TY - GEN
T1 - A GPU-Accelerated High-Performance Design for CRYSTALS-Dilithium Digital Signature
AU - Nguyen, Hien
AU - Cambou, Bertrand
AU - Nguyen, Tan Tuy
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - Our approach leverages the massive parallelism and computational power of a modern Graphics Processing Unit (GPU) to accelerate CRYSTALS-Dilithium's key operations. While post-quantum cryptographic algorithms like Dilithium offer robust security, they face computational challenges in high-throughput scenarios. Dilithium's performance bottlenecks, particularly in polynomial arithmetic and random sampling, have limited its practical deployment. To address these challenges, we leverage GPU acceleration as a promising solution to enhance efficiency. Our approach develops novel GPU-centric algorithms and data structures tailored to Dilithium's requirements. We focus on optimizing Number Theoretic Transforms (NTT), polynomial arithmetic, and random sampling, with an emphasis on batch processing and efficient memory management to maximize throughput. Experimental results demonstrate significant performance improvements over existing implementations. Our GPU-accelerated version consistently outperforms reference implementations, achieving speed-ups ranging from 53.7% to 59.9% for signature generation and 20.0% to 63.8% for verification across various security levels. These results highlight the potential of our approach in enabling efficient post-quantum cryptography for high-performance applications.
AB - Our approach leverages the massive parallelism and computational power of a modern Graphics Processing Unit (GPU) to accelerate CRYSTALS-Dilithium's key operations. While post-quantum cryptographic algorithms like Dilithium offer robust security, they face computational challenges in high-throughput scenarios. Dilithium's performance bottlenecks, particularly in polynomial arithmetic and random sampling, have limited its practical deployment. To address these challenges, we leverage GPU acceleration as a promising solution to enhance efficiency. Our approach develops novel GPU-centric algorithms and data structures tailored to Dilithium's requirements. We focus on optimizing Number Theoretic Transforms (NTT), polynomial arithmetic, and random sampling, with an emphasis on batch processing and efficient memory management to maximize throughput. Experimental results demonstrate significant performance improvements over existing implementations. Our GPU-accelerated version consistently outperforms reference implementations, achieving speed-ups ranging from 53.7% to 59.9% for signature generation and 20.0% to 63.8% for verification across various security levels. These results highlight the potential of our approach in enabling efficient post-quantum cryptography for high-performance applications.
KW - CRYSTALS-Dilithium
KW - digital signatures
KW - GPU
KW - NTT
KW - parallel processing
KW - post-quantum cryptography
UR - http://www.scopus.com/inward/record.url?scp=105006597479&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=105006597479&partnerID=8YFLogxK
U2 - 10.1109/ICCE63647.2025.10929968
DO - 10.1109/ICCE63647.2025.10929968
M3 - Conference contribution
AN - SCOPUS:105006597479
T3 - Digest of Technical Papers - IEEE International Conference on Consumer Electronics
BT - 2025 IEEE International Conference on Consumer Electronics, ICCE 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2025 IEEE International Conference on Consumer Electronics, ICCE 2025
Y2 - 11 January 2025 through 14 January 2025
ER -