2026-06-09 –, Poster Island B
Classical quantum computing simulation is computationally demanding due to exponential state-vector growth.This work evaluates parallelization strategies on the RISC-V SpacemiT K1 using the RISC-V Vector Extension (RVV v1.0) and OpenMP. The dominant qubit-wise multiplication kernel was implemented in four variants: Sequential, OpenMP (MIMD), RVV vectorized (SIMD), and hybrid (OpenMP+RVV). Benchmarks up to 30 qubits 2<sup>30</sup> show size-dependent behavior: SIMD benefits small systems, multithreading improves medium scales, and large systems become memory-bound. The hybrid configuration achieves a peak speedup of 72.1× at 16 qubits and maintains 34.7× at 30 qubits, demonstrating the benefits of vector extensions and multi-core parallelism for quantum computing simulation workloads.
Classical simulation of quantum circuits remains an essential tool for developing and validating quantum algorithms before they can run on real quantum hardware. However, the exponential growth of the quantum state vector quickly makes these simulations computationally demanding, requiring efficient use of modern hardware architectures.
In this work, we explore how RISC-V platforms can accelerate quantum simulation by combining vectorization and multithreaded parallelism. A quantum circuit simulator was implemented in C with a focus on optimizing the qubit-wise multiplication kernel, which represents the dominant computational cost in many simulations. Several implementations were evaluated, including a sequential baseline, a multithreaded version using OpenMP, a vectorized implementation using the RISC-V Vector Extension (RVV), and a hybrid approach combining both techniques.
Experiments were conducted on a Banana Pi BPI-F3 platform based on the RISC-V SpacemiT K1 processor, with simulations scaling up to 30 qubits. The results show that different optimization strategies become more effective depending on the problem size and memory behavior of the system. The hybrid OpenMP+RVV configuration achieves the best overall performance, reaching a peak speedup of 72.1× and maintaining strong acceleration even for the largest simulations tested.
These results highlight the potential of RISC-V architectures for accelerating demanding scientific workloads such as quantum circuit simulation.
Rebeca Rasco Flores holds a BSc in Health Engineering from the University of Seville and an MSc in Mechatronics Engineering from the University of Málaga. She is currently a Research Fellow in the Department of Computer Architecture at the University of Málaga, where she is pursuing a PhD in Mechatronics Engineering. Her research focuses on the optimization and acceleration of quantum simulators on high-performance architectures, with a particular interest in RISC-V vector extensions and multi-core parallelism. Her work aims to bridge the gap between advanced classical computing and the efficient simulation of quantum circuits.