Comment by fxtentacle
4 days ago
I don’t think they can.
NVIDIA, like everyone else on a bleeding edge node, has hardware defects. The chance goes up massively with large chips like modern GPUs. So you try to produce B200 cores but some compute units are faulty. You fuse them off and now the chip is a GP102 gaming GPU.
The gaming market allows NVIDIA to still sell partially defective chips. There’s no reason to stop doing that. It would only reduce revenue without reducing costs.
Nvidia doesn't share dies between their high-end datacenter products like B200 and consumer products. The high-end consumer dies have many more SMs than a corresponding datacenter die. Each has functionality that the other does not within an SM/TPC, nevermind the very different fabric and memory subsystem (with much higher bandwidth/SM on the datacenter parts). They run at very different clock frequencies. It just wouldn't make sense to share the dies under these constraints, especially when GPUs already present a fairly obvious yield recovery strategy.
You can't turn a GB200 into a GB202 (which I assume is what you meant since GP102 is from 2016), they are completely different designs. That kind of salvage happens between variants of the same design, for example the RTX Pro 6000 and RTX 5090 both use GB202 in different configurations, and chips which don't make the cut for the former get used for the latter.
> So you try to produce B200 cores but some compute units are faulty. You fuse them off and now the chip is a GP102 gaming GPU.
B200 doesn't have any graphics capabilities. The datacenter chips don't have any graphical units, it's just wasted die space.
As long as gaming GPUs will compete for same wafer space that AI chips use, the AI chips will be far more profitable to NVIDIA
Why don't they sell these to datacenters as well, which could run a "low core section" with reduced power and cooling?
Well the good thing for NVIDIA AI business is that most of your chips can sit unused in warehouses and still get rich. 6 million H100s sold but infrastructure (water cooled dc) for only a third of them exists in the world.