heterogeneous compute integration

This work addresses the challenges hindering the integration of quantum and high-performance computing (QHPC), including fragmented software stack interfaces, proprietary implementations, and poor ecosystem interoperability. Through a systematic survey of nine prominent QHPC software stacks, the study identifies common design patterns and core requirements, leading to the first proposal of openQSE—an open reference architecture. By explicitly defining key inter-layer interfaces for runtime abstraction, resource management, interconnect semantics, and observability, openQSE ensures deployment flexibility and backward compatibility while enabling a smooth evolution from Noisy Intermediate-Scale Quantum (NISQ) to Fault-Tolerant Quantum Computing (FTQC). This architecture establishes a standardized foundation for building a unified and scalable QHPC software ecosystem.

This work proposes the first cloud-native scheduling framework systematically designed for hybrid quantum-classical computing to address the challenge of efficiently orchestrating heterogeneous computational resources at scale. Built upon Kubernetes, Argo Workflows, and Kueue, the framework enables unified, resource-aware dynamic scheduling across CPUs, GPUs, and quantum processing units (QPUs), supporting multi-stage, reproducible, and observable hybrid workflows. The effectiveness of the framework is demonstrated through end-to-end collaborative experiments on distributed quantum circuit cutting tasks, which highlight its significant advantages in scalability, flexibility, and reproducibility.

Quantum-classical system-level integration faces challenges including high latency, weak determinism, and architectural heterogeneity. Method: This paper proposes a vertically integrated quantum-classical co-architecture: it abstracts the quantum processor as a schedulable peripheral device and designs a kernel-level Quantum Abstraction Layer (QAL) to enable low-latency, high-throughput real-time coordination and unified cross-architecture resource management. It innovatively supports tightly coupled tasks such as quantum error correction and implements a multi-architecture (x86_64/ARM64/RISC-V) quantum virtualization framework built upon QEMU, augmented with FPGA-based cycle-accurate timing simulation for full-system validation. Contribution/Results: Experiments demonstrate functional completeness and scalable performance across all three architectures. The work delivers the first extensible architecture blueprint supporting kernel-level quantum scheduling and hardware-software co-design, accompanied by an open-source simulation infrastructure for quantum-classical hybrid computing.

This study addresses the challenges of quantum-classical heterogeneous integration and collaborative scheduling in supercomputing by proposing a two-tier scheduling architecture and an open-source Slurm plugin suite. Leveraging GRES mechanisms, QRM&CI just-in-time compilation, and SPANK modules, this approach transparently integrates quantum processors as accelerators into existing HPC scheduling frameworks, enabling efficient hybrid workflow orchestration without modifying the scheduler core. Experimental evaluations on next-generation Cray platforms demonstrate negligible latency overhead, confirming both portability and practicality. Consequently, this work provides a standardized solution for managing heterogeneous quantum computing resources, facilitating seamless integration within current high-performance computing environments while maintaining system integrity and performance efficiency.

This work addresses the critical challenge of efficiently integrating quantum processing units (QPUs) into existing high-performance computing (HPC) systems to enable unified scheduling and协同 execution of classical and quantum resources. The paper proposes a Quantum-integrated High-Performance Computing (QHPC) architecture—the first HPC framework explicitly designed for quantum-classical convergence—featuring a layered design that holistically manages CPUs, GPUs, FPGAs, and QPUs. Key innovations include a user request abstraction layer offering a Slurm-like unified interface, a quantum-aware scheduling algorithm, a hybrid workflow engine, and a hierarchical execution model supported by high-speed interconnects. This architecture provides scalable heterogeneous computing support for emerging applications such as quantum chemistry, materials discovery, combinatorial optimization, and climate modeling, thereby laying the foundation for a future quantum-classical HPC ecosystem.

Addressing the challenges of heterogeneous resource scheduling, cross-paradigm data movement, and unified access to both NISQ and fault-tolerant quantum devices in deep quantum–HPC integration, this paper proposes the first hardware-agnostic quantum–supercomputing fusion software stack. Methodologically, it introduces (1) a quantum–classical unified resource management framework; (2) a hardware-abstracted programming interface and a cross-platform Quantum Platform Manager API; and (3) a quantum gateway supporting REST/gRPC, a hybrid scheduler, and a quantum-circuit co-optimization toolchain. The stack seamlessly integrates with mainstream HPC job schedulers (e.g., Slurm, PBS). Empirical evaluation on hybrid algorithms—including the variational quantum linear solver—on real supercomputing systems demonstrates significant improvements in quantum–classical resource utilization and task throughput. The design is both practically deployable and inherently scalable, establishing a foundational infrastructure for large-scale quantum–HPC convergence.

This work addresses the resource scheduling challenges faced by hybrid quantum-classical applications in heterogeneous and dynamic computing environments, where existing high-performance computing (HPC) schedulers lack application semantics awareness and runtime adaptability. To overcome these limitations, the authors propose a four-layer middleware architecture that integrates an abstract execution model for hybrid applications, a Pilot-Quantum dynamic scheduling framework, and the Q-Dreamer performance modeling toolkit. This integrated approach enables application-aware, adaptive resource management and optimized quantum circuit partitioning. The system supports coordinated scheduling across CPU, GPU, and quantum processing unit (QPU) backends and has been validated on the Perlmutter and NVIDIA DGX platforms. Experimental results demonstrate that Q-Dreamer achieves an 82% accuracy rate in predicting optimal circuit-cut configurations.

This study addresses the practical limitations of quantum computing by exploring the viability of hybrid classical-quantum architectures. Departing from the conventional view that treats such hybrid paradigms as merely transitional, this work advances the core argument that they should be established as a long-term computational norm. Methodologically, it systematically analyzes the hybrid computing software stack—encompassing middleware frameworks, API gateways, full-stack libraries, and simulators—while comprehensively surveying existing algorithms, toolkits, and cloud service provider ecosystems. The primary contribution lies in formulating development guidelines tailored for hybrid systems, delineating near-term priorities for functional evolution and robustness optimization, and establishing a future research agenda. Ultimately, this research provides systematic theoretical foundations and practical references to facilitate the engineering deployment of hybrid quantum computing.

This work addresses the challenge of meeting user quality-of-service (QoS) requirements under the constraints of noisy intermediate-scale quantum (NISQ) devices by proposing a service-oriented architecture for hybrid quantum-classical systems. It pioneers the integration of service-oriented architecture (SOA) with quantum computing, employing formal architectural style modeling and QoS-driven design space exploration to delineate architectural decision boundaries. The approach dynamically selects optimal execution strategies at both structural and behavioral levels in response to varying QoS demands. Experimental results demonstrate that the proposed method can dynamically configure the system under realistic NISQ constraints to deliver quantifiable performance guarantees aligned with user-specified QoS requirements.

This study addresses the challenge of integrating cross-platform hybrid quantum-HPC workflows by constructing a collaborative computing system comprising the Fugaku supercomputer, Quantinuum Reimei and ibm_kobe quantum processors, and the Tierkreis software framework. Through efficient classical-quantum task partitioning, the authors innovatively combine the Variational Quantum Eigensolver (VQE) and Quantum Phase Estimation (QPE) algorithms to design a multi-platform cooperative workflow. The proposed system successfully executes ground-state and excited-state energy calculations for biomolecules, validating its feasibility and accuracy on real quantum hardware. Ultimately, this work establishes a scalable hybrid architecture paradigm for large-scale quantum chemistry simulations.

This study addresses the lack of orchestration, recovery, and portability in driver scripts for hybrid quantum-classical optimization by modeling iterative decomposition-solving-aggregation loops as scientific workflows. A dedicated orchestration layer is constructed to uniformly manage task generation, data provenance, and fault recovery. The proposed workflow model incorporates termination predicates, subproblem-level recovery, and QPU-to-classical-backend failover, while integrating ADMM, hierarchical partitioning, speculative re-execution, and quantum-HPC middleware. Experiments quantify the orchestration overhead across different decomposition patterns, validate system robustness under fault injection, and perform cross-device latency analysis.