[gmx-users] Using multiple GPU's
paul buscemi
pbuscemi at q.com
Sat Aug 11 04:50:21 CEST 2018
Mark, Kevin,
I’ve uploaded two representative log files to Google Drive. gms users should get the invite.
thanks
Paul
> On Aug 10, 2018, at 6:27 PM, Mark Abraham <mark.j.abraham at gmail.com> wrote:
>
> Hi,
>
> Kevin means you to upload the file to a file sharing service and share the
> link. Everything you've shown points to using both GPUs, but the relevant
> output about the decision is not shown.
>
> Mark
>
> On Sat, Aug 11, 2018, 00:58 paul buscemi <pbuscemi at q.com> wrote:
>
>> Thanks Kevin. for the rapid response.
>>
>> I am using 2018. I’ll check the 2018 - make sure - I was look at the
>> proper docs. I should not note that the GPUs are not matched. a gtx
>> 1080ti and a gtx 1060
>>
>> below is some pertinent information from the log file. ( not too sure how
>> to post a link on the user group )
>>
>> Paul
>>
>>> On Aug 10, 2018, at 12:31 PM, Kevin Boyd <kevin.boyd at uconn.edu> wrote:
>>>
>>> Hi,
>>>
>>> Can you post a link to your log file?
>>>
>>> Also, what version of gromacs are you using? Make sure that the
>>> documentation you are following corresponds to the right version of
>>> gromacs. If you are using v 5.1 (as the link suggests), strongly consider
>>> upgrading to 2018.
>>>
>>> Kevin
>>>
>>> On Fri, Aug 10, 2018 at 12:57 PM, paul buscemi <pbuscemi at q.com> wrote:
>>>
>>>>
>>>> Dear Uses,
>>>>
>>>> I’ve been following the examples on https://na01.safelinks.
>>>> protection.outlook.com/?url=http%3A%2F%2Fmanual.gromacs.
>>>> org%2Fdocumentation%2F5.1%2Fuser-guide%2Fmdrun-
>>>> performance.html&data=02%7C01%7Ckevin.boyd%40uconn.edu%
>>>> 7Cb67f423cb92a4abac13508d5fee27522%7C17f1a87e2a254eaab9df9d439034
>>>> b080%7C0%7C1%7C636695170968044387&sdata=TBSbmbdU%
>>>> 2F5kxRGsaD1IqLXzEbcJUJ6Kqg7ub%2B%2B9m6xc%3D&reserved=0 for setting
>> up
>>>> multiple GP’s but have not succeeded.
>>>> Using a single GPU gmx runs well. Nvidia and gmx see the 2 PGUs. and
>>>> I‘ve tried mdrun with variations of -gpu_id 01, and -ntmpi,
>> but
>>>> the GPUs are not put to use.
>>>>
>>>> Would someone suggest the proper signals to mdrun for two GPU’s. ?
>>>>
>>>> Running on lilnix-min sarah, I7
>>>>
>>>> thanks
>>>> Paul
>>>> --
>>>>
>>
>> GROMACS: gmx mdrun, version 2018
>> Executable: /usr/local/gromacs/bin//gmx
>> Data prefix: /usr/local/gromacs
>> Working dir: /home/rgb/Desktop/PDMS
>> Command line:
>> gmx mdrun -deffnm pdms.sys.nvt -ntmpi 4 -ntomp 2 -gpu_id 01
>>
>> GROMACS version: 2018
>> Precision: single
>> Memory model: 64 bit
>> MPI library: thread_mpi
>> OpenMP support: enabled (GMX_OPENMP_MAX_THREADS = 64)
>> GPU support: CUDA
>> SIMD instructions: AVX2_256
>> FFT library: fftw-3.3.5-fma-sse2-avx-avx2-avx2_128-avx512
>> RDTSCP usage: enabled
>> TNG support: enabled
>> Hwloc support: disabled
>> Tracing support: disabled
>> Built on: 2018-07-06 18:24:42
>> Built by: rgb at RGB [CMAKE]
>> Build OS/arch: Linux 4.4.0-21-generic x86_64
>> Build CPU vendor: Intel
>> Build CPU brand: Intel(R) Core(TM) i7-7700K CPU @ 4.20GHz
>> Build CPU family: 6 Model: 158 Stepping: 9
>> Build CPU features: aes apic avx avx2 clfsh cmov cx8 cx16 f16c fma hle htt
>> intel lahf mmx msr nonstop_tsc pcid pclmuldq pdcm pdpe1gb popcnt pse rdrnd
>> rdtscp rtm sse2 sse3 sse4.1 sse4.2 ssse3 tdt x2apic
>> C compiler: /usr/bin/gcc GNU 5.4.0
>> C compiler flags: -march=core-avx2 -O3 -DNDEBUG -funroll-all-loops
>> -fexcess-precision=fast
>> C++ compiler: /usr/bin/c++ GNU 5.4.0
>> C++ compiler flags: -march=core-avx2 -std=c++11 -O3 -DNDEBUG
>> -funroll-all-loops -fexcess-precision=fast
>> CUDA compiler: /usr/lib/nvidia-cuda-toolkit/bin/nvcc nvcc: NVIDIA (R)
>> Cuda compiler driver;Copyright (c) 2005-2015 NVIDIA Corporation;Built on
>> Tue_Aug_11_14:27:32_CDT_2015;Cuda compilation tools, release 7.5, V7.5.17
>> CUDA compiler
>> flags:-gencode;arch=compute_20,code=sm_20;-gencode;arch=compute_30,code=sm_30;-gencode;arch=compute_35,code=sm_35;-gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_52,code=sm_52;-gencode;arch=compute_52,code=compute_52;-use_fast_math;-D_FORCE_INLINES;;
>> ;-march=core-avx2;-std=c++11;-O3;-DNDEBUG;-funroll-all-loops;-fexcess-precision=fast;
>> CUDA driver: 9.0
>> CUDA runtime: 7.50
>>
>> ===== latest attempt =======
>> Running on 1 node with total 4 cores, 8 logical cores, 2 compatible GPUs
>> Hardware detected:
>> CPU info:
>> Vendor: Intel
>> Brand: Intel(R) Core(TM) i7-7700K CPU @ 4.20GHz
>> Family: 6 Model: 158 Stepping: 9
>> Features: aes apic avx avx2 clfsh cmov cx8 cx16 f16c fma hle htt intel
>> lahf mmx msr nonstop_tsc pcid pclmuldq pdcm pdpe1gb popcnt pse rdrnd rdtscp
>> rtm sse2 sse3 sse4.1 sse4.2 ssse3 tdt x2apic
>> Hardware topology: Basic
>> Sockets, cores, and logical processors:
>> Socket 0: [ 0 4] [ 1 5] [ 2 6] [ 3 7]
>> GPU info:
>> Number of GPUs detected: 2
>> #0: NVIDIA GeForce GTX 1080 Ti, compute cap.: 6.1, ECC: no, stat:
>> compatible
>> #1: NVIDIA GeForce GTX 1060 6GB, compute cap.: 6.1, ECC: no, stat:
>> compatible
>>
>> --
>> Gromacs Users mailing list
>>
>> * Please search the archive at
>> http://www.gromacs.org/Support/Mailing_Lists/GMX-Users_List before
>> posting!
>>
>> * Can't post? Read http://www.gromacs.org/Support/Mailing_Lists
>>
>> * For (un)subscribe requests visit
>> https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-users or
>> send a mail to gmx-users-request at gromacs.org.
> --
> Gromacs Users mailing list
>
> * Please search the archive at http://www.gromacs.org/Support/Mailing_Lists/GMX-Users_List before posting!
>
> * Can't post? Read http://www.gromacs.org/Support/Mailing_Lists
>
> * For (un)subscribe requests visit
> https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-users or send a mail to gmx-users-request at gromacs.org.
More information about the gromacs.org_gmx-users
mailing list