Esha Choukse

À propos

I am a Researcher in the Azure Research- Systems (opens in new tab) team. I am currently leading the efficient AI (opens in new tab) research project, focusing on the power/energy/thermal bottlenecks of GenAI deployment in cloud, and datacenter sustainability.

For publications, visit this (opens in new tab) tab.

Most recent news:

1. September 2024: Our paper on input-dependent power consumption of GPUs was accepted by the Sustainable computing workshop at SC’24!
2. September 2024: Our joint paper with AMD on Optimizing GPU data center power was accepted by APCCAS 2024!
3. August 2024: DynamoLLM preprint is out!
4. July 2024: We received two paper acceptances at MICRO 2024!
5. July 2024: Served as Program co-chair for HotCarbon 2024 — stay tuned for a report out and proceedings.
6. June 2024: Co-authored 4 papers presented at ISCA, with Splitwise being nominated for Best Paper!
7. April 2024: Co-authored a paper on GenAI inference power provisioning at ASPLOS 2024.
8. April 2024: Gave invited talks at the EMC2 workshop at ASPLOS and at UCSD on the topic: «Rapid growth in GPU deployments in datacenters: With great power comes great responsibility».

Some of the amazing students I have been working with/ have worked with:

1. Amey Agrawal, Georgia Tech (opens in new tab)
2. Jovan Stojkovic, UIUC (opens in new tab)
3. Yuhan Liu, University of Chicago (opens in new tab)
4. Yueying Li, Cornell (opens in new tab)
5. Theo Gregersen, CMU (opens in new tab)
6. Pratyush Patel, UW Seattle (opens in new tab)
7. Muhammad Laghari, Virgina Tech (opens in new tab)
8. Gagandeep Panwar, Virginia Tech  (opens in new tab)
9. Jaylen Wang, CMU (opens in new tab)
10. Josh Fried, MIT (opens in new tab)
11. Gauhar Irfan Chaudhry, MIT (opens in new tab)
12. Edwin Lim, CMU (opens in new tab)
13. Kunal Jain, IIIT Hyderabad (opens in new tab)
14. Marcin Copik, ETH Zurich (opens in new tab)

I received my PhD in 2019 from the University of Texas at Austin, with a thesis on main memory compression for higher effective capacity and bandwidth. I am generally interested in hardware-software co-design for systems challenges.