Grouping similar rows via a fast SpGEMM-based clustering and processing them cluster-wise speeds up sparse matrix multiplication by 1.39x on average over 110 matrices.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving SpGEMM Performance Through Matrix Reordering and Cluster-wise Computation
Grouping similar rows via a fast SpGEMM-based clustering and processing them cluster-wise speeds up sparse matrix multiplication by 1.39x on average over 110 matrices.