Understanding and Estimating the Execution Time of Quantum Programs

2024-11-23

arXiv.org

AI Summary

Accurate runtime estimation for quantum programs remains challenging under scarce quantum computing resources, hindering efficient job scheduling. Method: We propose the first runtime prediction framework integrating graph transformers with active learning. Quantum circuits are modeled as structured program graphs, jointly encoding local gate-sequence features and global topological features to uniformly predict execution times on both simulators and real hardware. Contribution/Results: Our approach quantitatively characterizes the impact of single- and two-qubit gate types and their combinations on runtime, enabling platform-level dynamic priority decisions. Experiments show R² > 95% on simulators and R² > 90% on real devices using only 340 high-confidence hardware samples. The model is production-ready for integration into quantum cloud platforms, supporting real-time runtime estimation and intelligent job scheduling.

Technology Category

• Machine Learning: Quantum Machine Learning
• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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 program'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 programs' 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 programs to estimate their execution time. We selected a benchmark dataset comprising over 1510 quantum programs, initially predicting their execution times on simulators, which yielded promising results with an R-squared value over 95%. Subsequently, for the estimation of execution times on quantum computers, we applied active learning to select 340 samples with a confidence level of 95% to build and evaluate our approach, 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 programs in terms of execution time consumption, for example, by prioritizing one-qubit gates over two-qubit gates.

Problem

• Estimating quantum circuit execution time for resource planning
• Predicting runtime on simulators and real quantum computers
• Optimizing job scheduling and circuit performance prioritization

Innovation

• Graph transformer model estimates quantum circuit execution time
• Active learning selects circuits for quantum computer time prediction
• Method integrates into platforms for job prioritization and provisioning