On Fri, Mar 2, 2018 at 1:57 PM, Mahmood Naderan
wrote:
> Sorry for the confusion. My fault...
> I saw my previous post and found that I missed something. In fact, I
> couldn't run "-pme gpu".
>
> So, once again, I ran all the commands and uploaded the log files
>
>
> gmx
Sorry for the confusion. My fault...
I saw my previous post and found that I missed something. In fact, I couldn't
run "-pme gpu".
So, once again, I ran all the commands and uploaded the log files
gmx mdrun -nobackup -nb cpu -pme cpu -deffnm md_0_1
https://pastebin.com/RNT4XJy8
gmx mdrun
Once again, full log files, please, not partial cut-and-paste, please.
Also, you misread something because your previous logs show:
-nb cpu -pme gpu: 56.4 ns/day
-nb cpu -pme gpu -pmefft cpu 64.6 ns/day
-nb cpu -pme cpu 67.5 ns/day
So both mixed mode PME and PME on CPU are faster, the latter
Command is "gmx mdrun -nobackup -pme cpu -nb gpu -deffnm md_0_1" and the log
says
R E A L C Y C L E A N D T I M E A C C O U N T I N G
On 1 MPI rank, each using 16 OpenMP threads
Computing: Num Num Call Wall time Giga-Cycles
Ranks
Have you tried the mdrun options:
-pme cpu -nb gpu
-pme cpu -nb cpu
Cheers,
Magnus
On 2018-03-02 07:55, Mahmood Naderan wrote:
If you mean [1], then yes I read that and that recommends to use Verlet for the
new algorithm depicted in figures. At least that is my understanding about
If you mean [1], then yes I read that and that recommends to use Verlet for the
new algorithm depicted in figures. At least that is my understanding about
offloading. If I read the wrong document or you mean there is also some other
options, please let me know.
[1]
Have you read the "Types of GPU tasks" section of the user guide?
--
Szilárd
On Thu, Mar 1, 2018 at 3:34 PM, Mahmood Naderan
wrote:
> >Again, first and foremost, try running PME on the CPU, your 8-core Ryzen
> will be plenty fast for that.
>
>
> Since I am a computer guy
>Again, first and foremost, try running PME on the CPU, your 8-core Ryzen will
>be plenty fast for that.
Since I am a computer guy and not a chemist, the question may be noob!
What do you mean exactly by running pme on cpu?
You mean "-nb cpu"? or you mean setting cut-off to Group instead of
No, that does not seem to help much because the GPU is rather slow at
getting the PME Spread done (there's still 12.6% wait for the GPU to finish
that), and there are slight overheads that end up hurting performance.
Again, first and foremost, try running PME on the CPU, your 8-core Ryzen
will be
>- as noted above try offloading only the nonbondeds (or possibly the hybrid
>PME mode -pmefft cpu)
So, with "-pmefft cpu", I don't see any good impact!See the log at
https://pastebin.com/RTYaKSne
I will use other options to see the effect.
Regards,
Mahmood
--
Gromacs Users mailing list
On Thu, Mar 1, 2018 at 8:25 AM, Mahmood Naderan
wrote:
> >(try the other parallel modes)
>
> Do you mean OpenMP and MPI?
>
No, I meant different offload modes.
>
> >- as noted above try offloading only the nonbondeds (or possibly the
> hybrid PME mode -pmefft cpu)
>
>
>(try the other parallel modes)
Do you mean OpenMP and MPI?
>- as noted above try offloading only the nonbondeds (or possibly the hybrid
>PME mode -pmefft cpu)
May I know how? Which part of the documentation says about that?
Regards,
Mahmood
--
Gromacs Users mailing list
* Please search
PS:
Care to know what can you do?
- as noted above try offloading only the nonbondeds (or possibly the hybrid
PME mode -pmefft cpu)
- check if your GPU has application clocks that can be bumped
- if you have the means, consider getting a bit faster GPU; the Quadro
M2000 in your machine is both
Thanks!
Looking at the log file, as I guessed earlier, you can see the following:
- Given that you have a rather low-end GPU and a fairly fast workstation
CPU the run is *very* GPU-bound: the CPU spends 16.4 + 54.2 = 70.6% waiting
for the GPU (see lines 628 and 630)
- this means that the
>The list does not accept attachments, so please use a file sharing or content
>sharing website so >everyone can see your data and has the context.
I uploaded here
https://pastebin.com/RCkkFXPx
Regards,
Mahmood
--
Gromacs Users mailing list
* Please search the archive at
The list does not accept attachments, so please use a file sharing or
content sharing website so everyone can see your data and has the context.
--
Szilárd
On Wed, Feb 28, 2018 at 7:51 PM, Mahmood Naderan
wrote:
> >Additionally, you still have not provided the *mdrun log
>Additionally, you still have not provided the *mdrun log file* I requested.
>top output is not what I asked for.
See the attached file.
Regards,
Mahmood
--
Gromacs Users mailing list
* Please search the archive at
http://www.gromacs.org/Support/Mailing_Lists/GMX-Users_List before
Your run is probably GPU-bound because you have a rather slow GPU and as
per new mdrun defaults both PME and nonbondeds are offloaded which may not
be ideal for your case. Try the different offload modes to see which one is
best on your hardware.
Additionally, you still have not provided the
I forgot to say that gromacs reports
No option -multi
Using 1 MPI thread
Using 16 OpenMP threads
1 GPU auto-selected for this run.
Mapping of GPU IDs to the 2 GPU tasks in the 1 rank on this node:
PP:0,PME:0
NOTE: GROMACS was configured without NVML support hence it can not exploit
By runing
gmx mdrun -nb gpu -deffnm md_0_1
I see the following outputs
$ top -b | head -n 10
top - 19:14:10 up 7 min, 1 user, load average: 4.54, 1.40, 0.54
Tasks: 344 total, 1 running, 343 sleeping, 0 stopped, 0 zombie
%Cpu(s): 7.1 us, 0.5 sy, 0.0 ni, 91.9 id, 0.4 wa, 0.0 hi, 0.0
Hi,
Please provide details, e.g. the full log so we know what version, on what
hardware, settings etc. you're running.
--
Szilárd
On Mon, Feb 26, 2018 at 8:02 PM, Mahmood Naderan
wrote:
> Hi,
>
> While the cut-off is set to Verlet and I run "gmx mdrun -nb gpu -deffnm
>
Hi,
While the cut-off is set to Verlet and I run "gmx mdrun -nb gpu -deffnm
input_md", I see that 9 threads out of total logical 16 threads are running on
the cpu while the gpu is utilized. The gmx also says
No option -multi
Using 1 MPI thread
Using 16 OpenMP threads
I want to know, why 9
22 matches
Mail list logo