Verisium AI-Driven Verification Platform

Ever since Tim O'Reilly popularized the term Web 2.0 by starting the Web 2.0 Conference, major changes are often tagged with a version number as if they are software releases. Well, Cadence is making not just one, but two announcements that herald the arrival of EDA 2.0—EDA that preserves data from one tool run to the next and uses AI techniques to intelligently decide on what steps should happen next, what we call optimizing execution.

EDA 2.0 Begins Today

Today, we are announcing the Verisium AI-Driven Verification Platform. This is a suite of multi-run, multi-engine tools to optimize SoC verification. So Verification 2.0.

The challenge with verification is that it is never truly complete. The verification teams and their management must decide they are confident enough to tape out the chip and manufacture it. This dynamic means that more verification will always be better. The challenge is that there is never enough of everything: not enough servers, engineers, or time to debug issues. Since there will never be an unlimited supply of engineers, the solution is to work smarter not harder. That is what EDA 2.0 is all about. Under the hood of Verisium verification is the new Cadence.AI Platform.

Verisium AI-Driven Verification Platform

As you can see from the above diagram, the underlying verification engines remain the same:

• Jasper for formal
• Xcelium for simulation
• Palladium for emulation
• Protium for prototyping
• Helium for virtual platform

The Verisium platform contains several apps (in the turquoise boxes in the diagram):

• Verisium AutoTriage: Builds ML models that help automate the repetitive task of regression failure triage by predicting and classifying test failures with common root causes.
• Verisium SemanticDiff: Provides an algorithmic solution to compare multiple source code revisions of an IP or SoC, classify these revisions ,and rank which updates are most disruptive to the system's behavior to help pinpoint potential bug hotspots.
• Verisium WaveMiner: Applies powerful AI engines to analyze waveforms from multiple runs and determine which signals, at which times, are most likely to represent the root cause of a test failure.
• Verisium PinDown: Integrates with industry-standard revision control systems to build ML models of source code changes, test reports, and log files to predict which source code check-ins are most likely to have introduced failures.
• Verisium Debug: Delivers a holistic debug solution from IP to SoC and from single-run to multi-run, offering fast and comprehensive interactive and post-process debug flows with waveform, schematic, driver tracing and SmartLog technologies. Verisium Debug is natively integrated with other Verisium apps to enable AI-driven root cause analysis with the support of simultaneous automatic comparison of passing and failing tests.
• Verisium Manager: Brings Cadence’s full flow IP and SoC-level verification management solution with verification planning, job scheduling, and multi-engine coverage natively to support AI-driven test suite optimization to improve compute farm efficiency. Verisium Manager also integrates directly with other Verisium apps, enabling interactive push-button deployment of the complete Verisium platform from a unified browser-based management console.

The above diagram shows how these apps are marshaled to create jobs that are automatically run on the compute farm:

• Verisium Manager handles AI-driven submission of tests to the compute farm (or the cloud).
• Verisium AutoTriage groups tests failing due to the same underlying bug.
• Verisium SemanticDiff the automatically identifies code differences between recent versions that might have caused the bug.
• Verisium WaveMiner digs down to identify the root cause of the bug.
• Verisium Debug allows engineers to have an interactive display of passing versus failing tests with bug root causes highlighted.

Using the Verisium platform lets bugs be identified, prioritized, debugged, and fixed up to ten times faster than with the classical manual approach. It helps a lot to have a AI-driven apps at your side as you work.

Learn More

See the Verisium product page.

Sign up for Sunday Brunch, the weekly Breakfast Bytes email.

.