Google Cloud has become the first major cloud provider to offer Virtual machine instances using Intel’s Skylake processors.
The Skylake Xeon processors, which are now generally available, include up to 64 vCPUs and 455GB of RAM supporting a range of compute-intensive workloads, data analytics and engineering simulations.
Google Cloud revealed that the customer demand for Intel’s Skylake has increased and since its launch for the Compute Engine in February, customers have run several hours of compute Skylake VMs.
According to Google, the new general availability release enables customers to create new VMs with Skylake across all the VM instance types in Compute Engine. This includes standard, highmen, highcpu, Custom Machine types and Preemptible VMs.
The decision to begin offering virtual machine instances using Intel’s processors is a smart move made by Google to compete against its rival cloud providers such as AWS, which announced a set of Skylake-powered C5 instances for its Elastic Compute Cloud in 2016 but are still yet to launch.
The Google Cloud Platform also released several updates to its Compute Engine to allow developers to easily select their preferred CPU platform for VMs within a particular Google Cloud region, whilst also being able to choose the suited CPU features.
Developers were previously restricted with the amount of RAM space per vCPU they were entitled to, but Google has now extended the memory and removed the restrictions to up memory space to a maximum of 455GB per VM instance.
This helps Google offer a wider memory space to user applications that may benefit from flexible memory configurations for better performance.
Google Cloud has made Skylake available in three of its regions, Western US, Western Europe and Eastern Asia Pacific with general availability across every region at no extra cost for a limited time.
This article is from the CBROnline archive: some formatting and images may not be present.