Loading [MathJax]/jax/output/HTML-CSS/config.js
ECO-BIKE: Bridging the Gap Between PQC BIKE and GPU Acceleration | IEEE Journals & Magazine | IEEE Xplore

ECO-BIKE: Bridging the Gap Between PQC BIKE and GPU Acceleration


Abstract:

Advancements in quantum computing pose a threat to public-key cryptosystems, leading to the development of post-quantum cryptography. NIST is standardizing candidate algo...Show More

Abstract:

Advancements in quantum computing pose a threat to public-key cryptosystems, leading to the development of post-quantum cryptography. NIST is standardizing candidate algorithms, with BIKE, a code-based key encapsulation mechanism, among those under consideration. Performance is crucial in NIST PQC standardization process, and researchers have introduced a range of optimization techniques for BIKE across various platforms. To the best of our knowledge, our Efficient CryptOgraphy BIKE (ECO-BIKE) represents the first attempt at optimizing the implementation of BIKE on GPU architecture. In this paper, we introduce a comprehensive construction of a 3-threading parallel architecture tailored for the BIKE cryptosystem. This architecture covers a range of computational tasks, addressing operations from low-level to high-level computations. These include a parallel dense polynomial multiplication scheme with a better memory access pattern and a better XOR calculation, which forms the basis for a comprehensive parallel execution framework for the entire BIKE algorithm. Targeted optimizations are implemented for specific modules (KEYGEN, ENCAPS, DECAPS), which collectively enhance the overall efficiency of the algorithm. Our ECO-BIKE exhibits exceptional throughput performance on the NVIDIA GeForce RTX 4090. In the 3-thread mode, the throughput of the KEYGEN, ENCAPS, and DECAPS modules reaches 24.033 kops/s, 277.789 kops/s, and 5.817 kops/s, respectively. Our proposed optimal parallel multiplication scheme achieves a significantly higher overall throughput of 481.302 kops/s. These results highlight the substantial computational advantages our approach provides for cryptographic workloads.
Page(s): 8952 - 8965
Date of Publication: 22 August 2024

ISSN Information:

Funding Agency:


References

References is not available for this document.