wa-hls4ml: Benchmark and Surrogate Models for hls4ml Resource Estimation
Benchmark and dataset of over 680,000 synthesized neural networks to evaluate GNN- and transformer-based surrogate models predicting FPGA resource usage and latency
Publications
You can also find my articles on my Google Scholar profile.
Journal Articles
Neural Architecture Codesign for Fast Physics Applications
This paper presents a new hardware-aware neural architecture search pipeline for low latency deployment
Conference Papers
Surrogate Neural Architecture Codesign Package (SNAC-Pack)
Integrated framework that automates the discovery and optimization of neural networks focusing on FPGA deployment without requiring time-intensive synthesis
Neural Architecture Codesign for Fast Bragg Peak Analysis
This paper presents a new hardware aware neural architecture search pipeline for Bragg Peak Spectroscopy experiments