/home/leansigm/public_html/components/com_easyblog/services

SigmaWay Blog

SigmaWay Blog tries to aggregate original and third party content for the site users. It caters to articles on Process Improvement, Lean Six Sigma, Analytics, Market Intelligence, Training ,IT Services and industries which SigmaWay caters to

Artificial Intelligence: GPU in new trend

The rise in trend with mobile computing software like smartphones, the demand for PC was being declined for several years. PCs have become boring and market was get stagnated.  Then, GPUs (Graphic Processing Units) has become more interesting as they are the key enablers for the performance of PCs as it improves the graphic performance of games and coming up with various new design in the context of video and images. The industry was working to expand the use of GPUs as a computing accelerator. NVIDIA worked as pioneer in GPU computing market with its CUDA platform. Now, NVIDIA has introduced Tesla P100 platform. This is the first GPU designed for hyperscale datacenter application. It features over 15 billion transistors, combines 16Gb of die stacked 2nd generation High-Bandwidth memory (HBM2). It also has NVIDIA’s NVlink Interface technology to connect to multiple Tesla P100 GPU modules. This is the example how AI (Artificial Intelligence) is evolving and playing crucial roles. To know more, read this: http://www.forbes.com/sites/tiriasresearch/2016/04/05/nvidia-reinvents-the-gpu-for-artificial-intelligence-ai/#44fc297315b7

 

 

Rate this blog entry:
5513 Hits
0 Comments

Use of Bandwidth- GPUs for Graph and Predictive Analytics

Graphs are not just nodes or links. They are powerful data structures anyone can use to represent complex dependencies in their data. Graph applications are used in various places ranging from cancer research to large-scale cyber threat detection to collaborative filtering recommendation systems. In the world of data-intensive analytics, memory bandwidth is the primary performance restrictor. Because graph algorithms display non-locality and data-dependent parallelism. When you crisscross a large group, you are constantly asking for from main memory. For these problems, GPUs provides superior bandwidth to memory and can deliver significant speedups over CPUs. GPUs are very fast for graph processing and analytics, where memory bandwidth is a problem. The memory bandwidth of GPUs provides a new way to speed up data-intensive analytics and graph analytics. For more read the article written by Brad Bebee ( CEO, Blazegraph) : https://devblogs.nvidia.com/parallelforall/gpus-graph-predictive-analytics/

 

Rate this blog entry:
3104 Hits
0 Comments
Sign up for our newsletter

Follow us