Extending a predictable machine learning framework with efficient gemm-based convolution routines - Archive ouverte HAL
Article Dans Une Revue Real-Time Systems Année : 2023

Extending a predictable machine learning framework with efficient gemm-based convolution routines

Résumé

To implement machine learning applications in real-time safety-critical systems, we previously introduced a predictable framework named ACETONE. This framework compiles the detailed description of an off-line trained feed-forward deep neural network into an equivalent C code. In this paper, we improve the performance of the generated C code by including gemm-based convolutions in ACETONE. The code incorporating the gemm routines maintains the ACETONE properties of semantics preservation and timing predictability. We compare the proposed method with ACETONE ’s initial version, Keras2c and uTVM on a realistic set of machine learning benchmarks and show that the introduced convolution algorithms allow a trade-off between performance and memory footprint.
Fichier principal
Vignette du fichier
main.pdf (478.04 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04627347 , version 1 (27-06-2024)

Identifiants

Citer

Iryna De Albuquerque Silva, Thomas Carle, Adrien Gauffriau, Claire Pagetti. Extending a predictable machine learning framework with efficient gemm-based convolution routines. Real-Time Systems, 2023, 59 (3), pp.408-437. ⟨10.1007/s11241-023-09407-z⟩. ⟨hal-04627347⟩
38 Consultations
21 Téléchargements

Altmetric

Partager

More