Sidharth Kumar
Assistant professor, Computer Science
*Fully-funded Ph.D. positions open*
About me
I am an assistant professor at the Department of Computer science at UIC. My research lies at the intersection of high-performance computing (HPC) and Data visualization. More broadly, I work on problems in parallel I/O, big data processing, scalable algorithms, scientific visualiaztion, GPUs & performance modeling. I completed my Ph.D. in Computing at the SCI Institute at the University of Utah, advised by Valerio Pascucci.
As an undergraduate at DAIICT, I was fascinated by computer graphics, ultimately leading me to join The University of Utah. While at the U, I spent a summer at Argonne National Lab, where I was exposed to the world of supercomputing. I was thrilled by the idea of using supercomputers to solve computationally massive problems. Ever since, I have worked at the intersection of HPC, analytics and visualization, helping domain scientists extract knowledge from massive amounts of complex data.
Latest News
March 2024: Paper Configurable Algorithms for All-to-all Collectives
accepted at ISC 2024.
January 2024: Paper Bruck Algorithm Performance Analysis for Multi-GPU All-to-All Communication accepted at HPC Asia 2024.
October 2023: Paper titled Speculative progressive raycasting for memory constrained isosurface visualization of massive volumes received the best paper award at LDAV 2023.
October 2023: Served on the program committee (PC) of 38th IEEE International Parallel & Distributed Processing Symposium (IPDPS).
November 2023: Poster Two-Phase IO Enabling Large-Scale Performance Introspection was the best poster award finalist at SC 2023.
September 2023: Paper Communication-Avoiding Recursive Aggregation accepted at IEEE Cluster 2024.
July 2023: Paper Towards iterated relational algebra on the GPU accepted at USENIX ATC 2023.
October 2024: Paper Scalable, interactive and hierarchical visualization of virus taxonomic data accepted at workshop on Visual Analytics in Healthcare 2023.
August 2023: Moved to Department of Computer science at University of Illinois at Chicago from University of Alabama at birmingham.
June 2023: Paper titled The robustness of persistent homology of brain networks to data acquisition‐related non‐neural variability in resting state fMRI accepted at Human Brain Mapping (2023).
July 2023: Served on the program committee (PC) of International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2023).
January 2024: Paper Bruck Algorithm Performance Analysis for Multi-GPU All-to-All Communication accepted at HPC Asia 2024.
October 2023: Paper titled Speculative progressive raycasting for memory constrained isosurface visualization of massive volumes received the best paper award at LDAV 2023.
October 2023: Served on the program committee (PC) of 38th IEEE International Parallel & Distributed Processing Symposium (IPDPS).
November 2023: Poster Two-Phase IO Enabling Large-Scale Performance Introspection was the best poster award finalist at SC 2023.
September 2023: Paper Communication-Avoiding Recursive Aggregation accepted at IEEE Cluster 2024.
July 2023: Paper Towards iterated relational algebra on the GPU accepted at USENIX ATC 2023.
October 2024: Paper Scalable, interactive and hierarchical visualization of virus taxonomic data accepted at workshop on Visual Analytics in Healthcare 2023.
August 2023: Moved to Department of Computer science at University of Illinois at Chicago from University of Alabama at birmingham.
June 2023: Paper titled The robustness of persistent homology of brain networks to data acquisition‐related non‐neural variability in resting state fMRI accepted at Human Brain Mapping (2023).
July 2023: Served on the program committee (PC) of International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2023).
Research Projects
Data management at exascale
The project aims to develop a scalable and extensible I/O runtime and tools for the next-generation adaptive data layouts that inherently imbibe compression and progressive data access, advancing the state of art in the field of high-performance data management. The work will lay the foundation for end-to-end data management solutions catering to the challenging needs of the simulation-analysis pipeline, accelerating science at exascale.
MPI, Collectives
Enabling effective data transfer among components, such as memory to CPU, between cores, and from CPU to GPU, is crucial for achieving optimal performance in exascale systems. MPI Collectives that require simultaneous data exchanges among all processes imposes additional strain on these systems. The project aims to tackle this challenge by developing novel algorithms to improve the performance of collective functions. As an example, we are exploring low-level application-agnostic algorithmic innovations to generalize the logarithmic time Bruck algorithm to support non-uniform all-to-all workloads.
GPU accelerated visualization for the WEB
The project aims to provide a software stack for interactive web-based scientific data visualization and analysis leveraging the computational capabilities of GPUs. We are developing the building blocks necessary to advance analysis and visualization-specific applications, and also introduce necessary algorithmic innovations to overcome the limitations of memory constrained environments of the web browsers. In particular, we are leveraging WebGPU to enable low-level control over the GPU.
Artificial Intelligence (AI) at Scale
The project investigates full-stack implementation methodologies for expressive programming systems that effectively bridge the gap between human-level specification and high-performance implementation of complex reasoning tasks at scale. Declarative languages permit a programmer to provide high-level rules and declarations that define some sought-after solution as a latent implication to be materialized automatically by the computer. The project aims to scale this vision of high-performance declarative reasoning both to structured, higher-order, formulations and to next generation of supercomputers.
Topology driven analytics
The project aims to unify the study of mental illness across sites (and locations) by developing a topology driven analysis (TDA) cyberinfrastructure for weighted brain networks (FCNs). Topological data analysis (TDA) can extract the underlying shape (pattern) from a network, that can be used the then used in a statistical inferencing workflow to compare and classify brain networks effectively. The topology-based analysis and visualization framework will not only enable the study of fMRI data but will also make it possible to have a centralized curation of datasets.Awards
Best Research Paper Award, Winner, LDAV 2023
Speculative Progressive Raycasting for Memory Constrained Isosurface Visualization of Massive Volumes
Best Research Poster, Finalist, SC 2023
Two-Phase IO Enabling Large-Scale Performance Introspection
Best Research Poster Award (SRS), HiPC 2021
Parallel Implementations of Arithmetic Encoding on Shared Memory Systems
Hans Meuer Best Research Paper Award, ISC 2020
Load-balancing Parallel Relational Algebra
Best Research Paper Award, HiPC 2019
Distributed Relational Algebra at ScaleResearch grants
Directors Discretionary (DD) award, ANL, 2019-current
Distributed Relational AlgebraRole: Principal Investigator, UIC, 5+ million compute hours
Selected Publications
Configurable Algorithms for All-to-all Collectives
Ke Fan, Steve Petruzza, Thomas Gilray, Sidharth KumarThe International Supercomputing Conference (ISC 2024)
Acceptance rate: 29% (24/83)
Paper
Bruck Algorithm Performance Analysis for Multi-GPU All-to-All Communication
Andres Sewell, Ke Fan, Ahmedur Rahman Shovon, Landon Dyken, Sidharth Kumar, Steve PetruzzaHigh Performance Computing in Asia-Pacific Region (HPC Asia 2024)
Paper
The robustness of persistent homology of brain networks to data acquisition-related non-neural variability in resting state fMRI
Sidharth Kumar, Ahmedur Rahman Shovon, Gopikrishna Deshpande.In Human Brain Mapping (HBM 2023)
Paper
Towards iterated relational algebra on the GPU.
Ahmedur Rahman Shovon, Thomas Gilray, Kristopher Micinski, Sidharth Kumar.2023 USENIX Annual Technical Conference (USENIX ATC 2023)
Paper
Using Digital phenotyping to understand health-related outcomes: A scoping review.
Kyungmi Lee, Tim Cheongho Lee, Maria Yefimova, Sidharth Kumar, Frank Puga, Andres Azuero, Arif Kamal, Marie A Bakitas, Alexi A Wright, George Demiris, Christine S Ritchie, Carolyn EZ Pickering, J Nicholas Dionne-Odom.International Journal of Medical Informatics, Elsevier 2022
Paper
UALCAN: An update to the integrated cancer data analysis platform.
Darshan Shimoga Chandrashekar, Santhosh Karthikeyan, Praveen Korla, Ahmedur Rahman Shovon, Mohammad Athar, George Netto, Sidharth Kumar, Upender Manne, Chad Crieghton, Sooryanarayana Varambally.Neoplasia 25 (2022): 18-27
Paper
Scalable, interactive and hierarchical visualization of virus taxonomic data.
Kashyap Balakavi, Rushitha janga, Ahmedur Rahman Shovom, Don Dempsey, Elliot Lefkowitz, Sidharth Kumar.Workshop on Visual Analytics in Healthcare, co-located with IEEE Vis (VAHC 2023).
Paper
Communication-Avoiding Recursive Aggregation.
Yihao Sun, Sidharth Kumar, Thomas Gilray, Kristopher Micinski.IEEE International Conference on Cluster Computing (Cluster 2022).
Paper
Speculative Progressive Raycasting for Memory Constrained Isosurface Visualization of Massive Volumes.
Will Usher, Landon Dyken, Sidharth Kumar.The 13th IEEE Symposium on Large Data Analysis and Visualization. (LDAV 2023).
Paper
Optimizing the Bruck Algorithm for Non-uniform All-to-all Communication.
Ke Fan, Thomas Gilray, Valerio Pascucci, Xuan Huang, Kristopher Micinski Sidharth Kumar.International Symposium on High-Performance Parallel and Distributed Computing. (HPDC 2022).
Paper
GraphWaGu: GPU Powered Large Scale Graph Layout Computation and Rendering for the Web.
Landon Dyken, Pravin Poudel, Will Usher, Steve Petruzza, Jake Y. Chen, Sidharth Kumar.Eurographics Symposium on Parallel Graphics and Visualization (EGPGV 2022)
Paper
Load-balancing Parallel I/O of Compressed Hierarchical Layouts.
Ke Fan, Duong Hoang, Steve Petruzza, Thomas Gilray, Valerio Pascucci, Sidharth Kumar.IEEE Conference On High Performance Computing, Data, and Analytics (HiPC 2022)
Paper
An empirical investigation of OpenMP based implementation of Simplex Algorithm.
Arkaprabha Banerjee, Pratvi Shah , Shivani Nandani , Shantanu Tyagi , Sidharth Kumar , and Bhaskar Chaudhury.International Workshop on OpenMP (IWOMP 2021)
Paper
Compiling Data-Parallel Datalog.
Thomas Gilray, Sidharth Kumar, Kristopher Micinski.International Conference on Compiler Construction (CC 2021)
Paper
Adaptive Spatially Aware I/O for Multiresolution Particle Data Layouts.
Will Usher, Xuan Huang , Steve Petruzza, Sidharth Kumar, Stuart R. Slattery, Sam T. Reeve, Feng Wang, Chris R. Johnson and Valerio Pascucci.International Parallel and Distributed Processing Symposium (IPDPS 2021)
Paper
Load-balancing Parallel Relational Algebra.
Sidharth Kumar, Thomas Gilray.The International Supercomputing Conference (ISC 2020)
Paper
Distributed Relational Algebra at Scale.
Sidharth Kumar, Thomas Gilray.IEEE Conference On High Performance Computing, Data, and Analytics (HiPC 2019)
Paper
Spatially-aware Parallel I/O for Particle Data.
Sidharth Kumar, Steve Petruzza, Will Usher, Valerio Pascucci.ACM International Conference on Parallel Processing (ICPP 2019)
Paper
VisIt-OSPRay: Toward an Exascale Volume Visualization System.
Qi Wu, Will Usher, Steve Petruzza, Sidharth Kumar , Feng Wang, Ingo Wald, Valerio Pascucci and Charles D. Hansen.Eurographics Symposium on Parallel Graphics and Visualization (EGPGV 2018)
Paper
Scalable Data Management of the Uintah Simulation Framework for Next-Generation Engineering Problems with Radiation.
Sidharth Kumar, Alan Humphrey, Will Usher, Steve Petruzza, Brad Peterson, John A. Schmidt, Derek Harris, Ben Isaac, Jeremy Thornock, Todd Harman, Valerio Pascucci, Martin Berzins.Supercomputing Asia (SCA 2018)
Paper
Reducing network congestion and synchronization overhead during aggregation of hierarchical data.
Sidharth Kumar, Duong Hoang, Steve Petruzza, John Edwards, Valerio Pascucci.IEEE Conference On High Performance Computing, Data, and Analytics. (HiPC 2017)
Paper
Evaluation of In-Situ Analysis Strategies at Scale for Power Efficiency and Scalability.
Aaditya Landge, Ivan Rodero, Sidharth Kumar, Manish Parasar, Valerio Pascucci, Peer-Timo Bremer.IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid 2016)
Paper
Efficient I/O and storage of adaptive resolution data.
Sidharth Kumar, John Edwards, Peer-Timo Bremer, Aaron Knoll, Cameron Christensen, Venkatram Vishwanath, Phil Carns, John A. Schmidt, Valerio Pascucci.IEEE Conference On High Performance Computing Networking, Storage And Analysis (SC 2014)
Paper
Fast multi-resolution reads of massive simulation datasets.
Sidharth Kumar, Cameron Christensen, John. A Schmidt, Peer-Timo Bremer, Eric Brugger, Venkatram Vishwanath, Philip Carns, Giorgio Scorzelli, Hemanth Kolla, Ray Grout, Jacqueline Chen, and Valerio Pascucci.The International Supercomputing Conference (ISC 2014)
Paper
Characterization and modeling of pidx parallel I/O for performance optimization.
Sidharth Kumar, Avishek Saha, Venkatram Vishwanath, Philip Carns, John A Schmidt, Giorgio Scorzelli, Hemanth Kolla, Ray Grout, Robert Latham, Robert Ross, Michael E Papka, Jacqueline Chen, Valerio Pascucci.IEEE High Performance Computing Networking, Storage And Analysis. (SC 2013)
Paper
Efficient data restructuring and aggregation for I/O acceleration in PIDX.
Sidharth Kumar, Venkatram Vishwanath, Phil Carns, Joshua A. Levine, Robert Latham, Giorgio Scorzelli, Robert Ross, Hemanth Kolla, Ray Grout, Jackie Chen.IEEE High Performance Computing Networking, Storage And Analysis. (SC 2012)
Paper
PIDX: efficient parallel I/O for multiresolution multi-dimensional scientific datasets.
Sidharth Kumar, Venkatram Vishwanath, Phil Carns, Brian Summa, Giorgio Scorzelli, Valerio Pascucci, Robert Ross, Jackie Chen, Hemanth Kolla.Supercomputing Asia (Cluster 2011)
Paper
Courses Taught
Database Systems
Advanced algorithms
Data visualiaztion
Algorithms and data structures
Service
- IEEE International Parallel and Distributed Processing Symposium (IPDPS 2023), Technical program committee member
- ACM/IEEE Supercomputing Conference (SC 2023), technical program committee member
- International Supercomputing Conference (ISC 2023), workshops committee member
- International Supercomputing Conference (ISC 2023), technical program committee member
- IEEE International Parallel and Distributed Processing Symposium (IPDPS 2022), PC Chairs Team
- IEEE International Conference on high-performance Computing, data, and analytics (HiPC), technical program committee member
- ACM/IEEE Supercomputing Conference (SC 2022), technical program committee member
- ACM/IEEE Supercomputing Conference (SC 2022), tutorials committee member
- EuroMPI/USA 2022, technical program committee member
- IEEE International Conference on high-performance computing, data, and analytics (HiPC), technical program committee member
- ACM/IEEE Supercomputing Conference (SC 2021), tutorials committee member
- IEEE International Conference on high-performance computing, data, and analytics (HiPC), technical program committee member
- International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP 2019), technical program committee member
- International Parallel Data Systems Workshop (PDSW 2019), technical program committee member
© Sidharth Kumar