Intel "Crescent Island" GPU Gets D-Series Name, Supports Up to 480 GB of LPDDR5X
What happened
Intel has unveiled what its 'Crescent Island' D-Series GPUs will look like, introducing a dedicated AI accelerator in a server form factor after previous projects stalled. The GPU features 32 Xe3P cores, 256 XMX engines, 32 MB of unified L2 cache, and support for up to 480 GB of LPDDR5X memory. Intel rates it for up to 1.3 PetaFLOPS of FP8 performance, with support for formats ranging from FP4 to FP64. The card includes a media engine with four encoders and four decoders, which could assist with multimodal workloads requiring video generation and understanding. The card comes with a 160 GB memory configuration out of the box, exclusive to Intel-branded 'Crescent Island' graphics cards, while Intel allows its ODMs to equip the card with up to 480 GB of LPDDR5X memory for maximum VRAM capacity. The XMX engines have been redesigned from the four-deep systolic design on the regular Xe3 to 16-deep processing on the Xe3P. Additional details include FP4 data format support, large register files of 1 MB per core and L1 cache of 512 KB per core; in total there are 256 Vector engines and 256 of the new XMX engines, divided into groups of eight per Xe3P core. Additionally, the Xe3P has no graphics processing elements to output imagery, as the silicon is designed purely for AI inference workloads that require long context and agentic tasks.
Impact and signal
Affected components and suppliers
Source and time
Source: TechPowerUp · 10/12/2026 · View original source
Real-time pricing, supply signals and AI analysis for semiconductor traders