Abstract

The disclosed technology introduces an artificial intelligence-based spatial partitioning framework for integrated circuit testing. By extracting physical and electrical features from design instances, the system constructs optimized virtual tiles to manage power constraints dynamically during structural testing. The methodology utilizes machine learning refinement techniques to maintain load balancing and spatial contiguity, allowing test pattern generation tools to operate with granular, region-specific power awareness that aligns with the underlying power distribution network.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS