Intel plans cheaper air-cooled ai chip for inference

Intel will ship a new graphics processing unit designed for AI inference tasks by the end of this year. The chip uses lower-cost memory and air cooling to undercut rivals Nvidia and AMD.

The US chipmaker unveiled the Crescent Island GPU in October as part of efforts to regain ground in the AI semiconductor market. Kevork Kechichian, who leads Intel’s data center group, said the company is “starting with the basics” and will not target the model training segment after its earlier Gaudi product saw weak sales and a successor was cancelled last year.

Liittyvät artikkelit

Photorealistic image of engineers presenting the Jalapeño AI chip in a lab setting with company logos.
AI:n luoma kuva

OpenAI and Broadcom unveil Jalapeño AI chip design

Raportoinut AI AI:n luoma kuva

OpenAI and Broadcom have announced the design of Jalapeño, their first jointly developed AI accelerator chip. The processor targets large language model inference and marks OpenAI's entry into custom silicon production.

Chinese AI firm DeepSeek is moving to design its own chips for running trained models. The effort aims to cut reliance on suppliers including Nvidia and Huawei amid US export controls.

Raportoinut AI

Advanced Micro Devices posted first-quarter results that topped expectations, with revenue climbing 38 percent on robust server chip sales tied to artificial intelligence.

Nebius Group continues to see strong interest in its AI computing services.

Raportoinut AI

NVIDIA's latest AI infrastructure uses liquid cooling at temperatures hotter than a typical hot tub. The approach eliminates traditional fans and chillers in data centers. It aims to cut energy use, water consumption and noise.

Tämä verkkosivusto käyttää evästeitä

Käytämme evästeitä analyysiä varten parantaaksemme sivustoamme. Lue tietosuojakäytäntömme tietosuojakäytäntö lisätietoja varten.
Hylkää