Digital Event Horizon
NVIDIA has expanded its NVLink Fusion platform with the integration of NVIDIA High-Bandwidth Memory (HBM) technology, NVHBM, providing a next-generation solution for high-performance computing and artificial intelligence (AI) applications. The new technology offers improved memory performance and efficiency, and is being validated and offered by leading memory partners. This expansion is a significant step forward for the development of AI infrastructure and will enable hyperscalers and AI innovators to build the next generation of semi-custom AI infrastructure.
NVIDIA has expanded its NVLink Fusion platform with the integration of NVIDIA High-Bandwidth Memory (HBM) technology, NVHBM.The new NVHBM technology offers improved memory performance and efficiency.It delivers up to 30% greater memory bandwidth and 15% lower HBM power consumption compared to traditional HBM architectures.The integration of NVHBM technology enables partners to access a broad ecosystem of CPU partners and technology providers.Amazon's Annapurna Labs is the first company to collaborate with NVIDIA on NVHBM technology.The expansion of NVLink Fusion with NVHBM technology represents a significant step forward for the development of AI infrastructure.
NVIDIA has taken a significant step forward in the development of high-performance computing and artificial intelligence (AI) infrastructure by expanding its NVLink Fusion platform with the integration of NVIDIA High-Bandwidth Memory (HBM) technology, NVHBM. This new technology represents a major advancement in the field of high-performance computing, and is expected to play a crucial role in the development of AI applications.
The expansion of NVLink Fusion with NVHBM technology is a significant development in the field of AI infrastructure. The new technology offers improved memory performance and efficiency, and is being validated and offered by leading memory partners. This expansion is a result of NVIDIA's commitment to advancing the field of AI and providing its customers with the latest technology and innovations.
According to NVIDIA, the traditional HBM architectures place the memory controller on the XPU die, consuming valuable silicon area that could otherwise be dedicated to compute. In contrast, NVHBM integrates the memory controller into the 3D HBM stack instead of the XPU, delivering up to 30% greater memory bandwidth and 15% lower HBM power consumption, and freeing up to 25% more area on XPU compute die compared with standard HBM4E.
The integration of NVHBM technology with NVLink Fusion enables partners to access a broad ecosystem of CPU partners, ASIC designers, system manufacturers, and technology providers. This means that hyperscalers and AI-native companies can focus their engineering resources on XPU innovation while using a proven technology stack for scale-up and scale-out networking, rack-scale systems, and software.
Amazon's Annapurna Labs is the first company to collaborate with NVIDIA on NVHBM technology, and will be working closely with the company to enhance performance and efficiency for AI workloads. Annapurna Labs will support NVLink Fusion with its next-generation Trainium chips starting with Trainium4, which will allow Amazon chips and NVIDIA GPUs to work together with common rack-scale architecture.
NVIDIA's NVLink Fusion platform enables partners to connect custom XPUs and CPUs to NVIDIA's rack-scale platform, providing a vertically integrated and horizontally open solution for AI infrastructure development. The platform is designed to be flexible and scalable, allowing hyperscalers and AI-native companies to focus their engineering resources on XPU innovation while using a proven technology stack for scale-up and scale-out networking, rack-scale systems, and software.
The expansion of NVLink Fusion with NVHBM technology represents a significant step forward for the development of AI infrastructure. The new technology offers improved memory performance and efficiency, and is being validated and offered by leading memory partners. This expansion is expected to play a crucial role in the development of AI applications, and will enable hyperscalers and AI innovators to build the next generation of semi-custom AI infrastructure.
In conclusion, the expansion of NVLink Fusion with NVHBM technology is a significant development in the field of AI infrastructure. The new technology offers improved memory performance and efficiency, and is being validated and offered by leading memory partners. This expansion is a result of NVIDIA's commitment to advancing the field of AI and providing its customers with the latest technology and innovations.
Related Information:
https://www.digitaleventhorizon.com/articles/NVIDIA-NVLink-Fusion-Expands-with-NVHBM-Custom-High-Bandwidth-Memory-A-New-Era-for-AI-Infrastructure-deh.shtml
https://blogs.nvidia.com/blog/nvlink-fusion-nvhbm-custom-high-bandwidth-memory/
Published: Wed Aug 26 18:43:43 2026 by llama3.2 3B Q4_K_M
