To address the problems such as low resource utilization and insufficient circuit execution flexibility caused by the current static resource allocation mode of quantum cloud services, a multi-backend quantum resource virtualization scheduling framework is proposed. Firstly, a full-process scheduling system covering backend resource integration, virtual resource management, allocation, and mapping execution is constructed in the framework, which enables unified scheduling of multiple quantum backend resources. Secondly, a quantum chip virtual partitioning mechanism based on measurement and control readout lines is designed to achieve efficient abstraction of physical quantum resources into virtual resources and establish a global unified virtual resource pool. Finally, a virtual resource allocation algorithm is proposed, which comprehensively considers key attributes such as resource status and gate operation fidelity, supports dynamic merging of adjacent virtual resources, and can adapt to the execution requirements of circuits of different scales. Trials results show that under high-load scenarios, the scheme can increase quantum cloud throughput by more than 3 times, and the optimization effect of user waiting time is better than that of existing multi-programming design schemes, which effectively improves quantum resource utilization and circuit execution flexibility.
为验证虚拟资源分配层中量子虚拟资源性能评价指标的准确性,首先采用该评价指标对“Manhattan”后端的虚拟资源进行评分,其次从试验数据集选取10条量子线路,分别输入至该后端的不同虚拟量子资源中执行。试验过程中,同步统计各虚拟量子资源对应的线路执行保真度数据,本文采用试验成功率(Probability of a Successful Trial, PST)[23]进行评估,其被定义为获得预期结果的试验次数与总试验次数之比。相关结果如图3所示。图3(a)展示了虚拟资源评分情况,图3(b)展示了线路执行保真度,横坐标均为后端资源虚拟化后的编号。试验结果表明,虚拟量子资源的性能评分与线路实际执行保真度呈现显著正相关关系。性能评分较高的虚拟资源,其对应的线路执行保真度普遍处于更高水平,这一相关性验证了虚拟资源评分体系的有效性。
HERMAND, GOOGINC, LIUX Y, et al. Quantum computing for finance[J]. Nature Reviews Physics, 2023,5(8):450-465.
[2]
LUW, LUY, LIJ, et al. Quantum machine learning: classifications, challenges, and solutions[J]. Journal of Industrial Information Integration, 2024,42:No.100736.
[3]
PRESKILLJ. Quantum computing in the NISQ era and beyond[J]. Quantum, 2018,2:No.79.
[4]
HORNIBROOKJ M, COLLESSJ I, CONWAY LAMBI D, et al. Cryogenic control architecture for large-scale quantum computing[J]. Physical Review Applied, 2015,3(2):No.024010.
GOLECM, HATAYE S, GOLECM, et al. Quantum cloud computing: trends and challenges[J]. Journal of Economy and Technology, 2024,2:190-199.
[7]
SOEPARNOH, PERBANGSAA S. Cloud quantum computing concept and development: a systematic literature review[J]. Procedia Computer Science, 2021,179:944-954.
[8]
SINGHH, SACHDEVA. The quantum way of cloud computing[C]//Proceedings of the 2014 International Conference on Reliability Optimization and Information Technology. Piscataway, USA: IEEE, 2014:397-400.
[9]
BECHTOLDM. Bringing the concepts of virtualization to gate-based quantum computing[D]. Stuttgart, Germany: University of Stuttgart, 2021:22-32.
[10]
DAS P, TANNUS S, NAIRP J, et al. A case for multi-programming quantum computers[C]//Proceedings of the 52nd Annual IEEE/ACM International Symposium on Microarchitecture. New York, USA: ACM, 2019:291-303.
[11]
LIUL, DOUX L. QuCloud: a new qubit mapping mechanism for multi-programming quantum computing in cloud environment[C]//Proceedings of the 2021 IEEE International Symposium on High-Performance Computer Architecture. Piscataway, USA: IEEE, 2021:167-178.
[12]
NIUS Y, TODRI-SANIALA. How parallel circuit execution can be useful for NISQ computing?[C]//Proceedings of the 2022 Design, Automation & Test in Europe Conference & Exhibition. Piscataway, USA: IEEE, 2022:1065-1070.
[13]
NIUS Y, TODRI-SANIALA. Enabling multi-programming mechanism for quantum computing in the NISQ era[J]. Quantum, 2023,7:No.925.
[14]
LIUL, DOUX L. QuCloud+: a holistic qubit mapping scheme for single/multi-programming on 2D/3D NISQ quantum computers[J]. ACM Transactions on Architecture and Code Optimization, 2024,21(1):No.9.
[15]
TICKOOO, IYERR, ILLIKKALR, et al. Modeling virtual machine performance: challenges and approaches[J]. ACM SIGMETRICS Performance Evaluation Review, 2010,37(3):55-60.
[16]
RAWATP S, GAURS, BARTHWALV, et al. Efficient virtual machine placement in cloud computing environment using BSO-ANN based hybrid technique[J]. Alexandria Engineering Journal, 2025,110:145-152.
[17]
HIDAYATT, ALAEI ROOZBAHANIP. Strategic scheduling of a live migration virtual machine using machine learning: a review[J]. International Journal of Management Science and Application, 2025,4(1):46-54.
[18]
LIUY, YAOM Y, YANGX L, et al. Advanced virtualization in automotive operating system: technology overview and scheme design[C]//Proceedings of the 2024 IEEE International Symposium on Parallel and Distributed Processing with Applications. Piscataway, USA: IEEE, 2024:74-81.
STEINS, WIEBEN, DINGY F, et al. EQC: ensembled quantum computing for variational quantum algorithms[C]//Proceedings of the 49th Annual International Symposium on Computer Architecture. New York, USA: ACM, 2022:59-71.
[21]
JAVADI-ABHARIA, TREINISHM, KRSULICHK, et al. Quantum computing with qiskit[DB/OL]. (2024-06-19)[2026-01-18].
[22]
LIA, STEINS, KRISHNAMOORTHYS, et al. QASMBench: a low-level quantum benchmark suite for NISQ evaluation and simulation[J]. ACM Transactions on Quantum Computing, 2023,4(2):No.10.
[23]
LASTT, SAMKHARADZEN, EENDEBAKP, et al. Quantum Inspire: QuTech’s platform for co-development and collaboration in quantum computing[C]//Proceedings of Novel Patterning Technologies for Semiconductors, MEMS/NEMS and MOEMS 2020. Bellingham, USA: SPIE, 2020:49-59.
[24]
TANNUS S, QURESHIM K. Not all qubits are created equal: a case for variability-aware policies for NISQ-era quantum computers[C]//Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems. New York, USA: ACM, 2019:987-999.