Surrogate Neural Architecture Codesign Package (SNAC-Pack)

TL;DR

SNAC-Pack is an integrated framework for neural architecture search that optimizes FPGA deployment by accurately predicting hardware performance, enabling efficient design of resource-aware neural networks without extensive synthesis.

Contribution

It introduces SNAC-Pack, a novel framework combining multi-stage search with resource and latency estimation for hardware-aware neural architecture optimization.

Findings

Achieves high accuracy with resource-efficient FPGA models.

Matches baseline accuracy on a high energy physics task.

Reduces need for time-consuming FPGA synthesis during search.

Abstract

Neural Architecture Search is a powerful approach for automating model design, but existing methods struggle to accurately optimize for real hardware performance, often relying on proxy metrics such as bit operations. We present Surrogate Neural Architecture Codesign Package (SNAC-Pack), an integrated framework that automates the discovery and optimization of neural networks focusing on FPGA deployment. SNAC-Pack combines Neural Architecture Codesign's multi-stage search capabilities with the Resource Utilization and Latency Estimator, enabling multi-objective optimization across accuracy, FPGA resource utilization, and latency without requiring time-intensive synthesis for each candidate model. We demonstrate SNAC-Pack on a high energy physics jet classification task, achieving 63.84% accuracy with resource estimation. When synthesized on a Xilinx Virtex UltraScale+ VU13P FPGA, the SNAC-Pack model matches baseline accuracy while maintaining comparable resource utilization to models optimized using traditional BOPs metrics. This work demonstrates the potential of hardware-aware neural architecture search for resource-constrained deployments and provides an open-source framework for automating the design of efficient FPGA-accelerated models.