Micron has just announced its new 9550 PCIe Gen5 E1.S data center SSDs have been added to the NVIDIA recommended vendor list (RVL) for the NVIDIA GB200 NVL72 AI system and its derivatives.
VIEW GALLERY – 2 IMAGES
The company announced today that the NVIDIA GB200 NVL72 uses the GB200 Grace Blackwell Superchip to deliver “rack-scale, energy-efficient AI infrastructure”, while the enablement of PCIe Gen5 storage in the system makes the Micron 9550 SSD an “ideal fit for optimizing performance and power efficiency in AI workloads like large-scale training of AI models, real-time trillion-parameter language model inference and high-performance computing (HPC) tasks”.
Compared with other industry offerings, the 9550 SSD delivers up to 34% higher throughput for NVIDIA Magnum IO GPUDirect (GDS) and up to 33% faster workload completion times in graph neural network (GNN) training with Big Accelerator Memory (BaM). The Micron 9550 SSD saves energy and sets new sustainability benchmarks by consuming 81% less SSD energy per 1TB transferred than other SSD offerings with NVIDIA Magnum IO GDS and up to 43% lower SSD power in GNN training with BaM.
Jeremy Werner, corporate vice president and general manager of Micron’s Storage Business Unit said: “Micron’s memory and storage products play a critical role in meeting the growing requirements of demanding AI workloads from the data center to the edge. By integrating the Micron 9550 SSD on the GB200 NVL72, server companies can integrate a high-performance, energy-efficient Gen5 data center storage solution into their AI server systems“.
Keith Morris, vice president of Product Management at NVIDIA said: “Ultra-fast and energy-efficient NVMe storage is crucial to the NVIDIA GB200 NVL72 rack-scale design. The Micron 9550 SSD can be integrated by our solution partners into their systems based on the GB200 NVL72 reference architecture to enable higher performance and efficiency“.