Azure instances powered by AMD Epyc are targeted at high-bandwidth applications. Credit: AMD AMD built it, and now the OEM has come. In this case, its Epyc server processors have scored their first big public win, with Microsoft announcing Azure instances based on AMD’s Epyc server microprocessors. AMD was first to 64-bit x86 design with Athlon on the desktop and Opteron on the servers. Once Microsoft ported Windows Server to 64 bits, the benefit became immediately apparent. Gone was the 4GB memory limit of 32-bit processors, replaced with 16 exabytes of memory, something we won’t live to see in our lifetimes (famous last words, I know). When Microsoft published a white paper in 2005 detailing how it was able to consolidate 250 32-bit MSN Network servers into 25 64-bit servers thanks to the increase in memory, which meant more connections per machine, that started the ball rolling for AMD. And within a few years, Opteron had 20 percent server market share. Then AMD stumbled, Intel got its act together, and the situation reversed itself. This year, Opteron accounted for less than 1 percent of server sales, according to Mercury Research. AMD has the power, now it needs the customers AMD is a competitive company again with its Epyc server processor, as benchmarks have shown. Now it just needs to win over the customers. And Microsoft is first by offering virtual instances running Epyc. The new instances — Lv2-Series of Virtual Machine — target workloads such as MongoDB, Cassandra and Cloudera that are storage intensive and demand high levels of I/O, according to Corey Sanders, director of compute, Azure, who wrote of the news in his blog. Lv2-Series VMs will come in sizes of up to 64 vCPUs and 15TB of local resource disk. AMD and Microsoft have been working on Microsoft’s Project Olympus, which is intended to deliver next-generation open-source hardware designed for cloud computing and developed with the Open Compute Community (OCP). “We think Project Olympus will be the basis for future innovation between Microsoft and AMD, and we look forward to adding more instance types in the future benefiting from the core density, memory bandwidth and I/O capabilities of AMD EPYC processors,” said Sanders in a statement from AMD. This is a big win for AMD, and if the Epyc instances deliver the performance they promise, it will be the first of many dominos to fall. AMD is pushing Epyc as a massively scalable and high-bandwidth solution thanks to its 128 lanes of PCI-Express connections per processor. It claims this provides more than 33 percent more connectivity than available two-socket solutions from Intel, which in turn means faster I/O. Microsoft made Opteron a player 12 years ago. Will history repeat itself? We’ll see. One thing is for certain: Intel has its act together much more than it did in 2005 when it clung to Itanium as its 64-bit offering. It’s not going to just cede the server market to AMD this time. Related content news analysis AMD launches Instinct AI accelerator to compete with Nvidia AMD enters the AI acceleration game with broad industry support. First shipping product is the Dell PowerEdge XE9680 with AMD Instinct MI300X. By Andy Patrizio Dec 07, 2023 6 mins CPUs and Processors Generative AI Data Center news analysis Western Digital keeps HDDs relevant with major capacity boost Western Digital and rival Seagate are finding new ways to pack data onto disk platters, keeping them relevant in the age of solid-state drives (SSD). By Andy Patrizio Dec 06, 2023 4 mins Enterprise Storage Data Center news Omdia: AI boosts server spending but unit sales still plunge A rush to build AI capacity using expensive coprocessors is jacking up the prices of servers, says research firm Omdia. By Andy Patrizio Dec 04, 2023 4 mins CPUs and Processors Generative AI Data Center news AWS and Nvidia partner on Project Ceiba, a GPU-powered AI supercomputer The companies are extending their AI partnership, and one key initiative is a supercomputer that will be integrated with AWS services and used by Nvidia’s own R&D teams. By Andy Patrizio Nov 30, 2023 3 mins CPUs and Processors Generative AI Supercomputers Podcasts Videos Resources Events NEWSLETTERS Newsletter Promo Module Test Description for newsletter promo module. Please enter a valid email address Subscribe