FINNAS is presented, a FINN-guided hardware-aware evolutionary neural architecture search framework that jointly searches quantised MLP depth, width, and global precision settings, and ranks candidates using proxy validation accuracy together with FINN-estimated LUT usage and latency under a fully parallel mapping.
Abstract
FPGAs are well suited to deploying quantised neural networks (QNNs) under strict accuracy, latency, and resource constraints; however, identifying efficient model-accelerator combinations commonly requires extensive manual design-space exploration and repeated hardware synthesis. This paper presents FINNAS, a FINN-guided hardware-aware evolutionary neural architecture search framework. FINNAS jointly searches quantised MLP depth, width, and global precision settings, and ranks candidates using proxy validation accuracy together with FINN-estimated LUT usage and latency under a fully parallel mapping. Selected finalists are fully retrained, subjected to post-search unstructured pruning, and validated using RTL simulation and Vivado out-of-context synthesis. On the CERNBox jet substructure classification task, the searched implementations expose competitive accuracy-resource trade-offs. Compared with a manually optimised dense FINN accelerator, a compact FINNAS design improves accuracy from 73.78\% to 74.36\%, while reducing LUT usage by \(8.5\times\) and RTL-simulation latency by \(1.77\times\). Unstructured pruning further provides consistent LUT and FF reductions across the fully parallel finalists.
This work proposes an LLM-guided DSE framework that integrates domain knowledge into the exploration through structured prompts, and progressively refines parameter ranges, steering a downstream optimization engine toward resource-feasible, high-performance subspaces.
Edoardo Trombotto, Valentino Peluso, A. Calimera et al.· Forum on Specification and D...· 0 citations
The growing adoption of dataflow accelerators for neural network inference introduces new attack surfaces that existing verification methodologies fail to address. Inference ac- celeration frameworks such as FINN, which transform quantized neural networks into FPGA-deployable dataflow architectures, implicitly assume s...
With the rapid growth of deep learning models, compiler optimization for heterogeneous accelerators has become critical to improving execution efficiency. Compared with GPUs, Neural Processing Units (NPUs) offer stronger domain-specific computing capability but impose more complex on-chip resource constraints. Existing...
Jia-Nan Li, Lin Han, Xiao-Nan Chai et al.· IEEE Access· 0 citations
Energy efficiency is a critical design constraint in FPGA-based embedded systems that deploy convolutional neural networks (CNNs). Rapid and accurate exploration methods facilitate optimized implementations. This paper proposes a frequency-scalable power modeling framework for CNN intel-lectual property (IP) libraries...
Philippe Magalhães, Virginie Fresse, Olivier Alata et al.· Symposium on Integrated Circ...· 0 citations
The platform exploits the reconfigurable logic of Field-Programmable Gate Arrays to implement approximate multipliers directly in hardware, eliminating the need for LUT-based emulation on CPU/GPU platforms and thereby enabling efficient DNN inference while significantly reducing evaluation time on large datasets.
Rappy Saha, Nima Amirafshar, Jude Haris et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.