Rambus Preps for HBM3
By Gary Hilson, EETimes (August 23, 2021)
Final specifications for High Bandwidth Memory (HBM) 3 haven’t been finalized, but that’s not preventing Rambus from laying the groundwork for its adoption, driven by the memory bandwidth requirements of for AI and machine learning model training.
The silicon IP vendor has released its HBM3-ready memory interface consisting of a fully integrated physical layer (PHY) and digital memory controller, the latter drawing on intellectual property from its recent acquisition of Northwest Logic.
The subsystem supports data rates of up to 8.4 Gbps, leveraging decades of experience in high-speed signaling expertise as well as 2.5D memory system architecture design and enablement, said Frank Ferro, senior director of product marketing for IP cores. By delivering 1 terabyte per second of bandwidth, Rambus’ HBM3-compliant memory interface is said to double the performance of high-end HBM2E memory subsystems.
To read the full article, click here
Related Semiconductor IP
- HBM3 PHY and Controller.
- HBM3 Memory Model
- HBM3 DFI Verification IP
- HBM3 Synthesizable Transactor
- HBM3 Controller IIP
Related News
- Rambus Boosts AI Performance with 9.6 Gbps HBM3 Memory Controller IP
- Rambus Advances AI/ML Performance with 8.4 Gbps HBM3-Ready Memory Subsystem
- Rambus and Micron Extend Patent License Agreement
- Rambus Advances HBM2E Performance to 4.0 Gbps for AI/ML Training Applications
Latest News
- GF unveils roadmap to deliver the world’s most advanced FD-SOI platform for Physical AI
- GlobalFoundries marks Dresden expansion milestone, announces next-generation platform for Physical AI
- TSMC September 2026 Revenue Report
- Lattice Collaborates with Arm to Advance Secure, Adaptable AI Data Center Infrastructure
- ZLG Selects CAST CAN XL and TSN IP for Next-Generation Vehicle-Network Development and Test Tools