Implementation of High Speed Hash Function Keccak Using CUDA on GTX 1080

Dat, Thuong Nguyen; Iwai, Keisuke; Kurokawa, Takakazu

doi:10.1109/candar.2017.47

Cited by 2 publications

(8 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dat et al proposed an optimization method for storing a constant values used in SHA-3 internal functions [22]. SHA-3 uses constant value table in internal function (θ process, ι process and π process).…”

Section: Existing Results Of Sha-3 Implementationmentioning

confidence: 99%

“…In this paper, we proposed an effective parallel message copy of input data and kernel execution methods by applying CUDA stream and we provided the result of SHA-3 implementation using CUDA stream. Also, in SHA-3 implementation, performance using CUDA stream, we present the result of comparing Dat et al's proposal and our implementation [22], [24]. Our optimized implementation of SHA-3 using 3 CUDA streams provides the maximum throughput of 95.67Gb/s in a GTX 1070 environment.…”

Section: Sha-3 Internal Statementioning

confidence: 94%

“…Kim et al proposed optimization method that minimized memory access by changing the order of SHA-3 internal process. In other related work, Dat et al proposed an optimization method for constant values used in the SHA-3 internal algorithm [22]. In GPU environment, there are global memory, constant memory, and shared memory, each memory access latency is different.…”

Section: Optimization Of Sha-3 Internal Processmentioning

confidence: 99%

“…Dat We proposed a method to customize the optimization technique proposed by Kim et al to the GPU environment. We focused on SHA-3 internal process optimization method proposed by Kim et al and we proposed a more efficient technique than storing the SHA-3 internal function constant value memory as proposed by Dat et al [22], [25]. In addition, we proposed the PTX Inline assembly implementation provided by CUDA C. Kim et al's first optimization method uses the fact that lanes belonging to the same sheet use the same value in the θ process [25].…”

Section: Optimization Of Sha-3 Internal Processmentioning

confidence: 99%

“…We ported the optimization method proposed by Kim et al to GPU environment. Dat et al proposed a SHA-3 optimization technique in GPU environment [22]. They proposed an optimization method mainly related to memory access.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Fast Implementation of SHA-3 in GPU Environment

Choi

Seo²

2021

IEEE Access

View full text Add to dashboard Cite

Recently, Graphic Processing Units (GPUs) have been widely used for general purpose applications such as machine learning applications, acceleration of cryptographic applications (especially, blockchains), etc. The development of CUDA makes this General-Purpose computing on GPU possible. In particular, currently GPU technology has been widely used for server-side applications so as to provide fast and efficient service to a number of clients. In other words, servers need to process a large amount of user data and execute authentication process. Verifying the integrity of transmitted data is essential for ensuring that the data is not modified during transmission. Hash functions are the cryptographic algorithm which can verify the integrity of data and there are SHA-1, SHA-2, and SHA-3 standard hash functions. In 2015, Keccak algorithm was selected for SHA-3 competition by NIST. However, until now, software implementations of SHA-3 have not provided enough performance for various applications. In addition, SHA-3 and SHAKE using SHA-3 are being used in many Post-Quantum Cryptosystems (PQC) submitted to NIST PQC competition. Therefore, SHA-3 optimization research is required in the software environment. We propose an optimized SHA-3 software implementation on GPU environment. For performance efficiency, we propose several techniques including optimization of SHA-3 internal process, inline PTX optimization, optimized memory usage, and the application of asynchronous CUDA stream. As a result of applying the proposed optimization method, our SHA-3(512) (resp. SHA-3(256)) implementation without CUDA stream provides a maximum throughput of 88.51 Gb/s (resp. 171.62 Gb/s) on RTX2080Ti GPU. Furthermore, without the application of CUDA stream, our SHA-3(512) software on GTX1070 provides about 49.73% improved throughput compared with the previous best work on GTX1080, which shows the superiority of our proposed optimization methods. Our optimized SHA-3 software on GPU can be efficiently used for block-chain applications and several PQCs (especially, key generation process in Lattice-based cryptosystems).

show abstract

Section: Existing Results Of Sha-3 Implementationmentioning

confidence: 99%

Section: Sha-3 Internal Statementioning

confidence: 94%

Section: Optimization Of Sha-3 Internal Processmentioning

confidence: 99%