Categorical Foundations for CuTe Layouts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Carlisle, Jack, Shah, Jay, Stern, Reuben, VanKoughnett, Paul
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917192645214208
author Carlisle, Jack
Shah, Jay
Stern, Reuben
VanKoughnett, Paul
author_facet Carlisle, Jack
Shah, Jay
Stern, Reuben
VanKoughnett, Paul
contents NVIDIA's CUTLASS library provides a robust and expressive set of methods for describing and manipulating multi-dimensional tensor data on the GPU. These methods are conceptually grounded in the abstract notion of a CuTe layout and a rich algebra of such layouts, including operations such as composition, logical product, and logical division. In this paper, we present a categorical framework for understanding this layout algebra by focusing on a naturally occurring class of tractable layouts. To this end, we define two categories Tuple and Nest whose morphisms give rise to layouts. We define a suite of operations on morphisms in these categories and prove their compatibility with the corresponding layout operations. Moreover, we give a complete characterization of the layouts which arise from our construction. Finally, we provide a Python implementation of our categorical constructions, along with tests that demonstrate alignment with CUTLASS behavior. This implementation can be found at our git repository https://github.com/ColfaxResearch/layout-categories.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05972
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Categorical Foundations for CuTe Layouts
Carlisle, Jack
Shah, Jay
Stern, Reuben
VanKoughnett, Paul
Programming Languages
Category Theory
NVIDIA's CUTLASS library provides a robust and expressive set of methods for describing and manipulating multi-dimensional tensor data on the GPU. These methods are conceptually grounded in the abstract notion of a CuTe layout and a rich algebra of such layouts, including operations such as composition, logical product, and logical division. In this paper, we present a categorical framework for understanding this layout algebra by focusing on a naturally occurring class of tractable layouts. To this end, we define two categories Tuple and Nest whose morphisms give rise to layouts. We define a suite of operations on morphisms in these categories and prove their compatibility with the corresponding layout operations. Moreover, we give a complete characterization of the layouts which arise from our construction. Finally, we provide a Python implementation of our categorical constructions, along with tests that demonstrate alignment with CUTLASS behavior. This implementation can be found at our git repository https://github.com/ColfaxResearch/layout-categories.
title Categorical Foundations for CuTe Layouts
topic Programming Languages
Category Theory
url https://arxiv.org/abs/2601.05972