Intel announces GPU D-series accelerators for AI
At the OCP Global Summit, Intel introduced GPU D-series accelerators aimed at data-center inference and agentic AI workloads. The company said the product was previously known by the codename Crescent Island and customer sampling is underway.
Event / data period: 2026-10-12
Published: · Updated:
Intel cites up to 480 GB LPDDR5X memory and 1.5 TB/s bandwidth per accelerator, plus 1.3 petaflops peak FP8 performance at 350 W. These are company specifications, not independent benchmarks.
Intel lists 160 GB of LPDDR5X memory on its PCIe card; it says partner designs can scale total memory up to 480 GB. Intel also cites 1.5 TB/s bandwidth, 1.3 petaflops peak FP8 performance and 350 W power. These are company statements, not independent benchmarks.
Data
Intel introduces GPU D accelerators
Intel introduced GPU D for AI data-center workloads at the OCP summit.
- · Occurred
Intel announces GPU D-series accelerators for AI
Intel introduced GPU D for AI data-center workloads at the OCP summit.
Methodology
The event is Intel’s product announcement dated October 12, 2026. Memory, bandwidth, FP8 and power figures are company-stated maximum specifications, not independent measurements.
Updated:
Subjects and places
Subject proposals
- Artificial intelligenceSuggested
- Subject suggested from the title or summary: AIwww.intel.com ↗
Geographic references
Only source-provided geographic references are shown. Opening an external map is optional. Optional story maps use OpenStreetMap. Opening a map sends your IP address and this site’s address to the map provider; location data remains readable as text without loading the map.
- United States · Place role: Coverage · Place type: Country or area · Location precision: RegionalEvidence
- Explicit preserved editorial country/region; no city or national centroid inferredwww.intel.com ↗