New on-premises data gateway and new Azure VM sizes as heard on the latest Need to Know podcast recorded May 10, 2017 AEST.
On-premises data gateway in Azure
The on-premises data gateway is now generally available in Azure. This gateway helps you securely connect your business apps in the cloud to your data sources on premises. You can use the gateway to move data to and from the cloud while keeping your data sources on premises. The gateway currently supports Azure Logic Apps. To access data sources on premises from your logic apps, set up an on-premises data gateway that logic apps can use with supported connectors. The gateway acts as a bridge that provides quick data transfer and encryption between data sources on premises and your logic apps. The gateway relays data from on-premises sources on encrypted channels through the Azure Service Bus. All traffic originates as secure outbound traffic from the gateway agent.
New Azure virtual machine sizes
Last year we introduced our first GPU N-series offering powered by NVIDIA’s Tesla-based GPUs and we have seen an amazing customer response. With the Azure NC-series, you can run CUDA workloads on up to four Tesla K80 GPUs in a single virtual machine. Additionally, unlike any other cloud provider, the NC-series offers RDMA and InfiniBand connectivity for extremely low-latency, high throughput and scale-out workloads. Your workloads can scale-up and scale-out.
InfiniBand (abbreviated IB) is a computer-networking communications standard used in high-performance computing that features very high throughput and very low latency.
RDMA is direct memory access from the memory of one computer into another computer without involving either one’s operating system. This permits high-throughput, low-latency networking, which is especially useful in massively parallel computer clusters
CUDA is a parallel computing platform and API model created by Nvidia
Use cases for the NC-series virtual machines are AI, Deep Learning, image recognition, speech training, natural language processing and even pedestrian detection for autonomous vehicles.
There is also the new ND-series virtual machines, powered by NVIDIA Tesla P40 GPUs based on the new Pascal Architecture. These instances also offer a much larger GPU memory size (24GB) and like our NC-series, the ND-series will offer RDMA and InfiniBand connectivity so you can run large-scale training jobs spanning hundreds of GPUs.
These new sizes will be available later in the year, but you can sign up for a preview.
Microsoft Build Conference
The Microsoft Conference starts this time tomorrow May 8 at 8am from Seattle. Stay tuned for all the announcements.
Marc Kean 