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.
GPU leader Nvidia is buying networking company Mellanox for $6.9 billion, further cementing Nvidia company as a data center player.
Facebook created a subsidiary called Middle Mile Infrastructure to sell excess capacity on its fiber, starting with new fiber-optic routes between its data center campuses in Virginia, Ohio, and North Carolina.
While many workloads are shifting to the cloud, on-premises server hardware continues to be vital to the workplace, a new Spiceworks survey finds.
Sales figures from companies participating in the Open Compute Project are starting to come in, and they are close to what was forecasted in 2017 and growing.
Western Digital, a company synonymous with hard-disk technology, introduced a pair of SSDs for markedly different use -- the Western Digital Ultrastar DC SN630 NVMe SSD and the Western Digital CL SN720 NVMe SSD.
Google announced the beta version of Cloud Services Platform, an on-premises software product that allows enterprises to deploy Google’s Kubernetes Engine inside their own data centers.
The first two chips in Arm Holdings’ cloud-to-edge platform, Neoverse N1 and Neoverse E1, promise greater performance and improved power efficiency.
The Kinetic Edge Alliance, a group of hardware, software and networking companies, will collaborate to accelerate the integration edge solutions.
Lentiq combines the concept of the data lake with edge computing into what it calls “interconnected micro data lakes,” or data pools.
Lenovo is launching TruScale, a pay-per-use system for its servers that it says offers true pay-per-use and no requirement of a minimum capacity purchase.
The data center isn't disappearing. Instead, it is being repurposed and some of its tasks are moving to the edge, says Dell CTO Robert Hormuth.
Dell EMC has introduced new software for its Data Domain and Integrated Data Protection Appliance products that it claims will significantly improve backup and restore performance.
Intel announced the promotion of CFO Bob Swan to CEO, ending a seven-month search, set a deadline for the life of its Itanium processor, and is looking to buy Mellanox.
Old SGI technology lives on in Jean Zay, an HPE SGI 8600 supercomputer designed for high-performance computing and artificial intelligence workloads.
Storage-class memory (SCM) will eventually supplant NAND flash as the high-speed storage medium of choice, says Ivan Iannaccone, VP and general manager of HPE’s 3PAR storage unit.
Contract prices for server DRAM are expected to fall by more than 20 percent this quarter thanks to slow demand and over production.
SUSE officially releases its enterprise Linux distribution, SUSE Linux Enterprise Server (SLES), for all major ARM server processors.
Huawei's new data center switches, the CloudEngine 16800 series, use an AI-powered chip to improve network operations.
Intel is executing fairly well for a company that doesn't have a leader, but this can’t go on forever.
New Xeons, AI processors, and 5G capabilities are among the announcements Intel made at CES this week.
Global server shipments are expected to slow down as new processors appear on the horizon, according to TrendForce. Meanwhile, an oversupply of NAND flash memory causes prices to drop.
Old servers don’t just burn electricity; they contribute heavily to toxicity of the environment.
Microsoft, Xilinx, Intel, and Broadcom are all reportedly interested in acquiring network chip maker Mellanox.
Oracle Cloud Native Framework is for organizations looking to build hybrid cloud architectures across both public cloud and on-premises infrastructure. But it is Oracle cloud only.
A third-party organization tested a sampling of Super Micro motherboards and found no evidence of any spy chips.
IBM and Nvidia partner again to produce a tower-sized DGX server that combines high-end IBM hardware with Nvidia GPUs and is specific for AI.
It's the end of the road for Qualcomm's Centriq, its ARM-based server processor.
IoT spending will increase in 2019 due mostly to companies' need to integrate real-time intelligence into their business models.
What will 2019 hold for data centers and the cloud, both public and private? Here are our educated guesses.
By 2025, IDC says worldwide data will grow 61% to 175 zettabytes, with as much of the data residing in the cloud as in data centers.
Amazon Web Services (AWS) acknowledges it’s a hybrid world and announces eight hybrid storage offerings. Meanwhile, Red Hat acquires multi-cloud storage startup NooBaa.
Companies will invest more in building and renovating data centers and will look to alternative energy sources to power them, a new AFCOM survey finds.
Oracle has a significant communications software business, and it’s betting that Talari’s SD-WAN technology will ensure performance and reliability of communications over any network.
AMD has a few things in its favor as it takes on Nvidia in the high-performance computing (HPC) and artificial intelligence (AI) arena.
After the initial rush to the cloud, many firms are discovering it’s not cheaper and are taking workloads back to their data centers, a Nutanix survey finds.
Researchers at UCLA Riverside discover GPUs can be victims of the same kinds of attacks as Meltdown and Spectre, which have impacted Intel and AMD CPUs.
AMD’s new GPUs designed for the data center give it a chance against Nvidia, but the software is still an issue.
AMD revealed the Zen 2 architecture for its family of microprocessors. Sold under the Epyc brand for servers, it’s expected to double the performance of the previous generation.
Intel formally announced a new class of Xeon Scalable processors that in many ways leapfrogs the best AMD has to offer.
Oracle was disturbingly quiet about its Exadata and Exalogix on-premises servers at the recent OpenWorld. But IDC's Ashish Nadkarni says not to worry yet.
The company says this is the last design before exascale, but it’s a big leap in its own right.
Rackspace's fully managed disaster recovery service promises improved business continuity for on-premises, colocation, and multi-cloud environments.
The Open Stack Foundation's StarlingX is designed to help organizations build mission-critical edge clouds needed for industrial IoT deployments.
Alibaba Cloud, Huawei, and server vendor Inspur will begin offering data center platforms based on Xilinx’s FPGA-as-a-service model, mostly targeting AI inference workloads.
The HCI platform combines Lenovo's hardware with Scale Computing's HC3 software platform to create edge computing systems designed for a single user's private corporate network.
The number of severe weather incidents is expected to increase, yet most data centers don't have plans to ensure uptime should an event hit, an Uptime Institute study finds.
Huawei's artificial intelligence (AI) strategy is not just chips, but a full-stack portfolio, including chips, cloud services, and products.
New IDC study shows private cloud spending increased 28.2 percent year over year. Off-premises private cloud, in particular, is seeing strong growth.
Intel reveals its FPGA strategy, which includes the Stratix 10 and Arria 10 chips, a Storefront for FPGA workloads, and support for VMware vSphere.
Intel announced 95 new performance world records for its Intel Xeon Scalable processors, while AMD and Xilinx set an AI inference processing record of 30,000 images per second.