HI-CKKS: Is High-Throughput Neglected? Reimagining CKKS Efficiency With Parallelism

The rapid advancement of the Industrial Internet of Things (IIoT) has positioned data privacy protection as a critical challenge in smart manufacturing. The Cheon–Kim–Kim–Song (CKKS) homomorphic encryption scheme, with its floating-point approximation and single instruction multiple data support capabilities, has emerged as a vital technology for IIoT privacy preservation. However, the high computational complexity of homomorphic multiplication significantly constrains its application performance in real-world industrial scenarios. While existing optimizations primarily focus on latency reduction, research on high-throughput parallel optimization remains notably insufficient. To address this, we propose HI-CKKS, a GPU-based high-throughput CKKS homomorphic multiplication optimization scheme for IIoT, achieving performance breakthroughs through multilevel technical innovations. By designing a batch-processing asynchronous execution architecture, we resolve host-server interaction delays in edge-cloud collaboration. A hierarchical hybrid optimization strategy combining instruction set acceleration, kernel fusion, and dynamic memory management significantly enhances (I)NTT operation efficiency. In addition, we construct a multidimensional parallel homomorphic multiplication model tailored for IIoT high-concurrency task characteristics. Experimental results show that HI-CKKS improves the throughput of NTT, INTT, and homomorphic multiplication by$175.08\times$,$191.27\times$, and$679.57\times$over CPU baselines. When compared to state-of-the-art GPU implementations on similar platforms, HI-CKKS attains$1.54\times$–$14.70\times$speedup for (I)NTT and$55.8\times$–$266.87\times$speedup for homomorphic multiplication. Our work provides an efficient solution for secure computation in IIoT and offers a new approach to performance optimization of homomorphic encryption in edge-cloud collaborative scenarios.