GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Artificial Intelligence and Deep Learning
Presentation
Media
Training Models in TensorFlow with Oversubscribed GPU Memory and NVLink 2.0 - Presented by IBM
Abstract:
We will explore what is possible with the unique combination of a model graph that swaps tensors between Volta GPUs and system memory using NVLink 2.0 connections between the GPUs and the system cores. GPU memory size limits the size of models, image resolution, and batch sizes allowed for neural network training. By combining a graph modification library that adds tensor swap-in / swap-out operations to the graph with NVLink 2.0 connections to the system cores and their memory, we can quickly train with models, image resolutions, and batch sizes that were previously impossible. We will review the graph modification module, the system architecture, and the performance results with standard benchmarks and other models.
 
Topics:
Artificial Intelligence and Deep Learning
Type:
Talk
Event:
GTC Europe
Year:
2018
Session ID:
E8336
Streaming:
Download:
Share: