Circuit knitting is the process of partitioning large quantum circuits into smaller subcircuits such that the result of the original circuits can be deduced by only running the subcircuits. Such techniques will be crucial for near-term and early fault-tolerant quantum computers, as the limited number of qubits is likely to be a major bottleneck for demonstrating quantum advantage. One typically distinguishes between gate cuts and wire cuts when partitioning a circuit. The cost for any circuit knitting approach scales exponentially in the number of cuts. One possibility to realize a cut is via the quasiprobability simulation technique. In fact, we argue that all existing rigorous circuit knitting techniques can be understood in this framework. Furthermore, we characterize the optimal overhead for wire cuts where the subcircuits can exchange classical information or not. We show that the optimal cost for cuttingnwires without and with classical communication between the subcircuits scales asO(16n) andO(4n), respectively.
Circuit knitting is the process of partitioning large quantum circuits into smaller subcircuits such that the result of the original circuits can be deduced by only running the subcircuits. Such techniques will be crucial for near-term and early fault-tolerant quantum computers, as the limited number of qubits is likely to be a major bottleneck for demonstrating quantum advantage. One typically distinguishes between gate cuts and wire cuts when partitioning a circuit. The cost for any circuit knitting approach scales exponentially in the number of cuts. One possibility to realize a cut is via the quasiprobability simulation technique. In fact, we argue that all existing rigorous circuit knitting techniques can be understood in this framework. Furthermore, we characterize the optimal overhead for wire cuts where the subcircuits can exchange classical information or not. We show that the optimal cost for cuttingnwires without and with classical communication between the subcircuits scales asO(16n) andO(4n), respectively.
The scarcity of qubits is a major obstacle to the practical usage of quantum computers in the near future. To circumvent this problem, various circuit knitting techniques have been developed to partition large quantum circuits into subcircuits that fit on smaller devices, at the cost of a simulation overhead. In this work, we study a particular method of circuit knitting based on quasiprobability simulation of nonlocal gates with operations that act locally on the subcircuits. We investigate whether classical communication between these local quantum computers can help. We provide a positive answer by showing that for circuits containingnnonlocal CNOT gates connecting two circuit parts, the simulation overhead can be reduced fromO(9n)toO(4n)if one allows for classical information exchange. Similar improvements can be obtained for general Clifford gates and, at least in a restricted form, for other gates such as controlled rotation gates.
Circuit knitting (see, e.g., [1]) is a technique that allows circuits that are too large to run on a given quantum processing unit (QPU) to be decomposed into an equivalent series of smaller subcircuits that can run on the QPU, where the resulting measurement outcomes of the subcircuits are then classically combined via post-processing. Circuits are decomposed by cutting gates and/or wires. To obtain results to the same accuracy as those of the original problem, each cut incurs additional sampling overhead (denoted γ2) that grows exponentially with the number of cuts. It is therefore desirable to find optimal sets of cuts that minimize the sampling overhead. To this end, we present the “cut-finder” (Sec. I) module of the Circuit Knitting Toolbox (CKT) [2], which performs an automated search for LO gate and wire cuts that minimize the sampling overhead. Circuit knitting can also be used to engineer gates between distant qubits which would otherwise require a large swap overhead to implement. In Sec II, we show how this capability can be used to calculate certain expectation values on a graph state with a cylindrical topology to a better degree of accuracy than if the experiment were to be performed without circuit knitting.
Circuit knitting emerges as a promising technique to overcome the limitation of the few physical qubits in near-term quantum hardware by cutting large quantum circuits into smaller subcircuits. Recent research in this area has been primarily oriented towards reducing subcircuit sampling overhead. Unfortunately, these works neglect hardware information during circuit cutting, thus posing significant challenges to the follow on stages. In fact, direct compilation and execution of these partitioned subcircuits yields low-fidelity results, highlighting the need for a more holistic optimization strategy.
A limited number of qubits, high error rates, and limited qubit connectivity are major challenges for effective near-term quantum computations. Quantum circuit partitioning divides a quantum computation into classical postprocessing steps and a set of smaller-scale quantum computations that individually require fewer qubits, lower qubit connectivity, and typically incur less error. However, as partitioning generally increases the duration of a quantum computation exponentially in the required partitioning effort, it is crucial to select optimal partitioning points, so-called cuts, and to use optimal cut realizations. In this work, we develop the first optimal partitioning method relying on quantum circuit knitting for optimal cut realizations and an optimal selection of wire cuts and gate cuts that trades off ancilla qubit insertions for a decrease in quantum computing time. Using this combination, the developed method demonstrates a reduction in quantum computing runtime by 41% on average compared to previous quantum circuit partitioning methods. Furthermore, the qubit requirement of the evaluated quantum circuits was reduced by 40% on average for a runtime budget of one hour and a sampling frequency of 1 kHz. These results highlight the optimality gap of previous quantum circuit partitioning methods and the possible extension in the computational reach of near-term quantum computers.
Quantum circuit cutting enables the execution of large circuits on devices with a limited number of qubits by partitioning circuits into independent subcircuits. However, this introduces a sampling overhead, which grows exponentially with the number of cuts, rendering the choice of cut placements critical for practical circuit cutting. Determining optimal cut placements remains computationally challenging, particularly as circuits grow in size. Additionally, existing circuit cutting approaches typically treat gate and wire cuts independently. Those combining both cutting approaches, however, do not take advantage of joint cutting, i.e., identifying common gate groups and cutting them jointly for a reduced overhead. This work presents a unified framework that combines gate and wire cutting within a single partitioning strategy, enabling more efficient circuit decompositions. Moreover, our approach incorporates joint cutting via a novel gate grouping technique, further reducing sampling overhead. By formulating the cut placement problem as a scalable graph partitioning task, our method efficiently identifies near-optimal cut placements for large circuits, also providing diagnostic feedback on whether circuits are suitable for cutting.
Distributing quantum workloads over many Quantum Processing Units (QPUs) is a crucial step in scaling up quantum computers toward practical quantum advantage due to the limitations in size of a single QPU. In the absence of high-fidelity quantum interconnects, circuit knitting could provide a path to computing certain properties of large quantum systems on many QPUs of limited size in a distributed fashion using only classical communication. Circuit knitting partitions large quantum circuits into manageable sub-circuits, however, reconstructing observables in a straightforward manner comes at an exponential cost in sampling and classical post-processing. To mitigate the overhead this technique incurs, we introduce an Adaptive Circuit Knitting (ACK) method that finds efficient partitions of quantum circuits by discovering regions of minimal entanglement between subsystems. We simulate 1D and 2D disordered mixed-field Ising models up to 60 qubits and show that the ACK approach can reduce circuit knitting sampling overheads by up to four orders of magnitude for observables of interest. We highlight our parallel GPU-accelerated implementation and discuss the need for efficient classical simulators to enable distributed quantum algorithm development. Our techniques could enable efficient distribution of quantum simulation for both near-term and fault-tolerant architectures.