[jart]

Bro, Jensen Huang just unveiled a chip yesterday that goes 20 petaflops. Intel's latest raptorlake cpu goes 800 gigaflops. Can you really explain 25000x progress by the 2x larger die size? I'm sure reactionary America wanted Moore's law to run out of steam but the Taiwanese betrayal made up for all the lost Moore's law progress and then some.

[mechagodzilla]

That speedup compared to Nvidia's previous generation came nearly entirely from: 1) a small process technology improvement from TSMC, 2) more silicon area, 3) more power consumption, and 4) moving to FP4 from FP8 (halving the precision). They aren't delivering the 'free lunch' between generations that we had for decades in terms of "the same operations faster and using less power." They're delivering increasingly exotic chips for increasingly crazy amounts of money.

[Nokinside]

Pro tip: If you want to know who is the king of AI chips, compare FLOPS (or TOPS) per chip area, not FLOPS/chip.

As long as the bottleneck is the fab capacity as wafers per hous, the number of operations per second per chip area determines who will produce more compute with best price. It's a good measure even between different technology nodes and superchips.

Nvidia is leader for a reason.

If manufacturing capacity increases to match the demand in the future, FLOPS or TOPS per Watt may become relevant, but now it's fab capacity.

[hock_ads_ad_hoc]

Taiwanese betrayal? I’m not sure I understand the reference.

[jart]

There's no reference. It's just a bad joke. What they did was actually very good.