Supercomputing stats

[gully]

We want to know the stats on different systems.

devel queue on NASA Pleiades with n_threads = n_cpus = 28 on the Broadwell system:

mgullysa at r633i2n8 in ~/GitHub/jammer/sf/2M0136/m112/output/marley_grid/run02
$ time $jammer/code/star_marley_beta.py --samples=200 --incremental_save=10
keeping grid as is

2017 Aug 17, 7:01 PM: 9/200 = 4.5%
...
2017 Aug 17, 7:07 PM: 199/200 = 99.5%
The end.

real	6m52.675s
user	112m18.393s
sys	1m0.155s

Only half the processes were used at one time...

[gully]

mgullysa at pfe27 in ~
$ qstat 2343993.pbspl1.nas.nasa.gov
                                              Req'd    Elap
JobID          User     Queue Jobname TSK Nds wallt S wallt Eff
-------------- -------- ----- ------- --- --- ----- - ----- ---
2343993.pbspl1 mgullysa devel STDIN    28   1 02:00 R 00:15 31%

[gully]

gopc

mgullysa at gopc in ~/GitHub/jammer/sf/2M0136/m112/output/marley_grid/run02 on master [!]
$ time /home/mgullysa/GitHub/jammer/code/star_marley_beta.py --samples=5000 --incremental_save=50
keeping grid as is
Using the user defined prior in $jammer/sf/2M0136/m112/output/marley_grid/run02/user_prior.py
2017 Aug 18, 5:59 PM: 49/5000 = 1.0%
2017 Aug 18, 6:08 PM: 99/5000 = 2.0%
2017 Aug 18, 6:18 PM: 149/5000 = 3.0%
...
2017 Aug 19,12:17 AM: 4899/5000 = 98.0%
2017 Aug 19,12:20 AM: 4949/5000 = 99.0%
2017 Aug 19,12:24 AM: 4999/5000 = 100.0%
The end.

real	394m46.761s
user	4214m32.112s
sys	196m40.513s

So ~6.6 hours of wall-clock time, and something like 10.6 concurrent processes?