12 papers
OpRAG: A Resource-Deterministic Runtime for GPU-Backed Multi-Stage RAG Workflows
Arup Kumar Sarker, Mills Staylor, Aymen Alsaadi +3
Agentic retrieval-augmented generation (RAG) systems combine preprocessing, embedding, retrieval, memory access, context construction, generation, and vector-index updates. Althoug…
[AAFLOW+] Stateful Operator Abstraction with Zero-Copy Distributed KV Cache Orchestration for Multi-Agent Workflows
Arup Kumar Sarker, Alexander James Halpern, Mills Staylor +5
Multi-agent LLM systems increasingly integrate retrieval, planning, and reasoning, but remain fundamentally text-centric, requiring agents to repeatedly recompute shared context th…
AAFLOW: Scalable Patterns for Agentic AI Workflows
Arup Kumar Sarker, Mills Staylor, Aymen Alsaadi +3
Agentic workflows in large language model systems integrate retrieval, reasoning, and memory, but existing frameworks suffer from scalability and reproducibility limitations due to…
RHAPSODY: Execution of Hybrid AI-HPC Workflows at Scale
Aymen Alsaadi, Mason Hooten, Mariya Goliyad +14
Hybrid AI-HPC workflows combine large-scale simulation, training, high-throughput inference, and tightly coupled, agent-driven control within a single execution campaign. These wor…
Adaptive Protein Design Protocols and Middleware
Aymen Alsaadi, Jonathan Ash, Mikhail Titov +4
Computational protein design is experiencing a transformation driven by AI/ML. However, the range of potential protein sequences and structures is astronomically vast, even for mod…
In-Transit Data Transport Strategies for Coupled AI-Simulation Workflow Patterns
Harikrishna Tummalapalli, Riccardo Balin, Christine M. Simpson +5
Coupled AI-Simulation workflows are becoming the major workloads for HPC facilities, and their increasing complexity necessitates new tools for performance analysis and prototyping…
Deep RC: A Scalable Data Engineering and Deep Learning Pipeline
Arup Kumar Sarker, Aymen Alsaadi, Alexander James Halpern +7
Significant obstacles exist in scientific domains including genetics, climate modeling, and astronomy due to the management, preprocess, and training on complicated data for deep l…
Exascale Workflow Applications and Middleware: An ExaWorks Retrospective
Aymen Alsaadi, Mihael Hategan-Marandiuc, Ketan Maheshwari +9
Exascale computers offer transformative capabilities to combine data-driven and learning-based approaches with traditional simulation applications to accelerate scientific discover…
ExaWorks Software Development Kit: A Robust and Scalable Collection of Interoperable Workflow Technologies
Matteo Turilli, Mihael Hategan-Marandiuc, Mikhail Titov +13
Scientific discovery increasingly requires executing heterogeneous scientific workflows on high-performance computing (HPC) platforms. Heterogeneous workflows contain different typ…
Hydra: Brokering Cloud and HPC Resources to Support the Execution of Heterogeneous Workloads at Scale
Aymen Alsaadi, Shantenu Jha, Matteo Turilli
Scientific discovery increasingly depends on middleware that enables the execution of heterogeneous workflows on heterogeneous platforms One of the main challenges is to design sof…
Design and Implementation of an Analysis Pipeline for Heterogeneous Data
Arup Kumar Sarker, Aymen Alsaadi, Niranda Perera +8
Managing and preparing complex data for deep learning, a prevalent approach in large-scale data science can be challenging. Data transfer for model training also presents difficult…
RADICAL-Pilot and Parsl: Executing Heterogeneous Workflows on HPC Platforms
Aymen Alsaadi, Logan Ward, Andre Merzky +4
Workflows applications are becoming increasingly important to support scientific discovery. That is leading to a proliferation of workflow management systems and, thus, to a fragme…