exa-AMD: A Scalable Workflow for Accelerating AI-Assisted Materials Discovery and Design

2025-06-26

AI Summary

To address the long development cycles and high computational costs in functional materials discovery, this paper proposes a scalable, AI-driven materials design workflow. Methodologically, it integrates machine learning models, materials databases (e.g., Materials Project), and first-principles calculation interfaces (e.g., VASP, Quantum ESPRESSO), and—uniquely—employs the Parsl task-parallel framework to decouple workflow logic from execution configuration, enabling seamless cross-platform deployment from laptops to HPC systems. Key contributions include: (i) support for thousand-scale concurrent task scheduling; (ii) over 100× acceleration in multi-scale materials screening tasks; and (iii) significantly enhanced synergy between quantum-mechanical calculations and data-driven modeling. The workflow establishes a general-purpose, robust, and reusable technical paradigm for high-throughput materials discovery.

Technology Category

• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems
• Machine Learning: Hardware-aware ML
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

exa-AMD is a Python-based application designed to accelerate the discovery and design of functional materials by integrating AI/ML tools, materials databases, and quantum mechanical calculations into scalable, high-performance workflows. The execution model of exa-AMD relies on Parsl, a task-parallel programming library that enables a flexible execution of tasks on any computing resource from laptops to supercomputers. By using Parsl, exa-AMD is able to decouple the workflow logic from execution configuration, thereby empowering researchers to scale their workflows without having to reimplement them for each system.

Problem

• Accelerating AI-assisted materials discovery and design
• Integrating AI tools with quantum mechanical calculations
• Scaling workflows across diverse computing resources

Innovation

• Python-based AI/ML materials discovery workflow
• Parsl for scalable task-parallel execution
• Decouples workflow logic from execution configuration