SCALABLE AND AUTOMATED IDENTIFICATION OF UNOBSERVABILITY CAUSALITY IN LOGIC OPTIMIZATION FLOWS
Patent №
US 9,715,564
Granted
2017-07-25
Filed 2015
Owner
INTERNATIONAL BUSINESS MACHINES CORPORATION
Lab
AI components
1
planning
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
14924898
A method for performing redundancy identification in an integrated circuit design. An optimized gate in a logic circuit is identified. A first netlist with a representation of the logic circuit is generated. An error is induced on the optimized gate. A second netlist is generated from a copy of the first netlist incorporating changes based on the error. Fan-out boundaries of the logic circuit are propagated for the first and second netlists. A redundancy report representing optimization steps performed to obtain the original logic circuit is analyzed to identify which steps are adequate to cause unobservability of the optimized gate. This is done by representing the optimization steps as constraints over the first and second netlists. Responsive to the error becoming undetectable under the constraints derived from the redundancy report, a minimal set of reductions is identified from the first netlist as the reason for unobservability of the optimized gate.
AI classification
Ownership
INTERNATIONAL BUSINESS MACHINES CORPORATION
assignment · 369850767
Assignors
BAUMGARTNER, JASON R., GAJAVELLY, RAJ K., MISRA, ASHUTOSH, NALLA, PRADEEP K.
On an employer assignment, the assignors are typically the inventors.