Register-based Implementation of the Sparse General Matrix-matrix Multiplication on GPUs
Journal article, Peer reviewed
Published version
Permanent lenke
http://hdl.handle.net/11250/2493148Utgivelsesdato
2018Metadata
Vis full innførselSamlinger
Originalversjon
ACMSIGPLAN Symposium on Principles and Practice of Parallel Programming. 2018, . https://doi.org/10.1145/3178487.3178529Sammendrag
General sparse matrix-matrix multiplication (SpGEMM) is an essential building block in a number of applications. In our work, we fully utilize GPU registers and shared memory to implement an efficient and load balanced SpGEMM in comparison with the existing implementations.