IOWarp publications https://iowarp.ai/research/#publications Papers and posters from the IOWarp research record, newest first by year. en-us PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference https://iowarp.ai/research/#chittyvenkata2026paged https://iowarp.ai/research/#chittyvenkata2026paged Paper <p>K. T. Chitty-Venkata, J. Ye, S. Raskar, A. Kougkas, X.-H. Sun, M. Emani, V. Vishwanath, B. Nicolae</p><p>Findings of the Association for Computational Linguistics: EACL 2026, 2026</p><p><a href="https://doi.org/10.18653/v1/2026.findings-eacl.168">Read it</a></p> PKAS: Predictive KVCache-Aware Scheduling for Faster LLM and Transformer Inferences https://iowarp.ai/research/#ye2026pkas https://iowarp.ai/research/#ye2026pkas Paper <p>J. Ye, A. Maurya, K. T. Chitty-Venkata, B. Nicolae, A. Kougkas, X.-H. Sun</p><p>Proceedings of the 35th International Symposium on High-Performance Parallel and Distributed Computing (HPDC), 2026</p><p><a href="https://doi.org/10.1145/3806645.3807819">Read it</a></p> Characterizing Dataflow for I/O-Aware Scheduling in HPC Workflows https://iowarp.ai/research/#tang2026dataflow https://iowarp.ai/research/#tang2026dataflow Paper <p>M. Tang, L. Guo, A. Kougkas, X.-H. Sun, N. R. Tallent</p><p>2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2026</p><p><a href="https://doi.org/10.1109/IPDPS65963.2026.00076">Read it</a></p> AgentStage: Exploiting LLM Thinking for Data Staging in Scientific Agents https://iowarp.ai/research/#yildirim2026agentstage https://iowarp.ai/research/#yildirim2026agentstage Paper <p>I. Yildirim, X.-H. Sun, A. Kougkas</p><p>2026 IEEE International Conference on eScience (eScience), 2026</p><p><a href="https://www.escience-conference.org/2026/papers">Read it</a></p> Acropolis: A Portable, AI-Driven Semantic Search System for HPC https://iowarp.ai/research/#pawar2026acropolis https://iowarp.ai/research/#pawar2026acropolis Paper <p>R. P. Pawar, L. Logan, J. Cernuda, X.-H. Sun, A. Kougkas</p><p>2026 IEEE International Conference on eScience (eScience), 2026</p><p><a href="https://www.escience-conference.org/2026/papers">Read it</a></p> Trigger, Render, Reason: Multimodal LLM Agents for Science-Aware Scientific Simulation Monitoring https://iowarp.ai/research/#xu2026triggerrenderreason https://iowarp.ai/research/#xu2026triggerrenderreason Paper <p>H. Xu, J. Cernuda, A. Gainaru, S. Klasky, A. Kougkas, X.-H. Sun</p><p>International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2026), 2026</p><p><a href="https://grc.iit.edu/publications/xu-2026-trigger-render-reason-multimodal-llm-agents-c360/">Read it</a></p> InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis https://iowarp.ai/research/#bentham2026infinitesciencegym https://iowarp.ai/research/#bentham2026infinitesciencegym Paper <p>O. Bentham, V. Srikumar</p><p>Conference on Language Modeling (COLM 2026), 2026</p><p><a href="https://arxiv.org/abs/2604.13201">Read it</a></p> WisIO: Automated I/O Bottleneck Detection with Multi-Perspective Views for HPC Workflows https://iowarp.ai/research/#yildirim_wisio_2025 https://iowarp.ai/research/#yildirim_wisio_2025 Paper <p>I. Yildirim, H. Devarajan, A. Kougkas, X.-H. Sun, K. Mohror</p><p>ICS'25: 2025 International Conference on Supercomputing, 2025</p><p><a href="https://doi.org/10.1145/3721145.3725742">Read it</a></p> Towards an AI-driven scientific workflow https://iowarp.ai/research/#islam2025aidriven https://iowarp.ai/research/#islam2025aidriven Poster <p>S. Islam, J. Cernuda, I. Muradli, A. Kougkas, X.-H. Sun</p><p>2025 IEEE International Conference on eScience (eScience), 2025</p><p><a href="https://doi.org/10.1109/eScience65000.2025.00074">Read it</a></p> Insights into GPUDirect Data Transfer through NIXL Benchmarking https://iowarp.ai/research/#muradli2025nixl https://iowarp.ai/research/#muradli2025nixl Poster <p>I. Muradli, J. Ye, L. Logan, A. Kougkas, X.-H. Sun</p><p>2025 IEEE International Conference on eScience (eScience), 2025</p><p><a href="https://doi.org/10.1109/eScience65000.2025.00075">Read it</a></p> Jarvis: Towards a Shared, User-Friendly, and Reproducible I/O Infrastructure https://iowarp.ai/research/#cernuda2024jarvis https://iowarp.ai/research/#cernuda2024jarvis Paper <p>J. Cernuda, L. Logan, N. Lewis, S. Byna, X.-H. Sun, A. Kougkas</p><p>The International Parallel Data Systems Workshop (PDSW'24), 2024</p> Uncover the Overhead and Resource Usage for Handling KV Cache Overflow in LLM Inference https://iowarp.ai/research/#ye2024kvcache_poster https://iowarp.ai/research/#ye2024kvcache_poster Poster <p>J. Ye, B. Nicolae, A. Kougkas, X.-H. Sun</p><p>The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC'24), 2024</p> MegaMmap: Blurring the Boundary Between Memory and Storage for Data-Intensive Workloads https://iowarp.ai/research/#logan2024megammap https://iowarp.ai/research/#logan2024megammap Paper <p>L. Logan, A. Kougkas, X.-H. Sun</p><p>Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis SC, 2024</p><p><a href="https://doi.org/10.1109/SC41406.2024.00114">Read it</a></p> DFTracer: An Analysis-Friendly Data Flow Tracer for AI-Driven Workflows https://iowarp.ai/research/#devarajan2024dftracer https://iowarp.ai/research/#devarajan2024dftracer Paper <p>H. Devarajan, L. Pottier, K. Velusamy, H. Zheng, I. Yildirim, O. Kogiou, W. Yu, A. Kougkas, X.-H. Sun, J. S. Yeom, K. Mohror</p><p>Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, 2024</p><p><a href="https://dl.acm.org/doi/abs/10.1109/SC41406.2024.00023">Read it</a></p> To Derive or Not to Derive: I/O Libraries Take Charge of Derived Quantities Computation https://iowarp.ai/research/#gainaru2024derive https://iowarp.ai/research/#gainaru2024derive Paper <p>A. Gainaru, N. Podhorszki, L. Dulac, Q. Gong, S. Klasky, G. Eisenhauer, A. Kougkas, X.-H. Sun, J. Lofstead</p><p>2024 IEEE 36th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), 2024</p><p><a href="https://ieeexplore.ieee.org/document/10763877">Read it</a></p> DaYu: Optimizing Distributed Scientific Workflows by Decoding Dataflow Semantics and Dynamics https://iowarp.ai/research/#tang2024dayu https://iowarp.ai/research/#tang2024dayu Paper <p>M. Tang, J. Cernuda, J. Ye, L. Guo, N. R. Tallent, A. Kougkas, X.-H. Sun</p><p>Proceedings of the IEEE International Conference on Cluster Computing, 2024</p><p><a href="https://ieeexplore.ieee.org/document/10740817">Read it</a></p> An Evaluation of DAOS for Simulation and Deep Learning HPCWorkloads https://iowarp.ai/research/#logan2024daos https://iowarp.ai/research/#logan2024daos Paper <p>L. Logan, J. Lofstead, X.-H. Sun, A. Kougkas</p><p>Proceedings of the ACM SIGOPS Operating Systems Review, 2024</p><p><a href="https://doi.org/10.1145/3689051.3689058">Read it</a></p> Viper: A High-Performance I/O Framework for Transparently Updating, Storing, and Transferring Deep Neural Network Models https://iowarp.ai/research/#ye2024viper https://iowarp.ai/research/#ye2024viper Paper <p>J. Ye, J. Cernuda, N. Rajesh, K. Bateman, O. Yildiz, T. Peterka, A. Nigmetov, D. Morozov, X.-H. Sun, A. Kougkas, B. Nicolae</p><p>Proceedings of the 53rd International Conference on Parallel Processing, 2024</p><p><a href="https://doi.org/10.1145/3673038.3673070">Read it</a></p> HStream: A hierarchical data streaming engine for high-throughput scientific applications https://iowarp.ai/research/#cernuda2024hstream https://iowarp.ai/research/#cernuda2024hstream Paper <p>J. Cernuda, J. Ye, A. Kougkas, X.-H. Sun</p><p>Proceedings of the 53rd International Conference on Parallel Processing, 2024</p><p><a href="https://dl.acm.org/doi/abs/10.1145/3673038.3673150">Read it</a></p> TunIO: An AI-powered Framework for Optimizing HPC I/O https://iowarp.ai/research/#rajesh2024tunio https://iowarp.ai/research/#rajesh2024tunio Paper <p>N. Rajesh, K. Bateman, J. L. Bez, S. Byna, A. Kougkas, X.-H. Sun</p><p>Proceedings of the International Parallel and Distributed Processing Symposium, 2024</p><p><a href="https://ieeexplore.ieee.org/document/10579249">Read it</a></p> Data Flow Lifecycles for Optimizing Workflow Coordination https://iowarp.ai/research/#lee2023data https://iowarp.ai/research/#lee2023data Paper <p>H. Lee, L. Guo, M. Tang, J. Firoz, N. Tallent, A. Kougkas, X.-H. Sun</p><p>Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2023</p><p><a href="https://dl.acm.org/doi/abs/10.1145/3581784.3607104">Read it</a></p> IOMax: Maximizing Out-of-Core I/O Analysis Performance on HPC Systems https://iowarp.ai/research/#yildirim2023iomax https://iowarp.ai/research/#yildirim2023iomax Paper <p>I. Yildirim, H. Devarajan, A. Kougkas, X.-H. Sun, K. Mohror</p><p>Proceedings of the SC'23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, 2023</p><p><a href="https://dl.acm.org/doi/abs/10.1145/3624062.3624191">Read it</a></p> An Evaluation of DAOS for Simulation and Deep Learning HPC Workloads https://iowarp.ai/research/#logan2023evaluation https://iowarp.ai/research/#logan2023evaluation Paper <p>L. Logan, J. Lofstead, X.-H. Sun, A. Kougkas</p><p>Proceedings of the 3rd Workshop on Challenges and Opportunities of Efficient and Performant Storage Systems, 2023</p><p><a href="https://dl.acm.org/doi/abs/10.1145/3578353.3589542">Read it</a></p> LabStor: A modular and extensible platform for developing high-performance, customized I/O stacks in userspace https://iowarp.ai/research/#logan2022labstor https://iowarp.ai/research/#logan2022labstor Paper <p>L. Logan, J. Cernuda, J. Lofstead, X.-H. Sun, A. Kougkas</p><p>Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2022</p><p><a href="https://ieeexplore.ieee.org/abstract/document/10046077">Read it</a></p> Stimulus: Accelerate Data Management for Scientific AI applications in HPC https://iowarp.ai/research/#devarajan2022stimulus https://iowarp.ai/research/#devarajan2022stimulus Paper <p>H. Devarajan, A. Kougkas, H. Zheng, V. Vishwanath, X.-H. Sun</p><p>Proceedings of the 22nd IEEE International Symposium on Cluster, Cloud and Internet Computing, 2022</p><p><a href="https://ieeexplore.ieee.org/abstract/document/9826104">Read it</a></p>