opal AT lists.psi.ch
Subject: The OPAL Discussion Forum
List archive
- From: Nicole Neveu <nneveu AT hawk.iit.edu>
- To: opal <opal AT lists.psi.ch>
- Subject: [Opal] overhead
- Date: Thu, 12 Jul 2018 23:27:53 -0500
Hi All,
I typically run small cases on 8 cores, and I'm noticing more overhead on 2.0 than 1.9 for xy parallelization:
1.9 vs 2.0 xy parallelization on 8 cores:
[neveu@beboplogin1 old_opal]$ grep --include=*.out -rnw './' -e "mainTimer"
2.0-> ./standalone_newopal/optLinac_40nC.569053.knld-0046.out:315:Timings{0}> mainTimer........... Wall tot = 570.886, CPU tot = 348.68
1.9-> ./standalone_myopal/optLinac_40nC.569040.knld-0037.out:295:Timings{0}> mainTimer........... Wall tot = 313.199, CPU tot = 313.04
2.0-> ./standalone_newopal/optLinac_40nC.569053.knld-0046.out:315:Timings{0}> mainTimer........... Wall tot = 570.886, CPU tot = 348.68
1.9-> ./standalone_myopal/optLinac_40nC.569040.knld-0037.out:295:Timings{0}> mainTimer........... Wall tot = 313.199, CPU tot = 313.04
2.0 z parallel only:
[neveu@beboplogin1 rand_sample_small_test]$ grep --include=*.out -rnw './' -e "mainTimer"
./optLinac_40nC_CORES=1/optLinac_40nC.569081.knld-0043.out:217:Timings> mainTimer........... Wall tot = 938.19, CPU tot = 935.99
./optLinac_40nC_CORES=2/optLinac_40nC.569080.knld-0042.out:303:Timings{0}> mainTimer........... Wall tot = 632.148, CPU tot = 631.86
./optLinac_40nC_CORES=4/optLinac_40nC.569079.knld-0041.out:307:Timings{0}> mainTimer........... Wall tot = 491.218, CPU tot = 432.94
./optLinac_40nC_CORES=8/optLinac_40nC.569078.knld-0037.out:315:Timings{0}> mainTimer........... Wall tot = 504.177, CPU tot = 329.67
./optLinac_40nC_CORES=4/optLinac_40nC.569079.knld-0041.out:307:Timings{0}> mainTimer........... Wall tot = 491.218, CPU tot = 432.94
./optLinac_40nC_CORES=8/optLinac_40nC.569078.knld-0037.out:315:Timings{0}> mainTimer........... Wall tot = 504.177, CPU tot = 329.67
2.0 xy parallel only:
./optLinac_40nC_CORES=1/optLinac_40nC.569059.knld-0041.out:217:Timings>
mainTimer........... Wall tot = 934.293, CPU tot = 930.2
./optLinac_40nC_CORES=2/optLinac_40nC.569050.knld-0043.out:303:Timings{0}> mainTimer........... Wall tot = 654.175, CPU tot = 654.01
./optLinac_40nC_CORES=4/optLinac_40nC.569049.knld-0042.out:307:Timings{0}> mainTimer........... Wall tot = 522.647, CPU tot = 461.41
./optLinac_40nC_CORES=8/optLinac_40nC.569048.knld-0041.out:315:Timings{0}> mainTimer........... Wall tot = 520.827, CPU tot = 383.14
./optLinac_40nC_CORES=4/optLinac_40nC.569049.knld-0042.out:307:Timings{0}> mainTimer........... Wall tot = 522.647, CPU tot = 461.41
./optLinac_40nC_CORES=8/optLinac_40nC.569048.knld-0041.out:315:Timings{0}> mainTimer........... Wall tot = 520.827, CPU tot = 383.14
Did something change with the way decomposition is done?
Thanks,
Nicole
- [Opal] overhead, Nicole Neveu, 07/13/2018
- Re: [Opal] overhead, Christof Metzger-Kraus, 07/13/2018
- Re: [Opal] overhead, Adelmann Andreas (PSI), 07/14/2018
- Re: [Opal] overhead, Nicole Neveu, 07/17/2018
- Re: [Opal] overhead, Adelmann Andreas (PSI), 07/17/2018
- Re: [Opal] overhead, Nicole Neveu, 07/17/2018
- Re: [Opal] overhead, Adelmann Andreas (PSI), 07/14/2018
- Re: [Opal] overhead, Christof Metzger-Kraus, 07/13/2018
Archive powered by MHonArc 2.6.19.