Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

My Experience and Advice for Using GPUs in Deep Learning: Which GPU to get

timdettmers.com

Post reply on HN
Print view View original

11–20 of 34 posts

Re: My Experience and Advice for Using GPUs in Deep Learning: Which GPU to get

#11

Post by steve_musk »

shaklee3 wrote: post #10
ageitgey wrote: post #2

This is a great article and I highly respect his opinions. However, since you are probably eagerly reading this to see how fast the new RTX cards are, so you should know upfront that the numbers he has so far are just estimates based on specs: > Note that the numbers for the RTX 2080 and RTX 2080 Ti should be taken with a grain of salt since no hard performance numbers existed. I estimated performance according to a…

I'd guess that the performance could be slightly better than the 1080 scaled by cores/MHz/FLOPS. The reason being that the memory bandwidth is higher on the 2080, and that's hard to model unless the person knows exactly how efficient the kernel is and if it's memory bound.

Plus the architecture improvements. Do we know how many cores per SM? They’ve decoupled int and FP execution units which could give larger increases for certain kernels (although FP heavy deep learning kernels aren’t likely to benefit as much, they will still get address calculation benefits).

Re: My Experience and Advice for Using GPUs in Deep Learning: Which GPU to get

#12

Post by steve_musk »

syntaxing wrote: post #8

Hacker news hug of death? Anyone here have any experience using AMD cards with something like PlaidML? I have a 1050Ti SSC but I'm starting to feel the limitation as my complexity grows. But getting a 1080 is a bit out of my budget right now. I'm tempted to get the new Vega 56 released recently.

You could wait and see how pascal prices fall after Turing comes out.

Re: My Experience and Advice for Using GPUs in Deep Learning: Which GPU to get

#13

Post by fermienrico »

wmf wrote: post #9
fermienrico wrote: post #7

The cost/performance plot - shouldn't it be "Lower is better"? It says "Higher is better". Lower value would indicate lower cost per unit level of performance. It should be "Lower is better" or the plot needs to say "Performance/Cost". Am I missing something?

You're missing the principle of charity.

huh?

Re: My Experience and Advice for Using GPUs in Deep Learning: Which GPU to get

#14

Post by shaklee3 »

steve_musk wrote: post #11
shaklee3 wrote: post #10

Earlier quoted context omitted.

I'd guess that the performance could be slightly better than the 1080 scaled by cores/MHz/FLOPS. The reason being that the memory bandwidth is higher on the 2080, and that's hard to model unless the person knows exactly how efficient the kernel is and if it's memory bound.

Plus the architecture improvements. Do we know how many cores per SM? They’ve decoupled int and FP execution units which could give larger increases for certain kernels (although FP heavy deep learning kernels aren’t likely to benefit as much, they will still get address calculation benefits).

I hadn't seen the whitepaper on Turing yet. Where did you see they decoupled them?

Re: My Experience and Advice for Using GPUs in Deep Learning: Which GPU to get

#15

Post by scottlegrand2 »

The biggest advance here is that Nvidia has produced a consumer card that has all the high-end deep-learning features. This was missing in both the Pascal and Volta Generations even though in Pascal fp32 was full power. I think the TPU scared them and that's a good thing.

Re: My Experience and Advice for Using GPUs in Deep Learning: Which GPU to get

#16

Post by lern_too_spel »

The "I have almost no money" recommendation should include Colab. https://medium.com/deep-learning-turkey/google-colab-free-gp...

Somebody who has almost no money isn't going to be able to equip a desktop with a GTX 1050 Ti ($175), fast disk ($50), and RAM ($50) on an entry level cpu/motherboard/power supply/case/monitor/peripherals ($300) and pay for the electricity used during training. Colab can be accessed from a free public computer or a cheap Chromebook ($200).

Re: My Experience and Advice for Using GPUs in Deep Learning: Which GPU to get

#17

Post by p1necone »

nolok wrote: post #3
ageitgey wrote: post #2

This is a great article and I highly respect his opinions. However, since you are probably eagerly reading this to see how fast the new RTX cards are, so you should know upfront that the numbers he has so far are just estimates based on specs: > Note that the numbers for the RTX 2080 and RTX 2080 Ti should be taken with a grain of salt since no hard performance numbers existed. I estimated performance according to a…

A great way to turn a listing you can trust enough to use as one of your comparison basis, into a listing made up of imaginary marketing numbers. I guess the click baiting is needed / the best option, but I hate that's it's what most web resources are like now.

The clock rates, number of CUDA cores, memory size/type etc in the new cards aren't really "imaginary marketing numbers". NVidia could have changed their hardware so they could put bigger numbers on paper without corresponding real world performance gains, but that's a big assumption for you to seemingly take as fact.

Re: My Experience and Advice for Using GPUs in Deep Learning: Which GPU to get

#18

Post by KSS42 »

fermienrico wrote: post #7

The cost/performance plot - shouldn't it be "Lower is better"? It says "Higher is better". Lower value would indicate lower cost per unit level of performance. It should be "Lower is better" or the plot needs to say "Performance/Cost". Am I missing something?

Do you mean "Figure 3: Normalized performance/cost numbers"?

Its performance/cost and not cost/performance.

Or maybe the author fixed a typo?

Re: My Experience and Advice for Using GPUs in Deep Learning: Which GPU to get

#19

Post by songgao »

KSS42 wrote: post #18
fermienrico wrote: post #7

The cost/performance plot - shouldn't it be "Lower is better"? It says "Higher is better". Lower value would indicate lower cost per unit level of performance. It should be "Lower is better" or the plot needs to say "Performance/Cost". Am I missing something?

Do you mean "Figure 3: Normalized performance/cost numbers"? Its performance/cost and not cost/performance. Or maybe the author fixed a typo?

I think it used to be cost/performance and was later fixed. GP left comment before the fix.
Post reply on HN