Intel quietly adds Jaguar Shores to its Gaudi AI Accelerator roadmap as it seeks to compete more fiercely with AMD and Nvidia


  • Intel is betting big on Jaguar Shores to compete in AI
  • Gaudi chips give Intel a shot at the AI ​​inference market
  • Intel hopes the 18A node will give it a production edge

Intel has been quietly building up its AI chip portfolio and recently added the Jaguar Shores AI accelerator to its roadmap, a major step in its bid to compete with the likes of Nvidia and AMD.

The Jaguar Shores AI accelerator, unveiled at the recent supercomputing conference SC2024, is a key part of Intel’s strategy to stay competitive. Although details are scarce, Jaguar Shores is likely a follow-up to Falcon Shores, which will be released in 2025.

Jaguar Shores could focus on AI inference – an area where Intel hopes to make progress against Nvidia and AMD. It remains unclear whether Jaguar Shores will be a GPU or an ASIC, but Intel’s current product roadmap suggests it could be a next-generation GPU designed for enterprise AI applications.

A battle for market relevance

Although Intel lags behind its competitors in AI training hardware, the company is now focusing on AI inference, leveraging its Gaudi chips and emerging technologies such as Falcon Shores and Jaguar Shores.

However, to regain its competitive advantage, Intel will have to overcome a number of technical and organizational challenges.

Intel has faced multiple setbacks in AI hardware, especially in the GPU segment. The company’s previous attempt to develop a GPU, Rialto Bridge, was canceled due to a lack of customer interest, leaving institutions like the Barcelona Supercomputer Center in a difficult position.

Intel’s plans for the Falcon Shores GPU have been revised several times, originally intended as an integrated CPU-GPU product and now reimagined as a standalone GPU.

Intel has largely ceded the AI ​​training market to Nvidia and AMD, with Nvidia dominating thanks to its GPUs and CUDA software stack. Intel CEO Pat Gelsinger acknowledged before his retirement the company’s distant position in the AI ​​race, admitting that Intel is currently behind Nvidia, AWS, Google Cloud and AMD.

Intel is banking on its upcoming 18A manufacturing node to give it an edge over rivals like TSMC. The 18A process, which includes new technologies such as RibbonFET transistors and back-end power delivery, promises to improve the chip’s efficiency and performance.

Via HPC wire

You might also like it

Related Post