Micron Technology Begins Mass Production of HBM4 Memory for NVIDIA, with Speed Increased by Approximately 2.3 Times Compared to Previous Generation HBM3E

robot
Abstract generation in progress

On March 17, during the NVIDIA GTC (GPU Technology Conference) held early this morning, Micron announced that several of its storage products have entered mass production, all designed around the NVIDIA Vera Rubin platform.

Micron stated that its HBM4 production line began mass production and shipment in the first quarter of this year. The initial products are 36GB, 12-high stacked versions, specifically built for the Vera Rubin platform. These products have pin speeds exceeding 11Gb/s, offering over 2.8TB/s of memory bandwidth, approximately 2.3 times faster than the previous generation HBM3E, with more than 20% improvement in power efficiency.

Additionally, Micron announced that it has provided early samples of 48GB HBM4 with 16-high stacking to customers. Compared to the 12-high version, this model has a 33% increase in single-chip capacity, further enhancing the available memory capacity per HBM module.

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin