Author name cluster

Andrea Bartolini

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

EAAI Journal 2026 Journal Article

A transformer-based approach for source code classification for heterogeneous device mapping

Marco Siino
Emanuele Parisi
Francesco Barchi
Andrea Acquaviva
Andrea Bartolini

The optimization of code allocation for heterogeneous architectures, such as Central Processing Units (CPUs) and Graphics Processing Units (GPUs), remains challenging due to the limitations of traditional compiler heuristics and existing machine learning approaches. This paper presents a systematic evaluation of Large Language Models (LLMs) for classifying source code execution targets in heterogeneous device mapping. We fine-tune and compare six models: Distilled Bidirectional Encoder Representations from Transformers (DistilBERT), Code Bidirectional Encoder Representations from Transformers (CodeBERT), Code Bidirectional Encoder Representations from Transformers with RoBERTa (Robustly Optimized BERT Pretraining Approach) architecture (CodeBERTa), CodeT5, jTrans, and Deep Learning Low Level Virtual Machine (DeepLLVM), trained on Open Computing Language (OpenCL) kernels. Results show that general-purpose LLMs achieve up to 92. 8% accuracy, matching or surpassing code-specific models, and outperform the previous state of the art (DeepLLVM) by up to 5%. Our findings indicate that LLMs pre-trained on general text are not necessarily inferior to code-specialized models, with tokenizer design and pre-training objectives impacting performance more than domain specialization. These results demonstrate the effectiveness of Transformer-based LLMs as a state-of-the-art approach for source code classification in heterogeneous computing contexts.

Details DOI

AAAI Conference 2026 Short Paper

Context-Aware Diffusion for Telemetry Time Series with Permutation-Stable Feature Modeling (Student Abstract)

Giovanni B. Esposito
Daniele Cesarini
Andrea Bartolini

We present a context-aware diffusion model for multivariate time series generation in dynamic and partially observed environments, with applications to data-center computing node's telemetry and beyond. The model integrates pretrained textual embeddings to represent feature semantics, enabling flexible, context-guided generation and improved adaptability to unseen or re-ordered input features. Built on a transformer architecture, it employs both time-wise and feature-wise masking to support missing data during training and inference. We show that the model is robust to permutations with respect to the feature dimension, mantaining stable performance in settings where input configurations vary. Empirical evaluations on HPC sensor data illustrate the model’s versatility across generation and imputation tasks. This work introduces a modular and generalizable framework for time series modeling in complex, high-dimensional systems which can serve as a digital-twin for data-center's compute node telemetry.

PDF Details DOI

TAAS Journal 2026 Journal Article

Modeling and Controlling Many-Core HPC Processors: An Alternative to PID and Moving Average Algorithms

Giovanni Bambini
Alessandro Ottaviano
Christian Conficoni
Andrea Tilli
Luca Benini
Andrea Bartolini

The race toward performance increase and computing power has led to chips with heterogeneous and complex designs, integrating an ever-growing number of cores on the same monolithic chip or chiplet silicon die. Higher integration density, compounded with the slowdown of technology-driven power reduction, implies that power and thermal management become increasingly relevant. Unfortunately, existing research lacks a detailed analysis and modeling of thermal, power, and electrical coupling effects and how they have to be jointly considered to perform dynamic control of complex and heterogeneous Multi-Processor System on Chips (MPSoCs). To close the gap, in this work, we first provide a detailed thermal and power model targeting a modern High Performance Computing (HPC) MPSoC. We consider real-world coupling effects such as actuators’ non-idealities and the exponential relation between the dissipated power, the temperature state, and the voltage level in a single processing element. We analyze how these factors affect the control algorithm behavior and the type of challenges that they pose. Based on the analysis, we propose a thermal capping strategy inspired by Fuzzy control theory to replace the state-of-the-art PID controller, as well as a root-finding iterative method to optimally choose the shared voltage value among cores grouped in the same voltage domain. We evaluate the proposed controller with model-in-the-loop and hardware-in-the-loop co-simulations. We show an improvement over state-of-the-art methods of up to \(5\times\) the maximum exceeded temperature while providing an average of \(3.56\%\) faster application execution runtime across all the evaluation scenarios.

Details DOI

EAAI Journal 2019 Journal Article

A semisupervised autoencoder-based approach for anomaly detection in high performance computing systems

Andrea Borghesi
Andrea Bartolini
Michele Lombardi
Michela Milano
Luca Benini

High Performance Computing (HPC) systems are complex machines with heterogeneous components that can break or malfunction. Automated anomaly detection in these systems is a challenging and critical task, as HPC systems are expected to work 24/7. The majority of the current state-of-the-art methods dealing with this problem are Machine Learning techniques or statistical models that rely on a supervised approach, namely the detection mechanism is trained to recognize a fixed number of different states (i. e. normal and anomalous conditions). In this paper a novel semi-supervised approach for anomaly detection in supercomputers is proposed, based on a type of neural network called autoencoder. The approach learns the normal state of the supercomputer nodes and after the training phase can be used to discern anomalous conditions from normal behavior; in doing so it relies only on the availability of data characterizing only the normal state of the system. This is different from supervised methods that require data sets with many examples of anomalous states, which are in general very rare and/or hard to obtain. The approach was tested on a real-life High Performance Computing system equipped with a monitoring infrastructure capable to generate large amount of data describing the system state. The proposed approach definitely outperforms the best current techniques for semi-supervised anomaly detection, with an increase in accuracy detection of around 12%. Two different implementations are discussed: one where each supercomputer node has a specific model and one with a single, generalized model for all nodes, in order to explore the trade-off between accuracy and ease of deployment.

Details DOI

AIJ Journal 2017 Journal Article

Empirical decision model learning

Michele Lombardi
Michela Milano
Andrea Bartolini

One of the biggest challenges in the design of real-world decision support systems is coming up with a good combinatorial optimization model. Often enough, accurate predictive models (e. g. simulators) can be devised, but they are too complex or too slow to be employed in combinatorial optimization. In this paper, we propose a methodology called Empirical Model Learning (EML) that relies on Machine Learning for obtaining components of a prescriptive model, using data either extracted from a predictive model or harvested from a real system. In a way, EML can be considered as a technique to merge predictive and prescriptive analytics. All models introduce some form of approximation. Citing G. E. P. Box [1] “Essentially, all models are wrong, but some of them are useful”. In EML, models are useful if they provide adequate accuracy, and if they can be effectively exploited by solvers for finding high-quality solutions. We show how to ground EML on a case study of thermal-aware workload dispatching. We use two learning methods, namely Artificial Neural Networks and Decision Trees and we show how to encapsulate the learned model in a number of optimization techniques, namely Local Search, Constraint Programming, Mixed Integer Non-Linear Programming and SAT Modulo Theories. We demonstrate the effectiveness of the EML approach by comparing our results with those obtained using expert-designed models.

Details DOI

ECAI Conference 2016 Conference Paper

DARDIS: Distributed And Randomized DIspatching and Scheduling

Thomas Bridi
Michele Lombardi 0001
Andrea Bartolini
Luca Benini
Michela Milano

Scheduling and dispatching are critical enabling technologies in supercomputing and grid computing. In these contexts, scalability is an issue: we have to allocate and schedule up to tens of thousands of tasks on tens of thousands of resources. This problem scale is out of reach for complete and centralized scheduling approaches.

Details

AAAI Conference 2012 Conference Paper

Optimization and Controlled Systems: A Case Study on Thermal Aware Workload Dispatching

Andrea Bartolini
Michele Lombardi
Michela Milano
Luca Benini

Although successfully employed on many industrial problems, Combinatorial Optimization still has limited applicability on several real-world domains, often due to modeling difficulties. This is typically the case for systems under the control of an on-line policy: even when the policy itself is well known, capturing its effect on the system in a declarative model is often impossible by conventional means. Such a difficulty is at the root of the classical, sharp separation between off-line and on-line approaches. In this paper, we investigate a general method to model controlled systems, based on the integration of Machine Learning and Constraint Programming (CP). Specifically, we use an Artificial Neural Network (ANN) to learn the behavior of a controlled system (a multicore CPU with thermal controllers) and plug it into a CP model by means of Neuron Constraints. The method obtains significantly better results compared to an approach with no ANN guidance. Neuron Constraints were first introduced in (Bartolini et al. 2011b) as a mean to model complex systems: providing evidence of their applicability to controlled systems is a significant step forward, broadening the application field of combinatorial methods and disclosing opportunities for hybrid off-line/on-line optimization.

PDF Details