Click “Watch Now” to login or join the NVIDIA Developer Program.

WATCH NOW

Accelerating DNN Inference with GraphBLAS and the GPU

Xiaoyun Wang, University of California, Davis

GTC 2020

Our work addresses the 2019 Sparse Deep Neural Network Graph Challenge with an implementation using the GraphBLAS programming model. We'll demonstrate our solution to this challenge with GraphBLAST, a GraphBLAS implementation on the GPU, and compare it to SuiteSparse, a GraphBLAS implementation on the CPU. The GraphBLAST implementation is 1.94x faster than SuiteSparse; the primary opportunity to increase performance on the GPU is a higher-performance sparse-matrix-times-sparse-matrix (SpGEMM) kernel.