Functional verification has been, and continues to be, one of the most challenging and time-consuming activities in the modern microprocessor design process.

Machine learning (AI) techniques are the key for many complex daily tasks and challenges – for the functional verification and in general.

    The Verification & Quality Analytics group addresses three main areas:
  • Verification Cockpit - Provides a consolidated platform and applies data analytics techniques (ML and others) to track and optimize large-scale verification projects
  • Identifying and Predicting Machine Learning Drift - Develops end-to-end methodologies and a framework to identify, predict, and send alerts for drift in ML deployment
  • Formal Verification Technologies - RuleBase SixthSense is a verification expert tool, and Diver is a tool for designer level verification.

Manager

Raviv Gal, Manager Verification & Quality Analytics, IBM Research - Haifa

Verification Cockpit Platform

Verification Cockpit Platform

TAC – Template Aware Coverage

TAC – Template Aware Coverage

Performance Verification

Performance Verification

CDG - Coverage Directed Generation

CDG - Coverage Directed Generation

Identifying and Predicting Machine Learning Drift

Identifying and Predicting Machine Learning Drift

Machine Learning Basics

Machine Learning Basics

RuleBase SixthSense Edition

RuleBase SixthSense Edition

Diver

Diver