Over the last 20 years, verification techniques have called for limited innovation compared to software, but for further evolution in the semiconductor industry, we need to continue finding better and more efficient debug methods.
While the fundamentals of good engineering remain the same, there’s always a better way to do ASIC verification, and this is exactly what our new Cogita machine learning features aim at – to develop new ways to accelerate debug and provide higher confidence for first silicon success.
What is your sign-off criteria for verification? We all know that 100% of code and functional coverage is no guarantee that the design is bug free.
Check out Hagai’s latest blog discussing how Cogita’s visual analysis and classification algorithms provide another layer of certainty that we hit 100% coverage and have our ASIC first-time-right on silicon.
Chip Debuggers and doctors, both work to make things better. But, what can bug hunters learn from medical professionals?
The key is good diagnostics methodology. Imagine we debuggers had the efficient guidelines, methods, and tools that doctors use, so we could simply see through and face failure causes directly.
Vtool’s Cogita is designed to be a powerful diagnostic tool, giving you a well-structured root-cause analysis methodology that lets you quickly understand various scenarios in random verification.
How many times did you hear yourself or a verification teammate say “I’m almost done”, while 100% coverage was many weeks away?
Hagai Arbel explains how Cogita can help converge on the last 10%, faster and smoother ?.
Can you find the hidden pattern without the color or shape?
Visualization is power. Your eyes pin down patterns, quicker than your mind reads text. It’s instinct.
What about when you deal with complex failing simulation scenarios? Is this also a moment for letting your ‘visual processors’ take control and lead the way?
We invite you to read a short story of how Cogita was born, on Vtool’s journey to leverage people’s inherent visual power for hunting down bugs – following their eyes.
Methodology or problem-solving. Should you follow a proven verification path or blaze your own way forward?
“When I was 18, I bought a Vespa ’67: the famous Italian scooter… One day, I began to hear strange voices from inside the engine. This kicked off several weeks of nighttime debugging. It was my first real engineering job,” recounts Vtool CEO, Hagai Arbel, in his new post on our blog #RuleTheBugs, sharing his angle on the tradeoffs of following a proven methodology step-by-step instead of exploring your own path of discovery.
Scooters or chips, our passion is to simply achieve a #BugFreeWorld?