dragnet:benchmarks_of_the_lotaas_pipelines

This is an old revision of the document!


Time taken by the individual pipeline components per beam (24-core node):
fits2fil: 6min
rfifind: 15min
mpiprepsubband (253 trials): 3min
single pulse search: 1min
realfft: 10sec
rednoise: 10sec
accelsearch (-zmax=0 ; –numharm=16): 1min20sec
accelsearch (-zmax=50 ; –numharm=16): 12min
plots: 20sec
python sifting and folding: 21min
pfd scrunching: 5sec
data copying: a few secs
candidate scoring: a few secs

Total time spent for the first large set of DM trials (0-4000)
mpiprepsubband 40min
sp:16min
realfft:3.5min
rednoise:3.5min
accelsearch (zmax=0;numharm=16):21min

Total time spent for the second large set of DM trials (4000-10000)
mpiprepsubband 24min
sp:8min
realfft:2min
rednoise:2min
accelsearch (zmax=0;numharm=16):11min

Total % time spent for a beam processing (zmax=0;numharm=16)
Fil conversion: 3%
Rfifind: 9%
Dedispersion: 37%
Single-pulse search: 14%
Realfft: 3%
Rednoise: 3%
Accelsearch: 18%
Folding: 12%
data copying/etc 1%

Total processing time per beam (zmax=0;numharm=16): ~3hours
Total processing time per beam (zmax=50;numharm=16): ~7hours

  • Last modified: 2015-08-19 23:49
  • by Sotiris Sanidas