Accelerating Sparse General Matrix-Matrix Multiplication for NVIDIA Volta GPU and Hygon DCU.

Zhuo Tian Shuai Yang Changyou Zhang

Published in: HPDC (2023)

Keyphrases

matrix multiplication
parallel implementation
special case
real time
message passing
high dimensional
distributed memory
image processing
graphics hardware
image sequences
lower bound
general purpose
missing data
graphics processing units