Using machine learning clustering to find large coverage holes
Raviv Gal, Giora Simchoni, et al.
MLCAD 2020
Understanding the relationship between coverage and test-Templates (a generic term we use to describe the inputs for the random stimuli generator) is an important layer in understanding the state and progress of the verification process. Today, this is extremely hard to achieve and is based on expert knowledge. Template Aware Coverage (TAC) is a novel approach to meeting this challenge. Based on collecting statistics of the relations between coverage and test-Templates, TAC maintains these statistics in efficient data structures. It also introduces analytics means to provide useful information based on this data. Template Aware Coverage is currently being used in the verification of a high-end processor systems, where it significantly helps hitting hard-To-hit coverage events as well as never hit events.
Raviv Gal, Giora Simchoni, et al.
MLCAD 2020
Eldad Haber, Brian Irwin, et al.
ICML 2023
Raviv Gal, Haim Kermany, et al.
DAC 2020
Raviv Gal, Eldad Haber, et al.
Optimization and Engineering