Re: [AMBER] cudaGetDeviceCount failed unknown error

From: Ross Walker <ross.rosswalker.co.uk>
Date: Sat, 25 Nov 2017 15:33:16 -0500

Hi Bogac,

Very weird behavior. Can you try running pmemd.cuda as root and see if that works?

All the best
Ross


> On Nov 23, 2017, at 13:51, Ercig Bogac (BIOCH) <b.ercig.maastrichtuniversity.nl> wrote:
>
> Dear Ross,
>
> Sorry for the missing details. I am using CUDA 8.0 on Ubuntu 16.04 LTS.
>
> I installed the nvidia driver from .run installer. I assume I did the installation properly, because I have also done the same driver installation on our other computers and AMBER works smoothly on them.
>
> Please let me know if there is need for further details to solve this problem.
>
> Thank you very much for you help
>
> Best regards
>
> Bogac
> ________________________________________
> From: Ross Walker <ross.rosswalker.co.uk>
> Sent: 23 November 2017 17:08
> To: AMBER Mailing List
> Subject: Re: [AMBER] cudaGetDeviceCount failed unknown error
>
> Hi Bogac,
>
> Are you using CUDA 7.5 or CUDA 8.0? If 7.5 then upgrade to 8.0, there was a bug in 7.5 related to the way AMBER locates idle GPUs.
>
> Next, are you using Ubuntu? And if yes did you install the drivers by downloading the .run installer from the NVIDIA site or through apt-get?
>
> If the later I suspect you are hitting a bug in the way the package manager works that a couple of other people have run into as well recently. It appears that when one installs the NVIDIA driver through apt-get for some reason it doesn't install nvidia-modprobe and this is what leads to the cryptic behavior you are seeing.
>
> Try
>
> sudo apt-get install nvidia-modprobe
>
> Then try again.
>
> If you aren't running Ubuntu then please provide more details about your Linux install and environment.
>
> All the best
> Ross
>
>> On Nov 23, 2017, at 08:29, Ercig Bogac (BIOCH) <b.ercig.maastrichtuniversity.nl> wrote:
>>
>> Dear all,
>>
>>
>> I am trying to install Amber16 to my computer with the CUDA support. All steps of the installation went without any errors.
>>
>>
>> I have used ./configure -cuda gnu
>>
>>
>> Then make install
>>
>>
>> But when I try the make test , I get the following error.
>>
>>
>> cudaGetDeviceCount failed unknown error
>>
>> 0 file comparisons passed
>> 0 file comparisons failed
>> 333 tests experienced errors
>>
>>
>> I cant find any solutions on internet. I have seen one entry on the mail list, but there was no solution for this case. I have updated my driver and reinstalled cuda but it did not changed anything.
>>
>>
>> Here is what I obtain from nvidia-smi
>>
>>
>> Thu Nov 23 14:27:12 2017
>> +-----------------------------------------------------------------------------+
>> | NVIDIA-SMI 384.81 Driver Version: 384.81 |
>> |-------------------------------+----------------------+----------------------+
>> | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
>> | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
>> |===============================+======================+======================|
>> | 0 Tesla C2075 Off | 00000000:01:00.0 On | Off |
>> | 30% 57C P12 34W / N/A | 470MiB / 6066MiB | 9% Default |
>> +-------------------------------+----------------------+----------------------+
>>
>> +-----------------------------------------------------------------------------+
>> | Processes: GPU Memory |
>> | GPU PID Type Process name Usage |
>> |=============================================================================|
>> | No running processes found |
>> +-----------------------------------------------------------------------------+
>>
>>
>>
>> And the nvcc -v
>>
>>
>> nvcc warning : The 'compute_20', 'sm_20', and 'sm_21' architectures are deprecated, and may be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
>> nvcc fatal : No input files specified; use option --help for more information
>>
>>
>> I am looking forward to hear your help
>>
>>
>> Best regards
>>
>>
>> Bogac Ercig
>> _______________________________________________
>> AMBER mailing list
>> AMBER.ambermd.org
>> http://lists.ambermd.org/mailman/listinfo/amber
>
>
> _______________________________________________
> AMBER mailing list
> AMBER.ambermd.org
> http://lists.ambermd.org/mailman/listinfo/amber
>
> _______________________________________________
> AMBER mailing list
> AMBER.ambermd.org
> http://lists.ambermd.org/mailman/listinfo/amber


_______________________________________________
AMBER mailing list
AMBER.ambermd.org
http://lists.ambermd.org/mailman/listinfo/amber
Received on Sat Nov 25 2017 - 13:00:02 PST
Custom Search