Intel patents chiplet GPU design
By Jon Peddie (October 29, 2024)
The device could be first commercial GPU using chiplets.
Intel’s recent GPU patent focuses on a chiplet architecture to improve scalability, computing power, and energy efficiency. The design uses separate chiplets for specific tasks, enabling flexibility by allowing components to be swapped or selectively activated as needed. Intel’s approach includes parallel processing with SIMT architecture, optimizing performance through synchronized thread execution, and enhanced pipelining. This could support Intel’s Falcon Shores GPU.
Intel has patented an innovative GPU architecture leveraging separate logic chiplets to enhance performance. This disaggregated design aims to boost scalability, computing capabilities, and energy efficiency, marking significant advancements in graphics processing technology.
To read the full article, click here
Related News
- New AMD Patent Describes Potential Chiplet-Based GPU Design
- SEMI 3D & Systems Summit to Spotlight Trends in Hybrid Bonding, Chiplet Design and Environmental Sustainability
- NEDO Selects Rapidus for “Development of Chiplet, Package Design, and Manufacturing Technology for 2nm-Generation Semiconductors”
- AMD Receives IEEE 2024 Corporate Innovation Award for Leadership in Chiplet Design for High-Performance and Adaptive Computing
Latest News
- HyperLight Launches 110GHz Intensity Modulator with Record low Vπ, Leveraging Its TFLN Chiplet™ Platform
- OFC 2025: Scintil Photonics showcases LEAF Light™, world’s first single-chip, multi-wavelength laser source for DWDM co-packaged optics in AI datacenters
- Lightmatter Welcomes Industry Leader Jason Zander to Its Board of Directors
- Alphawave Semi Reveals Suite of Optoelectronics Silicon Products addressing Hyperscaler Datacenter and AI Interconnect Market
- Zuken Joins IBM Research AI Hardware Center to Develop Next-Generation AI Hardware Solutions