Tarikul Islam Papon

PhD Researcher

Computer Science Department
Boston University

      

I am Md Tarikul Islam Papon, a PhD candidate at the Computer Science Department of Boston University advised by Professor Manos Athanassoulis. I am a member of the BU Data-intensive Systems and Computing (DiSC) lab, and part of the MiDAS group@BU. My research interests broadly include Data Systems, specifically focusing on hardware-aware data management challenges, stemming from the evolution of storage and memory devices. During my PhD, I also worked as a Research Intern at Intel's Parallel Computing Lab (Summer '22) and at Microsoft Research's Data Systems Group (Summer '21).

Prior to joining Boston University, I was a lecturer at the Department of Computer Science & Engineering (CSE) in Bangladesh University of Engineering & Technology (BUET) for 4 years. I completed my MSc and BSc degree from the same department under the supervision of Dr. Ashikur Rahman. There I worked on medical informatics using various machine learning and embedded system techniques for health monitoring.


Outside of the office I enjoy traveling and playing Pool (mostly 8 Ball and 9 Ball) and Table Tennis. I also love watching movie and tv series.


I am in the academic job market! [Research Statement] [Teaching Statement] [CV]

Professional Experience

  • PhD Researcher, Boston University (Sept 2019 - Present)
  • Course Instructor, Boston University (Spring 2024)
  • Research Scientist Intern, Intel Corporation (May 2022 - Sept 2022)
  • Research Intern, Microsoft Research (May 2021 - Aug 2021)
  • Lecturer, Bangladesh University of Engineering and Technology (Oct 2015 - August 2019)

[Recent News]

  • Publication
  • Highlight
  • Dec 2024 - I will present a poster on our Reinforcement-learning based data migration policy for tiered storage in NEDB Day, 2025! [Abstract]
  • July 2024 - I will serve in the program committee of SIGMOD 2025 Demo.
  • May 2024 - I received the 2024 SIGMOD Student Scholarship to attend the conference and present our CAVE work in Chile!
  • Apr 2024 - I will give a talk on CAVE and present a poster on design principles of ZNS SSD in NEDB Day, 2024! [Talk Abstract]
  • Mar 2024 - Our invited article on "Effortless Locality on Data Systems using Relational Fabric" got accepted in IEEE Transactions on Knowledge and Data Engineering (TKDE)! [Official Paper]
  • Feb 2024 - Our work "CAVE: Concurrency-Aware Graph Processing on SSDs" got accepted in SIGMOD 2024! [Local Paper] [Official Paper]
  • Feb 2024 - My research work on SSD-aware data system design has been accepted in IEEE ICDE 2024 Ph.D. Symposium! [Local Paper]
  • Jan 2024 - I will serve as a course instructor for "CS 561: Data Systems Architectures" in Spring 24 at Boston University! [Class Website]
  • Nov 2023 - My internship work at Intel titled "Silhouette: Toward Performance-Conscious and Transferable CPU Embeddings" got accepted in the Workshop on ML for Systems at NeurIPS 2023! [Official Paper]
  • Sept 2023 - "On-the-fly Data Transformation in Action" wins the Best Demo Award at VLDB 2023!
  • June 2023 - Our demonstration "On-the-fly Data Transformation in Action" got accepted in VLDB 2023! [Official Paper]
  • Apr 2023 - Our journal work "Enabling Timely and Persistent Deletion in LSM-Engines" got accepted in ACM Transactions on Database Systems (TODS)! [Official Paper]
  • Mar 2023 - Our work "Software-Shaped Platforms" got accepted in CPS-IoT Week Workshops 2023! [Official Paper]
  • Feb 2023 - Our vision paper "Relational Fabric: Transparent Data Transformation" got accepted in IEEE ICDE 2023! [Official Paper]
  • Nov 2022 - Our work "ACEing the Bufferpool Management Paradigm for Modern Storage Devices" got accepted in IEEE ICDE 2023! [Paper]
  • June 2022 - Our work "Relational Memory: Native In-Memory Accesses on Rows and Columns" got accepted in EDBT 2023! [Official Paper]
  • May 2022 - Really excited to share that I have joined Intel as a Research Scientist Intern for this Summer!
  • May 2022 - I am have been awarded this year's BU Computer Science Research Excellence Award!
  • Mar 2022 - Our invited article on "Building Deletion-Compliant Data Systems" has been accepted in IEEE DEBull. [Official Paper]
  • Jan 2022 - One of my MSc works "UACD: A Local Approach for Identifying the Most Influential Spreaders in Twitter in a Distributed Environment" got accepted in Social Network Analysis and Mining (SNAM)! [Official Paper]
  • June 2021 - Our work "A Parametric I/O Model for Modern Storage Devices" got accepted in DaMoN 2021! [Official Paper] [Video] [Slides]
  • Mar 2021 - Really excited to share that I will be joining Microsoft Research as a Research Intern in Summer 2021!
  • Jan 2021 - Our work "The Need for a New I/O Model" wins honorable mention for Best Gong Show talk at CIDR 2021! [Paper] [Video] [Slides]
  • Mar 2020 - Our work "Lethe: A Tunable Delete-Aware LSM Engine" has been accepted for publication in SIGMOD, 2020! [Paper] [arXiv] [Website] [SIGMOD Presentation Video] [Slides] [Poster]

Research

Research Overview

I am currently developing a new design paradigm for interacting with durable storage that takes into account performance asymmetry between read and write operations, as well as the variable access concurrency that different devices may support. Toward this, I have proposed the Parametric I/O Model that captures these key modern storage properties. Following the model, I have developed an asymmetry/concurrency-aware bufferpool manager and a concurrency-aware graph manager. In addition, we are working on hardware/software co-design approaches using reprogrammable technology to support on-the-fly near-data transformation that supports efficient hybrid transactional/analytical processing (HTAP). Prior to joining BU, I worked on the intersection of medical informatics, machine learning and embedded systems.


Current Projects


ReStore: RL-Based Page Migration in Tiered Storage

We propose a reinforcement learning-based page migration policy for a multi-tiered storage architecture that considers both workload and device (SSD) properties.

Coming Soon...
CAVE Graph Manager

We develop a concurrency-aware graph manager CAVE that exploits full SSD parallelism and implement five popular graph traversal algorithms.

Learn more
ACE Bufferpool Manager

We propose an SSD-aware bufferpool manager ACE, that writes multiple dirty pages concurrently to amortize the asymmetric write cost.

Learn more
Relational Memory

We introduce a new type of near-memory computation to transform between row-wise data to column-wise data on the fly via an FPGA-based custom hardware. This reduces cache pollution while ensuring optimal data layout for any query.

Learn more
The New Parametric I/O Model

We propose a simple yet expressive I/O model that considers asymmetry and concurrency of contemporary storage devices.

Learn more
Lethe: A Tunable Delete-Aware LSM Engine

Lethe provides persistence guarantees for delete operations within bounded time and enables efficient secondary range deletes in LSM-based storage engines.

Learn more


Contact

papon@bu.edu
Computer Science Department, CDS 925
Boston University
665 Commonwealth Avenue
Boston, MA 02215