Percene Systems — Disorder quantified

Application 01 · Data centres

Heat is what costs you throughput.

A GPU cluster only earns while it stays inside its thermal window. Percene sits between the CDU and the GPU layer, reading live thermal telemetry and modelling the full distribution of what the system does next. We forecast thermal outcomes over long horizons, surface hotspots before they throttle, and route work away from them. The result is more usable throughput from the fleet you already own.

See hotspots six hours out We identify thermal hotspots six hours in advance, while there’s still time to act. Conventional monitoring alarms once the threshold is already crossed.
Long-horizon statistical fidelity Validated to 200 hours on open M100 supercomputer telemetry. We model the distribution and the extremes, not just the mean.
Workload placement Redistribute jobs away from thermally stressed GPUs before derating costs you performance.
Coolant control Roadmap Closing the loop with the CDU to adjust flow rate against predicted hotspots.

A real chaotic flow field from the Percene pipeline — the class of spatiotemporal disorder that governs coolant and heat transport.

Application 02 · Chemistry

A new paradigm of molecular modelling

Density functional theory carries systematic errors that no amount of compute removes. Percene models electron densities, energetics and configurations directly, lifting the accuracy ceiling on prediction of advanced materials. That opens up discovery in MOFs, polymers and larger chained chemicals — systems where the cost of being wrong is a wasted synthesis cycle.

Electron densities and energetics Model configurations and energetics directly, rather than inheriting DFT’s systematic errors.
Built for large systems MOFs, polymers and extended chained chemicals, where classical methods degrade fastest.
Discovery, not just evaluation Search configuration space for candidate structures, not only score the ones you already have.
PFAS applications Currently applied to PFAS configuration optimisation and novel candidate search.

Finalist — RSC Emerging Technologies 2026

A frontier natural orbital of [CuCO₂]⁻ under thermal motion — the strongly correlated metal-site chemistry where classical approximations hit their accuracy ceiling.

Partner with us

We work with data-centre operators, research partners and investors. If the problems on this page are yours, we’d like to hear from you.