APPLICATIONS OF TECHNOLOGY: Applications that utilize sparse graph or matrix algorithms in their computational workloads, like: Scientific computing Machine learning Social network analysis Image and signal processing BENEFITS: Improved sparse accumulation (SPA) throughput Improved core utilization Reduced energy consumption Minimal hardware … [Read more...] about A Hardware Accelerator for Optimized Sparse Accumulation in High Performance Computing 2022-066
Computer Architecture
Unary Single Flux Quantum (U-SFQ) Architecture for Scaling Superconducting Accelerators 2021-112
APPLICATIONS OF TECHNOLOGY: Applications that require high performance computing or high performance digital communications, such as: Artificial intelligence/Machine learning Image and video processing Digital signal processing Infrared sensors Space exploration equipment Quantum technology BENEFITS: Better performance and lower power/energy … [Read more...] about Unary Single Flux Quantum (U-SFQ) Architecture for Scaling Superconducting Accelerators 2021-112
An Area-efficient Superconducting Unary Convolutional Neural Network (CNN) Accelerator for High Performance Computing Systems 2022-056
APPLICATIONS OF TECHNOLOGY: Applications that require high performance computing using convolutional neural networks (CNNs), like: Data mining Medical imaging Autonomous vehicles National defense/security Scientific research Control circuits for quantum computing BENEFITS: More energy efficient than existing CNN hardware accelerators Smaller form … [Read more...] about An Area-efficient Superconducting Unary Convolutional Neural Network (CNN) Accelerator for High Performance Computing Systems 2022-056
Hecate: Data-driven, Machine Learning Augmented Dynamic Path Optimization for Network Performance 2021-010
APPLICATIONS OF TECHNOLOGY: Packet route calculation using real-time dynamic path optimization BENEFITS: Offers more reliable and optimal network performance compared to previous technologies BACKGROUND: Packet route calculation for traffic is routed through a large network based on label stack, such as in segment routing cases and SDN-controlled networks. … [Read more...] about Hecate: Data-driven, Machine Learning Augmented Dynamic Path Optimization for Network Performance 2021-010
A Novel Design Method for On-Chip Superconducting Networks Using Race Logic 2021-009
APPLICATIONS OF TECHNOLOGY: Quantum Computing High performance computing (HPC) Machine learning National security computing BENEFITS: Implements both data and control paths using race logic Increases device performance per unit area Produces higher throughput per port per Josephson Junction compared to best performing state of the art on-chip … [Read more...] about A Novel Design Method for On-Chip Superconducting Networks Using Race Logic 2021-009