Wednesday, October 2nd 2024

NVIDIA Cancels Dual-Rack NVL36x2 in Favor of Single-Rack NVL72 Compute Monster

NVIDIA has reportedly discontinued its dual-rack GB200 NVL36x2 GPU model, opting to focus on the single-rack GB200 NVL72 and NVL36 models. This shift, revealed by industry analyst Ming-Chi Kuo, aims to simplify NVIDIA's offerings in the AI and HPC markets. The decision was influenced by major clients like Microsoft, who prefer the NVL72's improved space efficiency and potential for enhanced inference performance. While both models perform similarly in AI large language model (LLM) training, the NVL72 is expected to excel in non-parallelizable inference tasks. As a reminder, the NVL72 features 36 Grace CPUs, delivering 2,592 Arm Neoverse V2 cores with 17 TB LPDDR5X memory with 18.4 TB/s aggregate bandwidth. Additionally, it includes 72 Blackwell GB200 SXM GPUs that have a massive 13.5 TB of HBM3e combined, running at 576 TB/s aggregate bandwidth.

However, this shift presents significant challenges. The NVL72's power consumption of around 120kW far exceeds typical data center capabilities, potentially limiting its immediate widespread adoption. The discontinuation of the NVL36x2 has also sparked concerns about NVIDIA's execution capabilities and may disrupt the supply chain for assembly and cooling solutions. Despite these hurdles, industry experts view this as a pragmatic approach to product planning in the dynamic AI landscape. While some customers may be disappointed by the dual-rack model's cancellation, NVIDIA's long-term outlook in the AI technology market remains strong. The company continues to work with clients and listen to their needs, to position itself as a leader in high-performance computing solutions.
Source: Ming-Chi Kuo
Add your own comment

3 Comments on NVIDIA Cancels Dual-Rack NVL36x2 in Favor of Single-Rack NVL72 Compute Monster

#1
Gucky
Wait was GB200 already sold?
Posted on Reply
#2
hsew
GuckyWait was GB200 already sold?
It was made available for preorder in batches of 100,000+ units for nVidia’s biggest customers. I don’t believe any have been delivered yet, however.
Posted on Reply
#3
Jism
Frigging 1000+ amps an hour at 110V or 550+ amps an hour at 220V. I know some DC's allow for 380V which still yields 300+ amps an hour to run that thing fulltime.

And you need to cool all that 120KWH lol. This is no efficiency thing anymore.
Posted on Reply
Nov 23rd, 2024 03:22 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts