Nvidia · Intel · Tom's Hardware
Intel's Crescent Island AI accelerator officially powers new GPU D-Series products
Compiled by KHAO Editorial — aggregated from 2 sources. See llms.txt for citation guidance.
◎ Multiple-sources
At OCP 2026 today, Intel has given Crescent Island a proper name: the Intel GPU D-Series.
Key facts
- For reference, each of the 72 Rubin GPUs in Nvidia's Vera Rubin NVL72 rack-scale system can push a theoretical 17.5 PFLOPS of FP8 throughput, but each of those chips requires liquid cooling
- At OCP 2026 today, Intel has given Crescent Island a proper name: the Intel GPU D-Series
- It also disclosed the final memory bandwidth to expect from these AI inference accelerators: 1.5 TB/s
- Intel GPU D-Series products, in contrast, are meant to be deployed in traditional air-cooled rack servers scaling up to eight GPUs, like Nvidia's HGX systems
Summary
The team already knew that Crescent Island is the first chip to be built on Intel's Xe3P graphics architecture (or massively parallel computing architecture, really, as the chip lacks most or all of the graphics-specific functional units that would characterize a true GPU). For reference, each of the 72 Rubin GPUs in Nvidia's Vera Rubin NVL72 rack-scale system can push a theoretical 17.5 PFLOPS of FP8 throughput, but each of those chips requires liquid cooling and likely has a TGP measured in kilowatts. Intel GPU D-Series products, in contrast, are meant to be deployed in traditional air-cooled rack servers scaling up to eight GPUs, like Nvidia's HGX systems. In order for that kind of distributed inference deployment to work, in which multiple GPUs will presumably act as one, Intel will also need a robust software stack.