aiqbench analysis
SNAC-Pack addresses a critical bottleneck in deploying neural networks to FPGAs by automating the codesign of architectures that balance accuracy with specific hardware resource constraints like DSPs and BRAM. By utilizing surrogate models for rapid cost estimation, this framework significantly accelerates design space exploration compared to traditional manual tuning or synthesis-heavy loops. The tool demonstrates practical utility in high-stakes domains such as particle physics experiments and quantum computing readout systems where FPGA efficiency is paramount.
SNAC-Pack 2.0: Scaled-Out Surrogate Neural Architecture Codesign
arXiv:2605.16138v3 Announce Type: replace Abstract: Neural architecture search (NAS) is a powerful approach for automating model design, but existing methods often optimize for accuracy alone or rely on proxy metrics such as bit operations (BOPs) that correlate poorly with hardware cost. This gap is particularly large for FPGA deployment, where cost is dominated by a multi-dimensional budget of lookup tables, DSPs, flip-flops, BRAM, and latency. We present the Surrogate Neural Architecture Codesign Package (SNAC-Pack), an open-source AutoML framework for hardware-aware neural architecture codesign and end-to-end FPGA deployment. SNAC-Pack runs a multi-objective global search with Optuna and NSGA-II, loading trials to a shared SQLite store that enables parallel workers across compute nodes. A hardware surrogate model outputs per-trial resource and latency estimates, avoiding the synthesis cost that would otherwise dominate the search loop. A local search stage then applies quantization-aware training (QAT) together with iterative magnitude pruning in a combined compression loop, after which the final model is synthesized to FPGA firmware via the hls4ml Python library. A YAML configuration and an optional agentic frontend let users run the pipeline on new datasets without modifying the framework. We demonstrate SNAC-Pack on jet classification at the Large Hadron Collider and superconducting qubit readout, discovering compact Pareto-optimal architectures that either match baseline task performance while reducing FPGA resource utilization or substantially reduce hardware utilization with only modest decreases in task performance. In the qubit readout case, SNAC-Pack also reduces the design space exploration process from months of manual fine-tuning to hours of automated search.
Abstract:Neural architecture search (NAS) is a powerful approach for automating model design, but existing methods often optimize for accuracy alone or rely on proxy metrics such as bit operations (BOPs) that correlate poorly with hardware cost. This gap is particularly large for FPGA deployment, where cost is dominated by a multi-dimensional budget of lookup tables, DSPs, flip-flops, BRAM, and latency. We present the Surrogate Neural Architecture Codesign Package (SNAC-Pack), an open-source AutoML framework for hardware-aware neural architecture codesign and end-to-end FPGA deployment. SNAC-Pack runs a multi-objective global search with Optuna and NSGA-II, loading trials to a shared SQLite store that enables parallel workers across compute nodes. A hardware surrogate model outputs per-trial resource and latency estimates, avoiding the synthesis cost that would otherwise dominate the search loop. A local search stage then applies quantization-aware training (QAT) together with iterative magnitude pruning in a combined compression loop, after which the final model is synthesized to FPGA firmware via the hls4ml Python library. A YAML configuration and an optional agentic frontend let users run the pipeline on new datasets without modifying the framework. We demonstrate SNAC-Pack on jet classification at the Large Hadron Collider and superconducting qubit readout, discovering compact Pareto-optimal architectures that either match baseline task performance while reducing FPGA resource utilization or substantially reduce hardware utilization with only modest decreases in task performance. In the qubit readout case, SNAC-Pack also reduces the design space exploration process from months of manual fine-tuning to hours of automated search.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); High Energy Physics - Experiment (hep-ex)
arXiv:2605.16138 [cs.LG]
(or arXiv:2605.16138v3 [cs.LG] for this version)
Full text under the publisher's open licence · 266 words
Related coverage
Surrogate Neural Architecture Codesign Package (SNAC-Pack)
arXiv · Jun 6, 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · May 21, 2026
[AINews] not much happened today
Latent Space · Sep 10, 2026
Efficient Neural Surrogates for Linear Radiation Transport on the Lattice and Hohlraum benchmarks
arXiv · Oct 7, 2026