Nicolò Ghielmetti

Nicolò Ghielmetti

Auto-generated profile, based on publicly available information

Nicolò Ghielmetti

European Organization for Nuclear Research (CERN), Geneva, Switzerland

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 November 2022 in Machine Learning: Science and Technology
Verified
Journal Article
Open access
NGNicolò Ghielmetti
Nicolò Ghielmetti
VLVladimir Loncar
Vladimir Loncar
MPMaurizio Pierini
Maurizio Pierini
MRMarcel Roed
Marcel Roed
SSSioni Summers
Sioni Summers
PHPhilip Harris
Philip Harris
In this paper, we investigate how field programmable gate arrays can serve as hardware accelerators for real-time semantic segmentation tasks relevant for autonomous driving. Considering compressed versions of the ENet convolutional neural network architecture, we demonstrate a fully-on-chip deployment with a latency of 4.9 ms per image, using less than 30% of the available resources on a Xilinx ZCU102 evaluation board. The latency is reduced to 3 ms per image when increasing the batch size to ten, corresponding to the use case where the autonomous vehicle receives inputs from multiple cameras simultaneously. We show, through aggressive filter reduction and heterogeneous quantization-aware training, and an optimized implementation of convolutional layers, that the power consumption and resource utilization can be significantly reduced while maintaining accuracy on the Cityscapes dataset.

27 May 2026 in ACM Transactions on Reconfigurable Technology and Systems
Verified
Journal Article
Open access
JSJan-Frederik Schulte
Jan-Frederik Schulte
BRBenjamin Ramhorst
Benjamin Ramhorst
CSChang Sun
Chang Sun
JMJovan Mitrevski
Jovan Mitrevski
NGNicolò Ghielmetti
Nicolò Ghielmetti
SHScott Hauck
Scott Hauck
We present hls4ml , a free and open source platform that translates machine learning (ML) models from modern deep learning frameworks into high-level synthesis (HLS) code that can be integrated into full designs for field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs). With its flexible and modular design, hls4ml supports a large number of deep learning frameworks and can target HLS compilers from several vendors, including Vitis HLS, Intel oneAPI and Catapult HLS. Together with a wider eco-system for software-hardware co-design, hls4ml has enabled the acceleration of ML inference in a wide range of commercial and scientific applications where low latency, resource usage, and power consumption are critical. In this article, we describe the structure and functionality of the hls4ml platform. The overarching design considerations for the generated HLS code are discussed, together with selected performance results.