Andy Patrizio is a freelance technology writer based in Orange County, California. He's written for a variety of publications, ranging from Tom's Guide to Wired to Dr. Dobbs Journal, and has been on staff at IT publications like InternetNews, PC Week and InformationWeek.
Scaleway explains how it plans to use servers for a decade and why it's getting rid of RAID controllers.
New Nvidia hardware and software are tailored to supporting AI.
In addition to sinking billions into OpenAI, Microsoft spent hundreds of millions on hardware.
Dell teams with colocation services provider Cyxtera to provide on-demand access to PowerEdge infrastructure, while a partnership with ZutaCore gives Dell access to liquid cooling technology.
Intel boosts bandwidth per channel in latest FPGA, Marvell unveils low-latency Teralynx 10 switch chip, and Ranovus previews co-packaged optics platform with AMD.
Storage vendor Vast Data adds built-in metadata index, called the Vast Catalog, which details every bit of data stored on its arrays.
Competitors AMD and Nvidia are already working on high-performance computing processors that combine CPU and GPU cores.
Nvidia says it will make it's brand of generative AI available through Oracle Cloud, Microsoft Azure, Google Cloud Platform, and other cloud providers.
AWS claims its new Amazon EC2 M7g and R7g instances provide 25% better performance vs. the past generation of instances.
After a dip due to surplus inventory and economic concerns, server CPU market expected to rebound.
Snapdragon X35 5G Modem-RF caters to edge devices in low-power environments.
Hardware durability metrics are drawn from the cloud storage provider’s portfolio of more than 230,000 hard drives under management.
IBM says its roadmap for AIX development and new features runs through 2030, countering a published commentary.
AMD issued 31 alerts covering client and desktop that allow for a BIOS attack.
ECL says its hydrogen fuel cells will provide electricity to power its data centers while producing enough water to cool the servers.
From HPE to Inspur, server vendors are coming out with dozens of new configurations.
IBM will quadruple the core count of its RISC CPUs specifically to benefit one of Oracle’s databases, perhaps to get around licensing issues, but won't say exactly why.
New server processors include virtual machine security as well as AI accelerators.
The Instinct MI300 server accelerator from AMD looks like an absolute beast on paper, with eight times the performance of its predecessor.
Giga Computing Technology is a new Gigabyte subsidiary focused on supporting servers and other enterprise gear as well as liquid cooling.
New Arm-based Mt. Hamilton servers target a range of use cases, from traditional server workloads to cloud and AI.
TrendForce believes core parts of the server supply chain will shift to Southeast Asia and the Americas as a result of geopolitical risks and trade disputes.
Restructuring move puts Intel's gaming and data center products into separate categories to better serve both markets.
GreenLake enhancements include expanded container deployment options and workload-optimized instances for compute, memory, and storage.
Equinix is considering a multi-year project to run its data centers at higher temperatures to conserve energy.
Tests by Meta and Iceotope find that new, sealed hard disk drives can be given precision liquid cooling that is more even than air cooling.
Intel's new server chips will have special functions locked away and available to turn on—for a fee.
AWS re:Invent: An Arm-based CPU for high-performance computing, a networking chip that doubles performance of its predecessor, and a TCP protocol replacement to speed up networks in the AWS cloud.
Seagate's Exos 2X18 features multiple drive heads that enable it to match SATA SSD speeds.
News includes upgrade of Dell’s APEX data storage services to provide more secure backup storage in a pay-per-use consumption model.
Deal involves AMD’s Instinct GPU accelerators, which are also used in Frontier, the fastest supercomputer in the world.
OEMs including HPE, Dell and Supermicro, along with cloud providers Microsoft and Oracle, showed up for the debut of AMD’s fourth-generation server processor.
You can now get a scaled-down and less expensive supercomputer that's based on the same architecture of the machine that broke the exaFLOP barrier.
Intel's CPU Max and GPU Max HPC chips use high bandwidth memory to solve bottlenecks and underpin supercomputers.
The chips were delayed nearly two years due to manufacturing challenges.
The tests are for their technology but the findings can be applied to any DPU.
HPE ProLiant Gen11 servers are designed with heavy emphasis on security and a hybrid-cloud workloads.
The Open Compute Project's Caliptra spec for Root of Trust could lead to better interoperability among cards used in data-center servers.
Oracle Cloud Infrastructure will feature tens of thousands of Nvidia GPUs and software that are aimed at artificial-intelligence processing.
InspireSemi's Thunderbird chips are compatible with multiple programming languages, making it easier to compile existing HPC code for them.
Now you can start very small with a single 1U server and expand.
Google Cloud says its new C3 virtual machine instances deliver performance gains up to 20% over its previous generation C2 instances.
Intel is taking its FGPA lineup beyond the data center and extending its Agilex products to remote, edge computing, and embedded systems.
TrendForce Research predicts that oversupply of SSDs will lead to price cuts as much as 20% in Q4 2022.
SambaNova DataScale servers can perform both AI training and inference, which eliminates expensive data movement.
New Lenovo servers, storage, edge products, and liquid cooling options are each part of an announcement deluge.
Some apps need CPU clock speed while others need multiple cores, so base your server purchases accordingly.
Consultancies bring experience that enterprises may not have to develop their AI strategy and products.
The H100 Tensor Core GPU is in full production, and the first servers based on Nvidia's new Hopper architecture are due next month.
Seagate's Exos storage arrays can rebuild data from failed hard drives, leaving the rest of the drives in the array operational and reducing the frequency of swapping out bad drives.