Nvidia Ampere Discussion [2020-05-14]

PS:

For Jensen personal usage

 

"Nvidia claims the A100 has 20x the performance of the equivalent Volta device for both AI training (single precision, 32-bit floating point numbers) and AI inference (8-bit integer numbers)." ....if you use new Tensor Float 32 -precision not supported by Volta

 

Ya i knew there was some type of typical Nvidia shenanigans at play when i read that 20x blurb.

 

And it'll be "just" 2.5x if you don't.

 

Some DGX A100 Test runs?
https://folding.extremeoverclocking.com/user_summary.php?s=&u=1096093

 

That UE5 demo is probably even more impressive compared to what NV can tech demo on a 3080/nvme optane system.

 

it's a change from previous Volta / Turing gen

another source:
https://www.marketwatch.com/story/n...is-coronavirus-2020-05-14?link=MW_latest_news

 

I sure hope this server GPU isn't the only thing they're going to show today, and we'll be able to get a glimpse of the new consumer lineup.

 

So now that Ampere is the overall arch for consumer and HPC, consumer chips will most likely cut down on Tensor units count, there is also a possibility of a Titan Ampere GPU as well, like Titan V.

The bigAmpere HPC is definitely a 128SM GPU, we need to figure out the frequency and power consumption now so we can infer some info about the rest of the lineup.

 

To reach 5PTFLOPS it needs a bit more than 128SM. Or really high clocks.

 

I haven't done the math but is that based on CUDA FLOPS or Tensor FLOPS? As the Tensor cores pump out a lot more.

 

8 GPUs pushing 5 PFLOPS is around 625 TFLOPS per GPU, clearly they're talking about Tensor-FLOPS and not general FP32 FLOPS

 

The A100 comes with
6,912 FP32 CUDA Cores @~1.41GHz
3,456 FP64 CUDA Cores,
432 Tensor Cores,
108 streaming multiprocessors
40 GB of GPU memory
within a 400-watt power envelope.

https://www.crn.com/news/components...m-ampere-a100-gpu-to-unify-training-inference
https://www.anandtech.com/show/15801/nvidia-announces-ampere-architecture-and-a100-products

 

DGX A100 specs

AMD EPIC 7742 !!!

 

Yeah I was being very lazy on the maths. This sounds correctto me then as the 2080Ti is rated at 440 TFLOPS in INT4 and that's with 80SM's. So it seems to be running at a slightly slower clock than the 2080Ti all else being equal.

 

So the first iteration: Tesla A100 is a cut down one, from 128SM to 108SM.

 

Big numbers here !!!

 

Omniverse ray tracing stuff looks great. Link should be to right time, if not it starts around 9:42. The actual explanation what omniverse is before the demo part

 

So NVIDIA effectively traded FP32 CUDA cores with FP32 Tensor Cores, Tesla A100 is really just Ampere optimized for AI.

Regular FP32 is : 19.5 TF
Tensor FP32: 156 TF, accelerated to 312 TF effective through "sparse acceleration"

Consumer Ampere will definitely cut down on the advanced tensor stuff and trade back the lost FP32 CUDA cores.