TuniQ: Autotuning Compilation Passes for Quantum Workloads at Scale for Effectiveness and Efficiency

2026-05-11

AI Summary

This work addresses the limitations of existing quantum compilers, which employ fixed optimization pipelines that struggle to adapt to diverse quantum circuits, hardware architectures, and noise conditions, thereby constraining fidelity and efficiency. To overcome this, the authors propose an adaptive quantum compilation framework based on reinforcement learning that dynamically selects optimal operations at each compilation stage. Key innovations include a stage-aware dual-encoder representation that jointly encodes circuit and hardware characteristics, a shaped reward mechanism enabling cross-stage credit assignment, and dynamic action masking to guarantee compilation validity. Experimental results demonstrate that the approach significantly improves gate fidelity and reduces compilation time across multiple IBM quantum processors, generalizes to unseen backends without retraining, and exhibits strong scalability on practically sized quantum circuits.

Abstract

Quantum processors are being integrated into HPC ecosystems as co-processors, where compilation of quantum circuits into hardware-executable form determines both output fidelity and runtime. Current compilers use a fixed pass sequence and ignore the fact that optimal pass selection varies with circuit, hardware, and noise conditions. We present TuniQ, a reinforcement learning-based system that selects compilation passes at each pipeline stage, adapting to circuit, backend, and current noise profile. TuniQ introduces several novel design components like a dual-encoder for stage-aware representation, shaped rewards for cross-stage credit assignment, and dynamic action masking for valid compilation. Evaluated across diverse quantum workloads on multiple IBM Quantum Cloud processors, TuniQ improves fidelity and reduces compilation time over the state-of-the-art IBM Qiskit transpiler, generalizes across backends without retraining, and scales strongly to utility-scale circuits with growing advantage.

Problem

• quantum compilation
• compiler optimization
• hardware variability
• noise-aware compilation
• quantum circuit optimization

Innovation

• reinforcement learning
• quantum compilation
• autotuning
• noise-aware optimization
• scalable quantum circuits