GPU Headaches: Notes on Installing CUDA, CuDNN and Tensorflow on Manjaro
1–10 of 42 posts
Re: GPU Headaches: Notes on Installing CUDA, CuDNN and Tensorflow on Manjaro
#2Add Bumblebee to the mix and you get even more headache. Argh.
Re: GPU Headaches: Notes on Installing CUDA, CuDNN and Tensorflow on Manjaro
#3So basically, your calculations for deciding whether purchasing physical GPUs or using cloud GPUs is more cost effective should add $5,000 (50 hours at $100 an hour seems reasonable) onto the cost of any physical rig, and assume you have a spare 50 hours of opportunity cost to set it up.
All the ML researchers lusting for bare metal need to decide if they want to be "Gentoo Ricers" - https://funroll-loops.teurasporsaat.org/ - or if they just want to train models and get real work done.
Re: GPU Headaches: Notes on Installing CUDA, CuDNN and Tensorflow on Manjaro
#4So basically, your calculations for deciding whether purchasing physical GPUs or using cloud GPUs is more cost effective should add $5,000 (50 hours at $100 an hour seems reasonable) onto the cost of any physical rig, and assume you have a spare 50 hours of opportunity cost to set it up. All the ML researchers lusting for bare metal need to decide if they want to be "Gentoo Ricers" - https://funroll-loops.teurasporsa…
Or assume you aren't an outlier and can do it in 0.5-3 hours.
Re: GPU Headaches: Notes on Installing CUDA, CuDNN and Tensorflow on Manjaro
#5So basically, your calculations for deciding whether purchasing physical GPUs or using cloud GPUs is more cost effective should add $5,000 (50 hours at $100 an hour seems reasonable) onto the cost of any physical rig, and assume you have a spare 50 hours of opportunity cost to set it up. All the ML researchers lusting for bare metal need to decide if they want to be "Gentoo Ricers" - https://funroll-loops.teurasporsa…
Why spend 50 hours figuring it out from scratch again if the guy in the article already told you exactly what you need to do?
Re: GPU Headaches: Notes on Installing CUDA, CuDNN and Tensorflow on Manjaro
#6So basically, your calculations for deciding whether purchasing physical GPUs or using cloud GPUs is more cost effective should add $5,000 (50 hours at $100 an hour seems reasonable) onto the cost of any physical rig, and assume you have a spare 50 hours of opportunity cost to set it up. All the ML researchers lusting for bare metal need to decide if they want to be "Gentoo Ricers" - https://funroll-loops.teurasporsa…
Except that I set up CUDA and Tensorflow in less than an hour. Admittedly, this is on Ubuntu (my colleagues don't like wild distro experiments), which may be easier.
I compile every Tensorflow version (to compile with march=native). It is usually uneventful and takes a couple of minutes of my time.
By the way, a Tesla card also costs > 5000 Euro and then add the cost of a machine with enough fast cores, memory, and disk space and you are north of 25000.
Re: GPU Headaches: Notes on Installing CUDA, CuDNN and Tensorflow on Manjaro
#7So basically, your calculations for deciding whether purchasing physical GPUs or using cloud GPUs is more cost effective should add $5,000 (50 hours at $100 an hour seems reasonable) onto the cost of any physical rig, and assume you have a spare 50 hours of opportunity cost to set it up. All the ML researchers lusting for bare metal need to decide if they want to be "Gentoo Ricers" - https://funroll-loops.teurasporsa…
50 hours is definitely an outlier. I'm pretty clueless when it comes to linux and drivers, and I managed to get an nvidia GPU working on ubuntu in about an hour or two of swearing and a dozen reboots.
Re: GPU Headaches: Notes on Installing CUDA, CuDNN and Tensorflow on Manjaro
#8Yeah, not sure why you would be in Grub for Nvidia graphics drivers. This whole thing seems pretty odd to me since I've not seen a Nvidia driver problem in several years. Was he trying to use like Ubuntu 12.04 or something.
Manjaro is a great choice and it does "just work" the best. All the others work just fine though.
Re: GPU Headaches: Notes on Installing CUDA, CuDNN and Tensorflow on Manjaro
#9So basically, your calculations for deciding whether purchasing physical GPUs or using cloud GPUs is more cost effective should add $5,000 (50 hours at $100 an hour seems reasonable) onto the cost of any physical rig, and assume you have a spare 50 hours of opportunity cost to set it up. All the ML researchers lusting for bare metal need to decide if they want to be "Gentoo Ricers" - https://funroll-loops.teurasporsa…
Except that I set up CUDA and Tensorflow in less than an hour. Admittedly, this is on Ubuntu (my colleagues don't like wild distro experiments), which may be easier. I compile every Tensorflow version (to compile with march=native). It is usually uneventful and takes a couple of minutes of my time. By the way, a Tesla card also costs > 5000 Euro and then add the cost of a machine with enough fast cores, memory, and d…
The author says they chose Manjaro because they couldn't get Ubuntu to work.
Re: GPU Headaches: Notes on Installing CUDA, CuDNN and Tensorflow on Manjaro
#10Yeah, not sure why you would be in Grub for Nvidia graphics drivers. This whole thing seems pretty odd to me since I've not seen a Nvidia driver problem in several years. Was he trying to use like Ubuntu 12.04 or something. Manjaro is a great choice and it does "just work" the best. All the others work just fine though.
I have had issues with centos 7.2 and nvidia drivers. Nvidia assume linux kernel sources are installed, but centos 7.2 puts them in a directory that the nvidia driver can't find. I ended up having to scp sources from a working machine and add symbolics links to get the drivers working (1080Ti card - i assume the Tesla drivers work better).