zkPHIRE: A Programmable Accelerator for ZKPs over HIgh-degRee, Expressive Gates

2025-08-22

AI Summary

Zero-knowledge proof (ZKP) generation incurs prohibitive computational overhead, particularly when supporting high-degree and complex gate operations; the SumCheck protocol thus becomes a critical performance bottleneck. This work introduces the first programmable hardware accelerator architecture for ZKPs, specifically designed to accelerate customizable gate evaluations within SumCheck—supporting constraint systems of up to 2³⁰ size while preserving compact proof sizes and expressive high-degree arithmetic. Our design features a customized pipeline, dedicated polynomial evaluation units, and end-to-end system integration. Experimental evaluation demonstrates that, across diverse gate types, SumCheck computation achieves over 1000× average speedup versus CPU execution; the full-system geometric mean speedup reaches 1486×, and area-normalized performance improves by 11.87× over state-of-the-art solutions.

Technology Category

• Machine Learning: Hardware-aware ML
• Constraint Satisfaction and Optimization: Satisfiability
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

Zero-Knowledge Proofs (ZKPs) have emerged as powerful tools for secure and privacy-preserving computation. ZKPs enable one party to convince another of a statement's validity without revealing anything else. This capability has profound implications in many domains, including: machine learning, blockchain, image authentication, and electronic voting. Despite their potential, ZKPs have seen limited deployment because of their exceptionally high computational overhead, which manifests primarily during proof generation. To mitigate these overheads, a (growing) body of researchers has proposed hardware accelerators and GPU implementations for kernels and complete protocols. Prior art spans a wide variety of ZKP schemes that vary significantly in computational overhead, proof size, verifier cost, protocol setup, and trust. The latest, and widely used ZKP protocols are intentionally designed to balance these trade-offs. A particular challenge in modern ZKP systems is supporting complex, high-degree gates using the SumCheck protocol. We address this challenge with a novel programmable accelerator that efficiently handles arbitrary custom gates via SumCheck. Our accelerator achieves upwards of $1000 imes$ geomean speedup over CPU-based SumChecks across a range of gate types. We integrate this unit into a full-system accelerator, zkPHIRE, which achieves $1486 imes$ geomean speedup over CPU and $11.87 imes$ speedup over the state-of-the-art at iso-area. zkPHIRE is the first accelerator to scale to problem sizes of $2^{30}$ nominal constraints while maintaining small proof sizes and programmability.

Problem

• Accelerating SumCheck protocol for high-degree custom gates
• Reducing computational overhead in Zero-Knowledge Proof generation
• Enabling programmable hardware acceleration for complex ZKP circuits

Innovation

• Programmable accelerator for high-degree custom gates
• Uses SumCheck protocol for efficient proof generation
• Achieves over 1000x speedup over CPU implementations