Word level feature discovery to enhance quality of assertion mining

Automatic assertion generation methodologies based on machine learning generate assertions at bit level. These bit level assertions are numerous, making them unreadable and frequently unusable. We propose a methodology to discover word level features using static and dynamic analysis of the RTL sour...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2012 IEEE/ACM International Conference on Computer-Aided Design (ICCAD) S. 210 - 217
Hauptverfasser: Liu, Lingyi, Lin, Chen-Hsuan, Vasudevan, Shobha
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: New York, NY, USA ACM 05.11.2012
IEEE
Schriftenreihe:ACM Conferences
Schlagworte:
Algorithm design and analysis
Applied computing > Arts and humanities > Architecture (buildings) > Computer-aided design
Applied computing > Physical sciences and engineering > Engineering > Computer-aided design
Computational modeling
Computer systems organization > Architectures > Parallel architectures > Very long instruction word
Computer systems organization > Architectures > Serial architectures > Complex instruction set computing
Computer systems organization > Architectures > Serial architectures > Reduced instruction set computing
Computing methodologies > Machine learning
Concrete
Decision trees
Hardware design languages
Input variables
Machine learning algorithms
ISBN:9781450315739, 1450315739
ISSN:1092-3152
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Automatic assertion generation methodologies based on machine learning generate assertions at bit level. These bit level assertions are numerous, making them unreadable and frequently unusable. We propose a methodology to discover word level features using static and dynamic analysis of the RTL source code. We use discovered word level features for the underlying learning algorithms to generate word level assertions. A post processing of assertions is employed to remove redundant propositions. Experimental results on Ethernet MAC, I2C, and OpenRISC designs show that the generated word level assertions have higher expressiveness and readability than their corresponding bit level assertions.
ISBN:9781450315739
1450315739
ISSN:1092-3152
DOI:10.1145/2429384.2429424