Hacker News Reader

Comment by liuliu | Hacker News Reader

Seems to be good speedup overall relative to 2080 Ti (including FP16: see relatives 2080 Ti v Titan: https://lambdalabs.com/blog/2080-ti-deep-learning-benchmarks...). This suggests we should see another Titan card that is even more expensive in the pipeline given the FP16 performance? Or maybe TF32 performance is going to be what NVIDIA promotes in this generation (only if they have better number than FP16?)?

View on HN

Here's hoping for an A100 titan with un-nerfed FP64. The 3090 is twice as nerfed as previous generations, which were also bad at 1:32. Now it's 1:64 :(

It seems that Radeon VII and Titan V are the last cards with decent fp64 performance for foreseeable future. Both Nvidia and AMD now basically have different architectures for their consumer and data-center products.

Yep, sure looks that way. I'll still be dreaming of a Titan A!

The FP64 units are a separate addition that eat a lot of die space, right? I wouldn't use the word "nerf" for the tradeoff between having more SMs versus having more features in the SMs.

They eat die space but not TDP.

What workloads do you run that require fp64?

Simulation.

Radeon VII is the best bang for the bucks in the FP64 space, then older K80s. Titan V/V100 are still expensive.

Yep! I've got CUDA, so I still have to pay the green tax.

FP64 is not needed for deep learning.

What makes you think I'm doing deep learning?

You’re commenting on the post called “Benchmarking deep learning workloads”.

Reply on news.ycombinator.com