LightSpMV is a novel CUDA-compatible sparse matrix-vector multiplication (SpMv) algorithm using the standard compressed sparse row (CSR) storage format. We have evaluated LightSpMV using various sparse matrices and further compared it to the CSR-based SpMV subprograms in the state-of-the-art CUSP and cuSPARSE. Performance evaluation reveals that on a single Tesla K40c GPU, LightSpMV is superior to both CUSP and cuSPARSE, with a speedup of up to 2.60 and 2.63 over CUSP, and up to 1.93 and 1.79 over cuSPARSE for single and double precision, respectively.

Project Activity

See All Activity >

License

Apache License V2.0

Follow LightSpMV

LightSpMV Web Site

You Might Also Like
Top-Rated Free CRM Software Icon
Top-Rated Free CRM Software

216,000+ customers in over 135 countries grow their businesses with HubSpot

HubSpot is an AI-powered customer platform with all the software, integrations, and resources you need to connect your marketing, sales, and customer service. HubSpot's connected platform enables you to grow your business faster by focusing on what matters most: your customers.
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of LightSpMV!

Additional Project Details

Operating Systems

Linux, BSD

User Interface

Console/Terminal

Programming Language

C++

Related Categories

C++ Bio-Informatics Software, C++ Machine Learning Software, C++ Statistics Software

Registered

2014-12-18