News and analysis on networking, the data center, and IoT
01Â Jun, 2023
The DGX GH200 AI supercomputer is targeted toward developing and supporting large language models. Google Cloud, Meta, and Microsoft already have access to it.
After the Chinese government said it was banning the use of some Micron chips due to security risks, US lawmakers lobby for a ban on one of its biggest Chinese competitors.
The integration of Nvidiaâs software suite will further help enterprises build, deploy, and manage applications based on large language models.
Nvidia's Grace Hopper CPU/GPU combo underpins its supercomputer the company claims can crank out nearly an exaFLOP of AI performance.
While Qualcomm has faced challenges due to the declining smartphone market, the chip maker has set its sights on supporting demanding AI workloads with its upcoming Snapdragon X75 chipset.
AmpereOne chips are the first built around cores designed in-house and promise two to three times the power savings over x86.
Intel is switching up its data-center processor roadmap, and its proposed combination CPU and GPU, code-named Falcon Shores, will now be a GPU chip only.
