Udit Gupta

I am a rising Assistant Professor in the Department of Electrical and Computer Engineering at Cornell Tech. My research interests lie at the intersection of computer architecture, systems, machine learning, and environmental sustainability The central theme to my research is co-designing solutions across the computing stack (applications, algorithms, systems and architecture, circuits and devices) to design and implement computer systems and hardware in new ways to improve the performance, efficiency, and environmental sustainability of emerging applications.

Systems for AI at-scale: My research optimizes the at-scale deployment of deep learning based personalized recommendation in order to enable next generation recommendation systems. Personalized recommendation is central to many Internet services we use on a daily basis including social media, search, video and movie streaming, and e-commerce platforms. My analysis and characterization of personalized recommendation services at-scale is the first to identify the unique challenges recommendation models pose to efficient data center deployment, opening exciting new computing systems and architecture research directions. Building on the characterization, my work accelerates recommendation systems through a diverse spectrum of solutions including  novel near memory processing systems, inference schedulers, and data center-scale specialized hardware. Through my close collaboration with industry, our software solutions for optimizing recommendation have been deployed in production data centers, yielding significant performance and efficiency improvements at-scale.

Sustainability and Computing: My research goes beyond improving performance and efficiency to investigate new techniques towards enabling environmentally sustainable computing. My research is the first to show that the carbon footprint of modern mobile devices and data-centers requires owes not only to operational energy consumption and but also (and in fact is dominated by) embodied carbon from hardware manufacturing (Chasing Carbon). Building sustainable computer systems for the future requires us to fundamentally rethink research and development across the computing stack. My research has conducted in-depth studies understanding the challenges and opportunities for sustainable AI, developed methods towards 24/7 carbon-aware data centers, and built architectural carbon aware modeling tools.

In the past my research has also investigated co-designing neural networks and specialized hardware for low-power and energy-efficient mobile AI including image classification and speech recognition.

My work has been recognized as an IEEE MICRO Top Picks (2021) and IEEE MICRO Top Picks Honorable Mention (2020), as well as received best paper nominations at the Parallel Architectures and Compilation Techniques (PACT 2019) and Design Automation Conference (DAC 2018). I completed my Ph.D. in Computer Science at Harvard University.

I am actively looking for motivated, ambitious, and passionate graduate students, postdoctoral scholars, and undergraduate researchers!

If you are interested in working with me, please send me an email with your CV, your transcript, and brief summary of research areas that excite you.

If you are a PhD student interested in working with me, please apply to the Cornell ECE PhD program and mention me in your application. Cornell Tech and Cornell share the PhD application and end-to-end PhD program. Additional details can be found here!

• October 2022: Gave a talk on ``Sustainable Computing'' at IEEE Chapter on Society on Social Implications of Technology
• October 2022: Carbon Explorer was accepted to ASPLOS 2023!
• October 2022: Presented DeepRecSys at the EmergingBench workshop at MICRO 2022
• October 2022: Hosted ACT tutorial at MICRO 2022
• September 2022: I will be at Meta as a Visiting Researcher for 1 year until I start at Cornell Tech!
• August 2022: Officially graduated with a PhD from Harvard University!
• June 2022: Presented ACT, our Architectural Carbon Modeling Tool, at ISCA 2022. [PDF] [Slides] [Github]
• June 2022: Successfully hosted student activites at MLSys 2022 as the Young Professional Activities Chair
• May 2022: Accepted position to become an Assistant Professor at Cornell Tech starting summer 2023!!
• March 2022: ACT was accepted to ISCA 2022!
• November 2021: I am on the academic job market!
• August 2021: Accepted to be a Fellow in the 3C (Cultural Competence in Computing) program

For a complete and up to date list of publications please visit Google Scholar.

• ACT: Designing Sustainable Computer Systems With An Architectural Carbon Modeling Tool
  Udit Gupta, Mariam Elgamal, Gage Hills, Gu-Yeon Wei, Hsien-Hsin S. Lee, David Brooks, Carole-Jean Wu
  International Symposium on Computer Architecture (ISCA 2022)
  [PDF] [Slides] [Github]


• A Holistic Approach for Designing Carbon Aware Datacenters
  Bilge Acun, Benjamin Lee, Kiwan Maeng, Manoj Chakkaravarthy, Udit Gupta, David Brooks, Carole-Jean Wu
  To appear in International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2023)
  [ArXiv]


• Sustainable AI: Environmental Implications, Challenges and Opportunities
  Carole-Jean Wu, Ramya Raghavendra, Udit Gupta, Bilge Acun, Newsha Ardalani, Kiwan Maeng, et. al.
  Machine Learning and Systems (MLSys 2022)
  [ArXiv]


• Hercules: Heterogeneity-Aware Inference Serving for At-scale Personalized Recommendation
  Liu Ke, Udit Gupta, Mark Hempstead, Carole-Jean Wu, Hsien-Hsin Sean Lee, Xuan Zhang
  IEEE International Symposium on High-Performance Computer Architecture (HPCA 2022)
  


• RecPipe: Co-designing Models and Hardware to Jointly Optimize Recommendation Quality and Performance
  Udit Gupta, Samuel Hsia, Jeff Zhang, Mark Wilkening, Javin Pombra, Hsien-Hsin S. Lee, Gu-Yeon Wei, Carole-Jean Wu, David Brooks
  IEEE/ACM International Symposium on Microarchitecture (MICRO 2021)
  [ArXiv] [Github] [MICRO 2021 Talk] [MICRO 2021 Lightning Talk] [PDF]
  [Artifact] (available, functional, and reproducible)


• RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference
  Mark Wilkening, Udit Gupta, Samuel Hsia, Caroline Trippel, Carole-Jean Wu, Gu-Yeon Wei
  International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2021)
  [ArXiv]


• Chasing Carbon: The Elusive Environmental Footprint of Computing
  Udit Gupta, Young Geun Kim, Sylvia Lee, Jordan Tse, Hsien-Hsin S. Lee, Gu-Yeon Wei, David Brooks, Carole-Jean Wu
  IEEE International Symposium on High-Performance Computer Architecture (HPCA 2021)
  Selected as IEEE MICRO's Top Picks
  Featured by: Harvard Gazette, Tech @ Facebook, Bloomberg Green
  [PDF] [Slides] [HPCA 2021 Long Talk] [HPCA 2021 Short Talk]


• DeepRecSys: A System for Optimizing End-To-End At-scale Neural Recommendation Inference
  Udit Gupta, Samuel Hsia, Vikram Saraph, Xiaodong Wang, Brandon Reagen, Gu-Yeon Wei, Hsien-Hsin S. Lee, David Brooks, Carole-Jean Wu
  International Symposium on Computer Architecture (ISCA 2020)
  [PDF] [Slides] [ISCA 2020 Talk] [Github] [PeRSonAl Tutorial Talk]


• RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing
  Liu Ke, Udit Gupta, Carole-Jean Wu, Benjamin Youngjae Cho, Mark Hempstead, Brandon Reagen, Xuan Zhang, David Brooks, Vikas Chandra, Utku Diril, Amin Firoozshahian, Kim Hazelwood, Bill Jia, Hsien-Hsin S. Lee, Meng Li, Bert Maher, Dheevatsa Mudigere, Maxim Naumov, Martin Schatz, Mikhail Smelyanskiy, Xiaodong Wang
  International Symposium on Computer Architecture (ISCA 2020)
  [PDF]


• Architectural Implications of Facebook’s DNN-based Personalized Recommendation
  Udit Gupta, Carole-Jean Wu, Xiaodong Wang, Maxim Naumov, Brandon Reagen, David Brooks, Bradford Cottel, Kim Hazelwood, Bill Jia, Hsien-Hsin S. Lee, Andrey Malevich, Dheevatsa Mudigere, Mikhail Smelyanskiy, Liang Xiong, Xuan Zhang
  IEEE International Symposium on High-Performance Computer Architecture (HPCA 2020)
  Selected as Honorable Mention for IEEE MICRO's Top Picks
  Featured by: Facebook Research
  [PDF] [Slides] [Github] [PeRSonAl Tutorial Talk]


• MASR: A Modular Accelerator for Sparse RNNs
  Udit Gupta, Brandon Reagen, Lillian Pentecost, Marco Donato, Thierry Tambe, Alexander Rush, Gu-Yeon Wei, David Brooks
  Parallel Architectures and Compilation Techniques (PACT 2019)
  Best Paper Nominee
  [PDF], [Slides], [ArXiv]

Facebook, Inc.

Facebook AI Research (FAIR) Visiting Research Scientist	January 2021 - Present
Facebook AI Research (FAIR) Intern	January 2020 - December 2020
AI Infrastructure Research Intern	September 2018 - January 2020

Algo Logic Systems Inc.

Hardware Design and Verification Engineer

May 2015 - August 2015

Panels and Young Professionals Activities Chair at MLSys 2023	2023
Panels and Young Professionals Activities Chair at MLSys 2022	2022

CLEAR at ISCA 2021 Co-Founder and Co-Organizer	2021
NOPE at ASPLOS 2021 Co-Organizer	2021
JOURNE at MLSys 2021 Co-Founder and Co-Organizer	2021
PeRSonAl at MLSys 2021 Co-Founder and Co-Organizer	2021
PeRSonAl at ISCA 2020 Co-Founder and Co-Organizer	2020
PeRSonAl at ASPLOS 2020 Co-Founder and Co-Organizer	2020
NOPE at ASPLOS 2019 Co-Organizer	2019

Computer Architecture Student Association (Co-chair)	2022 - Present
Computer Architecture Student Association (steering committee member)	2020 - 2022
3C (Cultural Competence in Computing) Fellow	2021 - 2022