HPE announced new ProLiant DL385 Gen10 servers running AMD’s Epyc processor, plus Apollo-based servers running ARM processors developed by Cavium. Credit: AMD It’s been said that the industry dislikes too many choices, but HPE is offering more choices for server products with new ARM- and AMD Epyc-based servers. And in both cases, HPE is touting price-performance efficiency. The company today announced new ProLiant DL385 Gen10 servers running AMD’s Epyc processor, the server version of its Zen-based core that has shot the company back into serious competitiveness with Intel. HPE claims that with the Epyc chips, customers can have more virtual machines per server and the ability to process more data in parallel, thanks to the 32 cores with two threads per core in the Epyc processor. The result, it says, is up to 50 percent lower cost per virtual machine than “traditional” servers. The Epyc is also a performant chip, and HPE says its servers have broken two world records in SPEC 2017 scores, a benchmark used by all the server vendors where new records are set almost weekly. (Lenovo claimed a world record just two weeks ago.) Still, it remains a point of bragging rights. HPE’s scores were for two-socket systems on the SPECrate2017_fp_base and SPECfp_rate2006 benchmarks. A two-socket system, that’s 64 cores and 128 threads per server, with 4TB of memory and 128 lanes of PCIe connectivity, makes for some hefty performance capacity. And the Epyc processor has integrated hardware security for full virtual machine (VM) encryption to protect data against memory hacks and scrapes. VMs also have separate encryption keys, as does the hypervisor, isolating the VMs from one another and from the hypervisor itself. HPE Apollo servers running Cavium ARM processors Just a week prior, HPE announced new Apollo-based servers running ARM processors developed by Cavium, Qualcomm’s chief competitor in the ARM server processor market and now being acquired by Marvell. This mark’s HPE’s first ARM-based servers, if you exclude the Project Moonshot servers that were targeted at data centers but never came to market. The new Apollo 70 system uses Cavium’s ThunderX2 server processor and is designed for memory-intensive HPC and artificial intelligence (AI) workloads. HPE sees the Apollo being used in areas such as financial trading, computer-aided design and engineering, video surveillance and text analytics. Operating systems for the Apollo are Red Hat Enterprise Linux and SUSE Linux Enterprise Server for ARM, along with support for Mellanox InfiniBand and Ethernet fabrics. HPE introduces new Xeon-based servers, new tape backup unit HPE also introduced new Xeon-based servers and in what some would see as a surprise move, an update to its StoreEver LTO-8 Tape backup unit. Yes, tape is still alive and, in fact, making something of a comeback. Part of the reason is because of big data. These massive datasets require much larger backup capacity than regular hard disks, and tape can hold enormous quantities of data. But there is a decidedly low-tech reason, as well. Unlike a hard disk, tape can’t be hacked. The loading mechanism is unlike a traditional SAS or SATA interface and not crossable like a disk, and once you remove the tape from the reader and put it on the shelf, that’s it. It’s offline, and there is no breaking into it. HPE has been awfully aggressive in the server business lately, with its Rackspace private cloud announcement and new Superdome servers with SGI technology. The momentum may be against on-premises servers, but HPE isn’t going to just roll over and take it. Related content 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 news VMware stung by defections and layoffs after Broadcom close Layoffs and executive departures are expected after an acquisition, but there's also concern about VMware customer retention. By Andy Patrizio Nov 30, 2023 3 mins Virtualization Data Center Industry news AI partly to blame for spike in data center costs Low vacancies and the cost of AI have driven up colocation fees by 15%, DatacenterHawk reports. By Andy Patrizio Nov 27, 2023 4 mins Generative AI Data Center Podcasts Videos Resources Events NEWSLETTERS Newsletter Promo Module Test Description for newsletter promo module. Please enter a valid email address Subscribe