Jeff Clarke, Dell Technologies COO, has updated investors as part of an earnings call for his company’s Q4 2024 financials, and with it comes the news that NVIDIA is currently developing an AI accelerator that will consume as much as 1,000 watts of power. It’s unclear what this GPU is, exactly, but this spec would make it 42% more power hungry than its predecessor. (The H100 has a TDP of 700 watts.)
Clarke teasing the power of NVIDIA’s next-gen hardware, which apparently won’t require liquid cooling:
Obviously, any line of sight to changes that we’re excited about what’s happening with the H200 and its performance improvement. We’re excited about what happens at the B100 and the B200, and we think that’s where there’s actually another opportunity to distinguish engineering confidence. Our characterization in the thermal side, you really don’t need direct liquid cooling to get to the energy density of 1,000 watts per GPU.
As for when it could be arriving:
That happens next year with the B200. The opportunity for us really to showcase our engineering and how fast we can move and the work that we’ve done as an industry leader to bring our expertise to make liquid cooling perform at scale, whether that’s things in fluid chemistry and performance, our interconnect work, the telemetry we are doing, the power management work we’re doing, it really allows us to be prepared to bring that to the marketplace at scale to take advantage of this incredible computational capacity or intensity or capability that will exist in the marketplace.
NVIDIA’s latest AI GPU roadmap:
The Register notes:
It’s not entirely clear what card Clarke is referring to with the “B200,” since no chip by that moniker appears on the roadmap Nvidia shared with investors last fall. However, we suspect Clarke is actually referring to the GB200 Superchip which, like the GH200, is expected to combine Nvidia’s Grace CPU with its B100 GPU.