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 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.
We propose a reinforcement learning-based page migration policy for a multi-tiered storage architecture that considers both workload and device (SSD) properties.
We develop a concurrency-aware graph manager CAVE that exploits full SSD parallelism and implement five popular graph traversal algorithms.
Learn moreWe propose an SSD-aware bufferpool manager ACE, that writes multiple dirty pages concurrently to amortize the asymmetric write cost.
Learn moreWe 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 moreWe propose a simple yet expressive I/O model that considers asymmetry and concurrency of contemporary storage devices.
Learn moreLethe provides persistence guarantees for delete operations within bounded time and enables efficient secondary range deletes in LSM-based storage engines.
Learn morepapon@bu.edu | |
Computer Science Department, CDS 925 Boston University 665 Commonwealth Avenue Boston, MA 02215 |