- OSS GPU appliances provide anywhere from 84 teraflops to 2.4 petaflops of single-precision performance using NVIDIA Tesla P100s in both the PCIe and SXM2 form factors
- OSS exhibits the OSS-PASCAL4 with NVLink for the first time at GTC
- OSS-PASCAL4 and OSS-PASCAL8 with NVIDIA® Pascal™ GPUs are purpose-built for deep learning applications
- Fully integrated hardware, software and GPU management and monitoring
Katie Garrison discusses The GPUltima, a petaflop in a rack of networked GPUs and how it can be used to accelerate deep learning applications.This article is published on insideHPC.
To read the article, click here.