Intel Unveils New Data Center GPU and AI-Focused Systems
Intel has introduced a new data center graphics processing unit (GPU), codenamed Crescent Island, as well as a rack-scale reference design based on its Gaudi 3 systems. This move is a significant step for the company in its pursuit of capturing a larger share of the artificial intelligence (AI) market, where it lags behind Nvidia and AMD. The new GPU, Crescent Island, is designed to be scalable and efficient, with up to 160GB of memory and employing Intel's Xe3P microarchitecture.
Key Takeaways:
- Intel has launched a new data center GPU, codenamed Crescent Island, which is part of the company's push into the AI market.
- The new GPU will utilize Intel's Xe3P microarchitecture and feature up to 160GB of memory.
- Crescent Island chips are expected to begin customer sampling in the second half of 2026.
- Intel's AI chips could offer efficiencies when used alongside Nvidia GPUs for certain workloads.
- The company will focus on AI inference and agentic AI, which involves running AI models in real-time.
- Intel is seeking to catch up with Nvidia and AMD in the AI space, a market where the latter two have established a significant presence.
- Wedbush analysts have expressed caution regarding Intel's potential revenue from AI accelerators in the near term.
Statistics:
- Intel shares have risen 84% year to date and 57% over the past 12 months.
- The new GPU, Crescent Island, is expected to be part of the Gaudi 3 systems.
- Intel's Xe architecture data center GPU will provide efficient headroom for customers, with up to 160GB of memory.
Sources:
- Intel Corporation - press release (Tuesday)
- Wedbush analysts - unnamed (acknowledging an Intel AI-related development niche)