English

NX-CGRA: A Programmable Hardware Accelerator for Core Transformer Algorithms on Edge Devices

Hardware Architecture 2025-11-24 v1

Abstract

The increasing diversity and complexity of transformer workloads at the edge present significant challenges in balancing performance, energy efficiency, and architectural flexibility. This paper introduces NX-CGRA, a programmable hardware accelerator designed to support a range of transformer inference algorithms, including both linear and non-linear functions. Unlike fixed-function accelerators optimized for narrow use cases, NX-CGRA employs a coarse-grained reconfigurable array (CGRA) architecture with software-driven programmability, enabling efficient execution across varied kernel patterns. The architecture is evaluated using representative benchmarks derived from real-world transformer models, demonstrating high overall efficiency and favorable energy-area tradeoffs across different classes of operations. These results indicate the potential of NX-CGRA as a scalable and adaptable hardware solution for edge transformer deployment under constrained power and silicon budgets.

Keywords

Cite

@article{arxiv.2511.17235,
  title  = {NX-CGRA: A Programmable Hardware Accelerator for Core Transformer Algorithms on Edge Devices},
  author = {Rohit Prasad},
  journal= {arXiv preprint arXiv:2511.17235},
  year   = {2025}
}

Comments

This paper has been accepted for publication at the Design, Automation and Test in Europe (DATE) Conference 2026. 2026 IEEE. Personal use of this material is permitted

R2 v1 2026-07-01T07:48:46.749Z