Achieving high efficiency on AI operators demands precise control over computation and data movement. However, existing scheduling languages are locked into specific compiler ecosystems, preventing fair comparison, reuse, and evaluation across frameworks. No unified interface currently decouples scheduling specification from code generation and measurement. We introduce XTC, a platform that unifies scheduling and performance evaluation across compilers. With its common API and reproducible measurement framework, XTC enables portable experimentation and accelerates research on optimization strategies.
@article{arxiv.2512.16512,
title = {XTC, A Research Platform for Optimizing AI Workload Operators},
author = {Pompougnac Hugo and Guillon Christophe and Noiry Sylvain and Dutilleul Alban and Iooss Guillaume and Rastello Fabrice},
journal= {arXiv preprint arXiv:2512.16512},
year = {2025}
}