Publications
Peer-reviewed papers, workshop publications, posters, and extended abstracts on parallel I/O, storage systems, and context infrastructure for scientific AI. The IOWarp and CLIO papers are listed on the IOWarp story; the earlier papers are behind Hermes, LABIOS, ChronoLog, DTIO, and DeepIO.
Bibliography downloads
2026
26 records
-
DataFlowDrs: Automating Performance Optimization of Data Flow Within HPC Workflows
IEEE Transactions on Parallel and Distributed Systems
-
Trigger, Render, Reason: Multimodal LLM Agents for Science-Aware Scientific Simulation Monitoring
International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2026)
-
GPUH5: A GPU-first I/O Library for Scientific Data
11th International Parallel Data Systems Workshop (PDSW 2026), held in conjunction with SC26
-
GDSight: Per-Operation Cross-Layer Attribution for GPUDirect Storage
11th International Parallel Data Systems Workshop (PDSW 2026), held in conjunction with SC26
-
Trigger-Gated Multimodal LLM Agents for In-situ Scientific Simulation Monitoring
11th International Parallel Data Systems Workshop (PDSW 2026), held in conjunction with SC26
-
Type-Safe, Dynamically Defined Metadata Support for Scientific Applications
11th International Parallel Data Systems Workshop (PDSW 2026), held in conjunction with SC26
-
StageOnce: Speculative Cross-Job Data Staging for LLM Agent Fleets
International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2026)
-
ToolFuse: Provenance-Aware In-Flight Coalescing of Redundant Agent Tool Calls
International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2026)
-
Extending I/O Observability to Explainability for Targeted Optimization
International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2026)
-
GNNs Beyond HBM: Compressed, Bit-Exact Feature Streaming for Out-of-Core Training
International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2026)
-
Agent Error Simulator: Fault Injection for Testing Recovery in Agentic Workflows
22nd IEEE International Conference on eScience (eScience 2026)
-
Acropolis: A Portable, AI-Driven Semantic Search System for HPC
22nd IEEE International Conference on eScience (eScience 2026)
-
Rich I/O-centric Derived Quantity Operators for Advanced In Situ Processing
22nd IEEE International Conference on eScience (eScience 2026)
-
AgentStage: Exploiting LLM Thinking for Data Staging in Scientific Agents
22nd IEEE International Conference on eScience (eScience 2026)
-
PKAS: Predictive KVCache-Aware Scheduling for Faster LLM and Transformer Inferences
35th International Symposium on High-Performance Parallel and Distributed Computing (HPDC 2026)
-
Characterizing Dataflow for I/O-Aware Scheduling in HPC Workflows
40th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2026)
-
Pre-RoPE versus Post-RoPE: Trading Per-Step Compute for KVCache Survivability
13th Greater Chicago Area Systems Research Workshop (GCASR 2026)
-
Agentic Search Efficiency for Scientific Data Discovery
13th Greater Chicago Area Systems Research Workshop (GCASR 2026)
-
The Hidden Cost of Storage Mismatches: Why Faster I/O Per Task Can Slow Down Entire Workflows
13th Greater Chicago Area Systems Research Workshop (GCASR 2026)
-
Accelerating Multi-Agent Orchestration with Speculative Dispatching
13th Greater Chicago Area Systems Research Workshop (GCASR 2026)
-
Correct Is Not I/O Efficient: Characterizing I/O Behavior of LLM Agents on Scientific Data
13th Greater Chicago Area Systems Research Workshop (GCASR 2026)
-
AgentRecall: Provenance and Rewind for Multi-Agent Workflows
13th Greater Chicago Area Systems Research Workshop (GCASR 2026)
-
ChronoLog: Distributed Shared Tiered Log Store
13th Greater Chicago Area Systems Research Workshop (GCASR 2026)
-
IO-Router: Transparent I/O Redirection for Legacy Applications
13th Greater Chicago Area Systems Research Workshop (GCASR 2026)
-
Benchmarking the Performance of Semantic Search Techniques for Agent Discovery
13th Greater Chicago Area Systems Research Workshop (GCASR 2026)
-
PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
Findings of the Association for Computational Linguistics (EACL 2026)
2025
13 records
-
Quantifying AWS S3 I/O Performance Boundaries Using the Roofline Model
The 10th International Parallel Data Systems Workshop
-
Optimizing I/O for an Exascale Implicit Kinetic Plasma Simulation using the Rabbit Storage System
REX-IO 2025 in conjunction with IEEE Cluster 2025
-
Towards an AI-driven scientific workflow
21st IEEE International Conference on eScience (eScience ’25), September 15-18, 2025
-
Insights into GPUDirect Data Transfer through NIXL Benchmarking
21st IEEE International Conference on eScience (eScience ’25), September 15-18, 2025
-
Characterizing the Behavior and Impact of KV Caching on Transformer Inferences under Concurrency
IPDPS’25: The 39th IEEE International Parallel and Distributed Processing Symposium
-
WisIO: Automated I/O Bottleneck Detection with Multi-Perspective Views for HPC Workflows
ICS ’25: 2025 International Conference on Supercomputing
-
DTIO: Data Stack for AI-driven Workflows
Proceedings of the 37th International Conference on Scalable Scientific Data Management
-
Analyzing I/O Patterns and Dataflow in HPC Workflows
The 37h International Conference on Scalable Scientific Data Management (SSDBM 2025)
-
Rich Operators for Advanced In Situ Processing
37th International Conference on Scalable Scientific Data Management (SSDBM 2025)
-
A Unified Data Stack for AI Workflows
37th International Conference on Scalable Scientific Data Management (SSDBM 2025)
-
ChronoLog & AI: A Scalable, Collaborative Solution for LLM Conversation Logging & Retrieval
37th International Conference on Scalable Scientific Data Management (SSDBM 2025)
-
Eris: A Trace-Driven Gym for AI-Powered Cache Optimization in HPC
37th International Conference on Scalable Scientific Data Management (SSDBM 2025)
-
Accelerate LLM inference with Asynchronous model offload
37th International Conference on Scalable Scientific Data Management (SSDBM 2025)
2024
11 records
-
MegaMmap: Blurring the Boundary Between Memory and Storage for Data-Intensive Workloads
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis SC
-
DFTracer: An Analysis-Friendly Data Flow Tracer for AI-Driven Workflows
Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis
-
To Derive or Not to Derive: I/O Libraries Take Charge of Derived Quantities Computation
2024 IEEE 36th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)
-
Jarvis: Towards a Shared, User-Friendly, and Reproducible, I/O Infrastructure.
The International Parallel Data Systems Workshop (PDSW’24)
-
Uncover the Overhead and Resource Usage for Handling KV Cache Overflow in LLM Inference
The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC’24)
-
DaYu: Optimizing Distributed Scientific Workflows by Decoding Dataflow Semantics and Dynamics
Proceedings of the IEEE International Conference on Cluster Computing
-
An Evaluation of DAOS for Simulation and Deep Learning HPC Workloads
ACM SIGOPS Operating Systems Review
-
Viper: A High-Performance I/O Framework for Transparently Updating, Storing, and Transferring Deep Neural Network Models
Proceedings of the 53rd International Conference on Parallel Processing
-
HStream: A hierarchical data streaming engine for high-throughput scientific applications
Proceedings of the 53rd International Conference on Parallel Processing
-
Hades: A Context-Aware Active Storage Framework for Accelerating Large-Scale Data Analysis
Proceedings of the 24th International Symposium on Cluster, Cloud and Internet Computing
-
TunIO: An AI-powered Framework for Optimizing HPC I/O
Proceedings of the International Parallel and Distributed Processing Symposium
2023
5 records
-
Data Flow Lifecycles for Optimizing Workflow Coordination
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis
-
IOMax: Maximizing Out-of-Core I/O Analysis Performance on HPC Systems
Proceedings of the SC’23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis
-
Optimizing Workflow Performance by Elucidating Semantic Data Flow
The International Conference for High Performance Computing, Networking, Storage and Analysis (SC’23)
-
Exploring the Impacts of Multiple I/O Metrics in Identifying I/O Bottlenecks
The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC’23), November 12-17, 2023
-
An Evaluation of DAOS for Simulation and Deep Learning HPC Workloads
Proceedings of the 3rd Workshop on Challenges and Opportunities of Efficient and Performant Storage Systems
2022
4 records
-
LuxIO: Intelligent Resource Provisioning and Auto-Configuration for Storage Services
Proceedings of the 29th International Conference on High Performance Computing, Data, and Analytics
-
LabStor: A modular and extensible platform for developing high-performance, customized I/O stacks in userspace
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis
-
A Multifaceted Approach to Automated I/O Bottleneck Detection for HPC Workloads
The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC’22)
-
Stimulus: Accelerate Data Management for Scientific AI applications in HPC
Proceedings of the 22nd IEEE International Symposium on Cluster, Cloud and Internet Computing
2021
8 records
-
Utilizing Persistent Memory in Parallel I/O Libraries
The 2021 International Conference for High Performance Computing, Networking, Storage, and Analysis (SC’21), November 14–19, 2021
-
Feature Reduction of Darshan Counters Using Evolutionary Algorithms
The 2021 International Conference for High Performance Computing, Networking, Storage, and Analysis (SC’21), November 14–19, 2021
-
HDF5 VOL Connector to Apache Arrow
The 2021 International Conference for High Performance Computing, Networking, Storage, and Analysis (SC’21), November 14–19, 2021
-
Performance Analysis of Containerized OrangeFS in HPC Environment
The 2021 International Conference for High Performance Computing, Networking, Storage, and Analysis (SC’21), November 14–19, 2021
-
pMEMCPY: a simple, lightweight, and portable I/O library for storing data in persistent memory
Proceedings of the International Conference on Cluster Computing
-
HFlow: A Dynamic and Elastic Multi-Layered I/O Forwarder
Proceedings of the International Conference on Cluster Computing
-
Apollo: An ML-assisted real-time storage resource observer
Proceedings of the 30th International Symposium on High-Performance Parallel and Distributed Computing
-
DLIO: A data-centric benchmark for scientific deep learning applications
Proceedings of the 21st International Symposium on Cluster, Cloud and Internet Computing
2020
10 records
-
HReplica: A Dynamic Data Replication Engine with Adaptive Compression for Multi-Tiered Storage
Proceedings of the International Conference on Big Data
-
A Dynamic Multi-Tiered Storage System for Extreme Scale Computing
The International Conference for High Performance Computing, Networking, Storage and Analysis (SC’20)
-
Quantifying the Overheads of the Modern Linux I/O Stack
The International Conference for High Performance Computing, Networking, Storage and Analysis (SC’20)
-
Characterizing and Approximating I/O Behavior of HDF5 Applications
The International Conference for High Performance Computing, Networking, Storage and Analysis (SC’20)
-
Bridging Storage Semantics Using Data Labels and Asynchronous I/O
ACM Transactions on Storage
-
ChronoLog: A Distributed Shared Tiered Log Store with Time-based Data Ordering
Proceedings of the 36th International Conference on Massive Storage Systems and Technology
-
HCL: Distributing Parallel Data Structures in Extreme Scales
Proceedings of the International Conference on Cluster Computing
-
HFetch: Hierarchical Data Prefetching for Scientific Workflows in Multi-Tiered Storage Environments
Proceedings of the International Parallel and Distributed Processing Symposium
-
HCompress: Hierarchical Data Compression for Multi-Tiered Storage Environments
Proceedings of the International Parallel and Distributed Processing Symposium
-
I/O Acceleration via Multi-Tiered Data Buffering and Prefetching
Journal of Computer Science and Technology
2019
5 records
-
NIOBE: An intelligent I/O bridging engine for complex and distributed workflows
Proceedings of the International Conference on Big Data
-
Efficient Data Eviction across Multiple Tiers of Storage
The International Conference for High Performance Computing, Networking, Storage and Analysis (SC’19)
-
HFetch: Hierarchical Data Prefetching in Multi-Tiered Storage Environments
The International Conference for High Performance Computing, Networking, Storage and Analysis (SC’19) Best Poster Nominee, Ph.D Forum
-
LABIOS: A Distributed Label-Based I/O System
Proceedings of the 28th International Symposium on High-Performance Parallel and Distributed Computing
-
An intelligent, adaptive, and flexible data compression framework
Proceedings of the 19th International Symposium on Cluster, Cloud and Grid Computing
2018
4 records
-
Vidya: Performing code-block I/O characterization for data access optimization
Proceedings of the 25th International Conference on High Performance Computing
-
Harmonia: An interference-aware dynamic I/O scheduler for shared non-volatile burst buffers
Proceedings of the International Conference on Cluster Computing
-
Hermes: a heterogeneous-aware multi-tiered distributed I/O buffering system
Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing
-
IRIS: I/O Redirection via Integrated Storage
Proceedings of the International Conference on Supercomputing
2017
4 records
-
Open Ethernet Drive: Evolution of Energy-Efficient Storage Technology
The ACM SIGHPC 8th International Workshop on Data-Intensive Computing in the Clouds (DataCloud 2017), in conjunction with SC’17, Denver, CO, USA, vol. 17
-
Enosis: Bridging the Semantic Gap between File-based and Object-based Data Models
The ACM SIGHPC 8th International Workshop on Data-Intensive Computing in the Clouds (DataCloud 2017), in conjunction with SC’17, Denver, CO, USA
-
Syndesis: Mapping Objects to Files for a Unified Data Access System
The ACM SIGHPC 8th International Workshop on Many-Task Computing on Clouds, Grids, and Supercomputers (MTAGS 2017), in conjunction with SC’17, Denver, CO, USA
-
Rethinking key–value store for parallel I/O optimization
International Journal of High Performance Computing Applications
2016
2 records
-
Towards energy efficient data management in HPC: the open ethernet drive approach
Proceedings of the 1st Joint International Workshop On Parallel Data Storage & Data Intensive Scalable Computing Systems
-
Leveraging burst buffer coordination to prevent I/O interference
Proceedings of the 12th International Conference on e-Science
2015
2 records
-
Efficient disk-to-disk sorting: a case study in the decoupled execution paradigm
Proceedings of the International Workshop on Data-Intensive Scalable Computing
-
A Heterogeneity-Aware Region-Level Data Layout Scheme for Hybrid Parallel File Systems
Proceedings of the 44th International Conference on Parallel Processing
2014
1 record
-
Rethinking Key-Value Store for Parallel I/O Optimization
Data Intensive Scalable Computing Systems Workshop (DISCS), in conjunction with ACM/IEEE SuperComputing 2014, New Orleans, LA, USA
No publication records match that filter.