Sign in

Accelerating distributed deep neural network training with pipelined MPI allreduce.

Adrián CastellóEnrique S. Quintana-OrtíJosé Duato
Published in: Clust. Comput. (2021)
Keyphrases
  • neural network training
  • neural network
  • training algorithm
  • distributed systems
  • parallel algorithm
  • parallel implementation
  • artificial neural networks
  • bp neural network
  • message passing