Deep learning setup

[__Peter__]

2 minutes ago, Crazycatman said:

Oh forgot about the security stuff, honestly didn't care about it. I mean't if you have a low tier CPU were you upgrading it ever in the future?

Yeah I don't care, either. No this is not planned for this computer. For any heavy training of tested nets I'll use web services.

[__Peter__]

On 14.5.2018 at 6:13 PM, brob said:

The Xeon E5-1650 v4 is rated at 140W TDP (thermal design power). It needs a fairly robust cooler.

 

The Dark Rock Pro 3 cooler will do a good job. However I believe it will interfere with the 1st PCIe slot. This is a general problem with larger coolers on the X99-WS/USB 3.1. The NH-U14S has the same problem.

 

The Noctua NH-U12S is compatible with the motherboard and is rated up to 165W TDP.

@brob Can I also buy a other CPU-Fan such as the BeQuiet Pure Rock (CPU-Fan)? Or is there any other good alternative that fits in the mobo, if I cant buy the  Noctua NH-U12S?

[brob]

32 minutes ago, __Peter__ said:

@brob Can I also buy a other CPU-Fan such as the BeQuiet Pure Rock (CPU-Fan)? Or is there any other good alternative that fits in the mobo, if I cant buy the  Noctua NH-U12S?

Sure, any cooler that is compatible with LGA2011 / LGA2011-3 could be used. So long as you are using standard height memory modules (~30mm) the only concern would be interference with the rightmost PCIe expansion slot. (ECC memory modules tend to be 30mm tall.)

 

Remember, the cpu is 140W TDP, so it needs a pretty good cooling solution. One rated for at least 140W.

 

[VanBantam]

A bit late to the party... for future folks that come across this thread here are my two cents.

In general, as of this writing, I would caution against getting a Titan V and for that matter a burly cpu and instead get two 1080 ti 11gb, and think REALLY hard about thermals.  The reason for this is that you can train two models at the same time with different hyper parameters.  In such a setup I would recommend picking a mobo that has two pcie rev 3 x16 slots.  In my own dev rig I have 4 x 1080 ti 11gb, yes two of them are on x8 slots.  I also have a 1tb nvme ssd to keep my gpus fed with data; sata ssds are a bottleneck for the work I do.

Remember for deep learning it's the gpu that is going to be doing the heavy lifting not the cpu, unless you're doing deep reinforcement learning which is a different thread all together.  

 

Side note I would also recommend making sure your psu can source enough watts to your gpu given everything else you have plugged in.  For example I can set the power target for my gpus to 300 watts, so x 4 that's 1200 watts.  So yeah I have a 80+ Ti 1600 watt psu, yes my electricity bill is high.