![\"\"](\".\/media_18c0607cae5d2a86832c87913331679960217fb99.jpg?width=750&format=jpg&optimize=medium\")
<\/p>\nRevealed this week at the 2025 OCP Global Summit, \u2018Crescent Island\u2019 marks the beginning of Intel\u2019s annual cadence of GPU releases that follows similar pushes by Nvidia and AMD after dealing with more than 15 years of missteps in the accelerator chip segment.<\/p>\n
<\/p>\n
Intel on Tuesday revealed a 160-GB, energy-efficient data center GPU that is part of a new annual GPU release cadence to deliver on the chipmaker\u2019s new strategy of providing open systems and software architecture for AI systems.<\/p>\n
Code-named \u201cCrescent Island,\u201d the GPU is \u201cpower- and cost-optimized\u201d for inference workloads running on air-cooled enterprise servers, according to Intel. The GPU features Intel\u2019s Xe3P microarchitecture that is optimized for performance-per-watt, 160 GB of LPDDR5X memory and support for a broad range of data types.<\/p>\n
[Related: Analysis: How Two Big Decisions Helped AMD Win The OpenAI Deal<\/a>]<\/p>\n The semiconductor giant said it plans to start sampling Crescent Island with customers in the second half of 2026. Until then, Intel is developing and testing what it\u2019s calling an open and unified software stack for heterogeneous AI systems on the company\u2019s Arc Pro B-Series GPUs to \u201cenable early optimizations and iterations.\u201d<\/p>\n The announcement confirms CRN\u2019s previous reporting last month<\/a> that Intel had an unannounced GPU design with a lower power requirement for servers on its road map that could arrive next year at some point.<\/p>\n Intel did not provide an update on \u201cJaguar Shores,\u201d the next-generation GPU announced earlier this year<\/a> that the company is designing for rack-scale platforms.<\/p>\n In a briefing with journalists last month, Sachin Katti, Intel\u2019s chief AI and technology officer, said that Crescent Island has \u201cenhanced memory bandwidth\u201d and \u201clots of memory capacity,\u201d making it a \u201cfantastic product for token clouds and enterprise-level inference.\u201d<\/p>\n Revealed this week at the 2025 OCP Global Summit, Crescent Island marks the beginning of a new annual cadence of GPU releases that Intel announced last week during its major press push<\/a> around its forthcoming \u201cPanther Lake\u201d and \u201cClearwater Forest\u201d CPUs.<\/p>\n Following similar pushes by Nvidia and AMD over the last two years to move to annual release strategies, this represents Intel\u2019s latest push to gain a foothold in the Nvidia-dominated AI infrastructure market after more than 15 years of missteps<\/a> in the accelerator chip segment that spanned across the company\u2019s last four CEOs.<\/p>\n