This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
cluster:175 [2018/09/26 20:01] hmeij07 [Gromacs] |
cluster:175 [2018/10/08 12:57] hmeij07 |
||
---|---|---|---|
Line 2: | Line 2: | ||
\\ | \\ | ||
**[[cluster: | **[[cluster: | ||
+ | |||
+ | As of | ||
+ | --- // | ||
+ | The P100 with 12 GB is end of life, replaced by the P100 16 GB and | ||
+ | The GTX 1080Ti is replaced by the GTX2060Ti (no specs yet and not certified for Amber18, yet) | ||
+ | |||
==== P100 vs GTX & K20 ==== | ==== P100 vs GTX & K20 ==== | ||
Line 120: | Line 126: | ||
==== Gromacs 2018.3 ==== | ==== Gromacs 2018.3 ==== | ||
+ | |||
+ | The multidir not running in Gromacs 2018 is a bug in the code clashing with the call MPI_Barrier (communication timing error). | ||
< | < | ||
- | multidir -gpu_id 0123 | + | |
+ | # multidir -gpu_id 0123 with four simultaneous gromacs processes | ||
-np 8 -ntomp | -np 8 -ntomp | ||
01/ | 01/ | ||
02/ | 02/ | ||
03/ | 03/ | ||
- | 04/ | + | 04/ |
-np 16 -ntomp | -np 16 -ntomp | ||
01/ | 01/ | ||
02/ | 02/ | ||
03/ | 03/ | ||
- | 04/ | + | 04/ |
+ | |||
+ | multidir -gpu_id 00112233 with eight simultaneous gromacs processes | ||
+ | sharing the gpus, 2 processes per gpu | ||
- | multidir -gpu_id 00112233 | ||
-np 8 -ntomp | -np 8 -ntomp | ||
Error in user input: | Error in user input: | ||
The string of available GPU device IDs ' | The string of available GPU device IDs ' | ||
device IDs | device IDs | ||
+ | |||
</ | </ | ||
+ | |||
+ | That last error when loading multiple processes per gpu is *not* according to their documentation. So the multidir performance is similar to previous single dir performance but still lags GTX performance by quite a bit. Albeit, there is room in utilization rate of the gpus. | ||
+ | |||
==== What to Buy ==== | ==== What to Buy ==== | ||
* Amber folks: does not matter | * Amber folks: does not matter | ||
- | * Lammps folks: P100 nodes please | + | * Lammps folks: P100 nodes please, although in hybrid runs does not matter |
* Gromacs folks: GTX nodes please | * Gromacs folks: GTX nodes please | ||