Remove 3D Remove Hardware Remove Network
article thumbnail

Nvidia’s silicon photonics switches bring better power efficiency to AI data centers

Network World

Nvidia introduced a new silicon photonics network switches that integrate network optics into the switch using a technique called co-packaged optics (CPO), replacing traditional external pluggable transceivers. improvement in power efficiency, 10x greater network resiliency, and 1.3x The use of CPO translates to a 3.5x

article thumbnail

What is an AI server? Why artificial intelligence needs specialized systems

Network World

Traditional servers consisting of CPUs, RAM, high-speed networking, hard disk drives (HDDs) and solid state drivers (SSDs), while critical to todays high-performance computing (HPC) , simply werent built to support such intense AI capabilities. Related : What is AI networking?

Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Nvidia points to the future of AI hardware

CIO Business Intelligence

Blackwell will also allow enterprises with very deep pockets to set up AI factories, made up of integrated compute resources, storage, networking, workstations, software, and other pieces. But Nvidia’s many announcements during the conference didn’t address a handful of ongoing challenges on the hardware side of AI.

Hardware 247
article thumbnail

3D audio could be the next big podcast trend

The Verge

Today, iHeart Media announced that it’s investing in binaural audio , also known as 3D audio, which effectively places listeners in the room of a recording and makes them feel like it’s happening around them. The Verge ’s audio director Andrew Marino published a ton of 3D audio clips here if you want some examples.).

3D 128
article thumbnail

Google Cloud Run now allows AI inferencing on Nvidia GPUs

Network World

The combination of GPU support and the serverless nature of the service, according to experts, should benefit enterprises trying to run AI workloads as with Cloud Run they don’t need to buy and station hardware compute resources on-premises and not spend relatively more by spinning up a typical cloud instance. But are there caveats?

Google 453
article thumbnail

Nvidia rides the AI wave to become the world’s most valuable public company

Network World

Nvidia, once known for its GPU computing capabilities in gaming and 3D graphics, has transformed into the cornerstone of the AI and cloud computing sectors, the fastest-growing areas as we enter the AI Super Cycle,” said Neil Shah, VP for research and partner at Counterpoint Research.

Company 418
article thumbnail

10 highest-paying IT skills for 2024

CIO Business Intelligence

SoC helps reduce power consumption, and can help ensure devices require less space and cost less to build from discrete components, making it an appealing choice for businesses developing technical hardware. Torch enables fast and efficient GPU support, focusing on improving flexibility and speed when building complex algorithms.