2022/02/09 by Aart J. C. Bik, Penporn Koanantakool, Tatiana Shpeisman +4 · 1 voice
Computer Science · Mathematics · #Analytics #Code (set theory) #Compiler #Computation #Computational science #Computer engineering #Computer science #Data mining #Exploit #Numerical Methods and Algorithms #Optimizing compiler #Parallel Computing and Optimization Techniques #Parallel computing #Programming language #Property (philosophy) #Software #Sparse matrix #Task (project management) #Tensor (intrinsic definition) #Tensor decomposition and applications #Theoretical computer science #cs.PL
paper · pdf · doi:10.1145/3544559
arxiv published 2022/02/09 · arxiv updated 2022/02/09 · openalex publication_date 2022/08/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/15
Sparse tensors arise in problems in science, engineering, machine learning, and data analytics. Programs that operate on such tensors can exploit sparsity to reduce storage requirements and computational time. Developing and maintaining sparse software by hand, however, is a complex and error-prone task. Therefore, we propose treating sparsity as a property of tensors, not a tedious implementation task, and letting a sparse compiler generate sparse code automatically from a sparsity-agnostic definition of the computation. This article discusses integrating this idea into MLIR.