The Arm processor isn’t setting the world on fire on regular servers, but it does seem to have found a home in the cloud. While the on-premises server business remains firmly in the grip of the x86 world, cloud service providers are giving Arm-based servers a much more welcoming embrace. Both Chinese cloud giant Alibaba and Microsoft Azure have recently launched new instances with Arm processors. Alibaba Cloud unveiled its Yitian 710 processor design for use in its data centers back in October 2021. The company also announced the development of its proprietary servers, called Panjiu, promising optimized computing performance and energy efficiency. Yitian 710 is built on a 5nm manufacturing process and has 128 Arm cores, each with a top clock speed of 3.2GHz. It’s built on the Armv9 architecture and includes eight DDR5 memory channels per CPU and 96-lane PCIe 5.0. Alibaba claims the Yitian 710 achieved a SPECint2017 that beat the current state-of-the-art Arm server processor by 20% in performance and 50% in energy efficiency. Panjiu was developed with a separation of computing and storage so the servers are optimized for general-purpose computing as well as AI computing. Alibaba also claims Panjiu is suitable for high-performance storage and a variety of cloud-native workloads, such as containerized applications. Alibaba is offering trial instances. The operative question is: What are Alibaba’s ambitions with Panjiu? If it’s content to stay within the Chinese market, then it is no threat to the existing dominant players like AWS. But most Chinese companies seek to expand beyond just the China market, and Alibaba is modeled after Amazon in many ways. John Dinsdale, chief analyst & research director with Synergy Research Group, which follows the cloud market, says Alibaba has been more successful than other Chinese cloud providers at expanding its footprint and services beyond its home market of China. He says that Alibaba now has a substantial cloud presence in Hong Kong, Indonesia, Malaysia, India and Singapore, but still derives the vast majority of its revenues from China and Hong Kong. “If Alibaba’s Arm-based services are a strong competitor to AWS technologically, should AWS be worried? Well, even in APAC region excluding China, AWS cloud revenues are several times as big as Alibaba’s. So I don’t imagine AWS is losing much sleep,” he said via email. Azure embraces Arm It took a little while, but Microsoft Azure now offers a preview of Arm-based instances, something AWS has offered since last year. One possible reason for delay on Microsoft’s part is that it used a different processor. AWS’s Arm processor is Graviton, a homemade chip developed by Amazon. Microsoft, on the other hand, is using the Altra processor from Ampere, the startup led by former Intel executive Renee James. Paul Nash, head of product, Azure Compute Platform, said the Arm instances can achieve up to 50% better price-performance than comparable x86-based virtual machines (VMs) for scale-out workloads, which is what Microsoft is targeting with the Arm instances. These workloads include web servers, application servers, open-source databases, cloud-native, .NET applications, Java applications, and more. “The demand for compute capacity to sustain business modernization and digital transformation initiatives continues to grow. Organizations are facing a complex set of challenges as they deploy a broad range of workloads globally, from the edge to the cloud. There is also a need for a new breed of operationally efficient cloud-native computing solutions that can meet this demand without a massive growth in infrastructure footprint and energy consumption,” Nash said in a blog post announcing the instances. Microsoft is made its array of developer tools available on Arm Azure, including Visual Studio C++/C#/F# and .NET 6. OpenJDK is also available for Arm on Azure. The preview has limited availability for now and is only available in the West US 2, West Central US, and West Europe Azure regions. Related content news High-bandwidth memory nearly sold out until 2026 While it might be tempting to blame Nvidia for the shortage of HBM, it’s not alone in driving high-performance computing and demand for the memory HPC requires. By Andy Patrizio May 13, 2024 3 mins CPUs and Processors High-Performance Computing Data Center news CHIPS Act to fund $285 million for semiconductor digital twins Plans call for building an institute to develop digital twins for semiconductor manufacturing and share resources among chip developers. By Andy Patrizio May 10, 2024 3 mins CPUs and Processors Data Center news HPE launches storage system for HPC and AI clusters The HPE Cray Storage Systems C500 is tuned to avoid I/O bottlenecks and offers a lower entry price than Cray systems designed for top supercomputers. By Andy Patrizio May 07, 2024 3 mins Supercomputers Enterprise Storage Data Center news Lenovo ships all-AMD AI systems New systems are designed to support generative AI and on-prem Azure. By Andy Patrizio Apr 30, 2024 3 mins CPUs and Processors Data Center PODCASTS VIDEOS RESOURCES EVENTS NEWSLETTERS Newsletter Promo Module Test Description for newsletter promo module. Please enter a valid email address Subscribe