Inna Partin-Vaisband

The paper introduces a physics-informed active learning framework to optimize GaN tri-gate FinFETs for vertical power delivery, identifying a multi-fin device (D1) that significantly outperforms a single-fin counterpart (D2) based on an application-specific figure of merit.

This paper proposes SHIFT, a topology-agnostic approach for communication-aware workload placement and routing optimization in large-scale heterogeneous systems, achieving up to 12.5x throughput improvement, 8% power reduction, and 58.3% energy-per-bit reduction.