
AI Means Re-Architecting The Datacenter Network
SPONSORED FEATURE: There are a lot of pressures on the datacenter network these days just to deal with expanding data and the increasing use of microservices architectures for modern applications. …
SPONSORED FEATURE: There are a lot of pressures on the datacenter network these days just to deal with expanding data and the increasing use of microservices architectures for modern applications. …
We said it from the beginning: There is no way that Meta Platforms, the originator of the Open Compute Project, wanted to buy a complete supercomputer system from Nvidia in order to advance its AI research and move newer large language models and recommendation engines into production. …
For the past decade or so, we have been convinced by quite a large number of IT suppliers that security functions, network and storage virtualization functions, and even the server virtualization hypervisor for carving up compute itself should be offloaded from servers to intermediaries somewhat illogically called data processing units, or DPUs. …
There are a lot of things going on in the datacenter and campus interconnect markets, but one of the weirder things we observe from the most recent market data coming out of IDC about the Ethernet portion of this market is that it is like a country music record being played backwards. …
As we are fond of pointing out, when it comes to high performance, low latency InfiniBand-style networks, Nvidia is not the only choice in town and has not been since the advent of InfiniBand interconnects back in the late 1990s. …
Data changes behavior and behavior changes data. It is a phenomenon that is akin to the Observer Effect in physics in that you can’t observe something without changing its behavior. …
Not everybody can afford an Nvidia DGX AI server loaded up with the latest “Hopper” H100 GPU accelerators or even one of its many clones available from the OEMs and ODMs of the world. …
Here we go again. Some big hyperscalers and cloud builders and their ASIC and switch suppliers are unhappy about Ethernet, and rather than wait for the IEEE to address issues, they are taking matters in their own hands to create what will ultimately become an IEEE standard that moves Ethernet forward in a direction and speed of their choosing. …
When system architects sit down to design their next platforms, they start by looking at a bunch of roadmaps from suppliers of CPUs, accelerators, memory, flash, network interface cards – and PCI-Express controllers and switches. …
There is no shortage of silicon photonics technologies under development, and every few months it seems like another startup crops up promising massive bandwidth, over longer distances, while using less power than copper interconnects. …
All Content Copyright The Next Platform