cluster:109
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
cluster:109 [2013/01/17 16:42] hmeij [Laamps GPU Testing at MW] |
cluster:109 [2013/10/16 19:13] (current) hmeij [Lammps GPU Testing (EC)] |
||
|---|---|---|---|
| Line 2: | Line 2: | ||
| **[[cluster: | **[[cluster: | ||
| - | ===== Laamps | + | ===== Lammps |
| + | |||
| + | * 32 cores E2660 | ||
| + | * 4 K20 GPU | ||
| + | * workstation | ||
| + | * MPICH2 flavor | ||
| + | |||
| + | |||
| + | Same tests (12 cpu cores) using lj/cut, eam, lj/expand, and morse: **AU.reduced** | ||
| + | |||
| + | CPU only 6 mins 1 secs | ||
| + | 1 GPU 1 mins 1 secs (a 5-6 times speed up) | ||
| + | 2 GPUs 1 mins 0 secs (never saw 2nd GPU used, problem set too small?) | ||
| + | |||
| + | Same tests (12 cpu cores) using a restart file and using gayberne: **GB** | ||
| + | |||
| + | CPU only 1 hour 5 mins | ||
| + | 1 GPU 5 mins and 15 secs (a 18-19 times peed up) | ||
| + | 2 GPUs 2 mins | ||
| + | |||
| + | Above results seems overall a bit slower that at other vendor, but same pattern. | ||
| + | |||
| + | Francis' | ||
| + | |||
| + | ^3d Lennard-Jones melt: for 10,000 steps with 32,000 atoms^^^^^^ | ||
| + | |CPU only| -np 1 | -np 6 | -np 12 | -np 24 | -np 36 | | ||
| + | |loop times| | ||
| + | |GPU only| 1xK20 | 2xK20 | 3xK20 | 4xK20 | (-np 1-4) | | ||
| + | |loop times| | ||
| + | ^3d Lennard-Jones melt: for 100,000 steps with 32,000 atoms^^^^^^ | ||
| + | |GPU only| 1xK20 | 2xK20 | 3xK20 | 4xK20 | (-np 1-4) | | ||
| + | |loop times| | ||
| + | |||
| + | * Serial' | ||
| + | * GPU's serial time matches MPI -np 24 and can be further reduced to 10s, a 3x speed up | ||
| + | |||
| + | ==== Redoing Above ==== | ||
| + | |||
| + | **10/ | ||
| + | |||
| + | Redoing the melt problem now on our own K20 hardware I get the following (observing with gpu-info that utilization runs about 20-25% on the GPU allocated) | ||
| + | |||
| + | Loop time of 345.936 on 1 procs for 100000 steps with 32000 atoms | ||
| + | |||
| + | < | ||
| + | |||
| + | # | ||
| + | # submit via 'bsub < run.gpu' | ||
| + | rm -f log.lammps melt.log | ||
| + | #BSUB -e err | ||
| + | #BSUB -o out | ||
| + | #BSUB -q mwgpu | ||
| + | #BSUB -J test | ||
| + | |||
| + | ## leave sufficient time between job submissions (30-60 secs) | ||
| + | ## the number of GPUs allocated matches -n value automatically | ||
| + | ## always reserve GPU (gpu=1), setting this to 0 is a cpu job only | ||
| + | ## reserve 6144 MB (5 GB + 20%) memory per GPU | ||
| + | ## run all processes (1< | ||
| + | |||
| + | #BSUB -n 1 | ||
| + | #BSUB -R " | ||
| + | |||
| + | # from greentail we need to recreate module env | ||
| + | export PATH=/ | ||
| + | / | ||
| + | / | ||
| + | / | ||
| + | / | ||
| + | / | ||
| + | / | ||
| + | / | ||
| + | export PATH=/ | ||
| + | export LD_LIBRARY_PATH=/ | ||
| + | / | ||
| + | / | ||
| + | / | ||
| + | / | ||
| + | / | ||
| + | / | ||
| + | |||
| + | # unique job scratch dirs | ||
| + | MYSANSCRATCH=/ | ||
| + | MYLOCALSCRATCH=/ | ||
| + | export MYSANSCRATCH MYLOCALSCRATCH | ||
| + | cd $MYSANSCRATCH | ||
| + | |||
| + | # LAMMPS | ||
| + | # GPUIDX=1 use allocated GPU(s), GPUIDX=0 cpu run only (view header au.inp) | ||
| + | export GPUIDX=1 | ||
| + | # stage the data | ||
| + | cp ~/ | ||
| + | # feed the wrapper | ||
| + | lava.mvapich2.wrapper lmp_nVidia \ | ||
| + | -c off -var GPUIDX $GPUIDX -in in.melt | ||
| + | # save results | ||
| + | cp log.lammps melt.log | ||
| + | |||
| + | |||
| + | </ | ||
| + | |||
| + | ===== Lammps GPU Testing (MW) ===== | ||
| Vendor: "There are currently two systems available, each with two 8-core Xeon E5-2670 processors, 32GB memory, 120GB SSD and two Tesla K20 GPUs. The hostnames are master and node2. | Vendor: "There are currently two systems available, each with two 8-core Xeon E5-2670 processors, 32GB memory, 120GB SSD and two Tesla K20 GPUs. The hostnames are master and node2. | ||
| Line 36: | Line 137: | ||
| </ | </ | ||
| - | Some tests using **lj/cut**, **eam**, | + | Some tests using **lj/cut**, **eam**, **lj/expand**, and **morse**: |
| * CPU only 4 mins 30 secs | * CPU only 4 mins 30 secs | ||
| Line 44: | Line 145: | ||
| Some tests using a restart file and using **gayberne**, | Some tests using a restart file and using **gayberne**, | ||
| - | * CPU only | + | * CPU only 1 hour 5 mins |
| - | * 1 GPU | + | * 1 GPU 3 mins and 33 secs (a 18-19 times peed up) |
| - | * 2 GPUs | + | * 2 GPUs 2 mins (see below) |
| + | |||
| + | < | ||
| + | node2$ gpu-info | ||
| + | ==================================================== | ||
| + | Device | ||
| + | ==================================================== | ||
| + | 0 Tesla K20m 36 C 96 % | ||
| + | 1 Tesla K20m 34 C 92 % | ||
| + | ==================================================== | ||
| + | </ | ||
| \\ | \\ | ||
| **[[cluster: | **[[cluster: | ||
cluster/109.1358440952.txt.gz · Last modified: 2013/01/17 16:42 by hmeij
Page Tools
Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 4.0 International
