Quantum Processing Units are rapidly scaling, with current systems exceeding 100 qubits and targeting one billion operations in the near future. However, Quantum Computing as a Service platforms are facing growing pressure due to high user demand and long execution queues. This is primarily due to resource underutilization and the current execution model, which typically allows only one job per queue slot. Additionally, high costs are associated with the execution of each job. To address these limitations, this paper proposes a multi-batch quantum circuit scheduling approach aimed at increasing hardware utilization and reducing execution queues. To achieve this, different circuits are packed into various batches to be executed within a single job, where the results obtained in each batch are measured in distinct classical registers. These features allow for the reuse of previously utilized qubits in previous batches, enabling them to be used again for execution without the need to submit a new job. The approach has been validated on the 133-qubit IBM Torino processor through large-scale experiments with multiple circuits and controlled noise isolation tests. By reducing repeated queue interactions and job submission overhead, the proposed method increases execution throughput, allowing for numerous circuit executions within a single job. Under the evaluated conditions, this approach achieves significant execution cost reductions compared to traditional circuit submissions. Although the method incurs an overall absolute noise penalty, it allows packing numerous circuits into a single iteration, resulting in substantial financial savings. Furthermore, the noise level remains stable from the first to the last batch, showing no progressive degradation over time.
Quantum Processing Units are rapidly scaling, with current systems exceeding 100 qubits and targeting one billion operations in the near future. However, Quantum Computing as a Service platforms are facing growing pressure due to high user demand and long execution queues. This is primarily due to resource underutilization and the current execution model, which typically allows only one job per queue slot. Additionally, high costs are associated with the execution of each job. To address these limitations, this paper proposes a multi-batch quantum circuit scheduling approach aimed at increasing hardware utilization and reducing execution queues. To achieve this, different circuits are packed into various batches to be executed within a single job, where the results obtained in each batch are measured in distinct classical registers. These features allow for the reuse of previously utilized qubits in previous batches, enabling them to be used again for execution without the need to submit a new job. The approach has been validated on the 133-qubit IBM Torino processor through large-scale experiments with multiple circuits and controlled noise isolation tests. By reducing repeated queue interactions and job submission overhead, the proposed method increases execution throughput, allowing for numerous circuit executions within a single job. Under the evaluated conditions, this approach achieves significant execution cost reductions compared to traditional circuit submissions. Although the method incurs an overall absolute noise penalty, it allows packing numerous circuits into a single iteration, resulting in substantial financial savings. Furthermore, the noise level remains stable from the first to the last batch, showing no progressive degradation over time.
Current quantum computing platforms often exhibit suboptimal hardware utilization, with most circuits engaging only a fraction of the available qubits. This inefficiency inflates execution costs, extends queueing times, and hampers scalability, particularly in shared, cloud-based environments. This paper introduces a service-oriented architecture for the parallel execution of quantum circuits that jointly schedules and executes logically independent circuits within a single task. The service supports multiple configurable scheduling policies, based on criteria such as circuit depth, number of qubits, and number of shots, and ensures logical separation of circuits with accurate result demultiplexing. Extensive validation on real quantum hardware, including IBM and AWS processors, demonstrates significant improvements: task submission reductions of up to 95%, cost savings of up to 93%, and fidelity levels exceeding 97% even under high utilization. This solution offers a reusable, extensible approach that enhances resource efficiency and performance in Quantum Computing as a Service platforms.
Quantum computing holds significant potential across various fields such as cybersecurity, finance, and health-care, among many others. However, we currently face multiple limitations such as the low availability of computers, the underutilization of available qubits, and the ever-increasing number of users, which results in prolonged waiting times. This, combined with the cost of executions, limits access to quantum computing. To address these challenges, we propose a scheduling process to optimize task execution on quantum computers. The proposed scheduling process unifies multiple circuits to enhance the efficiency of resource utilization in quantum machines. This approach allows for better use of available qubits and reduces the associated execution costs. We validate the proposed method employing various quantum algorithms by systematically examining the scheduling process through a comparative case study between two quantum service providers: IBM Quantum and Amazon Braket. This validation has shown that the scheduling process does not generate a significant impact on the results, ensuring similar results to single circuit executions with a fraction of the cost.
Quantum computing has gained considerable attention, especially after the arrival of the Noisy Intermediate-Scale Quantum (NISQ) era. Quantum processors and cloud services have been made worldwide increasingly available. Unfortunately, jobs on existing quantum processors are often executed in series, and the workload could be heavy to the processor. Typically, one has to wait for hours or even longer to obtain the result of a single quantum job on public quantum cloud due to long queue time. In fact, as the scale grows, the qubit utilization rate of the serial execution mode will further diminish, causing the waste of quantum resources. In this paper, to our best knowledge for the first time, the Quantum Job Scheduling Problem (QJSP) is formulated and introduced, and we accordingly aim to improve the utility efficiency of quantum resources. Specifically, a noise-aware quantum job scheduler (NAQJS) concerning the circuit width, number of measurement shots, and submission time of quantum jobs is proposed to reduce the execution latency. We conduct extensive experiments on a simulated Qiskit noise model, as well as on the Xiaohong (from QuantumCTek) superconducting quantum processor. Numerical results show the effectiveness in both the QPU time and turnaround time.
Currently, quantum processors offered by quantum service providers are significantly underutilized, resulting in high execution costs and limited scalability. Various approaches have explored parallelization and circuit scheduling techniques to improve resource utilization. While these methods can significantly reduce both cost and execution times, they often have an impact on the results' noise. Addressing this challenge, this emerging study proposes a technique called Quantum Island Mapping, which enables the execution of multiple quantum circuits by separating them into “islands” within the qubit topology of a processor. The goal is to schedule multiple circuits into a single task to reduce execution costs and queuing, while maintaining a controlled separation of qubits between circuits to minimize interferences. To achieve this, separation distance parameters are defined, specifying the minimum number of qubits between different islands. This allows for configurations ranging from zero separation (maximum processor utilization) to maximum separation (single-circuit execution). The technique has been validated through experiments on a real quantum computer using well-known quantum algorithms, achieving optimal results.
The current execution model of quantum computers, based on serialized task processing, leads to inefficient resource utilization and increased waiting times. This inefficiency persists even as the demand for quantum computing grows. To address this, an automated scheduling approach is proposed through the AutoScheduler library, which replicates quantum circuits to fully occupy the available qubits in a quantum processor. This strategy reduces the number of required shots per execution while optimizing hardware usage. Experimental validation on IBM Quantum and Amazon Braket platforms demonstrates that autoscheduling achieves substantial reductions in execution time and cost, with minimal impact on result fidelity despite inherent quantum noise. These findings suggest that circuit autoscheduling is a viable method for improving the scalability and efficiency of quantum computing in the NISQ era.
The rapid expansion of quantum cloud services has led to long job queues due to single-tenant execution models that underutilize hardware resources. Quantum multi-programming (QMP) mitigates this by executing multiple circuits in parallel on a single device, but existing methods target superconducting systems with limited connectivity, high crosstalk, and lower gate fidelity. Trapped-ion architectures, with all-to-all connectivity, long coherence times, and high-fidelity mid-circuit measurement properties, presents itself as a more suitable platform for scalable QMP. We present CircPack, a hardware-aware circuit packing framework designed for modular trapped-ion devices based on the Quantum Charge-Coupled Device (QCCD) architecture. CircPack formulates static circuit scheduling as a two-dimensional packing problem with hardware-specific shuttling constraints. Compared to superconducting-based QMP approaches, CircPack achieves up to 70.72% better fidelity, 62.67% higher utilization, and 32.80% improved layer reduction. This framework is also capable of scalable, balanced scheduling across a cluster of independent QCCD modules, highlighting trapped-ion systems' potential in improving the throughput of quantum cloud computing in the near future.