GLOMAP

Backward-Euler with GLOMAP

The page covers

Details of run

  • facec (mstringe) copied from anyfl (hadcj)
  • GLOMAP + dust
  • 128 PEs
  • Grid size is 192*144*85
  • Runs for 1 month

Calling tree

The times in the tables below are the total time, which is the time in each routine and the routines below it, except where `itself' is written to indicate time taken solely by that routine. Only the main routes - as given by time spent in them - are general shown. Routines with less than 50s total time are general not shown.

Profiling for UM_SHELL

Routines
UM_SHELL (5,000s)
U_MODEL_4A (4,997s)
ATM_STEP_4A* (3,374s) UKCA_MAIN1 (1,464s)
ATMOS _PHYS- ICS1 (1,493s) EG_ COR- RECT_ TRAC- ERS (214s) ATMOS _PHYS- ICS2 (442s) EG_ SL_ HELM- HOLTZ (227s) TR_ SET_ PHYS _4A* (76s) EG_CORRECT _TRACERS _UKCA (167s) SL_ TRAC- ER1_ 4A (162s) EG_ SL_ MOI- STURE (80s) EG_SL_ FULL_WIND (135s)  ⇓  UP- DATE _M_ STAR (74s) ATM_ STEP_ STASH (60s)  ⇓   ⇓  See profiling for UKCA_ MAIN1 below
See profile for ATMOS_ PHYSICS1 and EG_CORRECT _TRACERS below See profile for ATMOS_ PHYSICS2 and EG_SL_ HELMHOLTZ below EG_SL_WIND_U, EG_SL_WIND_V & EG_SL_WIND_W (38 + 38 + 45 = 121s)  ⇓  EG_Q_ TO_MIX (75s)  ⇓  STASH (172s)
Itself (120s) EG_INTERPOLATION _ETA (237s) DEP- ARTURE_ POINT _ETA (82s) EG_SWAP_ BOUNDS_DP (159s) STWORK (172s)
EG_ CUBIC_ LAG- RANGE (98s, itself) EG_VERT_ WEIGHTS_ ETA (19s, itself) MONO_ ENFORCE (19s, itself) Itself (36s) See profile for SWAP_ BOUNDS _DP below SPA- TIAL (64s) PP_ HEAD (54s) EXP- PXI (35s, itself)
*should also link to SWAP_BOUNDS_DP, like many other returns.

Profiling for UKCA_MAIN1

Routines Total mean time
UKCA_MAIN* (1,463s) 1,463s
UKCA_AERO_CTL (871s) UKCA_READ_OFFLINE_ OXIDANTS_CTL (212s) UKCA_ ACTIVATE (141s) 1,224s
UKCA_AERO_STEP (824s) UKCA_OFFLINE_ OXIDANTS_UPDATE (212s) UKCA_ ABDULRAZZAK_ GHAN (132s) 1,168s
UKCA_COAGWITHNUCL (368s) UKCA_ CONDEN (141s) UKCA_ CHECK_ MD_ND (70s, itself) UKCA_ CALCNUCRATE (69s) UKCA_ VOLUME_ MODE (50s) EM_GET_ DATA_REAL (116s, itself) EM_GET_ DATA_ REAL3D (65s, itself) Itself (125s) 1,004s
Itself (306s) UKCA_ SOLVECOAGNUCL _V (63s, itself) UKCA_ COND_ COFF_V (92s, itself) Itself (49s) UKCA_ BINAPARA (65s, itself) Itself (25s) 976s
*UCKA_MAIN also calls STASH

Profiling for ATMOS_PHYSICS1 and EG_CORRECT_TRACERS

ATMOS_PHYSICS1* (1,493s) EG_CORRECT_TRACERS (214s)
Itself (320s) RAD_CTL (494s) MICROPHYS_CTL (329s) NI_GWD _CTL (328s)  ⇓   ⇓  EG_MASS_ CONSERVATION (138s) Itself (39s)
LW_RAD (357s) SW_RAD (120s) LS_PPN (322s) G_ WAVE _5A (279s) GW_ USSP (47s) GLOBAL _2D_ SUMS (51s, itself) Itself (97s)
RADIANCE_CALC (470s) LS_PPNC (313s) SWAP_ BOUNDS (see table below)
UKCA_ RADAER _BAND_ AVERAGE (272s, itself) SOLVE_BAND_K_EQV (154s) UKCA_ RADAER_ COMPUTE _AOD (21s, itself) LSP_ICE (198s) Itself (114s)
MCICA_ SAMPLE (122s) SCALE_ ABSORB (20s) LSP_ SUBGRID (107s) LSP_ INIT (23s) LSP_ FALL (19s)
MONOCHR- OMATIC_ RADIANCE (107s) Itself (15s) LSP_ QCLEAR (77s) Itself (25s) Itself (12s) Itself (17s)
MONOCHR- OMATIC_ RADIANCE _TSEQ (94s) QWIDTH (77s, itself)
MCICA_ COLUMN (94s)
TWO_COEFF (67s)
TRANS_ SOURCE_ COEFF (37s) Itself (12s)
Itself (23s)
  
* ATMOS_PHYSICS1 also calls COSP_MAIN. However, the routines in atmosphere/COSP don't have Dr Hook calls. The TIMER output suggests that about 300s is spent in these routines.

Profiling for ATMOS_PHYSICS2 and EG_SL_HELMHOLTZ

ATMOS_PHYSICS2 (442s) EG_SL_HELMHOLTZ (227s)
NI_CONV_CTL (206s) NI_IMP_CTL (79s) SWAP_BOUNDS, SWAP_BOUNDS_2D_MV & SWAP_BOUNDS_MV (see table below) EG_BICGSTAB (128s) EG_HELM_RHS_STAR (67s)
GLUE_CONV_6A (155s) IMP_SOLVER (40s) EG_PRECON (87s) EG_SISL_INIT (51s)
Itself (64s) MID_CONV_6A (53s) TRI_SOR_DP_DP (87s) EG_SISL_INIT_UVW (48s)
Itself (17s) Itself (58s) Itself (33s)

Profiling for SWAP_* routines

Routines Total mean time
EG_SWAP_BOUNDS_DP (159s) ATMOS_PHYSICS1, ATMOS_PHYSICS2, G_WAVE_5A, ... 159 + ...
SWAP_BOUNDS & SWAP_BOUNDS_DP (547 + 187 = 734s) SWAP_BOUNDS_MV (112s, itself) 846s
SWAP_BOUNDS_EW_DP (393s) SWAP_BOUNDS_NS_DP (340s, itself) 845s
SWAP_BOUNDS_EW_H1_DP (280s, itself) Itself (113s) 845s

The disk usage

I'm told that thread 2 is the IO server - looks like it comes from a second thread for OpenMP.

Number of PEs: 128

Header fields
Min Mean Max (Max-Min)
Instrument overhead (%) 2.12 (PE 82) 3.42 4.45 (PE 76) 2.33
Heap (MB) 1458 (PE 4) 1478.27 1539 (PE 0) 81
RSS (MB) 596 (PE 52) 602.69 658 (PE 0) 62
Stack (MB) 239 (PE 0) 239.00 239 (PE 0) 0
Paging 398 (PE 17) 707.42 1429 (PE 82) 1031
Wall Time (s) 5002.84 (PE 126) 5032.56 5127.2 (PE 51) 124.36
Thread#1 (s) 5000.04 (PE 0) 5000.04 5000.05 (PE 96) 0.01
Thread#1 (%) 97.52 (PE 51) 99.36 99.94 (PE 126) 2.42
Thread#2 (s) 571.59 (PE 2) 822.72 1171.36 (PE 68) 599.77
Thread#2 (%) 11.42 (PE 2) 16.34 23.17 (PE 68) 11.75

Routines by total time

The numbers for the table below can be reproduced with the command

perl /home/cr/ukesm/mstringe/cgi-bin/drHook/drHook.pl --dir=/data/cr/ukesm/mstringe/facec29_7_14
--nRoutines=100 --orderBy=total:mean
where the command should all be on the same line.

Ordering routines by total: mean
Min (s) Mean (s) Max (s) (Max-Min) (s)
UM_SHELL@1 5000.035 (PE 70) 5000.04 5000.053 (PE 104) 0.02
U_MODEL_4A@1 4995.714 (PE 0) 4997.16 4998.311 (PE 77) 2.60
ATM_STEP_4A@1 3373.447 (PE 66) 3373.79 3374.197 (PE 84) 0.75
ATMOS_PHYSICS1@1 1439.35 (PE 65) 1493.19 1560.129 (PE 125) 120.78
UKCA_MAIN1@1 1328.088 (PE 2) 1463.99 1521.252 (PE 76) 193.16
UKCA_AERO_CTL@1 (<-UKCA_MAIN) 833.414 (PE 2) 870.72 895.97 (PE 64) 62.56
UKCA_AERO_STEP@1 (<-UKCA_AERO_CTL <-UKCA_MAIN) 786.715 (PE 2) 823.55 848.633 (PE 64) 61.92
SWAP_BOUNDS@1 325.426 (PE 68) 547.37 904.437 (PE 82) 579.01
RAD_CTL@1 (<-ATMOS_PHYSICS1) 368.69 (PE 2) 494.48 602.777 (PE 68) 234.09
RADIANCE_CALC@2 351.951 (PE 2) 471.97 584.913 (PE 68) 232.96
RADIANCE_CALC@1 352.48 (PE 2) 470.22 587.116 (PE 84) 234.64
ATMOS_PHYSICS2@1 428.758 (PE 18) 442.35 453.72 (PE 102) 24.96
HALO_EXCHANGE:SWAP_BOUNDS_EW_DP@1 236.86 (PE 124) 392.72 679.968 (PE 82) 443.11
UKCA_COAGWITHNUCL@1 (<-UKCA_AERO_STEP <-UKCA_AERO_CTL <-UKCA_MAIN1) 352.939 (PE 2) 368.34 380.381 (PE 48) 27.44
LW_RAD@2 279.391 (PE 2) 358.37 443.857 (PE 68) 164.47
LW_RAD@1 279.961 (PE 2) 356.67 443.6 (PE 84) 163.64
HALO_EXCHANGE:SWAP_BOUNDS_NS_DP@1 166.072 (PE 67) 340.02 552.464 (PE 5) 386.39
MICROPHYS_CTL@1 76.945 (PE 82) 329.38 473.981 (PE 68) 397.04
NI_GWD_CTL@1 93.49 (PE 68) 327.94 649.105 (PE 82) 555.62
LS_PPN@1 69.82 (PE 82) 322.12 466.864 (PE 68) 397.04
LS_PPNC@1 61.51 (PE 82) 312.57 456.327 (PE 68) 394.82
HALO_EXCHANGE:SWAP_BOUNDS_EW_H1_DP@1 135.068 (PE 124) 279.96 571.472 (PE 82) 436.40
G_WAVE_5A@1 56.196 (PE 68) 279.34 623.457 (PE 82) 567.26
UKCA_RADAER_BAND_AVERAGE@2 173.56 (PE 2) 275.99 371.806 (PE 61) 198.25
UKCA_RADAER_BAND_AVERAGE@1 170.587 (PE 2) 272.35 372.917 (PE 84) 202.33
EG_INTERPOLATION_ETA@1 227.565 (PE 63) 237.74 255.786 (PE 6) 28.22
EG_SL_HELMHOLTZ@1 214.414 (PE 116) 226.86 240.898 (PE 32) 26.48
EG_CORRECT_TRACERS@1 212.914 (PE 115) 214.45 215.905 (PE 100) 3
UKCA_READ_OFFLINE_OXIDANTS_CTL@1 (<-UKCA_MAIN1) 204.985 (PE 66) 212.44 218.769 (PE 52) 13.78
UKCA_OFFLINE_OXIDANTS_UPDATE@1 (<-UKCA_READ_OFFLINE_OXIDANTS_CTL <-UKCA_MAIN1) 204.291 (PE 66) 211.75 218.076 (PE 52) 13.78
NI_CONV_CTL@1 109.226 (PE 2) 205.86 305.606 (PE 75) 196.38
LSP_ICE@1 28.442 (PE 82) 198.16 333.94 (PE 68) 305.50
LSP_ICE@2 21.578 (PE 82) 189.07 350.825 (PE 68) 329.25
HALO_EXCHANGE:SWAP_BOUNDS_DP@1 101.084 (PE 112) 187.08 261.908 (PE 18) 160.82
STASH@1 (<-UKCA_MAIN,ATM_STEP_4A) 171.885 (PE 77) 172.53 173.694 (PE 46) 1.81
STWORK@1 171.445 (PE 77) 172.10 173.265 (PE 46) 1.82
EG_CORRECT_TRACERS_UKCA@1 165.919 (PE 97) 167.34 169.21 (PE 82) 3.29
SL_TRACER1_4A@1 157.668 (PE 127) 161.78 164.993 (PE 31) 7.32
EG_SWAP_BOUNDS_DP@1 89.294 (PE 112) 159.04 213.101 (PE 81) 123.81
GLUE_CONV_6A@1 63.979 (PE 10) 154.63 259.753 (PE 84) 195.77
SOLVE_BAND_K_EQV@1 115.834 (PE 82) 153.70 177.465 (PE 118) 61.63
SOLVE_BAND_K_EQV@2 123.167 (PE 63) 151.80 177.176 (PE 113) 54
GLUE_CONV_6A@2 66.7 (PE 119) 149.40 256.217 (PE 51) 189.52
UKCA_CONDEN@1 (<-UKCA_AERO_STEP <-UKCA_AERO_CTL <-UKCA_MAIN1) 129.111 (PE 1) 141.36 154.469 (PE 64) 25.36
UKCA_ACTIVATE@1 (<-UKCA_MAIN1) 45.547 (PE 4) 141.22 179.205 (PE 69) 133.66
EG_MASS_CONSERVATION@1 136.042 (PE 97) 137.88 140.075 (PE 125) 4.03
EG_SL_FULL_WIND@1 127.884 (PE 63) 134.65 144.49 (PE 125) 16.61
UKCA_ABDULRAZZAK_GHAN@1 (<-UKCA_ACTIVATE <-UKCA_MAIN1) 35.95 (PE 4) 131.61 169.569 (PE 69) 133.62
EG_BICGSTAB@1 127.362 (PE 119) 128.23 129.701 (PE 60) 2.34
MCICA_SAMPLE@1 84.178 (PE 82) 121.95 144.617 (PE 118) 60.44
SW_RAD@2 78.857 (PE 2) 120.47 147.914 (PE 68) 69.06
SW_RAD@1 78.843 (PE 2) 120.39 150.33 (PE 84) 71.49
MCICA_SAMPLE@2 91.244 (PE 63) 120.25 143.359 (PE 113) 52.12
GET_EMFILE_REC@1 (<-UKCA_OFFLINE_OXIDANTS_UPDATE <-UKCA_READ_OFFLINE_OXIDANTS_CTL <-UKCA_MAIN1) 112.34 (PE 66) 118.14 122.35 (PE 39) 10
EM_GET_TIME_REC@1 (<-GET_EMFILE_RE <-UKCA_OFFLINE_OXIDANTS_UPDATE <-UKCA_READ_OFFLINE_OXIDANTS_CTL <-UKCA_MAIN1) 112.257 (PE 66) 118.05 122.27 (PE 39) 10.01
EM_GET_DATA_REAL@1 (<-UKCA_OFFLINE_OXIDANTS_UPDATE <-UKCA_READ_OFFLINE_OXIDANTS_CTL <-UKCA_MAIN1) 110.594 (PE 66) 116.40 120.618 (PE 39) 10.02
SWAP_BOUNDS_MV@1 24.754 (PE 75) 112.15 200.533 (PE 126) 175.78
MONOCHROMATIC_RADIANCE@1 79.54 (PE 82) 106.79 125.111 (PE 118) 45.57
LSP_SUBGRID@1 10.554 (PE 82) 106.72 190.988 (PE 68) 180.43
MONOCHROMATIC_RADIANCE@2 84.103 (PE 63) 105.51 123.698 (PE 116) 39.59
LSP_SUBGRID@2 8.902 (PE 82) 101.93 204.152 (PE 68) 195.25
eg_CUBIC_LAGRANGE@1 95.845 (PE 20) 97.52 102.623 (PE 123) 6.78
MONOCHROMATIC_RADIANCE_TSEQ@1 66.468 (PE 82) 93.76 111.891 (PE 124) 45.42
MCICA_COLUMN@1 66.262 (PE 82) 93.54 111.679 (PE 124) 45.42
MONOCHROMATIC_RADIANCE_TSEQ@2 70.89 (PE 63) 92.60 109.7 (PE 116) 38.81
MCICA_COLUMN@2 70.671 (PE 63) 92.38 109.465 (PE 116) 38.79
UKCA_COND_COFF_V@1 (<-UKCA_CONDEN <-UKCA_AERO_STEP <-UKCA_AERO_CTL <-UKCA_MAIN1) 81.588 (PE 1) 92.06 103.885 (PE 21) 22.30
UKCA_SYNC@1 33.008 (PE 76) 90.30 226.285 (PE 2) 193.28
EG_PRECON@1 84.224 (PE 69) 86.88 91.342 (PE 110) 7.12
TRI_SOR_DP_DP@1 84.091 (PE 69) 86.76 91.214 (PE 110) 7.12
DEPARTURE_POINT_ETA@1 77.699 (PE 7) 81.93 85.337 (PE 68) 7.64
EG_SL_MOISTURE@1 78.05 (PE 67) 79.52 81.456 (PE 96) 3.41
NI_IMP_CTL@1 45.841 (PE 67) 78.71 130.791 (PE 0) 84.95
LSP_QCLEAR@1 30.478 (PE 82) 77.40 118.728 (PE 68) 88.25
TR_SET_PHYS_4A@1 66.971 (PE 125) 76.72 83.084 (PE 24) 16.11
QWIDTH@1 21.354 (PE 82) 76.70 125.782 (PE 68) 104.43
EG_Q_TO_MIX@1 9.009 (PE 118) 75.06 130.092 (PE 65) 121.08
UPDATE_M_STAR@1 8.101 (PE 118) 73.80 128.548 (PE 65) 120.45
UKCA_CHECK_MD_ND@1 (<-UKCA_AERO_STEP <-UKCA_AERO_CTL <-UKCA_MAIN1) 69.353 (PE 111) 70.39 72.844 (PE 71) 3.49
UKCA_CALCNUCRATE@1 (<-UKCA_AERO_STEP <-UKCA_AERO_CTL <-UKCA_MAIN1) 68.434 (PE 122) 69.12 70.696 (PE 0) 2.26
TWO_COEFF@1 44.224 (PE 82) 67.16 81.861 (PE 124) 37.64
EG_HELM_RHS_STAR@1 54.647 (PE 116) 66.80 81.482 (PE 32) 26.84
TWO_COEFF@2 47.576 (PE 63) 66.30 79.812 (PE 102) 32.24
UKCA_BINAPARA@1 (<-UKCA_CALCNUCRATE <-UKCA_AERO_STEP <-UKCA_AERO_CTL <-UKCA_MAIN1) 64.945 (PE 114) 65.11 65.558 (PE 0) 0.61
EM_GET_DATA_REAL3D@1 (<-UKCA_OFFLINE_OXIDANTS_UPDATE <-UKCA_READ_OFFLINE_OXIDANTS_CTL <-UKCA_MAIN1) 64.263 (PE 31) 64.84 71.117 (PE 52) 6.85
SPATIAL@1 64.018 (PE 121) 64.46 65.145 (PE 49) 1.13
UKCA_SOLVECOAGNUCL_V@1 (<-UKCA_COAGWITHNUCL <-UKCA_AERO_STEP <-UKCA_AERO_CTL <-UKCA_MAIN1) 58.211 (PE 2) 62.81 67.322 (PE 77) 9.11
ATM_STEP_STASH@1 59.707 (PE 122) 59.99 60.409 (PE 44) 0.70
QWIDTH@2 4.968 (PE 82) 58.56 117.889 (PE 68) 112.92
PP_HEAD@1 54.012 (PE 124) 54.36 55.192 (PE 72) 1.18
MID_CONV_6A@1 20.984 (PE 13) 52.98 122.02 (PE 84) 101.04
MID_CONV_6A@2 23.004 (PE 121) 52.47 109.226 (PE 86) 86.22
EG_SISL_INIT@1 47.089 (PE 56) 50.86 90.781 (PE 45) 43.69
GLOBAL_2D_SUMS@1 24.181 (PE 103) 50.76 169.749 (PE 112) 145.57
UKCA_VOLUME_MODE@1 (<-UKCA_AERO_STEP <-UKCA_AERO_CTL <-UKCA_MAIN1) 47.873 (PE 1) 50.40 52.847 (PE 79) 4.97
LSP_QCLEAR@2 4.312 (PE 82) 50.02 101.898 (PE 68) 97.59
EG_SISL_INIT_UVW@1 44.152 (PE 56) 47.95 87.931 (PE 45) 43.78
GW_USSP@1 20.112 (PE 11) 47.49 87.73 (PE 114) 67.62
EG_SL_WIND_W@1 43.168 (PE 73) 44.50 46.194 (PE 116) 3.03
IMP_SOLVER@1 17.313 (PE 67) 40.31 89.786 (PE 15) 72.47

The most expensive routines

UKCA_SYNC is just the time waiting for the other PEs to catchup the work they do in UKCA_MAIN1 and below.

The numbers for the table below can be reproduced with the command

perl /home/cr/ukesm/mstringe/cgi-bin/drHook/drHook.pl --dir=/data/cr/ukesm/mstringe/facec29_7_14
--nRoutines=50 --orderBy=self:mean
where the command should all be on the same line.
Ordering routines by self: mean
Min Mean Max (Max-Min)
HALO_EXCHANGE:SWAP_BOUNDS_NS_DP@1 / SWAP_BOUNDS_NS_DP (<-SWAP_BOUNDS_NS <-SWAP_BOUNDS_DP <-SWAP_BOUNDS <- lots of routines, including ATMOS_PHYSICS1) 166.072 (PE 67) 340.02 552.464 (PE 5) 386.39
ATMOS_PHYSICS1@1 (<-ATM_STEP_4A) 292.894 (PE 82) 319.98 332.417 (PE 105) 39.52
UKCA_COAGWITHNUCL@1 (<-UKCA_AERO_STEP <-UKCA_AERO_CTL <-UKCA_MAIN1) 294.729 (PE 2) 305.53 315.846 (PE 48) 21.12
HALO_EXCHANGE:SWAP_BOUNDS_EW_H1_DP@1 / SWAP_BOUNDS_EW_H1_DP (<-SWAP_BOUNDS_EW_H1 <-SWAP_BOUNDS_EW_DP <-SWAP_BOUNDS_EW <-SWAP_BOUNDS_DP <-SWAP_BOUNDS <- lots of routines, including ATMOS_PHYSICS1) 135.068 (PE 124) 279.96 571.472 (PE 82) 436.40
UKCA_RADAER_BAND_AVERAGE@2 173.56 (PE 2) 275.99 371.806 (PE 61) 198.25
UKCA_RADAER_BAND_AVERAGE@1 (<-RADIANCE_CALC <-LW_RAD, SW_RAD <-RAD_CTL <-ATMOS_PHYSICS1) 170.587 (PE 2) 272.35 372.917 (PE 84) 202.33
UKCA_ABDULRAZZAK_GHAN@1 (<-UKCA_ACTIVATE<-UKCA_MAIN1) 29.336 (PE 4) 125.05 162.923 (PE 69) 133.59
EG_CORRECT_TRACERS_UKCA@1 (<-ATM_STEP_4A) 117.342 (PE 53) 120.13 122.591 (PE 0) 5.25
EM_GET_DATA_REAL@1 110.17 (PE 66) 115.98 120.195 (PE 39) 10.02
LS_PPNC@1 33.067 (PE 82) 114.41 155.4 (PE 84) 122.33
HALO_EXCHANGE:SWAP_BOUNDS_EW_DP@1 101.792 (PE 124) 112.76 123.802 (PE 95) 22.01
SWAP_BOUNDS_MV@1 24.754 (PE 75) 112.15 200.533 (PE 126) 175.78
eg_CUBIC_LAGRANGE@1 95.845 (PE 20) 97.52 102.623 (PE 123) 6.78
EG_MASS_CONSERVATION@1 95.753 (PE 106) 97.15 98.221 (PE 7) 2.47
UKCA_COND_COFF_V@1 81.588 (PE 1) 92.06 103.885 (PE 21) 22.30
UKCA_SYNC@1 33.008 (PE 76) 90.30 226.285 (PE 2) 193.28
QWIDTH@1 21.354 (PE 82) 76.70 125.782 (PE 68) 104.43
EG_INTERPOLATION_ETA@1 67.482 (PE 63) 76.66 91.294 (PE 18) 23.81
UKCA_CHECK_MD_ND@1 69.292 (PE 111) 70.35 72.821 (PE 71) 3.53
UKCA_BINAPARA@1 64.945 (PE 114) 65.11 65.558 (PE 0) 0.61
EM_GET_DATA_REAL3D@1 64.118 (PE 31) 64.69 70.957 (PE 52) 6.84
GLUE_CONV_6A@1 35.329 (PE 82) 64.08 97.788 (PE 58) 62.46
GLUE_CONV_6A@2 37.461 (PE 82) 63.05 98.031 (PE 58) 60.57
UKCA_SOLVECOAGNUCL_V@1 58.211 (PE 2) 62.81 67.322 (PE 77) 9.11
QWIDTH@2 4.968 (PE 82) 58.56 117.889 (PE 68) 112.92
TRI_SOR_DP_DP@1 55.396 (PE 66) 58.37 65.529 (PE 110) 10.13
GLOBAL_2D_SUMS@1 24.181 (PE 103) 50.76 169.749 (PE 112) 145.57
UKCA_CONDEN@1 46.512 (PE 11) 49.30 52.106 (PE 90) 5.59
UKCA_AERO_CTL@1 42.166 (PE 2) 42.65 43.549 (PE 60) 1.38
ATM_STEP_4A@1 39.709 (PE 84) 40.97 42.568 (PE 96) 2.86
NI_CONV_CTL@1 24.176 (PE 84) 40.72 84.101 (PE 49) 59.92
EG_CORRECT_TRACERS@1 37.639 (PE 109) 38.62 39.957 (PE 64) 2.32
DEPARTURE_POINT_ETA@1 32.515 (PE 71) 35.72 39.426 (PE 118) 6.91
EXPPXI@1 34.717 (PE 69) 34.85 35.211 (PE 23) 0.49
UKCA_COAG_COFF_V@1 33.718 (PE 92) 33.78 33.957 (PE 64) 0.24
EG_SISL_INIT_UVW@1 31.904 (PE 80) 33.08 34.129 (PE 101) 2.22
LSP_QCLEAR@1 11.972 (PE 82) 30.10 45.756 (PE 68) 33.78
EM_FOPEN@1 26.505 (PE 66) 28.41 29.539 (PE 47) 3.03
UKCA_MAIN1@1 25.063 (PE 101) 26.52 27.245 (PE 91) 2.18
GATHER_FIELD_MPL@1 18.392 (PE 0) 25.50 27.116 (PE 32) 8.72
LSP_SUBGRID@1 2.672 (PE 82) 25.40 44.859 (PE 68) 42.19
UKCA_VOLUME_MODE@1 24.444 (PE 118) 25.07 25.623 (PE 82) 1.18
SPATIAL@1 24.56 (PE 69) 24.70 24.923 (PE 13) 0.36
PP_HEAD@1 24.291 (PE 108) 24.49 24.844 (PE 72) 0.55
SWAP_BOUNDS_2D_MV@1 4.611 (PE 61) 24.16 61.229 (PE 15) 56.62
LSP_SUBGRID@2 2.191 (PE 82) 24.03 47.115 (PE 68) 44.92
TRANS_SOURCE_COEFF@1 16.784 (PE 82) 22.84 27.245 (PE 124) 10.46
TRANS_SOURCE_COEFF@2 17.887 (PE 63) 22.62 26.926 (PE 113) 9.04
STWORK@1 22.144 (PE 0) 22.52 22.817 (PE 44) 0.67
STEXTC@1 21.893 (PE 120) 22.26 22.611 (PE 49) 0.72

The most unbalanced routines

The numbers for the table below can be reproduced with the command

perl /home/cr/ukesm/mstringe/cgi-bin/drHook/drHook.pl --dir=/data/cr/ukesm/mstringe/facec29_7_14
--orderBy=selfPer:diff
where the command should all be on the same line.
Ordering routines by selfPer: diff
Min Mean Max (Max-Min)
MEANDIAG@1 84.36 (PE 0) 4727.40 4996.51 (PE 50) 4912.15
EXITPROC@1 6.47 (PE 0) 1248.66 2269.16 (PE 106) 2262.69
UM_SHELL:RENDEZ-VOUS@1 (PE 106) 1020.31 2261.95 (PE 17) 2261.95
U_MODEL_4A@1 1882.9 (PE 75) 2583.42 2759.91 (PE 126) 877
ACUMPS@1 68.1 (PE 68) 72.09 521.23 (PE 0) 453.13
UM_SHELL@1 71.12 (PE 10) 143.22 358.88 (PE 53) 287.76
UMPRINTOPENSTREAM@1 0.23 (PE 0) 69.84 286.02 (PE 58) 285.79
UM_WRITDUMP@1 8.16 (PE 81) 11.04 287.1 (PE 0) 278.94
IO:FILE_OPEN@1 13.99 (PE 0) 214.17 215.86 (PE 45) 201.87
UMPRINTLOADOPTIONS@1 0.16 (PE 0) 141.72 201.27 (PE 79) 201.11