NVIDIA Unveils Custom High-Bandwidth Memory for AI Infrastructure
NVIDIA has expanded its NVLink Fusion technology with the introduction of NVIDIA NVHBM (High-Bandwidth Memory), a custom high-bandwidth memory technology designed to bring higher memory performance and efficiency to Exposed Processing Units (XPUs).
The new technology integrates NVIDIA's custom memory controller into the High-Bandwidth Memory (HBM) base die, eliminating the need for a separate memory controller on the XPU. This integration delivers up to 30% greater memory bandwidth and 15% lower HBM power consumption compared to traditional HBM architectures.
NVIDIA is establishing a standard NVHBM implementation available from multiple memory providers, reducing the engineering effort required to integrate and qualify memory across multiple suppliers. This will give NVLink Fusion customers a faster path for bringing custom AI chips to market.
The first partner to work on NVHBM as part of its broader collaboration with NVIDIA around NVLink Fusion is Amazon's Annapurna Labs, which will support NVLink Fusion with its next-generation Trainium chips starting with Trainium4. This will enable Amazon's chips and NVIDIA GPUs to work together with a common rack-scale architecture.