Modular integration has emerged as the main pathway for scaling superconducting quantum processing units (QPUs) beyond the constraints of fabrication yield and physical footprint. Currently, two primary strategies lead this effort. Mirroring the "Scaling Up" and "Scaling Out" approaches in GPU architectures and AI infrastructures, these are: chiplet-based scaling, which preserves dense connectivity and high gate fidelity at the expense of engineering complexity, and distributed architectures, which decouple system scaling from monolithic QPU advancements at the expense of sparser connectivity and lower interconnect quality. To evaluate these approaches, we introduce a quantitative stress test measuring the execution cost of a dense workload of random logical entangling operations using a surface code scheme. Using a dedicated compiler, we compute the space-time cost as the number of network nodes increases, analysing this scaling behaviour across various surface code distances, Bell-state fidelities, and Bell-pair generation times. We find that distributed architectures incur an up to exponential space-time performance penalty compared to an effectively monolithic architecture across all simulations. Our results also show that as the network grows, this penalty manifests in two distinct scaling regimes: a noise-dominated regime constrained by insufficient Bell-state fidelity and generation rates, and a connectivity-dominated regime bottlenecked by lattice-surgery routing congestion.
Modular integration has emerged as the main pathway for scaling superconducting quantum processing units (QPUs) beyond the constraints of fabrication yield and physical footprint. Currently, two primary strategies lead this effort. Mirroring the "Scaling Up" and "Scaling Out" approaches in GPU architectures and AI infrastructures, these are: chiplet-based scaling, which preserves dense connectivity and high gate fidelity at the expense of engineering complexity, and distributed architectures, which decouple system scaling from monolithic QPU advancements at the expense of sparser connectivity and lower interconnect quality. To evaluate these approaches, we introduce a quantitative stress test measuring the execution cost of a dense workload of random logical entangling operations using a surface code scheme. Using a dedicated compiler, we compute the space-time cost as the number of network nodes increases, analysing this scaling behaviour across various surface code distances, Bell-state fidelities, and Bell-pair generation times. We find that distributed architectures incur an up to exponential space-time performance penalty compared to an effectively monolithic architecture across all simulations. Our results also show that as the network grows, this penalty manifests in two distinct scaling regimes: a noise-dominated regime constrained by insufficient Bell-state fidelity and generation rates, and a connectivity-dominated regime bottlenecked by lattice-surgery routing congestion.
Distributed Quantum Computing (DQC) addresses the physical scaling limitations of monolithic quantum processors by networking modular Quantum Processing Units (QPUs). Efficient execution of quantum algorithms on DQC architectures requires compiling them across QPUs while minimizing inter-QPU communication bottlenecks, primarily through circuit partitioning. However, current evaluations of state-of-the-art partitioning heuristics focus primarily on the total entanglement cost of the partitions, failing to capture the broader structural and temporal overheads introduced by distributed network constraints. This paper addresses this evaluation gap by applying established monolithic benchmarking metrics to partitioned distributed circuits to quantify the performance impact of network constraints. Using an open-source, automated evaluation pipeline, we systematically assess diverse partitioning algorithms across standardized workloads and quantum network topologies. Our empirical results reveal that partitioning algorithms with comparable entanglement costs can still introduce drastically different physical execution penalties. By exposing these hidden trade-offs, such as severe increases in circuit depth and substantial reductions in gate density, this study demonstrates that comprehensive circuit-level metrics are essential for guiding the future design of DQC compilers.
Scaling fault-tolerant superconducting quantum computers will likely require distributed architectures built from multiple manufacturable quantum processing units. A central question is whether noisy and slow inter-chip operations impose substantial spacetime overhead or orchestration burdens compared with monolithic architectures. To answer this question, we present a hardware-grounded architectural co-design together with a comprehensive resource-estimation protocol for surface-code-based modular processors. The design confines inter-chip latency and noise to module boundaries, preventing slow, noisy links from inducing prohibitive spacetime overhead or becoming a global orchestration bottleneck. The resource-estimation protocol integrates hardware constraints and circuit-level error-correction performance into utility-scale algorithmic cost estimates, enabling a controlled assessment of different architectures. Using RSA-2048 factorization as a demanding benchmark, we estimate resources under experimentally anchored parameters and realistic superconducting hardware constraints. Compared with a large, ideal monolithic baseline, the resulting distributed architecture requires only modest additional resource overhead in both qubit count and execution time. More importantly, the overhead is nearly scale-invariant across a broad module-capacity window, decoupling chip size from global performance. This decoupling turns module capacity from a finely tuned architectural parameter into a flexible engineering degree of freedom, allowing chip sizes to be set by manufacturability and control-packaging constraints rather than architectural fine-tuning. These results establish a viable route to distributed fault-tolerant superconducting quantum computation that scales without prohibitive resource growth or heavy orchestration burden.
This work presents a conceptual architecture and technological roadmap for a scalable superconducting quantum computing platform based on modular design principles. Rather than introducing a new qubit technology, the proposal focuses on addressing critical engineering bottlenecks that currently limit the large-scale deployment of quantum processors, including wiring complexity, electromagnetic crosstalk, fabrication yield, and latency in error-correction feedback loops.The proposed framework introduces a modular hybrid architecture (“Quantum Mesh”), where medium-scale quantum chiplets containing 25–50 superconducting transmon qubits are interconnected through advanced 3D packaging and cryogenic infrastructure. This approach aims to improve manufacturing yield, reduce wiring density, and enable rack-level integration of quantum processing units while maintaining high gate fidelities and manageable thermal loads.A second central element of the proposal is the integration of a high-fidelity digital twin environment capable of simulating qubit dynamics, noise sources, control latency, and thermal constraints at nanosecond resolution. This predictive framework is intended to support hardware iteration cycles prior to fabrication, potentially accelerating design optimization and system validation.The document outlines a three-year development pathway targeting 100–200 physical qubits and several logical qubits using surface code error correction, followed by a longer-term scaling strategy toward quantum fabrics exceeding one thousand qubits. By combining modular quantum chiplets, partial cryogenic electronics, and predictive digital twin modeling, the proposed architecture explores a plausible industrial pathway toward large-scale quantum computing systems.
Modular quantum computing is a leading paradigm for scaling quantum computation beyond the resource limitations of monolithic devices. In this architecture, multiple quantum processing units (QPUs), employing identical or distinct qubit modalities, are interconnected via shared entanglement. Here, we investigate how errors at module interfaces and within individual QPUs affect fault-tolerant computation when qubits are encoded using the rotated surface code. Going beyond the logical-memory benchmark, we perform circuit-level simulations of fault-tolerant nonlocal CNOT gates implemented via lattice surgery between QPUs connected by noisy Bell pairs, and analyze the resulting logical error rates. Our results show that interfaces can tolerate noise up to an order of magnitude higher than intra-QPU noise, with only a minor reduction in the fault-tolerance threshold. We further develop an efficient protocol for preparing distributed fault-tolerant logical GHZ states, reducing ancilla overhead, time, and nonlocal Bell-pair consumption. We show that ancilla minimization in this setting is equivalent to a vertex-cover problem on an associated graph, and introduce a polynomial-time heuristic algorithm for finding low-overhead solutions. Our results provide quantitative evidence that distributed quantum error correction can enable scalable, fault-tolerant quantum computation in modular architectures.
Physical constraints and engineering challenges, including wafer dimensions, classical control cabling, and refrigeration volumes, impose significant limitations on the scalability of quantum computing units. As a result, a modular quantum computing architecture, comprising small processors interconnected by quantum links, is emerging as a promising approach to fault-tolerant quantum computing. However, the requirements that the network must fulfill to enable distributed quantum computation remain largely unexplored. We consider an architecture tailored for qubits with nearest-neighbor physical connectivity, leveraging the surface code for error correction and enabling fault-tolerant operations through lattice surgery and magic state distillation. We propose measurement teleportation as a tool to extend lattice surgery techniques to qubits located on different computing units interconnected via Bell pairs. Through memory simulations, we build an error model for logical operations and deduce an end-to-end resource estimation of Shor’s algorithm over a minimalist distributed architecture. Concretely, for a characteristic physical gate error rate of 10 − 3 , a processor cycle time of 1 µs, factoring a 2048-bit RSA integer is shown to be possible with 379 computing processors, each made with 89 781 qubits, with negligible space and time overhead with respect to a monolithic approach without parallelization, if 70 Bell pairs are available per cycle time between each processor with a fidelity exceeding 98.1 % .
Abstract: This study investigates photonic-interconnected quantum chiplets as a modular hardware pathway for scalable and networked quantum computing. The central problem is that monolithic quantum processors face compounding constraints in yield, wiring density, cryogenic routing, interconnect loss, calibration complexity and non-local connectivity. Photonic interconnection offers a technically plausible route to divide a large quantum computer into smaller processors while preserving quantum communication across modules through fibre links, photonic switches, optical transduction or integrated photonic interposers. The paper develops an academically rigorous framework that connects quantum-chiplet architecture, photonic integration, quantum error correction, control latency and manufacturability. It uses secondary real-data anchors from recent public demonstrations and a transparent engineering analysis to evaluate whether modular photonic networking can satisfy requirements for distributed logical qubits, entanglement generation and fault-tolerant operation. Results indicate that photonic chiplets can reduce scaling penalties relative to a monolithic wiring strategy when interconnect loss, feed-forward latency and module yield are jointly optimized. The study concludes that photonic-interconnected chiplets are not a minor packaging improvement but a possible architectural transition comparable to the movement from single-die classical processors to heterogeneous chiplet systems. The strongest contribution is a system-level evaluation model that links physical photonic performance with computer-architecture metrics and identifies the practical thresholds that must be met for Nature-level experimental validation. Keywords quantum computing chips, photonic chiplets, modular quantum computing, quantum interconnects, distributed quantum processors, silicon photonics, quantum networking, fault-tolerant quantum computing, optical interposers, quantum error correction, entanglement routing, wafer-scale quantum manufacturing, cryogenic control, quantum architecture, quantum hardware scalability