Paper 2022/1243
Hybrid scalar/vector implementations of Keccak and SPHINCS+ on AArch64
Abstract
This paper presents two new techniques for the fast implementation of the Keccak permutation on the A-profile of the Arm architecture: First, the elimination of explicit rotations in the Keccak permutation through Barrel shifting, applicable to scalar AArch64 implementations of Keccak-f1600. Second, the construction of hybrid implementations concurrently leveraging both the scalar and the Neon instruction sets of AArch64. The resulting performance improvements are demonstrated in the example of the hash-based signature scheme SPHINCS+, one of the recently announced winners of the NIST post-quantum cryptography project: We achieve up to 1.89× performance improvements compared to the state of the art. Our implementations target the Arm Cortex-{A55,A510,A78,A710,X1,X2} processors common in client devices such as mobile phones.
Metadata
- Available format(s)
-
PDF
- Category
- Implementation
- Publication info
- Published elsewhere. Indocrypt 2022
- Keywords
- Arm AArch64 Armv8-A Keccak SIMD Neon Post-Quantum Cryptography SPHINCS+
- Contact author(s)
-
hanno becker @ arm com
matthias @ kannwischer eu - History
- 2022-10-27: revised
- 2022-09-19: received
- See all versions
- Short URL
- https://ia.cr/2022/1243
- License
-
CC BY
BibTeX
@misc{cryptoeprint:2022/1243,
author = {Hanno Becker and Matthias J. Kannwischer},
title = {Hybrid scalar/vector implementations of Keccak and {SPHINCS}+ on {AArch64}},
howpublished = {Cryptology {ePrint} Archive, Paper 2022/1243},
year = {2022},
url = {https://eprint.iacr.org/2022/1243}
}
