A Work-Efficient Parallel Sparse Matrix-Sparse Vector Multiplication Algorithm
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
We design and develop a work-efficient multithreaded algorithm for sparse matrix-sparse vector multiplication (SpMSpV) where the matrix, the input vector, and the output vector are all sparse. SpMSpV is an important primitive in the emerging GraphBLAS standard and is the workhorse of many graph algorithms including breadth-first search, bipartite graph matching, and maximal independent set. As thread counts increase, existing multithreaded SpMSpV algorithms can spend more time accessing the sparse matrix data structure than doing arithmetic. Our shared-memory parallel SpMSpV algorithm is work efficient in the sense that its total work is proportional to the number of arithmetic operations required. The key insight is to avoid each thread individually scan the list of matrix columns. Our algorithm is simple to implement and operates on existing column-based sparse matrix formats. It performs well on diverse matrices and vectors with heterogeneous sparsity patterns. A high-performance implementation of the algorithm attains up to 15x speedup on a 24-core Intel Ivy Bridge processor and up to 49x speedup on a 64-core Intel KNL manycore processor. In contrast to implementations of existing algorithms, the performance of our algorithm is sustained on a variety of different input types include matrices representing scale-free and high-diameter graphs.
- Research Organization:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC)
- Grant/Contract Number:
- AC02-05CH11231
- OSTI ID:
- 1525227
- Journal Information:
- Proceedings - IEEE International Parallel and Distributed Processing Symposium (IPDPS), Vol. 2017; Conference: 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), Orlando, FL (United States), 29 May - 2 Jun 2017; ISSN 1530-2075
- Publisher:
- IEEECopyright Statement
- Country of Publication:
- United States
- Language:
- English
Web of Science
Similar Records
Task Parallel Incomplete Cholesky Factorization using 2D Partitioned-Block Layout
High-Performance Sparse Matrix-Matrix Products on Intel KNL and Multicore Architectures