Towards Accelerating Data Intensive Application’s Shuffle Process Using SmartNICs

Efficiently Offloading Intra-Server Orchestration to NICs

TCP is Harmful to In-Network Computing: Designing a Message-Oriented Transport Protocol (MTP)

In-network Aggregation for Multi-tenant Learning

A High-Performance Programmable NIC for Multi-tenant Networks

Flexible Learning-based CDN Caching

Resilient Baseband Processing in Virtualized RANs

Enabling Resilience in Virtualized RANs

Redesigning both the control plane and data plane for service meshes

Memory Deduplication for Serverless Computing

A Scalable Low-Latency Serverless Platform

Serverless Network Functions

Lowering the Pre-training Tax for Gradient-based Subset Training

Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning

Jointly Optimizing ML Collective Scheduling and Execution Planning

Fair and efficient GPU cluster scheduling for machine learning workloads

Network-accelerated distributed machine learning

Accelerating deep learning inference

Fast, fair, and efficient execution of multiple analytics at scale

Analytics in the face of data geo-distribution and extreme compute volatility

Enabling data-driven computation