Abstract
AbstractSparse matrix-vector multiplication (SpMV) is one of the most basic operation in numerical and scientific computing and engineering. The efficiency of SpMV operation determines the performance of related practical applications. To improve the computational efficiency of SpMV operation, researchers need to develop accelerated programs on parallel computing platforms. Therefore, in this paper, we design the GPU-based parallelization of SpMV operation using different compressed storage formats for the input sparse matrix, including coordinate (COO) format, compressed sparse rows (CSR) format, and compressed sparse columns (CSC) format. The experimental results show that, on average, the parallel COO-, CSR-, and CSC-based SpMV algorithms achieve the speedup of 17.31, 21.61, and 19.40 over the serial SpMV algorithms, respectively.KeywordsCompressed sparse matrix storageGPUParallelSparse matrix-vector multiplication (SpMV)
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
