Find Academic Supervisors

• Database Systems
• Data Mining
• Query Optimization
• +3 more

Jeffrey F. Naughton is a Professor at the University of Wisconsin and works at Google Inc in Madison, WI, USA. His academic career spans decades with significant contributions to database systems, data mining, and privacy-preserving analytics. Research Interests : Distributed query processing and optimization Machine learning integration with relational databases Differential privacy in data analysis Scalable data warehousing systems Energy-efficient database architectures Temporal data management Article Trends : Over the past decade, Naughton's publications demonstrate a trajectory from foundational database optimization to modern challenges in scalable analytics and privacy-preserving techniques. Key themes include query execution prediction, workload summarization, and system design for big data environments. Scientific Awards : ACM Software System Award (2008) - Recognizing his contributions to database software systems Collaborative Network : He has collaborated with leading researchers including AnHai Doan (entity matching), Somesh Jha (privacy), and Stratis Viglas (query optimization), producing impactful work in SIGMOD, VLDB, and ICDE venues.

Dong DaiView profile

Associate Professor

• Artificial Intelligence
• Machine Learning
• High-Performance Computing
• +5 more

Dong Dai is an Associate Professor at the University of Delaware in the Department of Computer and Information Sciences under the College of Engineering. He directs the Data Intelligence Research Lab (DIRLab) , focusing on optimizing intelligent infrastructure for high-performance, data-intensive systems using machine learning techniques. Research Interests : Artificial Intelligence, Machine Learning, High-Performance Computing, Storage Systems, Metadata Management, Graph Storage, Job Scheduling Education : PhD and BSc from the University of Science and Technology of China Grants : CCF-EAGER, CNS, CCF-Hybrid NVM, CCF-Parallel Graph-Based Paradigm, OAC-Provenance Collection Teaching : Courses include CISC 361 Operating Systems , CISC 360 Computer Architecture , ITCS 5145 Parallel Computing , and ITSC 3050 Undergraduate Research .

Rohan Basu RoyView profile

Assistant Professor

• Parallel Computing
• Distributed Systems
• Cloud Computing
• +3 more

Rohan Basu Roy is an Assistant Professor (tenure-track) at the University of Utah, affiliated with the Kahlert School of Computing and the SCI Institute. His research focuses on optimizing parallel and distributed computing systems, including cloud, serverless, and HPC environments, with an emphasis on sustainability and cost-effectiveness. He holds a Ph.D. in Computer Engineering from Northeastern University, advised by Prof. Devesh Tiwari. Affiliations: University of Utah (Kahlert School of Computing), SCI Institute. His research interests include scheduling algorithms, energy efficiency, and environmental sustainability in computing systems. He has pioneered open-source tools like GreenMix and ECOLIFE , widely adopted in the systems research community. Awards: ACM-IEEE CS George Michael Memorial HPC Fellowship (2023), MLCommons ML and Systems Rising Star (2023), Northeastern University Excellence in Research Award (2023). Rohan has served as a program committee member for top-tier conferences (ASPLOS, HPCA, SC) and co-chaired tracks such as AI/ML for Systems at HiPC 2025. He has also delivered invited talks at Google Brain and ParslFest 2023.

Xiaoyi LuView profile

Associate Professor

• Parallel and Distributed Computing
• High-Performance Communication and I/O Technologies
• Big Data Analytics
• +4 more

Dr. Xiaoyi Lu is an Associate Professor in the Department of Computer Science & Engineering at the University of California, Merced (UC Merced), where he founded and directs the Parallel and Distributed Systems Laboratory (PADSYS Lab). He is affiliated with the AgAID Institute since 2023 and has authored over 170 publications, including ten Best Paper Awards or Nominations (e.g., SC 2019, IPDPS 2024). His research outcomes like OpenDOTA and MVAPICH2-Virt are used by hundreds of organizations globally. Research Interests: He focuses on scalable parallel systems for HPC, Big Data, AI, Cloud, and Edge Computing, leveraging advanced technologies like RDMA/PMEM/NVMe/GPU/DPU. His work bridges high-performance computing with applications in precision agriculture, biostatistics, and digital twin technology. Article Trends: Recent publications emphasize DPU offloading, compression-optimized collective communication, error detection in HPC, and scalable Bayesian group testing. Topics span GPU clusters, NVMe-over-Fabrics, and adaptive networks for LLM training, reflecting his expertise in heterogeneous architectures and distributed systems. Scientific Awards: NSF CAREER Award (2024) Amazon Research Award (2023) Google Research Award (2022) Meta Faculty Research Award (2022) Multiple Best Paper Nominations Professional Activities: He serves as Associate Editor for Frontiers in High Performance Computing and organizes tracks at SCAsia and HiPC. His leadership in PADSYS Lab drives innovation in systems for social good.

Daisaku YokoyamaView profile

Assistant Professor

• Parallel and Distributed Processing
• Combinatorial Search
• Game Tree Search
• +4 more

Daisaku Yokoyama is an Assistant Professor at the Institute of Industrial Science, University of Tokyo, where he works in Department 3 of the Kitsuregawa-Toyoda Laboratory. His research focuses on parallel and distributed processing, combinatorial search, game tree search, and other search processes. He is also involved in the development of "Gekisashi," a computer shogi (Japanese chess) player. His academic background includes: March 1998: Graduated from the Department of Electronic and Information Engineering, Faculty of Engineering, The University of Tokyo March 2000: Completed Master's course in Information Engineering at the University of Tokyo 2002.3: Graduated from the Doctoral Program in Information Engineering, Graduate School of Engineering, The University of Tokyo September 2006: Obtained a PhD in Science from the Graduate School of Frontier Sciences, University of Tokyo Daisaku Yokoyama's research interests primarily center around parallel and distributed computing systems, with a particular focus on combinatorial search algorithms and game tree search techniques. His work bridges theoretical computer science with practical applications, especially in the domain of computer shogi where he has developed "Gekisashi." Beyond game AI, his research has expanded into big data analytics, particularly in transportation systems where he analyzes passenger flows in metro networks and driver behavior using vehicle recorder data. His work demonstrates a consistent thread of applying parallel processing techniques to solve computationally intensive problems across various domains. Yokoyama's publication record shows a clear evolution from foundational work in parallel combinatorial optimization (PopKern library) to more applied research in computer shogi and eventually to big data applications in transportation systems. His early work established frameworks for parallel search algorithms, while more recent publications demonstrate applications of these techniques to real-world problems involving massive datasets from metro systems and vehicle recorders. His research consistently emphasizes the importance of domain-specific knowledge in optimizing parallel algorithms. His notable scientific achievements include: DBSJ Best Paper Award 2014 for "Application and Evaluation of a Bayesian-Based Monte Carlo Tree Search Algorithm to Shogi" Game Programming Workshop Excellent Paper Award (awarded twice) Throughout his career, Yokoyama has been actively involved in academic service, serving on editorial boards, program committees, and as an organizer for numerous conferences and workshops related to programming, parallel computing, and game AI. His work on the Gekisashi shogi engine represents a long-term research project that has evolved from basic search algorithms to sophisticated AI systems, demonstrating both theoretical rigor and practical implementation skills. He is part of the Kitsuregawa-Toyoda Laboratory at the Institute of Industrial Science, University of Tokyo, which focuses on advanced computing systems, database technologies, and large-scale data processing. The laboratory provides a collaborative environment for research spanning theoretical computer science to real-world applications in transportation analytics and game AI.

David LowenthalView profile

Professor

• Parallel and distributed computing
• Operating systems
• Run-time systems

David Lowenthal is a Professor at the University of Arizona specializing in parallel and distributed computing, operating systems, and run-time systems, with his office located in GS 705. His research directly addresses critical challenges in modern high-performance computing infrastructure. His educational background includes: Ph.D. in Computer Science from the University of Arizona (1996) Professor Lowenthal's research centers on optimizing large-scale computing systems through innovative scheduling algorithms, power management techniques, and network optimization strategies. Key contributions include mitigating inter-job interference in cluster environments, developing quality-of-service mechanisms for MPI applications, and pioneering coscheduling approaches like the Jigsaw scheduler. His work bridges theoretical computer science with practical system implementation to enhance resource utilization under power constraints. Analysis of his 15 most recent publications (2016-2023) reveals three dominant research thrusts: intelligent job scheduling (particularly coscheduling and backfilling), power-aware computing for energy-constrained HPC systems, and network performance optimization in dragonfly/fat-tree topologies. These publications consistently demonstrate collaborative NSF-funded research with emphasis on real-world system implementation and performance evaluation. No scientific awards were documented in the provided text. While no student advisees were listed, his research program has secured substantial NSF funding through collaborative grants including "Collaborative Research: SHF: Medium: Co-Optimizing Computation and Data Transformations for Sparse Tensors" (2022) and "Collaborative Research: OAC Core: Improving Utilization of High-Performance Computing Systems via Intelligent Co-scheduling" (2021), indicating active grant management and interdisciplinary collaboration. No specific laboratories or research teams were mentioned in the source material.

Rajiv GuptaView profile

Professor

• Parallel Computing
• Compilers
• Computer Architectures
• +4 more

Rajiv Gupta is a Distinguished Professor and the Amrik Singh Poonian Professor of Computer Science at the University of California, Riverside (UCR), where he serves as Associate Dean for Academic Personnel in the Bourns College of Engineering (BCOE). He is a member of the RIPLE research group and has co-authored 327 papers with an h-index of 69 and over 16,600 citations. His extensive service includes chairing major conferences such as FCRC 2015, PPoPP 2020, ASPLOS 2011, and PLDI 2008. Professor Gupta's research focuses on Programming, Compiler, Runtime & Architectural Support for Parallel & Distributed Heterogeneous Systems and Software Tools for Monitoring and Managing Runtime Behavior . His work spans graph analytics with scalability and performance, understanding and managing the dynamic behavior of parallel programs, software speculation for irregular parallelism, dynamic program analysis for secure and reliable computing, and compiler optimizations with architectural support. His research has significant applications in high-performance computing, GPU programming, and distributed systems. Analysis of his recent publications reveals a strong focus on graph processing systems, with particular emphasis on evolving and streaming graph analytics. His work addresses critical challenges in memory management for large-scale graph processing, hardware acceleration for graph algorithms, and optimization techniques for concurrent and distributed graph computations. The research demonstrates a progression from foundational compiler and architecture work to increasingly sophisticated systems for handling modern data-intensive computing challenges. Fellow of the ACM (2009) Fellow of the IEEE (2008) Fellow of the AAAS (2011) NSF Presidential Young Investigator Award (1991) UCR Doctoral Dissertation Advisor/Mentor Award (2012) Multiple best paper awards across major conferences Two students won ACM SIGPLAN Outstanding Doctoral Dissertation Award Five advisees received NSF CAREER Award Professor Gupta has supervised 42 PhD students to completion and currently advises several doctoral candidates. His advising success is reflected in his students' achievements, including multiple award-winning dissertations and significant career accomplishments in academia and industry. His research has been supported by numerous grants from NSF, DARPA, and industry partners, enabling sustained investigation into parallel computing systems. The RIPLE research group under his leadership has produced influential work that bridges theoretical foundations with practical system implementations. As the leader of the RIPLE research group at UC Riverside, Professor Gupta oversees a vibrant team focused on innovative approaches to parallel and distributed computing. The group maintains strong collaborations with industry partners and other academic institutions, contributing to the development of next-generation computing systems. Current projects include GRASP (Graph Analytics with Scalability & Performance) and research on understanding and managing the dynamic behavior of parallel programs, reflecting the group's continued focus on cutting-edge computing challenges.

Konstantinos KallasView profile

Assistant Professor

• Computer Systems
• Compilers
• Programming Languages
• +1 more

Konstantinos Kallas serves as Assistant Professor of Computer Science at the University of California, Los Angeles (UCLA), commencing his appointment in January 2025. Previously affiliated with the University of Pennsylvania as evidenced by his 2020 PLDI contribution, his research bridges theoretical formal methods with practical systems engineering across multiple high-impact conferences including PLDI, POPL, and SPLASH. His research program centers on enhancing computational efficiency and correctness in systems software, with three flagship projects defining his trajectory: PaSh for automatic shell script parallelization, Durable Functions for stateful serverless computing semantics, and DiffStream for differential testing of stream processing. These efforts consistently target the intersection of programming language theory and real-world systems constraints, particularly in parallelism, concurrency, and cloud-native environments where correctness guarantees are challenging to implement. Analysis of his publication history since 2020 reveals a methodological pattern: developing formal semantic models to enable practical optimizations in distributed systems. His work increasingly focuses on serverless architectures and data-intensive pipelines, with recent contributions emphasizing automated verification techniques. The evolution from shell script optimization (2020-2021) to serverless state management (2021-2022) demonstrates strategic expansion into cloud computing's hardest problems. Dr. Kallas actively contributes to the academic community through program committee service for PLDI (2022, 2025), POPL (2021, 2022, 2023), and SPLASH (2020-2023), including leadership roles as Publicity Co-Chair for PLDI 2025 and 2026. His June 2024 announcement confirms recruitment for Fall 2025 students at UCLA, targeting researchers interested in systems, compilers, and programming languages who can advance his work on correctness-preserving parallelization and serverless computing.

Sang-Hoon KimView profile

Associate Professor

• Operating Systems
• Memory Systems
• Storage Systems
• +4 more

Sang-Hoon Kim is an Associate Professor in the Department of Software and Computer Engineering and Department of Artificial Intelligence at Ajou University, South Korea. He leads the Systems Software Lab (Paldal Hall 1004-2) and maintains active collaborations with Virginia Tech as a Visiting Scholar since August 2024. His academic journey includes a Ph.D. in Computer Science from KAIST (2016) under advisors Seungryoul Maeng and Jin-Soo Kim, and a B.S. in Computer Science from KAIST (2002). His research spans operating systems, memory management, and storage systems with focus on mobile platforms, heterogeneous architectures, and SSD technologies. Key interests include memory fragmentation control , distributed thread execution , key-value storage optimization , and resource disaggregation . His work bridges theoretical innovation with practical system implementations, particularly for mobile and datacenter environments. Kim's publication portfolio shows consistent output in top-tier venues including USENIX FAST, VLDB, ICDCS, and ASPLOS. His research demonstrates evolution from mobile memory management (2015-2017) toward distributed systems and hardware-aware software (2019-present), with recent emphasis on resource-disaggregated environments and heterogeneous-ISA computing. The 2024 Best Paper Award at USENIX FAST highlights his impact in storage systems research. Best Paper Award at USENIX FAST'24 Multiple patents including US-9588912B2 for memory control He directs significant research projects funded by ETRI, NRF, and US ONR, including current work on memory-centric computing systems (2020-2023) and disaggregated non-volatile memory systems using RDMA (2018-2020). His Systems Software Lab maintains strong industry partnerships with Samsung Electronics and NHN, with prior projects improving Android memory management and developing SSD-based storage systems for large-scale internet services.

Michael KuhnView profile

Professor

• Parallel Computing
• High-Performance Computing
• Storage Systems
• +3 more

Prof. Dr. Michael Kuhn is a Professor in the Faculty of Computer Science at Otto von Guericke University Magdeburg since 2020, leading the Parallel Computing and I/O Group. His work bridges theoretical parallel computing concepts with practical high-performance computing implementations. His academic journey includes: Bachelor's degree in Computer Science from Heidelberg University (2007) Master's degree in Computer Science from Heidelberg University (2009) Doctorate from Hamburg University (2015) with dissertation on "Dynamically Adaptable I/O Semantics for High Performance Computing" Prof. Kuhn's research tackles critical challenges in modern computing infrastructure where systems scale to millions of processor cores. He investigates fundamental improvements to storage architectures, I/O interfaces, and programming models that enable efficient data processing at exascale levels. His development of the JULEA storage framework provides dynamically adaptable solutions for high-performance computing environments, addressing the growing mismatch between computational power and data movement capabilities. As faculty public relations officer, he maintains the Faculty of Computer Science's digital presence while actively teaching courses that equip students with practical parallel programming skills. His group's work demonstrates how breaking computational problems into parallelizable components—like the matrix processing example reducing runtime to a quarter—enables scientific breakthroughs requiring massive computational resources. The Parallel Computing and I/O Group serves as a hub for advancing storage technologies and parallel processing methodologies, with applications spanning scientific computing, big data analytics, and next-generation supercomputer architectures.

Vincent WeaverView profile

Associate Professor

• Hardware Performance Counters
• Computer Architecture
• High Performance Computing
• +8 more

Vincent Weaver is an Associate Professor in the Electrical and Computer Engineering Department at the University of Maine's College of Engineering. He leads the VMW Research Group, focusing on low-level systems research including hardware performance counters, computer architecture, and operating systems. Weaver received his BS in Electrical Engineering from the University of Maryland College Park in December 2000, followed by MS (January 2009) and PhD (May 2010) degrees in Electrical and Computer Engineering from Cornell University. He joined the University of Maine faculty in July 2012 as an Assistant Professor and earned tenure and promotion to Associate Professor in September 2018. His research centers on hardware performance analysis, architectural simulation, and systems programming with emphasis on Linux kernel development and embedded systems. Weaver's work bridges theoretical computer architecture with practical systems implementation, often resulting in open-source tools that advance the field. His publications reveal a consistent focus on performance analysis techniques, code optimization, and security through low-level system understanding. Weaver maintains an active teaching schedule including courses in embedded systems, operating systems, and network engineering. He values students with strong programming skills and encourages open source contributions as part of the learning process. His research group provides hands-on experience with cutting-edge processor architectures and performance analysis tools.

• High Performance Computing
• Distributed Systems
• Deep Learning
• +4 more

Muhammad Mustafa Rafique is an Associate Professor in the Department of Computer Science at Rochester Institute of Technology's Golisano College of Computing and Information Sciences. His research specializes in optimizing large-scale computing systems, with focus areas including: High-performance computing (HPC) resource management Distributed deep learning acceleration Fault-tolerant cloud architectures GPU-accelerated checkpointing systems Serverless computing frameworks Dr. Rafique's work demonstrates consistent innovation in improving computational efficiency for containerized HPC workflows, multi-GPU scheduling, memory optimization, and distributed training pipelines. His publications frequently appear in premier IEEE/ACM conferences, reflecting contributions to systems performance engineering. While no awards or student advisees are mentioned in available materials, his research collaborations include co-authors from institutions worldwide, indicating active engagement in the high-performance computing research community. Current work explores emerging memory technologies like CXL and advanced containerization techniques for next-generation datacenters.

Myoungsoo JungView profile

Professor

• Computer Architecture
• Operating Systems
• Solid State Drives
• +6 more

Myoungsoo Jung is the KAIST Endowed Chair Professor and Full Professor at Korea Advanced Institute of Science and Technology, holding primary appointment in the School of Electrical Engineering with additional affiliations in the School of Semiconductor System Engineering, Graduate School of AI Semiconductor, Graduate School of System Architect, and Graduate School of AI. His research focuses on cutting-edge computer architecture and operating systems with specialization in memory and storage systems. Professor Jung's research interests span computer architecture, operating systems, flash memory, solid-state drives, non-volatile memory, file systems, parallel processing, and heterogeneous computing. He has pioneered work in CXL-based memory expansion, computational SSDs, and memory disaggregation technologies that are transforming modern data centers and AI infrastructure. His recent publications demonstrate significant advancements in CXL-driven architectures, computational storage, and memory systems. The research trends show increasing integration of storage and memory technologies with AI workloads, particularly in large-scale graph processing, federated learning, and billion-scale data management. His team's work frequently appears in top-tier venues including ISCA, HPCA, SOSP, and USENIX ATC. Hall of Fame, IEEE/ACM ISCA (2024) Digital Innovation Award from Minister of Science and ICT (2024) CES Innovation Award Winner, CXL-Enabled AI Accelerator (2025) Korea Innovative Startup Award, Ministry of Science and ICT (2025) Samsung Best Paper Award Winner (Grand Prize) (2022) Professor Jung has successfully advised numerous PhD students including Miryeong Kwon (recipient of KAIST Outstanding PhD Dissertation Award) and Donghyun Gouk. His CAMEL research lab has secured over $13M in funding from sources including DOE, NSF, and Korean government agencies. The lab maintains strong industry partnerships with Samsung, SK Hynix, and Panmnesia, focusing on translating research into practical systems. Current projects include CXL-based memory expansion, computational SSDs for AI acceleration, and next-generation storage architectures for hyperscale data centers.

Kawashima RyotaView profile

Associate Professor

• Network Function Virtualization
• Cloud-Native Networking
• High-Performance Computing
• +3 more

Kawashima Ryota is an Associate Professor at Chubu University in the Department of Information Engineering, Network Field. He holds a PhD in Information Science from The Graduate University for Advanced Studies (2010) and a Master's in Software Information Science from Iwate Prefectural University (2007). Prior to his academic career, he worked as an R&D Engineer at Stratosphere, Inc. and ACCESS CO., LTD. His research focuses on: High-performance cloud-native networking and NFV infrastructure optimization CPU cache efficiency and I/O parallelization in virtualized environments Transparent acceleration techniques for distributed databases and key-value stores Low-latency solutions for beyond-5G network architectures Recent publications (2020-2024) demonstrate strong emphasis on: Optimizing cloud-native network functions for terabit-class throughput Reducing virtualization overhead through hardware-aware resource allocation Developing proxy-based acceleration layers for NewSQL and distributed KVS Addressing latency/jitter challenges in next-generation networks Awards & Honors: IEEE FNWF'24 Best Paper Award (2024) IEICE ICM Research Award (2023) IEEE NFV-SDN Best Paper Award (2018) IEICE Communications Society Best Paper Award (2017) Research Leadership: Secured competitive grants including JSPS Kakenhi (¥16.9M direct funding) for terabit-class cloud networking research. Mentored award-winning students including IEEE Nagoya Section Excellent Student Award recipient Yuki Taguchi. Active in industry collaborations with Bosco Technologies on NFV efficiency.