The 9th Workshop on Benchmarking, Performance Tuning and Optimization for Big Data and Big Models (BPOD)

Collocated at the 2026 IEEE International Conference on Big Data

One day in December 14-17, 2026, Phoenix, AZ, USA
https://bdal.umbc.edu/bpod-2026/

Description

Applications of big data or big models such as large-language models (LLMs) have become ubiquitous, with models that can have billions of parameters and are trained on terabyte (TB) to petabyte (PB) data. Users of big data and large models are often not computer scientists, yet even for experts it is difficult to optimize performance because there are many decisions to make. Compared to “small data” and “small models,” these systems not only pose scalability challenges but also make it hard to optimize and fine-tune algorithms or models. In particular, there are many parameters to tune, and algorithms originally designed for “small” data or “small” models often need further optimization to work effectively in a big data or big model environment. It is also challenging to compare the performance of different algorithms, systems, or models across a variety of tasks.

To make things more complex, users must consider not only computational running time, response time or throughput, and storage cost, but also accuracy or quality of results, monetary cost, trustworthiness, security, privacy, and sustainability. In traditional algorithms and relational databases, these issues are addressed by query optimizers and automatic tuning tools (e.g., index selection tools), and benchmarks exist to compare different systems and optimization methods. However, such tools are largely unavailable in big data or big model environments, making the problem more complicated than in traditional relational databases.


Research Topics:

The aim of this workshop is to bring researchers and practitioners together to better understand the problems of optimization and performance tuning in a big data and big model environment, to propose new approaches to address such problems, and to develop related benchmarks, tools and best practices. Topics of interest include, but not limited to:


* Theoretical and empirical performance models, cost models, and performance prediction for big data applications, big data analytics, and large models
* Optimization for machine learning and data mining in big data, including optimization and fine-tuning of big models (e.g., model fine-tuning, prompt engineering, retrieval-augmented generation (RAG))
* Benchmarking and comparative studies for big data processing platforms, big data analytics algorithms, and large models
* Monitoring, analysis, and visualization of performance in big data environments and for big data analytics applications and large models
* Workflow and process management and optimization in big data and big data analytics environments
* Performance tuning and optimization for specific platforms, applications, and models (e.g., NoSQL databases, graph processing systems, stream systems, SQL-on-Hadoop systems, and large models)
* Performance tuning and optimization for specific data sets (e.g., scientific, spatial, temporal, text, image, video, and mixed data)
* Case studies and best practices for performance tuning and optimization in big data analytics and large models
* Impact of security, privacy, and other system settings on performance of big data systems and large models
* Self-adaptive or automatic tuning tools for big data applications, big data analytics, and large models
* Optimization of big data applications and large models on High Performance Computing (HPC) and cloud environments
* Trustworthiness, uncertainty, security, privacy, and other ethical considerations in big data analytics and LLMs

Important Dates

* Oct 1, 2026: Due date for full workshop papers submission
* Nov 4, 2026: Notification of paper acceptance to authors
* Nov 25, 2026: Camera-ready deadline for accepted papers
* Dec 14-17, 2026: Workshops

Paper Submission

Authors are invited to submit full papers (maximal 10 pages) or short papers (maximal 6 pages) as per IEEE 8.5 x 11 manuscript guidelines (templates for LaTex, Word and PDF can be found at Authors are invited to submit full papers (maximal 10 pages) or short papers (maximal 6 pages) as per IEEE 8.5 x 11 manuscript guidelines (templates for LaTex, Word and PDF can be found at https://www.ieee.org/conferences/publishing/templates.html).

All papers must be submitted via https://wi-lab.com/cyberchair/2026/bigdata26/scripts/submit.php?subarea=S23&undisplay_detail=1&wh=/cyberchair/2026/bigdata26/scripts/ws_submit.php.).

At least one author of each accepted paper is required to attend the workshop and present the paper. All the accepted papers by the workshops will be included in the Proceedings of the IEEE Big Data 2026 Conference (IEEE BigData 2026) which will be published by IEEE Computer Society.


Workshop Chairs

* Zhiyuan Chen, University of Maryland Baltimore County
* Jianwu Wang, University of Maryland Baltimore County
* Feng Chen, University of Texas at Dallas
* Junqi Yin, Oak Ridge National Laboratory

PC members (tentative)

* Laurent D’Orazio, Rennes University, France
* Madhusudhan Govindaraju, Binghamton University, United States
* Vidhya Govindaraju, Atlassian, United States
* Marek Grzegorowski, University of Warsaw, Poland
* Rachit Jain, Google, United States
* Xin Huang, Towson University, United States
* Md Azim Khan, Morgan State University, United States
* Shad Kirmani, LinkedIn Corp., United States
* Soufiana Mekouar, Mohammed V University Rabat, Morocco
* Aravind Mohan, McMurry University, United States
* Seraj Mostafa, Odyssey, United States
* Mijanur Palash, Oak Ridge National Laboratory, United States
* Frank Pallas, Paris Lodron University of Salzburg, Austria
* Lauritz Thamsen, University of Glasgow, United Kingdom
* Xiangfeng Wang, East China Normal University, China