Enroot sounds interesting:
https://github.com/NVIDIA/enroot
It basically returns containers to their chroot origins, promising "no performance overhead." I'm looking forward to more posts on that.
RTX3090 TensorFlow, NAMD and HPCG Performance on Linux
11–20 of 40 posts
Re: RTX3090 TensorFlow, NAMD and HPCG Performance on Linux
#12Earlier quoted context omitted.
Google Colab seems like a nice deal if you can't afford it.
What does google get for providing this service for free?
A way of creating a pipeline of future customers; goodwill; increased clue and interest in machine learning, which may help them sell more platform services in the future.
Re: RTX3090 TensorFlow, NAMD and HPCG Performance on Linux
#13When I first read the review, I couldn't understand why the author was mentioning that FP16 will surely be improved by new drivers despite not understanding that FP16 TFlops are exactly the same as FP32, tensor cores were nerfed and FP32 accumulate set to 0.5x speed, instead of Titan RTX's 1x. I'd say the results are as good as it gets, if you want a better performance, wait for Ampere Titan or Quadro.
I was under the impression the 3090 is the Titan of this generation.
Re: RTX3090 TensorFlow, NAMD and HPCG Performance on Linux
#14When I first read the review, I couldn't understand why the author was mentioning that FP16 will surely be improved by new drivers despite not understanding that FP16 TFlops are exactly the same as FP32, tensor cores were nerfed and FP32 accumulate set to 0.5x speed, instead of Titan RTX's 1x. I'd say the results are as good as it gets, if you want a better performance, wait for Ampere Titan or Quadro.
I was under the impression the 3090 is the Titan of this generation.
Rumor is that there will be a 48gb Ampere Titan. Nvidia has never been one to shy away from making money!
Re: RTX3090 TensorFlow, NAMD and HPCG Performance on Linux
#15Guess that is maximum many of us can afford. Hence features that are missing from A100 is a bit moot. But the update we are wait. Still based on what we saw 3090 really does not worth the money. Still 24gb is 24gb.
Google Colab seems like a nice deal if you can't afford it.
What is the vram they offer now? I forget if they give the full 24gb of k80 or not
Re: RTX3090 TensorFlow, NAMD and HPCG Performance on Linux
#16Re: RTX3090 TensorFlow, NAMD and HPCG Performance on Linux
#17Re: RTX3090 TensorFlow, NAMD and HPCG Performance on Linux
#18Guess that is maximum many of us can afford. Hence features that are missing from A100 is a bit moot. But the update we are wait. Still based on what we saw 3090 really does not worth the money. Still 24gb is 24gb.
If you run it 24/7, anyways the cost of electricity will be much more in a year or so. If you run it sparingly, within some time cloud based 30 series will be launched for sure.
Re: RTX3090 TensorFlow, NAMD and HPCG Performance on Linux
#19When I first read the review, I couldn't understand why the author was mentioning that FP16 will surely be improved by new drivers despite not understanding that FP16 TFlops are exactly the same as FP32, tensor cores were nerfed and FP32 accumulate set to 0.5x speed, instead of Titan RTX's 1x. I'd say the results are as good as it gets, if you want a better performance, wait for Ampere Titan or Quadro.
I was under the impression the 3090 is the Titan of this generation.
It's the "Titan class" card of this generation, which is the shady way Nvidia explained it wasn't a Titan. "Titan class" != Titan
Re: RTX3090 TensorFlow, NAMD and HPCG Performance on Linux
#20Guess that is maximum many of us can afford. Hence features that are missing from A100 is a bit moot. But the update we are wait. Still based on what we saw 3090 really does not worth the money. Still 24gb is 24gb.
If you run it 24/7, anyways the cost of electricity will be much more in a year or so. If you run it sparingly, within some time cloud based 30 series will be launched for sure.
0.35 kwh * 24 hours * 365 at $0.1/kwh is $300