NVLink Speeds Deep Learning on New OpenPOWER Servers
by Rich Brueckner from High-Performance Computing News Analysis | insideHPC on (#1XMA3)
Over at the IBM System Blog, Sumit Gupta writes that the company's new IBM Power System 822LC with Nvidia Tesla P100 GPUs is already demonstrating impressive performance on Deep Learning training applications. "A single S822LC for HPC with four NVIDIA Tesla P100 GPUs is 2.2 times faster reaching 50 percent accuracy in AlexNet than a server with four NVIDIA Tesla M40 GPUs!"
The post NVLink Speeds Deep Learning on New OpenPOWER Servers appeared first on insideHPC.