Compiler Support for Sparse Tensor Computations in MLIR
Top Cited Papers
Open Access
- 16 September 2022
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 19 (4) , 1-25
Abstract
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.Keywords
All Related Versions
This publication has 58 references indexed in Scilit:
- The Combinatorial BLAS: design, implementation, and applicationsThe International Journal of High Performance Computing Applications, 2011
- A sparse framework for the derivation and implementation of fermion algebraMolecular Physics, 2010
- Sparsity: Optimization Framework for Sparse Matrix KernelsThe International Journal of High Performance Computing Applications, 2004
- The automatic generation of sparse primitivesACM Transactions on Mathematical Software, 1998
- Vienna-Fortran/HPF extensions for sparse and irregular problems and their compilationIEEE Transactions on Parallel and Distributed Systems, 1997
- Automatic data structure selection and transformation for sparse matrix computationsIEEE Transactions on Parallel and Distributed Systems, 1996
- The performance of ITPACK on vector computers for solving large sparse linear systems arising in sample oil reseervoir simulation problemsCommunications in Applied Numerical Methods, 1987
- A compact row storage scheme for Cholesky factors using elimination treesACM Transactions on Mathematical Software, 1986
- Algorithm 586: ITPACK 2C: A FORTRAN Package for Solving Large Sparse Linear Systems by Adaptive Accelerated Iterative MethodsACM Transactions on Mathematical Software, 1982
- The Solution of Large Sparse Unsymmetric Systems of Linear EquationsIMA Journal of Applied Mathematics, 1971