This is the authors' abstract. We don't add key points for this paper.
A vector-processor architecture based on the RISC-V extended instruction set is proposed and evaluated for the acceleration of post-quantum cryptographic(PQC) algorithms. The core employs an in-order, partially four-way multi-issue pipeline and delivers a significant speed-up over pure-software RISC-V implementations. Unlike previous hardware–software co-designs that target specific PQC schemes, the instruction-set extensions are derived from fine-grained, fixed-point arithmetic primitives; consequently, the same core can speed up current NIST candidates and tolerate future algorithm updates while remaining useful for other cryptographic workloads. The processor was implemented in 28nm SMIC HKE+ process, and post-layout simulations were conducted. Results showed that under primary PQC standards, compared with the state-of-the-art counterparts, it can achieve a reduction in total cycles by 9.1%-12.7%. In terms of stream cipher, block cipher, and hash cipher algorithms, it can achieve 12×-24× performance improvement, which enables it to have higher flexibility in practical application scenarios.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: