AMD CDNA Discussion Thread

Is it 1:1 or 2:1 FP32?

“Inside the AMD Instinct MI200 is an Aldebaran GPU featuring two dies, a secondary and a primary. It has two dies with each consisting of 8 shader engines for a total of 16 SE's. Each Shader Engine packs 16 CUs with full-rate FP64, packed FP32 & a 2nd Generation Matrix Engine for FP16 & BF16 operations.”

 

Mostly the latter.

 

So, as I said, MI200 is ~5× better in FP64 than A100 (47,9 to 9,7 TFLOPS), possibly more than 2.4× better in FP64 tensor than A100 (47,9 compared to 19,5 TFLOPS) and faster in FP16 than A100 (383 compared to 78/312 TFLOPS). How dare they?

 

A100 has 19,5 TFLOPs FP64 with 350W (or 300W 80GB PCIe). I never questioned that MI200 will deliver more FP64. That AMD is going up to 500W shows more how desperate they are to be in the AI-compute game. 18 months after GA100 it is worse than other competitions like Tesla. MI200 is a optimized HPC product for FP64 supercomputers.

 

Half that but yes!

?
H100 is 1000W so 500W is super tame by OAM standards.

They dun give a fuck.
Matrix engine is mostly untouched gen over gen.

It's not even the truly funny product.
Just a pre-workout mix mostly.

 

…for tensor ops. For standard ops it's 9,7 TFLOPS.

 

They're all kinda memey numbers (also A100 is 400W vanilla and 500W cooker for 80GB SKUs).
Either way all arguments against MI250 the hardware are also kinda memey since exabowl is Intel vs AMD with not a single nV GPU in sight...

 

Is this exabowl only running for one season?

 

Those things are very not cheap so mostly one, yea.
Euros and China are looking into homegrown shit for exascale so that nulls out the big dGP three entirely.

 

Well Intel is mostly out for next wave as they pissed off everybody with their 4 years delay...
Nvidia is already offering much cheaper exascale systems with Grace-Hopper and better real world performance thanks to faster infiniband and offload DPU acceleration. Ironically, even AMD can't offer the full stack of CPU+GPU+DPU+Infiniband that is the base architecture of modern HPC and that Nvidia is heavily promoting/selling now....

 

Not bad for a two silicon GPU.

 

Which is why El Capitan is MI300!
Lmao.

No one wants that.

Ethernet won.
Pack up.

 

You can't measure the success of a product by few political government deals. I see financial earnings and market share where AMD is a dwarf in HPC and graphics compared to Intel and NV. MI300 won't change that. Whatever AMD does, at the end, they are severely limited by TSMC...

That's why Bluefield2 is exceeding sales expectation and BF3 has already a long list of customers waiting for delivery...

Yeah sure...


Stop your FUD and go back home

 

?
Looks like your eyes are still bad.

Way, way less so than Nvidia so dunno how that is relevant.

Hard to not beat expectations when there was no expectations.
Again, those things are only ever useful for hypervisor offload in VM favelas a-la Amazon Nitro...
...which brings on a whole other bag of funny given every SmartNIC customer of note can and will cook their own.

It sure did.
Even the new Cray recipe is just a slightly souped up Ethernet.
Pack up!

 

Is there an independent source for what the industry is actually using? It seems everyone cherry picks to show their product in the best light - e.g. Intel likes to talk about 100G class interconnects. Presumably this would exclude a ton of stuff including run of the mill Ethernet.

 

political? 5 years electricity spendings is comparable to cost of the hardware.
and Epic is f.... efficient comparing to Intel. that's why it was chosen.

 

No, all kinda of NIC MSS data are wonky as hell.
But Cray using souped up Ethernet for their newest shiniest HPC offering tells a lot.

No he means nV getting pwn'd out of El Capitan bidding.
Should've made a better APU!

 

and don't forget about cpu-gpu memory coherency. Intel doesn't have it.

 

I believe the reason it was chosen was intel didn't support PCIE-4. That's the only reason NV is using Epic in their DGX and HGX servers.

 

not really, power efficiency in MW per Exaflop was one of their goals.
“Aurora” is burning twice as much electricity to deliver slightly less performance than “Frontier”. And at $1 per watt per year to keep a supercomputer running, it could cost close to $60 million a year power “Aurora”, which adds up to close to $240 million over four years. At only 29 megawatts, you are talking only $116 million for “Frontier”.