![](https://www.techmonitor.ai/wp-content/uploads/sites/29/2016/11/nvidia-deep-learning-580x358-e1479123961661.jpg)
IBM and NVIDIA have collaborated on a new deep learning tool, optimised for the latest IBM and NVIDIA technologies to help train computers to think and learn in more human-like ways at a faster pace.
The IBM PowerAI is a new deep learning software toolkit which runs on an IBM server built for artificial intelligence featuring NVIDIA NVLink interconnect technology optimised for IBM’s power architecture.
Ken Kind, General Manager, OpenPOWER said: “PowerAI democratises deep learning and other advanced analytic technologies by giving enterprise data scientists and research scientists alike an easy to deploy platform to rapidly advance their journey on AI.
“Coupled with our high performance computing servers built for AI, IBM provides what we believe is the best platform for enterprises building AI-based software, whether it’s chatbots for customer engagement, or real-time analysis of social media data.”
IBM PowerAI is designed to run on its highest performing server in its OpenPOWER LC lineup, which features NVIDIA NVLink technology optimised for the power architecture and NVIDIA’s latest GPU technology.
The new solution supports emerging computing methods of artificial intelligence, particularly deep learning. It also provides a continued path for IBM Watson to extend its artificial intelligence expertise in the enterprise by using several deep learning methods.
All additional distributions of PowerAI are to include the IBM and NVIDIA versions of the Caffe deep learning frameworks, IBM-Caffe and NVCaffe, which is one of the five deep learing software frameworks available in the PowerAI toolkit.
The toolkit leverages NVIDIA GPUDL libraries including cuDNN, cuBLAS and NCCL as part of NVIDIA SDKs to deliver multi-GPU acceleration on IBM servers.
Customers of IBM’s Power S822LC for HPC servers will have no charge for PowerAI. It is designed to run on a single S822LC server and also to scale large scale supercomputing clusters consisting of dozens, hundreds or thousands of servers.
NVIDIA unveiled its DGX-1 supercomputer earlier this year, designed specifically for deep learning.