Exploration of Convolutional Neural Network models for source code classification
| Autor: | Gianvito Urgese, Elisa Ficarra, Andrea Acquaviva, Emanuele Parisi, Francesco Barchi |
|---|---|
| Přispěvatelé: | Barchi F., Parisi E., Urgese G., Ficarra E., Acquaviva A. |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
0209 industrial biotechnology
Source code Computer science Heterogeneous platform media_common.quotation_subject 02 engineering and technology computer.software_genre Execution time Convolutional neural network 020901 industrial engineering & automation Artificial Intelligence Robustness (computer science) 0202 electrical engineering electronic engineering information engineering Electrical and Electronic Engineering Edge computing media_common business.industry Deep learning LLVM-IR Heterogeneous platforms Code mapping Computer engineering Control and Systems Engineering 020201 artificial intelligence & image processing Compiler Artificial intelligence business computer |
| Popis: | The application of Artificial Intelligence is becoming common in many engineering fields. Among them, one of the newest and rapidly evolving is software generation, where AI can be used to automatically optimise the implementation of an algorithm for a given computing platform. In particular, Deep Learning technologies can be used to the decide how to allocate pieces of code to hardware platforms with multiple cores and accelerators, that are common in high performance and edge computing applications. In this work, we explore the use of Convolutional Neural Networks (CNN)s to analyse the application source code and decide the best compute unit to minimise the execution time. We demonstrate that CNN models can be successfully applied to source code classification, providing higher accuracy with consistently reduced learning time with respect to state-of-the-art methods. Moreover, we show the robustness of the method with respect to source code pre-processing, compiler options and hyper-parameters selection. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|