Intel · Tom's Hardware
Hot Chips 2026: Intel dives deep on Crescent Island AI accelerator
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
This Tom's Hardware Premium article is free to read with a Tom's Hardware account; no payment necessary.
Key facts
- Crescent Island is built up from four Xe3P slices, each containing eight Xe Cores, for a total of 32
- In addition, Xe3P offers 512KB of L1 cache or shared local memory per Xe Core, a structure that started out at 256KB on Battlemage and grew by approximately 1.33x on Panther Lake's Xe3 GPU
- Intel shared more details of its Crescent Island AI accelerator, powered by the Xe3P architecture, at the Hot Chips symposium this week
- As a refresher, Crescent Island is a 350W air-cooled PCIe card that uses up to 480 GB of LPDDR5X memory, meaning it can be deployed in traditional servers without exotic power and cooling requirements
Summary
Intel shared more details of its Crescent Island AI accelerator, powered by the Xe3P architecture, at the Hot Chips symposium this week. As a refresher, Crescent Island is a 350W air-cooled PCIe card that uses up to 480 GB of LPDDR5X memory, meaning it can be deployed in traditional servers without exotic power and cooling requirements. Crescent Island is built up from four Xe3P slices, each containing eight Xe Cores, for a total of 32. The Xe3 graphics architecture, as seen on Intel's Panther Lake processors, already modified the capacity and flexibility of the GPU cache hierarchy to improve utilization and decrease performance-sapping register spills, and Xe3P further refines that hierarchy.