Microsoft is preparing to launch a new range of GPU-enabled virtual machines. Built using NVIDIA Tesla-series M60 and K80 GPUs, the new virtual machines offer the fastest GPUs available in the public cloud. This move leapfrogs Azure over AWS in both performance and number of supported platforms.
Articles Tagged with VDI
In my previous article, I introduced the idea of data locality in HCI. I also explored some basic math that illustrates the impact of scaling an HCI cluster. I compared a cluster without data locality to a cluster that does have locality. Today, I want to look at what happens when we need more than two copies of data, as well as to examine the impact of IO size on the storage network. My third article in this series will discuss the causes and effects of incomplete data locality, and it will also present a special case of data locality.
When VDI and DaaS were first introduced, many claims were made for their superiority over distributed desktops. They were cheaper, faster, more secure, easier to manage, etc. At the time, with few exceptions, these claims were no more than fantasy. Over the last few years, though, sufficient improvements in the core platforms and underlying infrastructure have brought some truth to most of these claims. Management tools have improved beyond measure. High-performance converged infrastructure appliances can deliver performance as good as or better than even that of the fastest desktops, and they do so at a cost that is less than that of a managed, enterprise-class desktop PC.
One of the trends in virtual desktops is Desktop as a Service (DaaS). The premise here is that a cloud provider can run a massive multi-tenant VDI environment well, better than most medium organizations can run their VDI on-premises. The medium or smaller organizations just rent the desktops they need. The assumption here is that desktops are a commodity and any desktop anywhere is just fine. The problem comes with those DaaS desktops accessing data—in particular, desktops at a cloud provider accessing data inside the client’s network. The desktop may run just fine, but if every application accessing corporate data slows to a crawl, there won’t be many happy users.
Cloud this, cloud that…it seems that the cloud will heal all your woes. But will it really? Some vendors are using the term “cloud” to signify various services, such Software as a Service (SaaS), private cloud, public cloud, hybrid cloud, and more. With so many clouds, how can you be sure that you’re getting the right cloud for you or whether you even need a cloud?