Due to the continuous technology scaling and the ever-increasing complexity and size of the hardware designs, manufacturing defects have become a key obstacle in meeting end-user demand. Despite decades of research, traditional test-generation techniques often struggle to scale to massive and complex designs. Such scalability issues stem from the numerous backtracking the traditional test generation techniques perform before converging to a test pattern. In this work, we present DETECTive that leverages deep learning on graphs to learn fault characteristics and predict test pattern(s) to expose faults without requiring backtracking. DETECTive is trained on small circuits, and its learned knowledge is transferable to predict test patterns for circuits that contain up to 29x more gates than the training circuits. Since DETECTive avoids backtracking completely, it can predict test patterns up to 15x faster than academic tools and up to 2x faster than commercial tools. DETECTive achieves up to 100% pattern accuracy on synthetic designs and up to 95% test pattern accuracy on realistic designs. To our knowledge, DETECTive is the first to leverage deep learning to predict test patterns for digital hardware designs that can complement the traditional test generation techniques for faster design closure.
DETECTive: Machine Learning-driven Automatic Test Pattern Prediction for Faults in Digital Circuits / Petrolo, Vincenzo; Medya, Sourav; Graziano, Mariagrazia; Pal, Debjit. - ELETTRONICO. - (2024), pp. 32-37. (Intervento presentato al convegno Proceedings of the Great Lakes Symposium on VLSI 2024 tenutosi a Clearwater (USA) nel June 12-14, 2024) [10.1145/3649476.3658696].
DETECTive: Machine Learning-driven Automatic Test Pattern Prediction for Faults in Digital Circuits
Petrolo, Vincenzo;Graziano, Mariagrazia;
2024
Abstract
Due to the continuous technology scaling and the ever-increasing complexity and size of the hardware designs, manufacturing defects have become a key obstacle in meeting end-user demand. Despite decades of research, traditional test-generation techniques often struggle to scale to massive and complex designs. Such scalability issues stem from the numerous backtracking the traditional test generation techniques perform before converging to a test pattern. In this work, we present DETECTive that leverages deep learning on graphs to learn fault characteristics and predict test pattern(s) to expose faults without requiring backtracking. DETECTive is trained on small circuits, and its learned knowledge is transferable to predict test patterns for circuits that contain up to 29x more gates than the training circuits. Since DETECTive avoids backtracking completely, it can predict test patterns up to 15x faster than academic tools and up to 2x faster than commercial tools. DETECTive achieves up to 100% pattern accuracy on synthetic designs and up to 95% test pattern accuracy on realistic designs. To our knowledge, DETECTive is the first to leverage deep learning to predict test patterns for digital hardware designs that can complement the traditional test generation techniques for faster design closure.File | Dimensione | Formato | |
---|---|---|---|
DETECTive_OA.pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
613.56 kB
Formato
Adobe PDF
|
613.56 kB | Adobe PDF | Visualizza/Apri |
DETECTive_ Machine Learning-driven Automatic Test Pattern Prediction for Faults in Digital Circuits.pdf
accesso riservato
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
1.01 MB
Formato
Adobe PDF
|
1.01 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2990442