NEO Semiconductor Unveils X-HBM for AI Chips
NEO Semiconductor has introduced the world's first Extreme High Bandwidth Memory (X-HBM) architecture for AI chips, announced in a press release. This new architecture offers a 32K-bit wide data bus and potentially 512 Gbit per die density, providing 16 times more bandwidth or 10 times higher density compared to traditional HBM.
Built on NEO's proprietary 3D X-DRAM architecture, X-HBM is designed to meet the increasing demands of generative AI and high-performance computing. It significantly surpasses the capabilities of current memory technologies, such as HBM5 and the projected HBM8, by eliminating long-standing limitations in bandwidth and density.
NEO Semiconductor's CEO, Andy Hsu, emphasized that X-HBM is a fundamental breakthrough, offering AI chipmakers a path to deliver next-generation performance well ahead of the existing roadmap. The company will showcase this technology at the Future of Memory and Storage event in Santa Clara, California.
We hope you enjoyed this article.
Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.
Also, consider following us on social media:
More from: Data Centers
Subscribe to Silicon Brief
Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.
Whitepaper
Stanford HAI’s 2025 AI Index Reveals Record Growth in AI Capabilities, Investment, and Regulation
The 2025 AI Index by Stanford HAI provides a comprehensive overview of the global state of artificial intelligence, highlighting significant advancements in AI capabilities, investment, and regulation. The report details improvements in AI performance, increased adoption in various sectors, and the growing global optimism towards AI, despite ongoing challenges in reasoning and trust. It serves as a critical resource for policymakers, researchers, and industry leaders to understand AI's rapid evolution and its implications.
Read more