.png){kind=icon}
Return
Optimizing Sparse Tensor Compilation for Sparse Output
.png){kind=icon}
PRE
AI
DOI：10.1145/3771775.3786267.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Sparse tensor algebra plays an important role in many scientific and engineering applications, yet existing sparse libraries and compilers face challenges when the output tensor is sparse. Array-based storage formats, such as CSR, require costly memory reallocations and rely on intermediate tensors (workspaces) to handle sparse scattering into the output, which limits performance and scalability. We introduce a new approach that employs our proposed flexible map-based storage format to directly support sparse scattering into the output without requiring extra workspaces. Our system then applies code and storage-specific optimizations to maximize efficiency. Experimental results across a range of kernels and datasets demonstrate an average speedup of 8.06 Chi over a state-of-the-art compiler and 5.28 Chi over a sparse tensor library.
Keywords:
Sparse
Tensors
Sparse Data Structures
Tensor Algebra
Journal
P
IF:
0
Papers:
18
Citations:
0
Organization
Cited Papers
OpSparse: A Highly Optimized Framework for Sparse General Matrix Multiplication on GPUs.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAIShareSaveShareSaveShareSave
ShareSaveShareSaveShareSave
View more