Article 4BF5Z Accelerating TensorFlow with RDMA for High-Performance Deep Learning

Accelerating TensorFlow with RDMA for High-Performance Deep Learning

by
Rich Brueckner
from High-Performance Computing News Analysis | insideHPC on (#4BF5Z)
luxi2-139x150.jpg

Xiaoyi Lu from Ohio State University gave this talk at the 2019 OpenFabrics Workshop in Austin. "Google's TensorFlow is one of the most popular Deep Learning (DL) frameworks. We propose a unified way of achieving high performance through enhancing the gRPC runtime with Remote Direct Memory Access (RDMA) technology on InfiniBand and RoCE. Through our proposed RDMAgRPC design, TensorFlow only needs to run over the gRPC channel and gets the optimal performance."

The post Accelerating TensorFlow with RDMA for High-Performance Deep Learning appeared first on insideHPC.

External Content
Source RSS or Atom Feed
Feed Location http://insidehpc.com/feed/
Feed Title High-Performance Computing News Analysis | insideHPC
Feed Link https://insidehpc.com/
Reply 0 comments