Microsoft expands its capabilities based on gpus nvidia

Microsoft has announced an expansion of its Nvidia GPU capabilities, offering for the first time a powerful addition to its lineup that includes 8 Nvidia Tesla V100 cards, interconnected through NVLink for use in artificial intelligence and compute-intensive projects.

Microsoft already offers virtual machines with 8 Nvidia cards

Azure Corporate Vice President Corey Sanders announced the advancement of two new N-series virtual machines with Nvidia GPU capabilities. GPUs are ideal for graphics and compute-intensive workloads, and have helped innovate through scenarios such as high-end remote viewing, artificial intelligence, and predictive analytics. The new NVv2 VMs will feature Nvidia GRID and Tesla M60 GPU technology, up to 448 Gb of RAM, and will support Premium SSDs.

We recommend reading our post about Nvidia RTX 2080 Ti Review in Spanish

The NDv2 virtual machines that will be seen before the end of the year, is a new addition to the ND series. NDv2 virtual machines focus on training and inference, as well as machine learning. The new NDv2 will feature eight Tesla V100s interconnected via NVLink GPUs, and 40 Intel Skylake cores meant to deliver high-quality results even faster. NDv2 virtual machines are expected to be available in late 2018.

Vole also announces two new H-series virtual machines for high-performance computing scenarios. These new virtual machines are optimized for performance and cost, and are geared towards HPC workloads such as fluid dynamics, structural mechanics, energy exploration, weather forecasting, risk analysis, and more.

The HB VMs that will also be seen before the end of the year are virtual machines that have 60 AMD EPYC cores and 240 GB of RAM. They are said to have the largest amount of memory bandwidth (260GBps) in the public cloud. This is valuable for the required calculations in fluid dynamics and weather forecasting.

Fudzilla font