Compiler Support for Sparse Tensor Computations in MLIR

Compiler Support for Sparse Tensor Computations in MLIR
复制标题

MLIR 中稀疏张量计算的编译器支持

DOI:
10.1145/3544559
复制
发表时间:
2022
期刊:
ACM Transactions on Architecture and Code Optimization (TACO)
影响因子:
--
通讯作者:
["Aart J. C. Bik
["Aart J. C. Bik
中科院分区:
--
文献类型:
--
作者:
["Aart J. C. Bik

文献摘要

参考文献

被引文献

相似文献

稀疏张量出现在科学、工程、机器学习和数据分析的问题中。在此类张量上运行的程序可以利用稀疏性来减少存储需求和计算时间。然而,手动开发和维护稀疏软件是一项复杂且容易出错的任务。因此,我们建议将稀疏性视为张量的属性,而不是一项繁琐的实现任务,并让稀疏编译器根据与稀疏性无关的计算定义自动生成稀疏代码。本文讨论将这一想法集成到 MLIR 中。
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.
DOI: 10.1145/3466795
发表时间: 2019-08
期刊: ACM Transactions on Mathematical Software (TOMS)
影响因子: --
作者:
Carl Yang;A. Buluç;John Douglas Owens
通讯作者: Carl Yang;A. Buluç;John Douglas Owens