计算机科学
加速
可扩展性
加速度
并行计算
中央处理器
操作系统
经典力学
物理
作者
Ying Huang,Xiaoying Zheng,Yongxin Zhu,Xiangcong Kong,Xinru Jing
标识
DOI:10.1109/ispa-bdcloud-socialcom-sustaincom52081.2021.00098
摘要
Zero-knowledge proofs help to protect the privacy and security of blockchains by keeping the transaction information private. Bulletproofs are the state-of-the-art zero-knowledge technologies that perform confidential transactions without a trusted setup. However, Bulletproofs are still computationally inefficient to be applied in blockchain applications, and it is of great significance to parallelize Bulletproofs on GPUs. In this paper, we present a CPU-GPU collaborative framework to accelerate the inner-product arguments of Bulletproofs. To our best knowledge, it is the first time that Bulletproofs are implemented in a CPU-GPU hybrid system. The experiments show that our implementation achieves an average speedup ratio of 3.7x. The results also demonstrate that the CPU-GPU collaborative acceleration of Bulletproofs has properties of small size, high efficiency, and high scalability.
科研通智能强力驱动
Strongly Powered by AbleSci AI