I am a Research Staff Member at IBM T.J. Watson Research Center in Yorktown Heights. I joined IBM in 2022 after obtaining my PhD from Georgia Institute of Technology. I was advised by Dr. Tushar Krishna.
I am currently exploring accelerator design, and compilation/mapping strategies for DNN workloads on IBM's RaPiD AI accelerator. My research focuses mostly in computer archtitecture, but I also get excited with problems in VLSI design, computer systems design, machine learning algorithm development and other related topics. I explored design of efficient DNN accelerators, and machine learing techniques for accelerator design for my doctoral dissertation.
Click here for my CV.
SCALE-Sim is a DNN accelerator simulator widely used in industry and academic research. SCALE-Sim allows users to get cycle accurate performance, memory accesses and (soon) energy consumption estimates for various dataflows in a systolic array based accelerator setting. Please visit the project webpage for details about the simulator and the tutorials to get started.
Data orchestration in deep learning accelerators
Tushar Krishna, Hyoukjun Kwon, Angshuman Parashar, Michael Pellauer, Ananda Samajdar
Synthesis Lectures on Computer Architecture 15, no. 3 (2020)
[Morgan
And Claypool]
AIRCHITECT: Automating Hardware Architecture and Mapping Optimization
Ananda Samajdar, Jan Moritz Joseph, Tushar Krishna
Design, Automation, and Test in Europe Conference (DATE) 2023. Antwerp, Belgium
[Paper]
[Video]
Self-Adaptive Reconfigurable Arrays (SARA): Using ML to Assist Scaling GEMM Acceleration
Ananda Samajdar, Eric Qin, Michael Pellauer, Tushar Krishna
59th Design and Automation Conference (DAC) 2022. San Francisco, CA
[paper]
[arxiv]
Genesys: Enabling continuous learning through neural network evolution in hardware
Ananda Samajdar, Parth Mannan, Kartikay Garg, Tushar Krishna
51st Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) 2018. Fukuoka, Japan
Finalist, ACM Student Research Competition (ASPLOS-2018)
[arxiv],
[pdf]
A systematic methodology for characterizing scalability of dnn accelerators using SCALE-Sim
Ananda Samajdar, Jan Moritz Joseph, Yuhao Zhu, Paul Whatmough, Matthew Mattina, Tushar
Krishna
IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) 2020. Virtual event
[ieee],
[pdf]
SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training
Eric Qin, Ananda Samajdar, Hyoukjun Kwon, Vineet Nadella, Sudarshan Srinivasan, Dipankar Das,
Bharat Kaul, Tushar Krishna
IEEE International Symposium on High Performance Computer Architecture (HPCA) 2020. San Diego, CA
Winner of Best Paper Award
[ieee],
[pdf]
MAERI: Enabling Flexible Dataflow Mapping over DNN Accelerators via Programmable Interconnects
Hyoukjun Kwon, Ananda Samajdar, Tushar Krishna
23rd ACM International Conference on Architectural Support for Programming Languages and Operating Systems
(ASPLOS), 2018. Williamsburg, VA
IEEE MICRO Top Picks 2019 (Honorable Mention)
[pdf],
[webpage],
[acm]
Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision
Yuhao Zhu, Ananda Samajdar, Matthew Mattina, Paul Whatmough
International Symposium on Computer Architecture (ISCA) 2018. Los Angeles, CA
IEEE MICRO Top Picks 2019 (Honorable Mention)
[pdf],
[arxiv]
Please visit my google scholar profile for a detailed list of publications.
External Review Committee: International Symposium on Computer Architecture
(ISCA)
2023
Program Committee: IEEE International Symposium on Performance Analysis of Systems and Software
(ISPASS)
2023
Program Committee: IEEE International Symposium on Workload Characterization (IISWC)
2022
Virtual Logistics Chair: IEEE/ACM International Symposium on Network-on-Chips (NoCs)
2021, 2020
IEEE Transactions on Parallel and Distributed Systems (TPDS)
2023
ACM Computer Architecture Letters (CAL)
2021, 2022
ACM Transactions on Architecture and Code Optimization (TACO)
2021, 2022
ACM Transactions on Design Automation of Electronic Systems (TODAES)
2021
IEEE Transactions on Very Large Scale Integration Systems (TVLSI)
2022
ML for Computer Architecture and Systems (MLArchSys) at ISCA
2023
7th Workshop On Cognitive Architectures (CogArch) at ISCA
2023
International Workshop on Performance Analysis of Machine Learning Systems (FastPath) at ISPASS
2023
Third Workshop on Benchmarking Machine Learning Workloads on Emerging Hardware (MLBench) at MLSys
2022
Invitation to present at DAC 2022 PhD Forum
(To present) Jul 2022
Best Paper Award at HPCA 2020
Feb 2020
Silver Medal at ACM student research competition at ASPLOS 2019
Apr 2019
Finalist at ACM student research competition at ASPLOS 2018
Apr 2018