Understanding and Estimating the Execution Time of Quantum Circuits
Ning Ma, Heng Li
TL;DR
This work tackles the challenge of predicting quantum circuit execution time under resource-constrained, real-world conditions. It introduces a graph transformer-based model that combines global circuit features with detailed graph-structure information, and it leverages active learning to efficiently collect training data on real quantum hardware. The approach achieves high predictive accuracy on simulators ($R^2>0.95$) and substantial accuracy on real devices ($R^2\approx0.90$), while also providing insights into feature importance and backend-specific effects. The findings support better provisioning and prioritization of quantum workloads and offer practical guidance for circuit optimization to reduce execution time in near-term quantum computing platforms.
Abstract
Due to the scarcity of quantum computing resources, researchers and developers have very limited access to real quantum computers. Therefore, judicious planning and utilization of quantum computer runtime are essential to ensure smooth execution and completion of projects. Accurate estimation of a quantum circuit's execution time is thus necessary to prevent unexpectedly exceeding the anticipated runtime or the maximum capacity of the quantum computers; it also allows quantum computing platforms to make precisely informed provisioning and prioritization of quantum computing jobs. In this paper, we first study the characteristics of quantum circuits' runtime on simulators and real quantum computers. Then, we introduce an innovative method that employs a graph transformer-based model, utilizing the graph information and global information of quantum circuits to estimate their execution time. We selected a benchmark dataset comprising over 1,510 quantum circuits, initially predicting their execution times on simulators, which yielded promising results with an R-squared value greater than 95%. Subsequently, we applied active learning to select 340 circuit samples with a confidence level of 95% to build and evaluate our approach for the estimation of circuit execution times on quantum computers, achieving an average R-squared value exceeding 90%. Our approach can be integrated into quantum computing platforms to provide an accurate estimation of quantum execution time and be used as a reference for prioritizing quantum execution jobs. In addition, our findings provide insights for quantum program developers to optimize their circuits for reduced execution time.