Bixia Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Bixia Zheng has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Aart J. C. Bik
Google Research, Mountain View, USA
1 shared publication - Fredrik Kjolstad
Stanford University, Stanford, California, USA
1 shared publication - Nicolas Vasilache
Google
1 shared publication - Penporn Koanantakool
Google USA, Mountain View, CA, USA
1 shared publication - Tatiana Shpeisman
Google USA, Mountain View, CA, USA
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 16 September 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 19 (4) , 1-25
Compiler Support for Sparse Tensor Computations in MLIR
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.
- 16 September 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 19 (4) , 1-25
Top Cited PapersOpen AccessCompiler Support for Sparse Tensor Computations in MLIR
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.