Publications

Patents

• US 10,726,330 B2: System, Method, and Accelerator to Process Convolutional Neural Network Layers
  Michael Ferdman, Peter Milder, Manoj Alwani.

Academic Employment

• Microsoft Corporation Redmond, WA
• Visiting Researcher (academic sabbatical) June 2020-June 2021
• Stony Brook University Stony Brook, NY
• Associate Professor September 2018-present
• Assistant Professor August 2012-August 2018
• Ecole Polytechnique Fédérale de Lausanne Lausanne, Switzerland
• Research Assistant July 2008-June 2012
• Carnegie Mellon University Pittsburgh, PA
• Research Assistant August 2004-June 2012

Teaching

• Stony Brook University Stony Brook, NY
• CSE 502 - Graduate Computer Architecture Spring 2024
• CSE 356 - Cloud Computing Spring 2024
• CSE 356 - Cloud Computing Fall 2022
• CSE 502 - Graduate Computer Architecture Spring 2022
• CSE 356 - Cloud Computing Spring 2022
• CSE 502 - Graduate Computer Architecture Spring 2020
• CSE 356 - Cloud Computing Fall 2019
• CSE 356 - Cloud Computing Spring 2019
• CSE 502 - Graduate Computer Architecture Spring 2019
• CSE 356 - Cloud Computing Spring 2018
• CSE 506 - Graduate Operating Systems Fall 2017
• CSE 502 - Graduate Computer Architecture Spring 2017
• CSE 356 - Cloud Computing Spring 2017
• CSE 506 - Graduate Operating Systems Fall 2015
• CSE 356(391) - Cloud Computing Fall 2015
• CSE 506 - Graduate Operating Systems Spring 2015
• CSE 602 - Graduate Advanced Computer Architecture Fall 2014
• CSE 502 - Graduate Computer Architecture Spring 2014
• CSE 506 - Graduate Operating Systems Fall 2013
• CSE 502 - Graduate Computer Architecture Spring 2013
• CSE 602 - Graduate Advanced Computer Architecture Fall 2012
• Ecole Polytechnique Fédérale de Lausanne Lausanne, Switzerland
• TA - Advanced Topics on Memory Systems (graduate) Spring 2009 (Babak Falsafi)
• TA - Multiprocessor Architecture (graduate) Fall 2008 (Babak Falsafi)
• Carnegie Mellon University Pittsburgh, PA
• TA - Multiprocessor Architecture (graduate) Spring 2006 (Babak Falsafi)
• TA - Advanced Techniques in Microprocessors (PhD) Fall 2005 (Babak Falsafi)
• TA - Operating Systems (undergraduate) Fall 2001 (Gregory Kesden)
• TA - Embedded Systems (undergraduate) Fall 2001 (Raj Rajkumar)

Industry Employment

• Microsoft Corporation Redmond, WA
• Visiting Researcher 2020-2021
• T elinta, Inc. Springfield, NJ
• Chief Technology Officer 2002-present
• Cadence Design Systems Pittsburgh, PA
• Software Engineer April 2004-August 2007
• Neolinear, Inc. (startup acquired by Cadence) Pittsburgh, PA
• Software Engineer March 2003-April 2004
• Automatika, Inc. Pittsburgh, PA
• Independent Contractor September 2002-January 2003
• National Robotics Engineering Consortium Pittsburgh, PA
• Circuit Designer and Software Engineer February 2001-May 2002

Professional Service

• Organizing committees: ASPLOS'22 (co-general chair), ISPASS'21 (general chair), ISPASS'20 (program committee chair), HPCA'20 (registration chair), DPC'19 (program committee chair), ISCA'17 (finance chair), IISWC'17 (travel grant chair), HPCA'17 (workshops & tutorials chair), ISPASS'17 (workshops & tutorials chair), ISPASS'16 (publication chair), ACM SRC at CGO'15 (local organizer), ISPASS'15 (publication chair), MICRO'14 (publication chair), ISPASS'14 (web chair)
• Steering Committees: Architectural Support for Programming Languages and Operating Systems (ASPLOS), International Symposium on Performance Analysis of Systems and Software (ISPASS)
• Program committees: ASPLOS'24, MICRO'23, HotInfra'23, SIGMETRICS'23, SIGMETRICS'22, MICRO'22, ISCA'21, IEEE MICRO's Top Picks'21, MICRO'20, IPC'20, USENIX ATC'20, IISWC'19, ISCA'19, HPCA'19, MICRO'18, ICCD'18, IISWC'18, ISCA'18, DAC'18, GLSVLSI'18, HPCA'18, MICRO'17, ISCA'17, HPCA'17, CRC'17, ISCA'16, IISWC'16, ISPASS'16, MICRO'15, IISWC'15, ISCA'15, CGO'15, MICRO'14, ICS'14, ICPP'14, HiPEAC'14, ICCD'13, WIVOSCA'13, DATE'13, CCGrid'13, ISPASS'13, IPDPS'13
• University Service: Graduate Council Representative for CS (F'21), College of Engineering and Applied Sciences Executive Committee (S'21), CS Executive Committee (S'19-), CS Operations Committee (S'17, F'16, S'16), Graduate Committee (S'17, F'16, S'16), Undergraduate Committee (S'16), Open House Chair (S'17, S'16, S'15), Graduate Admission Committee (S'20, F'19, S'19, F'18, S'18, F'17, S'17, F'16, S'16, F'15, S'15, S'14, F'14, F'13, S'13, F'12), Faculty Recruitment Committee (S'17, S'14, F'14), Department Orientation Organizer (F'16)
• NSF invited workshops: Workshop on Sustainable Data Centers '15, XPS Workshop on Exploiting Parallelism and Scalability '15
• External reviewer: HPCA'23, MICRO'21, ASPLOS'21, SIGMETRICS'21, ISCA'20, CAL'19, IEEE Micro'19, TECS'19, MICRO'19, CAL'19, TACO'19', CAL'18, TOCS'18, TACO'18, CAL'17, IEEE Micro'17, ACM TACO'17, ACM TOS'16, MICRO'16, ACM TACO'16, HPCA'16, ACM TACO'15, CAL'15, HPCA'15, ASPLOS'15, CF'14, ISCA'14, TC'14, HPCA'14, PPoPP'14, CAL'13, DAC'13, HPCA'13, JCST'13, MICRO'12, IISWC'12, CAL'12, HPCA'12, IISWC'11, MICPRO/DSD'11, ICS'11, ISCA'11, HPCA'11, HiPEAC'10, ISCA'10, HPCA'10, JPDC'09
• NSF service: 2023, 2022 (panelist x2), 2021 (panelist), 2020 (panelist), 2019 (panelist), 2016 (panelist, reviewer), 2014 (panelist)
• Invited Lectures and Talks: Cloud Computing course at HiPEAC ACACES'17, Keynote at RAPIDO'13
• PhD committees: Ivan Miketic (Hardware Security Techniques against Information Leakage and Counterfeiting in Integrated Circuits), Prashant Pandey (Fast and Space-Efficient Maps for Large Data Sets), Weicheng Liu (Low Voltage Clocking Methodologies for Nanoscale ICs), Tan Li (Harness Multicore Parallelism for High Performance Data Replication), Fatima Zarinni (Understanding and Improving Performance in Next-Generation WiFi and Cellular Networks), Mingwei Zhang (Static Binary Instrumentation with Applications to COTS Software Security), Niranjan Hasabnis (Infrastructure for Architecture-independent Binary Analysis and Transformation), Vasily Tarasov (Multi-dimensional Analysis of I/O Workloads for Modern Storage Systems), Zhichao Li (GreenDM: A Versatile Tiering Hybrid Drive for the Trade-Off Evaluation of Performance, Energy, and Endurance), Cheng-Chun (William) Tu (Memory-based Rack-area Network)
• MS committees: Bharath Kumar Reddy Vangoor (To FUSE or not to FUSE?), Kavita Agarwal (A Study of Virtualization Overheads), Arun Olappamanna Vasudevan (Finding the right balance - Security vs Performance with Network Storage Systems)
• Co-developer of CloudSuite, a benchmark suite for scale-out workloads.
• Co-developer of FLEXUS, a scalable, full-system, cycle-accurate multi-processor and multi-core simulation framework between 2005 and 2012.
• SIMFLEX and ProtoFlex: Fast, Accurate, and Flexible Simulation of Computer Systems Tutorial at
• 2010 IEEE International Symposium on Workload Characterization (IISWC). Atlanta, GA, December 2010 with Eric Chung, Pejman Lotfi-Kamran, and Michael Papamichael.
• 42st Annual IEEE/ACM International Symposium on Microarchitecture (MICRO). New York, NY, December 2009 with Eric Chung and Michael Papamichael.
• 17th International Conference on Parallel Architectures and Compilation Techniques (PACT), Toronto, Canada, October 2008 with Eric Chung and Nikos Hardavellas.
• Organizer of the Fall 2009 weekly seminar of the Systems Labs at Ecole Polytechnique Fédérale de Lausanne.
• Organizer of the Fall 2007 weekly seminar of the Computer Architecture Lab at Carnegie Mellon (CALCM).
• Senior Member: IEEE, Member: ACM SIGARCH, ACM SIGMICRO, ACM SIGOPS, HiPEAC Associate.

Funding

• AMD Corporation - FPGA Hardware for research
  Donation, equipment ($7,717), 6/25/2023
• Ampere Computing - ARM Server Hardware for research
  Donation, equipment ($17,400), 1/10/2023
• Stony Brook University-Brookhaven National Lab Seed Grant - Exploration of FPGAs for Real-Time ML-Based Data Compression in sPHENIX
  Co-PI ,$37,000, 8/1/2022 - 3/1/2023
• National Science Foundation - SHF: Small: Massively Parallel Server Processors
  PI, $600,000, 6/15/2022 - 5/31/2025
• OVPR Revise&Resubmit - Distributed Protocol Offload using FPGA SmartNICs
  Co-PI, $13,000, 4/22/2022
• AMD Corporation - FPGA Hardware for research
  Donation, equipment ($13,195), 3/9/2022
• Ampere Computing - ARM Server Hardware for research
  Donation, equipment ($32,000), 5/28/2021
• National Science Foundation - SHF: Small: Sparsity-Aware Hardware Accelerators for Natural Language Processing with Transformers
  Co-PI, $500,000, 10/01/2020 - 9/30/2023
• Stony Brook University-Brookhaven National Lab Seed Grant - Software Assist for Hardware-Managed Virtual Memory on FPGA Accelerators
  PI, $37,000, 8/1/2020 - 3/1/2022
• Xilinx Corporation - FPGA Hardware for research
  Donation, equipment ($6,495), 6/16/2020
• Xilinx Corporation - FPGA Hardware for research
  Donation, equipment ($6,495), 2/20/2020
• National Science Foundation - MRI: Acquisition of Heterogeneous Computer System for Machine Learning
  Co-PI, $561,000, 7/15/2019 - 7/14/2022
• National Science Foundation / Intel Corporation - FoMR: IPC Improvement through Hardware Memoization
  PI, $400,000, 8/1/2019 - 7/31/2022
• Telluric Labs LLC / Department of Energy - IP Access Gateway
  PI, $168,000, 4/8/2019 - 4/7/2020
• National Science Foundation - CSR: Medium: Approximate Membership Query Data Structures in Computational Biology and Storage
  Co-PI, $1,200,000, 8/15/2018 - 8/14/2022
• Intel Corporation - FPGA Hardware for research
  Donation, equipment ($5,500), 6/22/2018
• National Science Foundation - SPX: Harnessing the Power of High-Bandwidth Memory via Provably Efficient Parallel Algorithms
  PI, $750,000 ($500,000 SBU, $250,000 WUSTL), 9/15/2017 - 8/14/2021
• Xilinx Corporation - FPGA Hardware for research
  Donation, equipment ($7,000), 7/28/2017
• Samsung - SSD Hardware for research
  Donation, equipment ($2,000), 7/6/2017
• National Science Foundation - Domestic student travel grant funding for IISWC
  PI, $15,000, 6/01/2017 - 12/31/2017
• National Science Foundation - EAGER: Measuring the Stability of Web Links
  Co-PI, $89,200, 4/15/2017 - 10/15/2017
• National Science Foundation - Research Experiences for Undergraduates: Secure and Efficient Cloud Infrastructure and Accessibility Services
  PI, $21,900, 8/10/2016 - 8/9/2017
• National Science Foundation - EAGER: Preliminary Study to Demonstrate Feasibility and Advantages of Massively Parallel Server Processors
  Co-PI, $146,000, 10/1/2016 - 9/30/2017
• Oracle Labs - Exploring Custom Graph Algorithms with PGX and Green-Marl
  Gift, $55,000, 8/17/2016
• Google - Taming the Killer Microsecond
  Gift, $58,500, 9/2/2016
• National Science Foundation - XPS: FPGA Cloud Platform for Deep Learning, Applications in Computer Vision
  PI, $875,000 ($574,000 SBU, $301,000 UNC), 9/1/2015 - 8/31/2019
• Intel Corporation - Hardware for research
  Donation, equipment ($21,600), 8/6/2015
• National Science Foundation - CAREER: Leveraging temporal streams for micro-architectural innovation in data center servers
  PI, $500,000, 2/15/2015 - 1/31/2020
• National Science Foundation - EAGER: Preliminary Study to Demonstrate the Performance and Power Advantages of FPGAs for Deep Learning in Computer Vision
  PI, $95,000, 8/1/2014 - 7/31/2016
• Altera Corporation - FPGA Hardware for research
  Donation, equipment ($16,000), 10/22/2014
• Cavium - Support of research activities
  Gift, $34,400 + equipment, 7/17/2014
• National Science Foundation - CRI: Secure and Efficient Cloud Infrastructure and Accessibility Services
  PI, $200,000, 9/1/2014 - 8/31/2017
• Semiconductor Research Corporation - Flexible Hardware Acceleration of the Network Stack for Performance and Energy Efficiency
  PI, $300,000, 1/1/2014 - 1/31/2017

Advisees

• Natheesan Ratnasegar, 2022-present
• Hieu Mai, 2021-present
• Reza Ali Modadi, 2018-present
• Farid Samandi, 2019-present

• Yongming Shen, 2014-2021
• Shenghsun Cho, 2014-2021
• Varun Agrawal, 2013-2020

• Sergey Madaminov, 2016-2022
• Zavosh Mottahedeh, 2019-2023
• Raveendra Soori, 2018-2020, NUCAlloc: Fine-Grained Block Placement in Hashed Last-Level NUCA Caches
• Mina Abbasi Dinani, 2016-2020, Massively Parallel Server Processors
• Raghav Dogra, 2017-2018, Predictive Batching for Deep Learning Inference Servers
• Manoj Alwani, 2015-2016, Fused Convolutional Neural Network Accelerators
• Tapti Palit, 2014-2015, Benchmarking Network-Intensive Applications

• Aakshintala Amogh, Aavuty Rajesh, Abhiroop Dabral, Abhishek Chauhan, Abhishek Patil, Aditi Singh, Ajay Gopal Krishna, Ajay Paddayuru Shreepathi Akshay Kale, Alok Thatikunta, Anirudh Mallick, Ankit Dewan, Anurag Porripireddi, Arjun Mathew Dan, Arnabjyoti Kalita, Balaji Srinivasan, Basavaraj Kaladagi, Bhavya Agarwal, Bhuvnesh Kumar Biswaranjan Panda, Chaitanya Chakka Krishna, Chidambaram Ramanathan, Devashish Thakur, Dhruva Kumar Devineni, Gangabarani Balakrishnan, Harinath Kanchu, Heta Ashit Saraiya, Jacob Samuel Harder, Jerrin Shaji George, Jiemin Zeng, Jihyu Yang, Kai-Chieh Huang, Karan Pugla, Komal Agrawal, Kushal Dhar, Malvika Modi, Mandar Naik, Michael Laurence Anderson, Mingchen Zhang, Mitesh Kumar Singh, Neeraj Dixit, Palit Tapti, Parag Gupta, Parikshit Bhattacharjee, Paul Mathew, Pratik Sudarshan Pantode, Priyanka Nath, Pruthvi Kumar Madugundu, Rahul Gadi, Rajendra Kumar Raghupatruni, Ravi Prakash Pandey, Ravikiran Patil, Rohit Chandramohanan, Romeyo Dsouza, Sahil Parmar, Sai Madan Mohan Reddy Patlolla, Sai Shashank Gaddam, Saptarshi Sen, Saraj Munjal, Sayli Yogesh Karnik, Scott Harvey, Shantanu Potdar, Shanuj Shekhar, Shreyas Prabhu Binnamangala, Shubham Pandurang Zope, Shubham Rajesh Jawandhiya, Shubhanga Narasimha, Shyam Sundar Chandrasekaran, Sneha Pathrose, Sri Krishna Jayadev Peddibhotla, Srinath Battula Yagna Reddy, Subin Mathew, Sumeeth Kyathanahalli, Sunad S Bhandary, Tamilmani Manoharan, Taylor Giles, Toby Babu, Vaibhav Srivastav Bandikatla, Vamshi Muthineni, Varsha Venkatesh, Vertika Vaid Vinay Krishnamurthy, Vinay Shetty, Vishal Nayak, Yigong Wang, Yu-Jiun Kao, Yuxuan Shui

• David Pokryvailo, Lise Ho, Mehrab Hoque, Yang Sheng Fang

• Benjamin Michalowicz, Brandon Paradiso, Edgar Samudio, Eniola Abdul, Gabriel Kim, Jacky Xie, Janet Vorobyeva Jessica Chan, John Ranzie, Kevin Wei, Kihoon Kim, Lawrence Lin, Matthew Ng, Minqi (Jason) Shi, Mrunal Patel, Qi Zhang, Roman Scher, Surya Patil