- edited description
CloverLeaf_MPI
Issue #15
new
CloverLeaf_MPI is a pure MPI/F90 test (with no OpenMP).
Get the src
- ssh -Y daint01
- cd $SCRATCH
- git clone https://github.com/Warwick-PCAV/CloverLeaf_MPI.git
- TODO: cscs git
- cd CloverLeaf_MPI
scorep/1.3
GNU
module swap PrgEnv-cray PrgEnv-gnu
module swap craype/2.05 craype/2.1.3
module swap cray-mpich/6.2.2 cray-mpich/7.0.1
module swap cray-libsci/12.1.3 cray-libsci/13.0.0
module swap pmi/5.0.2-1.0000.9906.117.2.ari pmi/5.0.4-1.0000.10161.132.4.ari
module load cudatoolkit
module load scorep/1.3
- make clean
make \
MPI_COMPILER="scorep --mpp=mpi ftn" \
C_MPI_COMPILER="scorep --mpp=mpi cc" \
COMPILER=GNU \
CFLAGS_GNU= \
FLAGS_GNU=
- mv GNU.DAINT.MPI GNU.DAINT.MPI.scorep13
8 mpi tasks
- grep end_time clover.in
PROFILING
export SCOREP_ENABLE_PROFILING=true
export SCOREP_ENABLE_TRACING=false
export SCOREP_CUDA_ENABLE=no
aprun -n8 -N4 -d1 GNU.DAINT.MPI.scorep13 clover.in
-
Ignore: ERROR:150: Module 'cray-mpich/6.2.2' conflicts with the currently loaded module(s) 'cray-mpich/7.0.1'
-
scorep-score scorep-20140921_1633_608628491056605/profile.cubex
Estimated aggregate size of event trace: 1501MB
Estimated requirements for largest trace buffer (max_buf): 207MB
Estimated memory requirements (SCOREP_TOTAL_MEMORY): 209MB
(hint: When tracing set SCOREP_TOTAL_MEMORY=209MB to avoid intermediate flushes
or reduce requirements using USR regions filters.)
flt type max_buf[B] visits time[s] time[%] time/visit[us] region
ALL 216,914,561 40,163,008 53.69 100.0 1.34 ALL
MPI 140,012,255 16,450,744 40.24 74.9 2.45 MPI
USR 64,356,682 19,451,944 5.17 9.6 0.27 USR
COM 13,846,040 4,260,320 8.28 15.4 1.94 COM
- cube scorep-20140921_1633_608628491056605/profile.cubex
Comments (6)
-
reporter -
reporter - edited description
-
reporter - edited description
TRACING
export SCOREP_ENABLE_PROFILING=false export SCOREP_ENABLE_TRACING=true export SCOREP_CUDA_ENABLE=no aprun -n8 -N4 -d1 GNU.DAINT.MPI.scorep13 clover.in
-
Ignore: ERROR:150: Module 'cray-mpich/6.2.2' conflicts with the currently loaded module(s) 'cray-mpich/7.0.1'
-
vampir83 scorep-20140921_1736_612445138776044/traces.otf2
-
reporter perftools/6.2.1
GNU
module swap PrgEnv-cray PrgEnv-gnu module swap craype/2.05 craype/2.1.3 module swap cray-mpich/6.2.2 cray-mpich/7.0.1 module swap cray-libsci/12.1.3 cray-libsci/13.0.0 module swap pmi/5.0.2-1.0000.9906.117.2.ari pmi/5.0.4-1.0000.10161.132.4.ari module load perftools/6.2.1 # perftools/621jg
- make clean
make \ MPI_COMPILER=ftn \ C_MPI_COMPILER=cc \ COMPILER=GNU \ CFLAGS_GNU= \ FLAGS_GNU=
- mv GNU.DAINT.MPI GNU.DAINT.MPI.perft621
pat_build -g mpi,io GNU.DAINT.MPI.perft621
8 MPI TASKS
- grep end_time clover.in
aprun -n8 -N4 -d1 GNU.DAINT.MPI.perft621+pat clover.in
- Ignore: ERROR:150: Module 'cray-mpich/6.2.2' conflicts with the currently loaded module(s) 'cray-mpich/7.0.1'
- pat_report GNU.DAINT.MPI.perft621+pat+32267-3678t > xf.txt
Table 1: Profile by Function Group and Function Time% | Time | Imb. | Imb. | Calls |Group | | Time | Time% | | Function | | | | | PE=HIDE 100.0% | 3.519134 | -- | -- | 2112690.6 |Total |----------------------------------------------------------------------- | 56.1% | 1.974115 | -- | -- | 2056343.0 |MPI ||---------------------------------------------------------------------- || 33.0% | 1.161910 | 0.256009 | 20.6% | 575020.0 |mpi_waitall_ || 12.8% | 0.451565 | 0.079247 | 17.1% | 718775.0 |mpi_isend_ || 7.1% | 0.251233 | 0.014611 | 6.3% | 37500.0 |mpi_allreduce_ || 2.8% | 0.098882 | 0.027397 | 24.8% | 718775.0 |mpi_irecv_ ||====================================================================== | 23.4% | 0.822777 | 0.484992 | 42.4% | 1.0 |USER ||---------------------------------------------------------------------- | 23.4% | 0.822777 | 0.484992 | 42.4% | 1.0 | main ||====================================================================== | 19.3% | 0.679128 | -- | -- | 43771.0 |MPI_SYNC ||---------------------------------------------------------------------- || 17.4% | 0.611054 | 0.366420 | 60.0% | 37500.0 |mpi_allreduce_(sync) || 1.3% | 0.045135 | 0.019517 | 43.2% | 6260.0 |mpi_reduce_(sync) ||====================================================================== | 1.2% | 0.043114 | -- | -- | 12575.6 |ETC ||---------------------------------------------------------------------- | 1.0% | 0.036490 | 0.255428 | 100.0% | 6305.6 | raw_write |=======================================================================
- app2 *.ap2
Use energy hardware counters
export PAT_RT_SUMMARY=0 export PAT_RT_PERFCTR=default_samp
- More infos about the counters (SandyBridge):
- $CRAYPAT_ROOT/share/counters/Counters.papi_intel_fam6mod45
- $CRAYPAT_ROOT/share/counters/CounterGroups.intel_fam6mod4
- man pmpc
- aprun -n1 papi_avail
-
reporter - edited description
-
reporter scorep/1.3
export SCOREP_ENABLE_PROFILING=false export SCOREP_ENABLE_TRACING=true export SCOREP_CUDA_ENABLE=no export SCOREP_METRIC_PAPI_SEP=@ export SCOREP_METRIC_PAPI=PAPI_FP_OPS@PAPI_NATIVE_craypm:::PM_POWER_CAP:NODE
- Empty :-( => Score-P metric plugin to monitor the application external energy and power information on Cray platforms
- Log in to comment