Has anyone "actually physically tried" installing Tesla K80's in a R720 server? If so, how did it turn out? I am interested in hearing both success and failure stories. And yes, I know it's documented as unsupported. That is not the question. I have seen reference to a University that had several servers in this configuration as part of their school cluster. I have R720's running with K20's that I want to upgrade. I have both K40's and K80's in my possession. Looking for some "been there, tried that" enlightenment in reference to the K80's.
Update: Installed second Tesla K80 in the R720 and everything is working fine.
Everything is functioning correctly and operating as expected.
Dual K80's at 100% are obviously much warmer overall than dual K20's, but they are staying well within their operating temp specs as the fans are running at a higher rpm. I was quite happy to find out the system fans are properly reactive to the K80 operating temp changes. This was a point of major concern going into this project.
All in all, I am quite pleased with how this project has turned out, as it really changes the landscape going forward now that we know it is possible.
The K80 works on R730 but the R720 may not be working. I could not see the K80 in their spare parts list for the R720. Apart from the any video card you will install, I would also like to draw your attention to power supplies. When you install a video card, please make sure that it meets the power. https://dell.to/3gzrZDO
Let us know if it helps!
DELL-Erman O
Social Media and Communities Professional
Dell Technologies | Enterprise Support Services
#IWork4Dell
Did I answer your query? Please click on ‘Mark as Accepted Answer’. ‘Thumbs up’ the posts you like!
Yeah, the K80's aren't in the R720 parts list as they are unsupported. They are on the R730 parts list since they are officially supported on that model, but I don't have any at this time. I'm good on the power, as I stated the R720's are currently running with dual K20's, I just need faster, that's why I have the K40's. The K80's are spares, but hey, if I can get them to work, then they're going in.
As an update, I drilled down deeper in the university's computer cluster specs. Deeper in the documentation the reference to R720's magically turns into R730's. My guess is that the R720 reference in the cluster spec overview was either a typo or someone just mistakenly referenced the wrong model number. I was bummed.
Still waiting to hear about actual attempts. Surely I'm not the first person to have all of this equipment sitting on a bench and wondered if it might actually work regardless of what the "official" docs indicated.
Hi. That server has Windows Server 2019 DataCenter on it. I have no idea how Windows 10 would run on a R720 with GPU's. Sorry for the late response, but I just saw your message. Did you ever get your Code 12 error resolved?
Hi. What happens if you leave the card in the machine, but unplug the cable to the GPU and try to boot it up? Does it halt still, or does it continue to boot up normally?
I successfully deployed the R720 system with two Tesla K80, however, the 2 Tesla cards cannot reach their theoretical performance (such as double-precision FP64 should be 1.37 TFLOPs for a single GPU, but only 0.9 TFLOPs or 3.6TFLOPs for 4 GPUs as shown in the AIDA64 GPGPU Benchmark). If you have any idea to solve this problem, please share it. Thank you.
OldSchoolAdm1n
1 Rookie
•
16 Posts
5993
1
Posted December 19th, 2020 06:00
Update: Installed second Tesla K80 in the R720 and everything is working fine.
Everything is functioning correctly and operating as expected.
Dual K80's at 100% are obviously much warmer overall than dual K20's, but they are staying well within their operating temp specs as the fans are running at a higher rpm. I was quite happy to find out the system fans are properly reactive to the K80 operating temp changes. This was a point of major concern going into this project.
All in all, I am quite pleased with how this project has turned out, as it really changes the landscape going forward now that we know it is possible.
James