The Next Platform
  • Home
  • Compute
  • Store
  • Connect
  • Control
  • Code
  • AI
  • HPC
  • Enterprise
  • Hyperscale
  • Cloud
  • Edge
Latest
  • [ October 24, 2025 ] Engineering CPO Is Easy – Scaling It For AI Will Take An Ecosystem Connect
  • [ October 23, 2025 ] IBM Is Playing A Very Long AI Game With Its Customers AI
  • [ October 22, 2025 ] NextSilicon Takes Aim At CPUs And GPUs With “Maverick-2” Dataflow Engine Compute
  • [ October 21, 2025 ] Software Pushes The AI Pareto Frontier More Than Hardware AI
  • [ October 20, 2025 ] “Polaris” AmpereOne M Arm CPUs Sighted In Oracle A4 Instances Compute
  • [ October 17, 2025 ] The Third Time Will Be The Charm For Broadcom Switch Co-Packaged Optics Connect
  • [ October 17, 2025 ] How HPC Is Igniting Discoveries In Dinosaur Locomotion – And Beyond HPC
  • [ October 16, 2025 ] TSMC Is Running Ahead Of Forecasts On AI Growth Compute
HomeUMI

UMI

Connect

How To Build A Better “Blackwell” GPU Than Nvidia Did

March 28, 2024 Timothy Prickett Morgan 9

While a lot of people focus on the floating point and integer processing architectures of various kinds of compute engines, we are spending more and more of our time looking at memory hierarchies and interconnect hierarchies. …

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