Exactly checking clock tree timings to improve chip scheduling precision

Beyond No-Good Benders Cuts: Exact Realizability for Discretely Tunable Clock Trees

Hardware Architecture

Summary

Designing computer chips involves making sure signals reach different parts at the right times using clock trees. Sometimes, schedules that look good on paper can't actually be built with the available hardware settings. The authors created a method to precisely verify if a given timing plan can be realized by the clock tree setup. Their approach can explain when and why a timing plan is impossible and can improve scheduling by avoiding impossible cases earlier. They also show limits where their method may be slower or less compact than traditional optimization.

What this means in practice

Authors

Boxiang Song, Keren Zhu

Abstract

Useful-skew schedules can satisfy timing constraints yet remain unrealizable by a fixed clock tree with discrete tuning choices. We formulate this mismatch as exact membership in a finite relative-latency set and develop a checkable feedback interface between the scheduler and the tree model. Arithmetic certificates explain unrealizable targets, while tree-specific contraction reduces the structural size of the exact relations projected onto selected sinks. These relations become realizability cuts that can exclude more candidates than a no-good on the same certificate support, including discrete holes that linear inequalities cannot separate. Controlled experiments confirm fewer oracle calls and faster projection construction. They also expose important limits: globally minimum certificates can cost more than they save, compact arithmetic feedback can fail on non-parity obstructions, and direct monolithic optimization remains faster on the tested additive models. The contribution is an exact, independently verifiable scheduler--tree interface, rather than a claim of universal solver acceleration or physical signoff.