As specifications grow to hundreds of pages, traditional verification workflows struggle to maintain consistency, traceability, and speed. This session demos Normal EDA, which replaces subjective, hand-written flows with NormML - a proprietary formal language that ingests raw specs, timing diagrams, and existing testbenches to build an auditable graph that auto-generates zero-to-one test plans, SystemVerilog/UVM stimulus, and traceable coverage links. The system reasons across multimodal data to flag inconsistencies before RTL reaches the simulator, slashing coverage closure time.
Maxim Khomiakov
Maxim Khomiakov, PhD, is a Senior AI Engineer at Normal Computing, building reliable, high‑performance AI software for automating chip verification and design. He previously developed and deployed production-scale machine learning models within Apple Maps. Before that, he led data science efforts at Otovo and co‑founded Sunmapper (acquired by Otovo). Maxim holds a PhD in Machine Learning from the Technical University of Denmark (DTU).
Normal Computing
Website: https://www.normalcomputing.com/
Normal Computing was founded in the USA by former members of Google Brain and Google X, who helped pioneer AI for the physical world and developed the leading ML frameworks for Probabilistic and Quantum AI.
Normal builds foundational software and hardware that help move technology forward - supporting the semiconductor industry, critical AI infrastructure, and the broader systems that power our world.
Normal deploys AI software to accelerate complex hardware engineering with zero defects in one unified EDA platform. Our flagship product, Normal EDA, is a holistic stack for complex IP and SoC verification, generating production-grade collateral directly from specifications and seamlessly integrating into existing verification workflows.
Normal is pioneering thermodynamic computing hardware that could reduce AI energy consumption by orders of magnitude, approaching near-physical limit efficiency for diffusion-like workloads - critical to reason coherently about the physical world, such as semiconductor design and verification.
By combining advanced probabilistic reasoning with formal logic, Normal Computing bridges AI and physics to address the silicon complexity crisis, enabling semiconductor companies to achieve faster time-to-market with zero-defect confidence.
