Devashree Tripathy

About

Dr. Devashree Tripathy is an Assistant Professor in Computer Science and Engineering at Indian Institute of Technology, Bhubaneswar. Her research spans in Computer Architecture , High Performance Computing, Fault-Tolerance systems, performance and power-efficient designs for accelerators, and machine learning. Her current research focuses on ML for Systems and Systems for ML. Prior to joining IIT Bhubaneswar, Dr. Tripathy was a Postdoctoral Fellow in Computer Science at Harvard University, working with Dr. David Brooks in Harvard Architecture, Circuits, and Compilers Group. She is currently working as an Associate with Harvard University. She graduated from University of California, Riverside with PhD in Computer Science and was advised by Distinguished Prof. Laxmi N. Bhuyan and Prof.Daniel Wong.
Homepage: https://devashreetrip.github.io/

Employment

• Indian Institute of Technology Bhubaneswar Assistant Professor
  2022 - Present
• Harvard University Associate
  2022 - Present
• Harvard University Postdoctoral Research Fellow
  2021 - 2022

Education

• CSIR-CEERI Masters in Technology
  2012 - 2014
• Veer Surendra Sai University of Technology Bachelor in Technology
  2008 - 2012

Projects & Funding

Projects & funding information is unavailable.

Publications (14)

• ArchGym: An Open-Source Gymnasium for Machine Learning Assisted Architecture Design
  2023 DOI: 10.1145/3579371.3589049
  +Save
• FARSI: An Early-stage Design Space Exploration Framework to Tame the Domain-specific System-on-chip Complexity
  Transactions on Embedded Computing Systems 2022 DOI: 10.1145/3544016
  +Save
• ICAP: Designing Inrush Current Aware Power Gating Switch for GPGPU
  2021 IEEE International Conference on Networking, Architecture and Storage, NAS 2021 - Proceedings 2021 DOI: 10.1109/NAS51552.2021.9605434
  +Save
• LocalityGuru: A PTX Analyzer for Extracting Thread Block-level Locality in GPGPUs
  2021 IEEE International Conference on Networking, Architecture and Storage, NAS 2021 - Proceedings 2021 DOI: 10.1109/NAS51552.2021.9605411
  +Save
• PAVER: Locality Graph-Based Thread Block Scheduling for GPUs
  ACM Transactions on Architecture and Code Optimization 2021 DOI: 10.1145/3451164
  +Save
• SAOU: Safe adaptive overclocking and undervolting for energy-efficient GPU computing
  ACM International Conference Proceeding Series 2020 DOI: 10.1145/3370748.3406553
  +Save
• Slumber: Static-power management for GPGPU register files
  ACM International Conference Proceeding Series 2020 DOI: 10.1145/3370748.3406577
  +Save
• GreenMM: Energy efficient GPU matrix multiplication through undervolting
  Proceedings of the International Conference on Supercomputing 2019 DOI: 10.1145/3330345.3330373
  +Save
• Real-Time BCI System Design to Control Arduino Based Speed Controllable Robot Using EEG
  Springer Briefs in Applied Sciences and Technology, 2018. 2019 DOI: 10.1007/978-981-13-3098-8
  +Save
• WIREFRAME: Supporting data-dependent parallelism through dependency graph execution in GPUs
  Proceedings of the Annual International Symposium on Microarchitecture, MICRO 2017 DOI: 10.1145/3123939.3123976
  +Save