Systems & networking
Researching next-generation systems and networks that power reliable, scalable, and efficient computing.
Publication
SOCK: Serverless-Optimized Containers.
Project
Gandiva: Scheduler for DNNs
Gandiva is a cluster scheduling framework that utilizes domain-specific knowledge of deep learning to improve the efficiency of training deep learning models in a GPU cluster.
Project
Astra: Custom-Wired DNNs
Astra is a compilation and execution framework that optimizes execution of a deep learning training job. Instead of treating the computation as a generic data flow graph, Astra exploits domain knowledge about deep learning training…
Project
Instalytics: Storage for Big Data
Instalytics (Intelligent Store-powered Analytics) is a vertically integrated infrastructure stack that enables efficient big data analytics in large-scale data centers, by careful co-design of the storage layer (cluster file system) with the compute layer (query…
Project
Deep Learning Compiler and Optimizer
Project Overview This project aims to build a deep learning compiler and optimizer infrastructure that can provide automatic scalability and efficiency optimization for distributed and local execution. Overall, this stack covers two types of general…