The Next Platform
  • Home
  • Compute
  • Store
  • Connect
  • Control
  • Code
  • AI
  • HPC
  • Enterprise
  • Hyperscale
  • Cloud
  • Edge
Latest
  • [ February 19, 2025 ] Arista Can Ride AI Up Past $10 Billion In 2026 Connect
  • [ February 18, 2025 ] Gordian Knot: Broadcom And TSMC To Cut Intel Into Two? Compute
  • [ February 13, 2025 ] German HPC Center Is The First Buyer For New D-Wave Quantum Computer Compute
  • [ February 13, 2025 ] The Hidden Cost Of Compromise: Why HPC Still Demands Precision HPC
  • [ February 12, 2025 ] Cisco Is The Bellwether Of Enterprise AI Adoption AI
  • [ February 12, 2025 ] HPE Sets Gen12 ProLiant Servers Loose On AI And The Edge Compute
  • [ February 11, 2025 ] Extended “Blackwell” GPU Ramp Cools Growth At Supermicro Compute
  • [ February 11, 2025 ] Cisco Cuts Network Costs By Welding Nexus Switch To AMD DPU Connect
HomeNVSwitch

NVSwitch

AI

Copper Wires Have Already Failed Clustered AI Systems

September 13, 2024 Timothy Prickett Morgan 7

It has become a well known fact these days that the switches that are used to interconnect distributed systems are not the most expensive part of that network, but rather it is the optical transceivers and fiber optic cables that comprise the bulk of the cost. …

Connect

This AI Network Has No Spine – And That’s A Good Thing

August 23, 2024 Timothy Prickett Morgan 6

When you are designing applications that run across the scale of an entire datacenter and that are comprised of hundreds to thousands of microservices running on countless individual servers and that have to be called within a matter of microseconds to give the illusion of a monolithic application, building fully connected, high bi-section bandwidth Clos networks is a must. …

Compute

When Nvidia Says Hot Chips, It Means Hot Platforms

August 23, 2024 Jeffrey Burt 1

Nvidia hit a rare patch of bad news earlier this month when reports started circulating claiming that the company’s much-anticipated “Blackwell” GPU accelerators could be delayed by as much as three months due to design flaws. …

AI

How Nvidia Blackwell Systems Attack 1 Trillion Parameter AI Models

March 19, 2024 Timothy Prickett Morgan 3

We like datacenter compute engines here at The Next Platform, but as the name implies, what we really like are platforms – how compute, storage, networking, and systems software are brought together to create a platform on which to build applications. …

AI

Half Eos’d: Even Nvidia Can’t Get Enough H100s For Its Supercomputer

February 15, 2024 Timothy Prickett Morgan 3

Note: There is a story called A Tale Of Two Nvidia Eos Supercomputers that augments and corrects information that originally appeared in this story as it was published on February 15. …

Connect

Crafting A DGX-Alike AI Server Out Of AMD GPUs And PCI Switches

August 15, 2023 Timothy Prickett Morgan 3

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. …

Connect

Nvidia Shows What Optically Linked GPU Systems Might Look Like

August 17, 2022 Timothy Prickett Morgan 3

We have been talking about silicon photonics so long that we are, probably like many of you, frustrated that it already is not ubiquitous. …

AI

The NVSwitch Fabric That Is The Hub Of The DGX H100 SuperPOD

March 23, 2022 Timothy Prickett Morgan 6

Normally, when we look at a system, we think from the compute engines at a very fine detail and then work our way out across the intricacies of the nodes and then the interconnect and software stack that scales it across the nodes into a distributed computing platform. …

AI

Nvidia Takes More Control Of Its GPU Compute Platform

May 30, 2018 Timothy Prickett Morgan 5

Nvidia got a little taste of hardware, and the company’s top brass have decided that they like having a lot of iron in their financial diet. …

AI

Building Bigger, Faster GPU Clusters Using NVSwitches

April 13, 2018 Paul Teich 1

Nvidia launched its second-generation DGX system in March. In order to build the 2 petaflops half-precision DGX-2, Nvidia had to first design and build a new NVLink 2.0 switch chip, named NVSwitch. …

Posts pagination

1 2 »
About

The Next Platform is part of the Situation Publishing family, which includes the enterprise and business technology publication, The Register.

TNP  offers in-depth coverage of high-end computing at large enterprises, supercomputing centers, hyperscale data centers, and public clouds. Read more…

Newsletter

Featuring highlights, analysis, and stories from the week directly from us to your inbox with nothing in between.
Subscribe now

  • RSS
  • Twitter
  • Facebook
  • LinkedIn
  • Email the editor
  • About
  • Contributors
  • Contact
  • Sales
  • Newsletter
  • Books
  • Events
  • Privacy
  • Ts&Cs
  • Cookies
  • Do not sell my personal information

All Content Copyright The Next Platform