BTTF
A method or tool for converting chip simulation waveforms into an SQLite database, used for efficient storage and querying of chip verification data.
Timeline (last 90 days)
Columbia University, Google DeepMind and other institutions used BTTF to convert chip simulation waveforms into SQLite databases.
BTTF uses a SQLite database: the signal_metadata table stores static information such as signal names, types and hierarchy, while the signal_changes table records signal IDs, timestamps and post-change values, with the two tables linked by ID.
BTTF experiments show: the untrimmed database occupies 1420 MB with queries taking about 410.5 milliseconds; after filtering out clocks and signals with no toggles, the size drops to 395 MB and the time drops to 94.8 milliseconds; if signals with toggle rates below the average are further removed, the database can shrink to 185 MB, but activity coverage is only 64.23%.
In experiments on 4.2 GB of waveforms, 18450 signals and 150 expert-annotated queries, the BTTF research team achieved 95.33% execution accuracy, with Multi-Agent quality scores 17.3% higher than single Agent, average latency increasing to about 1.96 times, and static SVA check accuracy of 84.62%.
All Facts (4)
Columbia University, Google DeepMind and other institutions used BTTF to convert chip simulation waveforms into SQLite databases.
50%UnverifiedBTTF uses a SQLite database: the signal_metadata table stores static information such as signal names, types and hierarchy, while the signal_changes table records signal IDs, timestamps and post-change values, with the two tables linked by ID.
50%UnverifiedBTTF experiments show: the untrimmed database occupies 1420 MB with queries taking about 410.5 milliseconds; after filtering out clocks and signals with no toggles, the size drops to 395 MB and the time drops to 94.8 milliseconds; if signals with toggle rates below the average are further removed, the database can shrink to 185 MB, but activity coverage is only 64.23%.
50%UnverifiedIn experiments on 4.2 GB of waveforms, 18450 signals and 150 expert-annotated queries, the BTTF research team achieved 95.33% execution accuracy, with Multi-Agent quality scores 17.3% higher than single Agent, average latency increasing to about 1.96 times, and static SVA check accuracy of 84.62%.
50%