swMATH ID: 40751
Software Authors: Ulu, Metin Evrim; Cenk, Murat
Description: A parallel GPU implementation of SWIFFTX. The SWIFFTX algorithm is one of the candidates of SHA-3 Hash Competition that uses the number theoretic transform (NTT). It has 256-byte input blocks and 65-byte output blocks. In this paper, a parallel implementation of the algorithm and particular techniques to make it faster on GPU are proposed. We target version 6.1 of NVIDIA extsuperscript{circledR}CUDA exttrademark compute architecture that employs an ISA (Instruction Set Architecture) called Parallel Thread Execution (PTX) which possesses special instrinsics, hence we modify the reference implementation for better results. Experimental results indicate almost 10x improvement in speed and 5 W decrease in power consumption per (2^{16}) hashes.
Homepage: https://link.springer.com/chapter/10.1007%2F978-3-030-43120-4_16
Keywords: hash function; SWIFFTX; SHA-3; NTT; GPU; CUDA
Related Software: SWIFFT; LibSWIFFT; CryptoStreams; EACirc; CUDA; SNARKs for C; MiMC; GitHub; SPECK; Geppetto; SIMON; SIMECK; Pinocchio; NOEKEON; Trivium; NTL; Whirlpool
Cited in: 4 Documents

Standard Articles

1 Publication describing the Software, including 1 Publication in zbMATH Year
A parallel GPU implementation of SWIFFTX. Zbl 07441070
Ulu, Metin Evrim; Cenk, Murat

Cited in 1 Serial

1 Journal of Cryptology

Citations by Year