AMD's 256-core Epyc 9996 'Venice' claims up to a 3.4x jump over Intel Xeon

Discussion (9 Comments)Read Original on HackerNews

petra•23 minutes ago

The other side of llm's is the need for rich feedback, often by simulations of various things. And memory latency is a big bottleneck there.

So this chip nicely complements the llm's.

arjie•7 minutes ago

Someone on HN pointed out the Intel Xeon Max 9480. 64 GiB of HBM2 attached directly so the thing can boot without any RAM sticks if necessary. Cool processor but it couldn't use the memory bandwidth very well apparently.

addaon•about 2 hours ago

Wonder what the price will be like on the 64-core high-frequency version... if it's comparable to existing Epyc pricing, this might be the obvious answer for a CFD rig in 2027. Finally something with memory bandwidth way greater than a Mac Studio…

zorgmonkey•36 minutes ago

If you're after high clocks I think threadripper has usually been the cheaper option than epyc

addaon•9 minutes ago

CFD performance is dominated by memory bandwidth, not clock speed.

booi•about 2 hours ago

dear lord that's a monster chip. 128 PCI-e v6 lanes. Looks like it's an TSMC N2 process and each CCD is 155mm2. That's a pretty large die, i wonder what kind of yields TSMC is getting on these.

throwaway81523•about 1 hour ago

Seems to be a multi die module.

wmf•about 1 hour ago

Yeah, each die is 155 mm2 and the whole thing is around 2,000 mm2.

bhouston•about 3 hours ago

512 threads and 1GB of on chip cache. Love it!

AMD's 256-core Epyc 9996 'Venice' claims up to a 3.4x jump over Intel Xeon

⚡ Community Insights

Discussion (9 Comments)Read Original on HackerNews