Microsoft has a decade’s worth of experience in supercomputing, using the latest advancements in AI, Microsoft is changing how people interact with computers forever. On 13 March 2023, Microsoft previews new virtual machines with Nvidia H100 GPUs, the ND H100 v5 VM.
A blog posted on Microsoft Azure page quoted Greg Brockman, President and Co-Founder of OpenAI, saying, “Co-designing supercomputers with Azure has been crucial for scaling our demanding AI training needs, making our research and alignment work on systems like ChatGPT possible.”
Must Read: Microsoft Announced 10 Year Licensing Deal with NVIDIA
The new ND H100 v5 VM enables on-demand in sizes ranging from eight to thousands of NVIDIA H100 GPUs interconnected by NVIDIA Quantum-2 InfiniBand networking. Microsoft’s customers will see significantly faster performance for AI models over our last generation ND A100 v4 VMs with innovative technologies like:
- 8x NVIDIA H100 Tensor Core GPUs interconnected via next gen NVSwitch and NVLink 4.0
- 400 Gb/s NVIDIA Quantum-2 CX7 InfiniBand per GPU with 3.2Tb/s per VM in a non-blocking fat-tree network
- NVSwitch and NVLink 4.0 with 3.6TB/s bisectional bandwidth between 8 local GPUs within each VM
- 4th Gen Intel Xeon Scalable processors
- PCIE Gen5 host to GPU interconnect with 64GB/s bandwidth per GPU
- 16 Channels of 4800MHz DDR5 DIMMs
Recommended: OpenAI Chatgpt 4 Will Let You Turn Text Into Video
As Microsoft previews new virtual machines with Nvidia H100 GPUs, ND H100 v5 VM is now available for preview and will be available as a standard offering by Azure to let anyone unlock the potential of AI at Scale in the cloud.
Stay tuned with TechCult to stay on top of everything AI, gadgets, and technology.
Source: Microsoft Azure Blog