Intel names Crescent Island GPUs D-Series with up to 480 GB of memory

First reported by Wccftech at · Updated · 4 sources

The upcoming D270 AI inference card offers 1.3 petaflops of dense FP8 compute and 1.5 TB/s of memory bandwidth. The lineup uses LPDDR5X memory, with capacity reaching 480 GB. According to Wccftech, the D-Series is based on Intel's Xe3P architecture, and the D270 delivers its stated compute performance at 350 watts.

Covered by 4 publishers within 1 hour of the first report.

Reporting4

Wccftech Intel Crescent Island Squeezes 1.3 PFLOPs Of FP8 Into Just 350W As D270 Targets The Competition With Value-Oriented LPDDR5X Up To 480 GB · Hassan Mujtaba
ServeTheHome Intel’s Crescent Island AI Server GPU Gets a Name and Specs: Meet the Intel GPU D-Series · Ryan Smith
Tom's Hardware Intel's Crescent Island AI accelerator officially powers new GPU D-Series products · Jeffrey Kampman
Phoronix Intel Announces The GPU D Series For Crescent Island · Michael Larabel

Related

Applied Materials and Intel expand chipmaking development partnership
Intel and Applied Materials expand collaboration on chipmaking technology
Musk says his companies will run Terafab as Intel keeps its role
Intel and Broadcom chiefs warn financing could limit AI growth

Topics Intel