Sergio Iserte

Malleability in HPC can cut node-hour consumption significantly without sacrificing performance, paving the way for more efficient resource management in production environments.

Unlock HPC application malleability without the headache of process respawning thanks to this unified dynamic resource management API.

Distributed GPU training slashes the time needed to train deep learning models for CFD, making accurate fluid simulation predictions accessible in a fraction of the time.

Circuit cutting just got a whole lot more practical: DQR lets HPC centers treat quantum circuit fragments as first-class schedulable units, paving the way for seamless integration of NISQ workloads into existing infrastructure.