Quantum-HPC Software Stacks and the openQSE Reference Architecture: A Survey

· Source: cs.SE updates on arXiv.org · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure · Depth: Expert, extended

Summary

Quantum resources are increasingly integrated into high-performance computing (HPC) and cloud environments, but quantum high-performance computing (QHPC) software stacks remain isolated and often proprietary. This paper analyzes nine production QHPC stacks, including those from AWS, IBM, IonQ, and Xanadu, identifying common design patterns and emerging requirements across deployment models, application interaction, SDK support, and fault-tolerant operation readiness. The survey exposes consistent needs in runtime abstraction, resource management, interconnect semantics, and observability. Based on these findings, the open quantum-HPC software ecosystem (openQSE) reference architecture is proposed. openQSE defines layer boundaries for interoperability and deployment flexibility, supporting both current noisy intermediate-scale quantum (NISQ) workloads and future fault-tolerant quantum computing (FTQC) systems without changes to upper-layer application interfaces.

Key takeaway

For AI Architects and MLOps Engineers integrating quantum resources, recognize the current fragmentation in QHPC software stacks. You should prioritize adopting vendor-neutral interfaces like QDMI and QRMI to ensure portability and reduce maintenance costs. Consider the openQSE reference architecture to guide your system design, enabling seamless integration of NISQ and future FTQC systems. This approach will future-proof your quantum-HPC deployments.

Key insights

QHPC software stacks are fragmented, necessitating a unified reference architecture like openQSE for interoperability and future-proofing.

Principles

Method

The openQSE architecture proposes five logical parts: HPC control plane, HPC/classical compute nodes, quantum access nodes, quantum resources, and shared infrastructure. It defines interfaces like QRI and QHPC-Interconnect API.

In practice

Topics

Code references

Best for: AI Scientist, Research Scientist, AI Architect, AI Engineer, MLOps Engineer

Related on AIssential

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by cs.SE updates on arXiv.org.