pith. machine review for the scientific record. sign in

arxiv: 2604.05505 · v2 · submitted 2026-04-07 · 🪐 quant-ph · cs.OS

Recognition: no theorem link

Qurator: Scheduling Hybrid Quantum-Classical Workflows Across Heterogeneous Cloud Providers

Amr Sabry, Peter Kogge, Sinan Pehlivanoglu, Ulrik de Muelenaere

Authors on Pith no claims yet

Pith reviewed 2026-05-10 20:07 UTC · model grok-4.3

classification 🪐 quant-ph cs.OS
keywords quantum cloud schedulinghybrid workflowsfidelity optimizationqueue time reductiondynamic DAGheterogeneous providerslogarithmic success score
0
0 comments X

The pith

Qurator jointly optimizes queue time and fidelity for hybrid quantum-classical workflows across heterogeneous providers by modeling them as dynamic DAGs with a unified logarithmic success score.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces Qurator as a scheduler for mixing quantum and classical tasks on shared devices from multiple cloud providers. It represents workloads as dynamic directed acyclic graphs that encode quantum-specific rules such as entanglement links, synchronization points, and circuit cutting choices, which make ordinary schedulers unsuitable. A single logarithmic score converts each provider's distinct calibration numbers into one comparable fidelity value. Simulator runs driven by four months of real queue records show the system stays near the best possible fidelity when few tasks are present and cuts waiting times substantially when many tasks compete, while respecting a user-set fidelity limit.

Core claim

Qurator is an architecture-agnostic quantum-classical task scheduler that jointly optimizes queue time and circuit fidelity across heterogeneous providers. It models hybrid workloads as dynamic DAGs with explicit quantum semantics, including entanglement dependencies, synchronization barriers, no-cloning constraints, and circuit cutting and merging decisions. Fidelity is estimated through a unified logarithmic success score that reconciles incompatible calibration data from IBM, IonQ, IQM, Rigetti, AQT, and QuEra into a canonical set of gate error, readout fidelity, and decoherence terms.

What carries the argument

The unified logarithmic success score that converts disparate provider calibration data into one comparable fidelity value, together with the dynamic DAG model that captures quantum-specific dependencies.

Load-bearing premise

A single logarithmic success score can accurately reconcile calibration data from different providers and the historical queue simulator faithfully predicts real-world joint optimization results.

What would settle it

Running the same workloads on live queues at the listed providers and checking whether observed queue times and achieved fidelities fall within the 1 percent and 30-75 percent bounds reported by the simulator.

Figures

Figures reproduced from arXiv: 2604.05505 by Amr Sabry, Peter Kogge, Sinan Pehlivanoglu, Ulrik de Muelenaere.

Figure 1
Figure 1. Figure 1: Task DAG for a textbook quantum teleportation circuit [33] where nodes labeled C represent classical tasks and nodes labeled Q represent quantum tasks. At the top, we have initialization tasks for Alice (A) and Bob (B) followed by a pair of entangled quantum nodes. The last task for Alice performs a measurement whose result is communicated to Bob’s entangled quantum task [PITH_FULL_IMAGE:figures/full_fig_… view at source ↗
Figure 2
Figure 2. Figure 2: Example DAG transformation for merging quan￾tum tasks to execute them in parallel on a single QPU. These limitations break several classical scheduling as￾sumptions. The No-Cloning Theorem rules out work steal￾ing and task duplication: a quantum state cannot be copied, so a cross-entangled task cannot be duplicated without si￾multaneously duplicating its entangled partner, which is physically impossible. N… view at source ↗
Figure 3
Figure 3. Figure 3: Example scheduling for least busy (gold), high fi￾delity (black) strategies and Qurator (blue). n denotes number of qubits. device topology available. The scheduler must therefore op￾erate with partial information, relying on historic data and calibration metrics to fill the gaps [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: validates the estimator against hardware outcomes across GHZ benchmarks of 2–10 qubits on all six providers. IonQ AQT IQM Rigetti QuEra IBM 0 0.2 0.4 0.6 0.8 1 Provider Fidelity / success probability Actual 2q Est. 2q Actual 4q Est. 4q Actual 7q Est. 7q Actual 10q Est. 10q [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Synchronization barrier imposed by entanglement distribution. Solid nodes represent tasks known at compile time; dashed nodes are submitted dynamically at run time. 𝐸1 cannot start until all three upstream paths complete. Once 𝐸1 finishes, it distributes EPR pairs to 𝑄4, 𝑄5, and 𝑄6, which execute on separate devices and must begin as close together in time as possible before the pairs decohere. device rank… view at source ↗
Figure 6
Figure 6. Figure 6: Fidelity and queue time across various load conditions. 2 3 4 0 500 1,000 1,500 Number of synchronized entangled tasks Skew / penalty (ms) 0.7 0.8 0.9 Survival proxy 5 10 15 20 30 40 103 104 105 106 Max circuit size (qubits) Skew / violation (ms, log scale) Synchronization quality summary 0 0.5 1 Budget / survival Start skew Finish skew Survival proxy Start skew, Queue=10 Finish skew, Queue=10 Violation+1,… view at source ↗
Figure 7
Figure 7. Figure 7: Synchronized-tree benchmark summary. Left: idle-network synchronization metrics for cross-entangled task groups. Right: mean start skew, mean finish skew, and mean violation (plotted as meanViolation + 1 for log-scale visibility) on the left axis, together with budget-met rate & survival proxy on the right axis. syncMerged presents survival when circuits are merged. time for low-qubit circuits across all l… view at source ↗
Figure 8
Figure 8. Figure 8: Percentage of synchronized tasks that were merged. highest-fidelity baseline and up to 50× longer than the least busy baseline. However, the least busy baseline achieves less than 10% probability of success for these circuits, mak￾ing those executions effectively worthless. Qurator’s queue time overhead buys a 60% fidelity gain over the least busy baseline and up to a 40% gain over the highest-fidelity de￾… view at source ↗
read the original abstract

As quantum computing moves from isolated experiments toward integration with large-scale workflows, the integration of quantum devices into HPC systems has gained much interest. Quantum cloud providers expose shared devices through first-come first-serve queues where a circuit that executes in 3 seconds can spend minutes to an entire day waiting. Minimizing this overhead while maintaining execution fidelity is the central challenge of quantum cloud scheduling, and existing approaches treat the two as separate concerns. We present Qurator, an architecture-agnostic quantum-classical task scheduler that jointly optimizes queue time and circuit fidelity across heterogeneous providers. Qurator models hybrid workloads as dynamic DAGs with explicit quantum semantics, including entanglement dependencies, synchronization barriers, no-cloning constraints, and circuit cutting and merging decisions, all of which render classical scheduling techniques ineffective. Fidelity is estimated through a unified logarithmic success score that reconciles incompatible calibration data from IBM, IonQ, IQM, Rigetti, AQT, and QuEra into a canonical set of gate error, readout fidelity, and decoherence terms. We evaluate Qurator on a simulator driven by four months of real queue data using circuits from the Munich Quantum Toolkit benchmark suite. Across load conditions from 5 to 35,000 quantum tasks, Qurator stays within 1% of the highest-fidelity baseline at low load while achieving 30-75% queue time reduction at high load, at a fidelity cost bounded by a user-specified target.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper presents Qurator, an architecture-agnostic scheduler for hybrid quantum-classical workflows modeled as dynamic DAGs that incorporate quantum semantics such as entanglement, no-cloning, and circuit cutting. It jointly optimizes queue time and execution fidelity across heterogeneous providers (IBM, IonQ, IQM, Rigetti, AQT, QuEra) via a unified logarithmic success score derived from gate error, readout, and decoherence terms, and evaluates the system on a simulator replaying four months of real queue traces with Munich Quantum Toolkit benchmark circuits. The central claims are that Qurator stays within 1% of the highest-fidelity baseline at low load (5 tasks) while delivering 30-75% queue-time reduction at high load (up to 35,000 tasks), with fidelity cost bounded by a user-specified target.

Significance. If the unified fidelity model and simulation predictions are shown to hold on real hardware, the work would be significant for practical quantum-cloud integration by demonstrating that joint queue-fidelity optimization is feasible at scale without classical scheduling techniques. The use of real multi-month queue data and standard benchmarks is a positive aspect that grounds the evaluation in realistic conditions.

major comments (2)
  1. [Abstract and Evaluation] Abstract and Evaluation section: the reported 1% fidelity adherence and bounded-cost claims at high load rest on the unified logarithmic success score, yet the manuscript supplies no derivation details, error bars, sensitivity analysis, or validation of this score against actual hardware executions on the listed providers; the simulator only replays historical wait times and does not run circuits or measure success probabilities, leaving the fidelity component of the joint objective unverified.
  2. [Fidelity Model] Fidelity Model description: the assumption that a single logarithmic score can produce accurate relative fidelity estimates across incompatible calibration formats and measurement protocols (gate error, readout, decoherence) from IBM, IonQ, IQM, Rigetti, AQT, and QuEra is load-bearing for all cross-provider scheduling decisions; without cross-architecture hardware benchmarks or explicit reconciliation methodology, the claim that fidelity cost remains bounded by the user target cannot be substantiated.
minor comments (2)
  1. [Evaluation] Clarify the precise number of benchmark circuits, task counts per load point, and how the four-month queue trace was sampled to enable reproducibility.
  2. [System Model] The DAG model description would benefit from an explicit statement of which quantum constraints (entanglement, synchronization, circuit cutting) are actually enforced in the scheduler implementation versus treated as soft constraints.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We thank the referee for the constructive comments highlighting the need for greater transparency in the fidelity model and its role in the evaluation. We address each major comment below, indicating revisions where appropriate while noting limitations that cannot be fully resolved without additional hardware experiments.

read point-by-point responses

  1. Referee: [Abstract and Evaluation] Abstract and Evaluation section: the reported 1% fidelity adherence and bounded-cost claims at high load rest on the unified logarithmic success score, yet the manuscript supplies no derivation details, error bars, sensitivity analysis, or validation of this score against actual hardware executions on the listed providers; the simulator only replays historical wait times and does not run circuits or measure success probabilities, leaving the fidelity component of the joint objective unverified.

    Authors: We acknowledge that the evaluation relies on the fidelity model for estimated success probabilities rather than direct hardware measurements of circuit outcomes. The simulator replays real queue traces to drive scheduling decisions and reports model-derived fidelity scores, but does not execute circuits. In revision we will add a detailed derivation of the logarithmic success score (including the precise formulas combining gate-error, readout, and decoherence contributions) together with sensitivity analysis over calibration-parameter ranges and error bars derived from the model. We will also explicitly state the reliance on the model and the absence of end-to-end hardware success-probability validation as a limitation of the current study. revision: partial

  2. Referee: [Fidelity Model] Fidelity Model description: the assumption that a single logarithmic score can produce accurate relative fidelity estimates across incompatible calibration formats and measurement protocols (gate error, readout, decoherence) from IBM, IonQ, IQM, Rigetti, AQT, and QuEra is load-bearing for all cross-provider scheduling decisions; without cross-architecture hardware benchmarks or explicit reconciliation methodology, the claim that fidelity cost remains bounded by the user target cannot be substantiated.

    Authors: The model first normalizes each provider’s published calibration data into a common canonical set of per-gate error rates, readout fidelities, and T1/T2 decoherence times, then applies a logarithmic aggregation to obtain a relative success score. We will expand the Fidelity Model section with an explicit reconciliation subsection that documents the mapping steps for every listed provider. The user-specified fidelity target is enforced directly as a hard constraint within the joint optimization, guaranteeing that no selected schedule exceeds the allowed degradation relative to the highest-fidelity feasible option under the model. Cross-architecture hardware benchmarks would strengthen the claims but lie outside the present simulation-based scope. revision: partial

standing simulated objections not resolved
  • Empirical validation of the unified logarithmic fidelity score against measured success probabilities obtained from actual circuit executions on the six listed hardware providers

Circularity Check

0 steps flagged

No significant circularity detected in Qurator's scheduling derivation

full rationale

The paper presents Qurator as modeling hybrid workloads as dynamic DAGs with quantum semantics and estimating fidelity via a unified logarithmic success score that maps provider calibrations to canonical terms. Performance results (1% fidelity adherence at low load, 30-75% queue time reduction at high load) are obtained from a simulator replaying four months of historical queue data on Munich Quantum Toolkit circuits, with comparisons to baselines. No equations, predictions, or central claims reduce by construction to fitted parameters defined from the evaluation data, self-citations, or ansatzes smuggled via prior author work; the unification and scheduling logic are presented as independent design choices grounded in external calibrations and traces.

Axiom & Free-Parameter Ledger

1 free parameters · 2 axioms · 0 invented entities

Central claims rest on the assumption that calibration data from heterogeneous providers can be mapped to a canonical fidelity score and that the dynamic DAG model captures all relevant quantum constraints without introducing unmodeled overheads.

free parameters (1)
  • user-specified fidelity target bound
    The maximum allowed fidelity cost is set by the user and directly affects the reported trade-off; its exact mapping into the scheduler objective is not specified.
axioms (2)
  • domain assumption Logarithmic success score unifies gate error, readout fidelity, and decoherence terms across providers
    Invoked to enable cross-provider comparison; no derivation or validation details provided.
  • domain assumption Simulator driven by four months of real queue data accurately represents production behavior
    Used to generate all reported performance numbers.

pith-pipeline@v0.9.0 · 5568 in / 1520 out tokens · 96761 ms · 2026-05-10T20:07:28.543924+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

91 extracted references · 72 canonical work pages · 1 internal anchor

  1. [1]

    Mohit Agarwal and Gur Mauj Saran Srivastava. 2016. A genetic algorithm inspired task scheduling in cloud computing. In2016 Inter- national Conference on Computing, Communication and Automation (ICCCA). 364–367. doi:10.1109/CCAA.2016.7813746

    work page doi:10.1109/ccaa.2016.7813746 2016

  2. [2]

    Alhusaini, V.K

    A.H. Alhusaini, V.K. Prasanna, and C.S. Raghavendra. 1999. A unified resource scheduling framework for heterogeneous computing envi- ronments. InProceedings. Eighth Heterogeneous Computing Workshop (HCW’99). 156–165. doi:10.1109/HCW.1999.765123

    work page doi:10.1109/hcw.1999.765123 1999

  3. [3]

    Jaime Alvarado-Valiente, Javier Romero-Álvarez, Enrique Moguel, Jose García-Alonso, and Juan M. Murillo. 2024. Orchestration for quantum services: The power of load balancing across multiple service providers. Science of Computer Programming237 (2024), 103139. doi:10.1016/j. scico.2024.103139

    work page doi:10.1016/j 2024

  4. [4]

    Amazon Web Services. [n. d.]. Amazon Braket.https://aws.amazon. com/braket/

  5. [5]

    Hamid Arabnejad and Jorge G. Barbosa. 2014. List Scheduling Algorithm for Heterogeneous Systems by an Optimistic Cost Ta- ble.IEEE Trans. Parallel Distrib. Syst.25, 3 (March 2014), 682–694. doi:10.1109/TPDS.2013.57

    work page doi:10.1109/tpds.2013.57 2014

  6. [6]

    Armstrong, A

    P. Armstrong, A. Agarwal, A. Bishop, A. Charbonneau, R. Desmarais, K. Fransham, N. Hill, I. Gable, S. Gaudet, S. Goliath, R. Impey, C. Leavett- Brown, J. Ouellete, M. Paterson, C. Pritchet, D. Penfold-Brown, W. Podaima, D. Schade, and R. J. Sobie. 2010. Cloud Scheduler: a resource manager for distributed compute clouds. arXiv:1007.0050 [cs.DC]

    work page arXiv 2010

  7. [7]

    Arora, S.K

    M. Arora, S.K. Das, and R. Biswas. 2002. A de-centralized scheduling and load balancing algorithm for heterogeneous grid environments. In Proceedings. International Conference on Parallel Processing Workshop. 499–505. doi:10.1109/ICPPW.2002.1039771

    work page doi:10.1109/icppw.2002.1039771 2002

  8. [8]

    Cédric Augonnet, Samuel Thibault, Raymond Namyst, and Pierre- André Wacrenier. 2011. StarPU: a unified platform for task scheduling on heterogeneous multicore architectures.Concurr. Comput.: Pract. Exper.23, 2 (Feb. 2011), 187–198. doi:10.1002/cpe.1631 12

    work page doi:10.1002/cpe.1631 2011

  9. [9]

    Rashmi Bajaj and D.P. Agrawal. 2004. Improving scheduling of tasks in a heterogeneous environment.IEEE Transactions on Parallel and Distributed Systems15, 2 (2004), 107–118. doi:10.1109/TPDS.2004. 1264795

    work page doi:10.1109/tpds.2004 2004

  10. [10]

    Humble, Ryan Landfield, Ketan Mahesh- wari, Sarp Oral, Michael A

    Thomas Beck, Alessandro Baroni, Ryan Bennink, Gilles Buchs, Ed- uardo Antonio Coello Pérez, Markus Eisenbach, Rafael Ferreira da Silva, Muralikrishnan Gopalakrishnan Meena, Kalyan Gottiparthi, Peter Groszkowski, Travis S. Humble, Ryan Landfield, Ketan Mahesh- wari, Sarp Oral, Michael A. Sandoval, Amir Shehata, In-Saeng Suh, and Christopher Zimmer. 2024. I...

    work page doi:10.1016/j.future.2024.06.058 2024

  11. [11]

    Martin Beisel, Johanna Barzen, Marvin Bechtold, Frank Leymann, Felix Truger, and Benjamin Weder. 2023. QuantME4VQA: Modeling and Executing Variational Quantum Algorithms Using Workflows. InInternational Conference on Cloud Computing and Services Science. doi:10.5220/0011997500003488

    work page doi:10.5220/0011997500003488 2023

  12. [12]

    Martin Beisel, Johanna Barzen, Simon Garhofer, Frank Leymann, Felix Truger, Benjamin Weder, and Vladimir Yussupov. 2022. Quokka: A Ser- vice Ecosystem for Workflow-Based Execution of Variational Quantum Algorithms. InService-Oriented Computing – ICSOC 2022 Workshops: ASOCA, AI-PA, FMCIoT, WESOACS 2022, Sevilla, Spain, November 29 – December 2, 2022 Procee...

    work page doi:10.1007/978-3-031-26507-5_35 2022

  13. [13]

    Debasmita Bhoumik, Ritajit Majumdar, Amit Saha, and Susmita Sur- Kolay. 2025. Distributed Scheduling of Quantum Circuits with Noise and Time Optimization. arXiv:2309.06005 [quant-ph]

    work page arXiv 2025

  14. [14]

    Nicola Capodieci, Roberto Cavicchioli, Marko Bertogna, and Aingara Paramakuru. 2018. Deadline-Based Scheduling for GPU with Pre- emption Support. In2018 IEEE Real-Time Systems Symposium (RTSS). 119–130. doi:10.1109/RTSS.2018.00021

    work page doi:10.1109/rtss.2018.00021 2018

  15. [15]

    Splitwise: Efficient generative llm inference using phase splitting

    Ishita Chaturvedi, Bhargav Reddy Godala, Yucan Wu, Ziyang Xu, Konstantinos Iliakis, Panagiotis-Eleftherios Eleftherakis, Sotirios Xy- dis, Dimitrios Soudris, Tyler Sorensen, Simone Campanoni, Tor M. Aamodt, and David I. August. 2024. GhOST: a GPU Out-of-Order Scheduling Technique for Stall Reduction. In2024 ACM/IEEE 51st An- nual International Symposium o...

    work page doi:10.1109/isca59077.2024.00011 2024

  16. [16]

    Srikar Chundury, Amir Shehata, Seongmin Kim, Muralikrish- nan Gopalakrishnan Meena, Chao Lu, Kalyana Gottiparthi, Eduardo Antonio Coello Perez, Frank Mueller, and In-Saeng Suh. 2025. Scaling Hybrid Quantum-HPC Applications with the Quantum Framework. arXiv:2509.14470 [quant-ph]

    work page arXiv 2025

  17. [17]

    Cross, A

    Andrew Cross, Ali Javadi-Abhari, Thomas Alexander, Niel De Beau- drap, Lev S. Bishop, Steven Heidel, Colm A. Ryan, Prasahnt Sivara- jah, John Smolin, Jay M. Gambetta, and Blake R. Johnson. 2022. OpenQASM 3: A Broader and Deeper Quantum Assembly Language. ACM Transactions on Quantum Computing3, 3 (Sept. 2022), 1–50. doi:10.1145/3505636

    work page doi:10.1145/3505636 2022

  18. [18]

    Difallah, Chris Douglas, Subru Krishnan, Raghu Ramakrishnan, and Sriram Rao

    Carlo Curino, Djellel E. Difallah, Chris Douglas, Subru Krishnan, Raghu Ramakrishnan, and Sriram Rao. 2014. Reservation-based Scheduling: If You’re Late Don’t Blame Us!. InProceedings of the ACM Symposium on Cloud Computing(Seattle, WA, USA)(SOCC ’14). Association for Computing Machinery, New York, NY, USA, 1–14. doi:10.1145/2670979.2670981

    work page doi:10.1145/2670979.2670981 2014

  19. [19]

    Axel Dahlberg, Matthew Skrzypczyk, Tim Coopmans, Leon Wubben, Filip Rozpędek, Matteo Pompili, Arian Stolk, Przemysław Pawełczak, Robert Knegjens, Julio de Oliveira Filho, Ronald Hanson, and Stephanie Wehner. 2019. A link layer protocol for quantum networks. InPro- ceedings of the ACM Special Interest Group on Data Communication (SIGCOMM ’19). ACM, 159–173...

    work page doi:10.1145/3341302.3342070 2019

  20. [20]

    Ulrik de Muelenaere, Sinan Pehlivanoglu, Amr Sabry, and Peter M. Kogge. 2025. A Formalization of Measurement-Commuting Unitaries. In2025 IEEE International Conference on Quantum Computing and Engineering (QCE), Vol. 01. 439–447. doi:10.1109/QCE65121.2025.00056

    work page doi:10.1109/qce65121.2025.00056 2025

  21. [21]

    Diamos and Sudhakar Yalamanchili

    Gregory F. Diamos and Sudhakar Yalamanchili. 2008. Harmony: an execution model and runtime for heterogeneous many core systems. In Proceedings of the 17th International Symposium on High Performance Distributed Computing(Boston, MA, USA)(HPDC ’08). Association for Computing Machinery, New York, NY, USA, 197–200. doi:10.1145/ 1383422.1383447

    work page arXiv 2008

  22. [22]

    Amr Elsharkawy, Xiaorang Guo, and Martin Schulz. 2024. Integration of Quantum Accelerators into HPC: Toward a Unified Quantum Plat- form. In2024 IEEE International Conference on Quantum Computing and Engineering (QCE), Vol. 01. 774–783. doi:10.1109/QCE60285.2024.00097

    work page doi:10.1109/qce60285.2024.00097 2024

  23. [23]

    Distribution of entanglement in two-dimensional square grid network,

    Aniello Esposito, Jessica R. Jones, Sebastien Cabaniols, and David Brayford. 2023. A Hybrid Classical-Quantum HPC Workload. In2023 IEEE International Conference on Quantum Computing and Engineering (QCE), Vol. 02. 117–121. doi:10.1109/QCE57702.2023.10194

    work page doi:10.1109/qce57702.2023.10194 2023

  24. [24]

    Lionel Eyraud-Dubois, Gregory Mounie, and Denis Trystram. 2007. Analysis of Scheduling Algorithms with Reservations. In2007 IEEE International Parallel and Distributed Processing Symposium. 1–8. doi:10.1109/IPDPS.2007.370304

    work page doi:10.1109/ipdps.2007.370304 2007

  25. [25]

    Ruwen Fan, Tingxu Ren, Minhui Xie, Shiwei Gao, Jiwu Shu, and Youyou Lu. 2025. GPREEMPT: GPU preemptive scheduling made general and efficient. InProceedings of the 2025 USENIX Conference on Usenix Annual Technical Conference(Boston, MA, USA)(USENIX ATC ’25). USENIX Association, USA, Article 16, 10 pages

    2025

  26. [26]

    Nordine Feddal, Giuseppe Lipari, and Houssam-Eddine Zahaf. 2025. Towards Efficient Parallel GPU Scheduling: Interference Awareness with Schedule Abstraction. InProceedings of the 32nd International Conference on Real-Time Networks and Systems (RTNS ’24). Association for Computing Machinery, New York, NY, USA, 82–93. doi:10.1145/ 3696355.3696361

    work page arXiv 2025

  27. [27]

    Vladlen Galetsky, Nilesh Vyas, Alberto Comin, and Janis Nötzel. 2025. Feasibility of logical Bell state generation in memory assisted quantum networks.Phys. Rev. Res.7 (July 2025), 033090. Issue 3. doi:10.1103/rsrk- c7yg

    work page doi:10.1103/rsrk- 2025

  28. [28]

    Emmanouil Giortamis, Francisco Romão, Nathaniel Tornow, Dmitry Lugovoy, and Pramod Bhatotia. 2024. Orchestrating Quantum Cloud Environments with Qonductor. arXiv:2408.04312 [quant-ph]

    work page arXiv 2024

  29. [29]

    Chris Gregg, Michael Boyer, Kim Hazelwood, and Kevin Skadron

  30. [30]

    (May 2012)

    Dynamic Heterogeneous Scheduling Decisions Using Historical Runtime Data. (May 2012)

    2012

  31. [31]

    HTCondor. [n. d.].https://htcondor.org/

  32. [32]

    Menglan Hu and Bharadwaj Veeravalli. 2014. Dynamic Scheduling of Hybrid Real-Time Tasks on Clusters.IEEE Trans. Comput.63, 12 (2014), 2988–2997. doi:10.1109/TC.2013.170

    work page doi:10.1109/tc.2013.170 2014

  33. [33]

    Anger, and Chung-Yee Lee

    Jing-Jang Hwang, Yuan-Chieh Chow, Frank D. Anger, and Chung-Yee Lee. 1989. Scheduling precedence graphs in systems with interproces- sor communication times.SIAM J. Comput.18, 2 (April 1989), 244–257. doi:10.1137/0218016

    work page doi:10.1137/0218016 1989

  34. [34]

    IBM Quantum. [n. d.]. Quantum teleportation.https: //quantum.cloud.ibm.com/learning/en/courses/basics-of-quantum- information/entanglement-in-action/quantum-teleportation

  35. [35]

    Alexey Ilyushkin, Bogdan Ghit, and Dick Epema. 2015. Scheduling Workloads of Workflows with Unknown Task Runtimes. In2015 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Com- puting. 606–616. doi:10.1109/CCGrid.2015.27

    work page doi:10.1109/ccgrid.2015.27 2015

  36. [36]

    Manar Jammal, Ali Kanso, and Abdallah Shami. 2015. CHASE: Compo- nent High Availability-Aware Scheduler in Cloud Computing Environ- ment. In2015 IEEE 8th International Conference on Cloud Computing. 477–484. doi:10.1109/CLOUD.2015.70

    work page doi:10.1109/cloud.2015.70 2015

  37. [37]

    Quantum computing with Qiskit

    Ali Javadi-Abhari, Matthew Treinish, Kevin Krsulich, Christopher J. Wood, Jake Lishman, Julien Gacon, Simon Martiel, Paul D. Nation, Lev S. Bishop, Andrew W. Cross, Blake R. Johnson, and Jay M. Gam- betta. 2024. Quantum Computing with Qiskit. arXiv:2405.08810 [quant- ph] 13

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  38. [38]

    Konstantinos Karanasos, Sriram Rao, Carlo Curino, Chris Douglas, Kishore Chaliparambil, Giovanni Matteo Fumarola, Solom Heddaya, Raghu Ramakrishnan, and Sarvesh Sakalanaga. 2015. Mercury: hybrid centralized and distributed scheduling in large shared clusters. In Proceedings of the 2015 USENIX Conference on Usenix Annual Technical Conference(Santa Clara, C...

    2015

  39. [39]

    Tran, Pradipta Ghosh, Pranav Sakulkar, Bhaskar Krishnamachari, and Murali Annavaram

    Aleksandra Knezevic, Quynh Nguyen, Jason A. Tran, Pradipta Ghosh, Pranav Sakulkar, Bhaskar Krishnamachari, and Murali Annavaram

  40. [40]

    InProceedings of the Second ACM/IEEE Symposium on Edge Computing(San Jose, California)(SEC ’17)

    CIRCE - a runtime scheduler for DAG-based dispersed com- puting: demo. InProceedings of the Second ACM/IEEE Symposium on Edge Computing(San Jose, California)(SEC ’17). Association for Computing Machinery, New York, NY, USA, Article 31, 2 pages. doi:10.1145/3132211.3132451

    work page doi:10.1145/3132211.3132451

  41. [41]

    Final result of the ma- jorana demonstrator’s search for neutrinoless double-β decay in 76Ge (2023)

    V. Krutyanskiy, M. Canteri, M. Meraner, J. Bate, V. Krcmarsky, J. Schupp, N. Sangouard, and B. P. Lanyon. 2023. Telecom-Wavelength Quantum Repeater Node Based on a Trapped-Ion Processor.Phys. Rev. Lett.130 (May 2023), 213601. Issue 21. doi:10.1103/PhysRevLett.130. 213601

    work page doi:10.1103/physrevlett.130 2023

  42. [42]

    Kumar, D.M

    R. Kumar, D.M. Tullsen, P. Ranganathan, N.P. Jouppi, and K.I. Farkas

  43. [43]

    InProceedings

    Single-ISA heterogeneous multi-core architectures for multi- threaded workload performance. InProceedings. 31st Annual Interna- tional Symposium on Computer Architecture, 2004.64–75. doi:10.1109/ ISCA.2004.1310764

    work page arXiv 2004

  44. [44]

    Mehmet Can Kurt, Sriram Krishnamoorthy, Kunal Agrawal, and Gagan Agrawal. 2014. Fault-Tolerant Dynamic Task Graph Scheduling. InSC ’14: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. 719–730. doi:10.1109/ SC.2014.64

    2014

  45. [45]

    Chung-Yee Lee, Jing-Jang Hwang, Yuan-Chieh Chow, and Frank D. Anger. 1988. Multiprocessor scheduling with interprocessor commu- nication delays.Oper. Res. Lett.7, 3 (June 1988), 141–147. doi:10.1016/ 0167-6377(88)90080-6

    1988

  46. [46]

    Tingting Li and Ziming Zhao. 2024. Moirai: Optimizing Quantum Serverless Function Orchestration via Device Allocation and Circuit Deployment. In2024 IEEE International Conference on Web Services (ICWS). 707–717. doi:10.1109/ICWS62655.2024.00090

    work page doi:10.1109/icws62655.2024.00090 2024

  47. [47]

    Linderman, Jamison D

    Michael D. Linderman, Jamison D. Collins, Hong Wang, and Teresa H. Meng. 2008. Merge: a programming model for heterogeneous multi- core systems. InProceedings of the 13th International Conference on Ar- chitectural Support for Programming Languages and Operating Systems (Seattle, WA, USA)(ASPLOS XIII). Association for Computing Machin- ery, New York, NY, ...

    work page doi:10.1145/1346281.1346318 2008

  48. [48]

    Chi-Keung Luk, Sunpyo Hong, and Hyesoon Kim. 2009. Qilin: Ex- ploiting parallelism on heterogeneous multiprocessors with adaptive mapping. In2009 42nd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO). 45–55. doi:10.1145/1669112.1669121

    work page doi:10.1145/1669112.1669121 2009

  49. [49]

    Eleonora Maria Mocanu, Mihai Florea, Mugurel Ionuţ Andreica, and Nicolae Ţăpuş. 2012. Cloud Computing—Task scheduling based on ge- netic algorithms. In2012 IEEE International Systems Conference SysCon

    2012

  50. [50]

    doi:10.1109/SysCon.2012.6189509

    1–6. doi:10.1109/SysCon.2012.6189509

    work page doi:10.1109/syscon.2012.6189509 2012

  51. [51]

    Nation, Abdullah Ash Saki, Sebastian Brandhofer, Luciano Bello, Shelly Garion, Matthew Treinish, and Ali Javadi-Abhari

    Paul D. Nation, Abdullah Ash Saki, Sebastian Brandhofer, Luciano Bello, Shelly Garion, Matthew Treinish, and Ali Javadi-Abhari. 2024. Benchmarking the performance of quantum computing software. arXiv:2409.08844 [quant-ph]

    work page arXiv 2024

  52. [52]

    Kelvin K. W. Ng, Henri Maxime Demoulin, and Vincent Liu. 2023. Paella: Low-latency Model Serving with Software-defined GPU Sched- uling. InProceedings of the 29th Symposium on Operating Systems Prin- ciples(Koblenz, Germany)(SOSP ’23). Association for Computing Ma- chinery, New York, NY, USA, 595–610. doi:10.1145/3600006.3613163

    work page doi:10.1145/3600006.3613163 2023

  53. [53]

    NVIDIA. [n. d.]. CUDA.https://developer.nvidia.com/cuda

  54. [54]

    Omara and Mona M

    Fatma A. Omara and Mona M. Arafa. 2010. Genetic algorithms for task scheduling problem.J. Parallel and Distrib. Comput.70, 1 (2010), 13–22. doi:10.1016/j.jpdc.2009.09.009

    work page doi:10.1016/j.jpdc.2009.09.009 2010

  55. [55]

    OpenACC. [n. d.].https://www.openacc.org/

  56. [56]

    Aaron Orenstein and Vipin Chaudhary. 2024. QGroup: Parallel Quan- tum Job Scheduling Using Dynamic Programming. In2024 IEEE Inter- national Conference on Quantum Computing and Engineering (QCE), Vol. 01. 990–999. doi:10.1109/QCE60285.2024.00118

    work page doi:10.1109/qce60285.2024.00118 2024

  57. [57]

    Page and T.J

    A.J. Page and T.J. Naughton. 2005. Dynamic task scheduling us- ing genetic algorithms for heterogeneous distributed computing. In 19th IEEE International Parallel and Distributed Processing Symposium. doi:10.1109/IPDPS.2005.184

    work page doi:10.1109/ipdps.2005.184 2005

  58. [58]

    Badia, Eduard Ayguadé, and Jesús Labarta

    Judit Planas, Rosa M. Badia, Eduard Ayguadé, and Jesús Labarta. 2015. SSMART: smart scheduling of multi-architecture tasks on heteroge- neous systems. InProceedings of the Second Workshop on Accelerator Programming Using Directives(Austin, Texas)(W ACCPD ’15). Associa- tion for Computing Machinery, New York, NY, USA, Article 1, 11 pages. doi:10.1145/28321...

    work page doi:10.1145/2832105.2832109 2015

  59. [59]

    Nils Quetschlich, Lukas Burgholzer, and Robert Wille. 2023. MQT Bench: Benchmarking Software and Design Automation Tools for Quantum Computing.Quantum(2023). doi:10.22331/q-2023-07- 20-1062MQT Bench is available athttps://www.cda.cit.tum.de/ mqtbench/

    work page doi:10.22331/q-2023-07- 2023

  60. [60]

    Andrei Radulescu and Arjan JC Van Gemund. 2000. Fast and effective task scheduling in heterogeneous systems. InProceedings 9th het- erogeneous computing workshop (HCW 2000)(Cat. No. PR00556). IEEE, 229–238. doi:10.1109/HCW.2000.843747

    work page doi:10.1109/hcw.2000.843747 2000

  61. [61]

    Andrei Radulescu and Arjan J. C. Van Gemund. 1999. FLB: Fast Load Balancing for Distributed-Memory Machines. InProceedings of the 1999 International Conference on Parallel Processing (ICPP ’99). IEEE Computer Society, USA, 534. doi:10.1109/ICPP.1999.797442

    work page doi:10.1109/icpp.1999.797442 1999

  62. [62]

    Smith, Prakash Murali, and Fred- eric T

    Gokul Subramanian Ravi, Kaitlin N. Smith, Prakash Murali, and Fred- eric T. Chong. 2021. Adaptive Job and Resource Management for the Growing Quantum Cloud. In2021 IEEE International Conference on Quantum Computing and Engineering (QCE). IEEE, Broomfield, CO, USA, 301–312. doi:10.1109/QCE52317.2021.00047

    work page doi:10.1109/qce52317.2021.00047 2021

  63. [63]

    Ravi and Gagan Agrawal

    Vignesh T. Ravi and Gagan Agrawal. 2011. A dynamic scheduling framework for emerging heterogeneous systems. In18th International Conference on High Performance Computing. 1–10. doi:10.1109/HiPC. 2011.6152724

    work page doi:10.1109/hipc 2011

  64. [64]

    Ravi, Michela Becchi, Wei Jiang, Gagan Agrawal, and Srimat Chakradhar

    Vignesh T. Ravi, Michela Becchi, Wei Jiang, Gagan Agrawal, and Srimat Chakradhar. 2012. Scheduling Concurrent Applications on a Cluster of CPU-GPU Nodes. In2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012). 140–

    2012

  65. [65]

    doi:10.1109/CCGrid.2012.78

    work page doi:10.1109/ccgrid.2012.78 2012

  66. [66]

    Sakellariou and H

    R. Sakellariou and H. Zhao. 2004. A hybrid heuristic for DAG scheduling on heterogeneous systems. In18th International Par- allel and Distributed Processing Symposium, 2004. Proceedings.111. doi:10.1109/IPDPS.2004.1303065

    work page doi:10.1109/ipdps.2004.1303065 2004

  67. [67]

    Nishant Saurabh, Shantenu Jha, and Andre Luckow. 2023. A Con- ceptual Architecture for a Quantum-HPC Middleware. In2023 IEEE International Conference on Quantum Software (QSW). 116–127. doi:10. 1109/QSW59989.2023.00023

    work page arXiv 2023

  68. [68]

    Philipp Seitz, Amr Elsharkawy, Xiao-Ting Michelle To, and Mar- tin Schulz. 2023. Toward a Unified Hybrid HPCQC Toolchain. arXiv:2309.01661 [quant-ph]

    work page arXiv 2023

  69. [69]

    Philipp Seitz, Manuel Geiger, and Christian B. Mendl. 2024. Mul- tithreaded Parallelism for Heterogeneous Clusters of QPUs. InISC High Performance 2024 Research Paper Proceedings (39th International Conference). IEEE, 1–8. doi:10.23919/isc.2024.10528940

    work page doi:10.23919/isc.2024.10528940 2024

  70. [70]

    Seitz, M

    Philipp Seitz, Manuel Geiger, Christian Ufrecht, Axel Plinge, Christo- pher Mutschler, Daniel D. Scherer, and Christian B. Mendl. 2024. SCIM MILQ: An HPC Quantum Scheduler. In2024 IEEE International Con- ference on Quantum Computing and Engineering (QCE). IEEE, 292–298. doi:10.1109/qce60285.2024.10294

    work page doi:10.1109/qce60285.2024.10294 2024

  71. [71]

    Dipanjan Sengupta, Anshuman Goswami, Karsten Schwan, and Kr- ishna Pallavi. 2014. Scheduling Multi-tenant Cloud Workloads on 14 Accelerator-Based Systems. InSC ’14: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. 513–524. doi:10.1109/SC.2014.47

    work page doi:10.1109/sc.2014.47 2014

  72. [72]

    Jialun Shao, Junming Ma, Yan Li, Bo An, and Donggang Cao. 2019. GPU Scheduling for Short Tasks in Private Cloud. In2019 IEEE International Conference on Service-Oriented System Engineering (SOSE). 215–2155. doi:10.1109/SOSE.2019.00037

    work page doi:10.1109/sose.2019.00037 2019

  73. [73]

    Amir Shehata, Peter Groszkowski, Thomas Naughton, Muralikrishnan Gopalakrishnan Meena, Elaine Wong, Daniel Claudino, Rafael Fer- reira da Silva, and Thomas Beck. 2026. Bridging paradigms: Designing for HPC-Quantum convergence.Future Generation Computer Systems 174 (Jan. 2026), 107980. doi:10.1016/j.future.2025.107980

    work page doi:10.1016/j.future.2025.107980 2026

  74. [74]

    Clements, and James Fletcher

    Mateusz Slysz, Piotr Rydlichowski, Krzysztof Kurowski, Omar Bacar- reza, Esperanza Cuenca Gomez, Zohim Chandani, Bettina Heim, Prad- nya Khalate, William R. Clements, and James Fletcher. 2025. Hybrid Classical-Quantum Supercomputing: A demonstration of a multi-user, multi-QPU and multi-GPU environment. arXiv:2508.16297 [quant-ph]

    work page arXiv 2025

  75. [75]

    Smith, I

    W. Smith, I. Foster, and V. Taylor. 2000. Scheduling with advanced reservations. InProceedings 14th International Parallel and Distributed Processing Symposium. IPDPS 2000. 127–132. doi:10.1109/IPDPS.2000. 845974

    work page doi:10.1109/ipdps.2000 2000

  76. [76]

    Taylor, and Ian T

    Warren Smith, Valerie E. Taylor, and Ian T. Foster. 1999. Using Run- Time Predictions to Estimate Queue Wait Times and Improve Sched- uler Performance. InProceedings of the Job Scheduling Strategies for Parallel Processing (IPPS/SPDP ’99/JSSPP ’99). Springer-Verlag, Berlin, Heidelberg, 202–219. doi:10.1007/3-540-47954-6_11

    work page doi:10.1007/3-540-47954-6_11 1999

  77. [77]

    Wei Tang, Teague Tomesh, Martin Suchara, Jeffrey Larson, and Mar- garet Martonosi. 2021. CutQC: Using Small Quantum Computers for Large Quantum Circuit Evaluations. InProceedings of the 26th ACM International Conference on Architectural Support for Program- ming Languages and Operating Systems. ACM, Virtual USA, 473–486. doi:10.1145/3445814.3446758

    work page doi:10.1145/3445814.3446758 2021

  78. [78]

    Xiaoyong Tang, Kenli Li, Guiping Liao, and Renfa Li. 2010. List schedul- ing with duplication for heterogeneous computing systems.J. Parallel and Distrib. Comput.70, 4 (2010), 323–329. doi:10.1016/j.jpdc.2010.01. 003

    work page doi:10.1016/j.jpdc.2010.01 2010

  79. [79]

    The Khronos Group. [n. d.]. OpenCL.https://www.khronos.org/ opencl/

  80. [80]

    Topcuoglu, S

    H. Topcuoglu, S. Hariri, and Min-You Wu. 1999. Task scheduling algorithms for heterogeneous processors. InProceedings. Eighth Het- erogeneous Computing Workshop (HCW’99). 3–14. doi:10.1109/HCW. 1999.765092

    work page doi:10.1109/hcw 1999

Showing first 80 references.