Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Yifan, Yang, Yuchen, Budiu, Matei, Misailovic, Sasa
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915940432609280
author Zhao, Yifan
Yang, Yuchen
Budiu, Matei
Misailovic, Sasa
author_facet Zhao, Yifan
Yang, Yuchen
Budiu, Matei
Misailovic, Sasa
contents We present Nautilus, a novel tensor compiler that moves toward fully automated math-to-kernel optimization. Nautilus compiles a high-level algebraic specification of tensor operators into efficient tiled GPU kernels. Nautilus's successive lowering design allows high-level optimizations, expression rewrites, and tile optimizations to be jointly applied in a single end-to-end system. Nautilus presents a novel auto-scheduler that discovers sequences of high-level optimizations, while preserving the regular program structure needed by tile optimizers. Nautilus's auto-scheduler captures complex interactions and trade-offs in the high-level optimizations, including aggressive global transformations like advanced reduction fusion. Nautilus is the first end-to-end tensor compiler capable of starting from a math-like description of attention and automatically discovering FlashAttention-3-like kernels, offloading the entire burden of optimization from the programmer to the compiler. Across five transformer-based models and 150 evaluation configurations on NVIDIA GH200 and RTX 5090 GPUs, Nautilus achieves up to 23% higher throughput than state-of-the-art compilers on GH200 and up to 42% on RTX 5090, while matching or exceeding manually written cuDNN kernels on many long-sequence configurations.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14825
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels
Zhao, Yifan
Yang, Yuchen
Budiu, Matei
Misailovic, Sasa
Programming Languages
Machine Learning
We present Nautilus, a novel tensor compiler that moves toward fully automated math-to-kernel optimization. Nautilus compiles a high-level algebraic specification of tensor operators into efficient tiled GPU kernels. Nautilus's successive lowering design allows high-level optimizations, expression rewrites, and tile optimizations to be jointly applied in a single end-to-end system. Nautilus presents a novel auto-scheduler that discovers sequences of high-level optimizations, while preserving the regular program structure needed by tile optimizers. Nautilus's auto-scheduler captures complex interactions and trade-offs in the high-level optimizations, including aggressive global transformations like advanced reduction fusion. Nautilus is the first end-to-end tensor compiler capable of starting from a math-like description of attention and automatically discovering FlashAttention-3-like kernels, offloading the entire burden of optimization from the programmer to the compiler. Across five transformer-based models and 150 evaluation configurations on NVIDIA GH200 and RTX 5090 GPUs, Nautilus achieves up to 23% higher throughput than state-of-the-art compilers on GH200 and up to 42% on RTX 5090, while matching or exceeding manually written cuDNN kernels on many long-sequence configurations.
title Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels
topic Programming Languages
Machine Learning
url https://arxiv.org/abs/2604.14825