I lead the WISR research group. We work on building software systems that improve the performance, security and correctness of modern cloud computing infrastructure and applications. Our current focus is on network verification/repair/synthesis, systems for efficient big data processing, low latency networking, and serverless computation.

Recent Highlights

Jul 2018 QOOP (OSDI'18) and CHC (NSDI'19) accepted!
Feb 2018 Awarded H. I. Romnes Faculty Fellowship!
Feb 2018 Google Faculty Research Award for Low Latency Networking!
Dec 2017 Iron (NSDI), Zeppelin (Sigmetrics) and ServerlessNF (HotNets) accepted!
Aug 2017 Elected vice-chair of ACM SIGCOMM.

Recent papers (Complete list here)

arXiv Network-accelerated Distributed Machine Learning Using MLFabric [pdf]
Raajay Viswanathan, Aditya Akella.
arXiv Themis: Fair and Efficient GPU Cluster Scheduling for Machine Learning Workloads [pdf]
Kshiteej Mahajan, Arjun Singhvi, Arjun Balasubramanian, Varun Batra, Surya Teja Chavali, Shivaram Venkataraman, Aditya Akella, Amar Phanishayee, Shuchi Chawla.
arXiv Whiz: A Fast and Flexible Data Analytics System [pdf]
Robert Grandl, Arjun Singhvi, Raajay Viswanathan, Aditya Akella.
arXiv Tiramisu: Fast and General Network Verification [pdf]
Anubhavnidhi Abhashkumar, Aaron Gember-Jacobson, Aditya Akella.
APNET 19 On the Impact of Cluster Configuration on RoCE Application Design
Yanfang Le, Brent Stephens, Aditya Akella, Michael Swift.
ATC 19 The Design and Operation of a Platform for Advanced Cloud Experimentation
Cloudlab Team.
HotCloud 19 Accelerating Deep Learning Inference via Freezing
Adarsh Kumar, Arjun Balasubramanian, Shivaram Venkataraman, Aditya Akella.
NSDI 19 Loom: Flexible and Efficient NIC Packet Scheduling [pdf]
Brent Stephens, Aditya Akella, Michael Swift.
NSDI 19 Correctness and Performance for Stateful Chained Network Functions [pdf]
Junaid Khalid, Aditya Akella.
VLDB 19 Smurf: Self-Service String Matching Using Random Forests [pdf]
Paul Suganthan, Adel Ardalan, AnHai Doan, Aditya Akella