MeNTT: A Compact and Efficient Processing-in-Memory Number Theoretic Transform (NTT) Accelerator

TL;DR

MeNTT is a compact, energy-efficient in-memory NTT accelerator optimized for lattice-based cryptography, reducing latency and energy consumption through novel data mapping and specialized peripherals.

Contribution

It introduces a novel in-memory NTT architecture with optimized computation, data mapping, and peripherals, significantly improving latency and energy efficiency over previous designs.

Findings

Significant latency reduction compared to prior arts

Lower energy consumption in NTT processing

Simplified routing reduces area overheads

Abstract

Lattice-based cryptography (LBC) exploiting Learning with Errors (LWE) problems is a promising candidate for post-quantum cryptography. Number theoretic transform (NTT) is the latency- and energy- dominant process in the computation of LWE problems. This paper presents a compact and efficient in-MEmory NTT accelerator, named MeNTT, which explores optimized computation in and near a 6T SRAM array. Specifically-designed peripherals enable fast and efficient modular operations. Moreover, a novel mapping strategy reduces the data flow between NTT stages into a unique pattern, which greatly simplifies the routing among processing units (i.e., SRAM column in this work), reducing energy and area overheads. The accelerator achieves significant latency and energy reductions over prior arts.