Saved in:
Bibliographic Details
Main Authors: Hugo, Pompougnac, Christophe, Guillon, Sylvain, Noiry, Alban, Dutilleul, Guillaume, Iooss, Fabrice, Rastello
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.16512
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917154091171840
author Hugo, Pompougnac
Christophe, Guillon
Sylvain, Noiry
Alban, Dutilleul
Guillaume, Iooss
Fabrice, Rastello
author_facet Hugo, Pompougnac
Christophe, Guillon
Sylvain, Noiry
Alban, Dutilleul
Guillaume, Iooss
Fabrice, Rastello
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_16512
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle XTC, A Research Platform for Optimizing AI Workload Operators
Hugo, Pompougnac
Christophe, Guillon
Sylvain, Noiry
Alban, Dutilleul
Guillaume, Iooss
Fabrice, Rastello
Performance
Artificial Intelligence
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.
title XTC, A Research Platform for Optimizing AI Workload Operators
topic Performance
Artificial Intelligence
url https://arxiv.org/abs/2512.16512