Well ok, if they double perf every 2 years, 2^5 = 32 times speedup. Llama gave us a 10 times speedup and a 10 times reduction in memory, so if they get to account for that, that’s 320 times. Memory architectures where all of the accelerator can be active all the time, and chiplet or whole wafer designs so you can have a lot more silicon than the reticle limit could be a lot more gain.
They already are using AI to design the new chips and will likely use it more heavily.
It really depends on which bottleneck is the limiting factor. I wouldn’t bet that they can’t. Simply using more silicon and calling it a ‘chip’ counts for this claim. (with multiple chiplet designs or whole wafer designs, the ‘package’ now has more silicon area than the reticle limit allows. So it’s not really a chip anymore, but an entire cluster of ‘chips’ sharing a common package. There is technically no limit to how big this can go, though the cost scales proportionally)
Nvidia claims their chips improved by a factor of a million over the past ten years and predicts they are going to do it again in the next ten. I do not believe they can pull this off, or at least I don’t believe they can pull this off without AI designing the new chips.
Well ok, if they double perf every 2 years, 2^5 = 32 times speedup. Llama gave us a 10 times speedup and a 10 times reduction in memory, so if they get to account for that, that’s 320 times. Memory architectures where all of the accelerator can be active all the time, and chiplet or whole wafer designs so you can have a lot more silicon than the reticle limit could be a lot more gain.
They already are using AI to design the new chips and will likely use it more heavily.
It really depends on which bottleneck is the limiting factor. I wouldn’t bet that they can’t. Simply using more silicon and calling it a ‘chip’ counts for this claim. (with multiple chiplet designs or whole wafer designs, the ‘package’ now has more silicon area than the reticle limit allows. So it’s not really a chip anymore, but an entire cluster of ‘chips’ sharing a common package. There is technically no limit to how big this can go, though the cost scales proportionally)