Latest about Servers
Micron unveils MRDIMMs for Intel Xeon 6: Up to 256GB DDR5-8800 modules
Micron's MRDIMMs wed maximum performance with maximum capacity for Intel Xeon 6 servers.
China to boost its state-owned compute performance by 30% by 2025, plans to hit 300 exaflops
China is set to increase its computing capacity to 300 ExaFLOPS by 2025.
Lenovo adopts Chinese Loongson CPUs for cloud servers
Lenovo puts Loongson's 3C5000 and 3A6000 CPUs into its datacenters.
Intel launches optical compute interconnect chiplet: Adding 4 Tbps optical connectivity to CPUs or GPUs
Intel unveils optical compute interconnect chiplet, industry's first fully integrated optical I/O solution that enables up to 4 Tbps connectivity.
Microsoft shelves its underwater data center
Although Microsoft quietly discontinued 'Project Natick,' its undersea data center returned excellent results. Throughout the experiment, 0.7% of servers failed, compared to 5.9% on land.
A single modern AI GPU consumes up to 3.7 MWh of power per year
The over 3.8 million GPUs sold last year has the power requirement of 1.3 million homes in a year, or about 7% of California's annual electricity output.
HPE flaunts El Capitan supercomputer blade with AMD's Instinct MI300A — projected to be world's fastest when finished this year
Images of one of the El Capitan's server blades taken at a recent computing event in Germany shows how absurdly dense each blade is packed in with AMD MI300A APUs.
AMD increases Instinct MI1300 sales guidance to $4 billion — pales in comparison to Nvidia's $40B projection
AMD starts looking at sales of datacenter GPUs more optimistically, expects sales of Instinct MI300, other processors to top $4 billion in 2024.
