we can choose the optimization with the most balanced performance.