←back to thread

AMD now has more compute on the top 500 than Nvidia

(www.nextplatform.com)
195 points rbanffy | 5 comments | 18 Nov 24 18:54 UTC | HN request time: 0s | source
Show context
pie420 ◴[18 Nov 24 20:14 UTC] No.42176400[source]▶
layperson with no industry knowledge, but it seems like nvidia's CUDA moat will fall in the next 2-5 years. It seems impossible to sustain those margins without competition coming in and getting a decent slice of the pie
replies(5): >>42176440 #>>42177575 #>>42177944 #>>42178259 #>>42179625 #
metadat ◴[18 Nov 24 20:17 UTC] No.42176440[source]▶
But how will AMD or anyone else push in? CUDA is actually a whole virtualization layer on top of the hardware and isn't easily replicable, Nvidia has been at it for 17 years.

You are right, eventually something's gotta give. The path for this next leg isn't yet apparent to me.

P.s. how much is an exaflop or petaflop, and how significant is it? The numbers thrown around in this article don't mean anything to me. Is this new cluster way more powerful than the last top?

replies(14): >>42176567 #>>42176711 #>>42176809 #>>42177061 #>>42177287 #>>42177319 #>>42177378 #>>42177451 #>>42177452 #>>42177477 #>>42177479 #>>42178108 #>>42179870 #>>42180214 #
1. NineStarPoint ◴[18 Nov 24 21:49 UTC] No.42177479[source]▶
A high grade consumer gpu a (a 4090) is about 80 teraflops. So rounding up to 100, an exaflop is about 10,000 consumer grade cards worth of compute, and a petaflop is about 10.

Which doesn’t help with understanding how much more impressive these are than the last clusters, but does to me at least put the amount of compute these clusters have into focus.

replies(2): >>42177621 #>>42177989 #
2. vitus ◴[18 Nov 24 22:05 UTC] No.42177621[source]▶
You're off by three orders of magnitude.

My point of reference is that back in undergrad (~10-15 years ago), I recall a class assignment where we had to optimize matrix multiplication on a CPU; typical good parallel implementations achieved about 100-130 gigaflops (on a... Nehalem or Westmere Xeon, I think?).

replies(2): >>42177945 #>>42178222 #
3. NineStarPoint ◴[18 Nov 24 22:47 UTC] No.42177945[source]▶
You are 100% correct, I lost a full prefix of performance there. Edited my message.

Which does make the clusters a fair bit less impressive, but also a lot more sensibly sized.

4. winwang ◴[18 Nov 24 22:51 UTC] No.42177989[source]▶
4090 tensor performance (FP8): 660 teraflops, 1320 "with sparsity" (i.e. max theoretical with zeroes in the right places).

https://images.nvidia.com/aem-dam/Solutions/geforce/ada/nvid...

But at these levels of compute, the memory/interconnect bandwidth becomes the bottleneck.

5. ◴[18 Nov 24 23:14 UTC] No.42178222[source]▶