- edited description
MAQAO:LPROF
Issue #30
new
Goal: test maqao
Comments (3)
-
reporter -
reporter BT-MZ
Compile
- module swap PrgEnv-cray PrgEnv-intel
- make COMPILER="-openmp -extend-source" CLASS=C NPROCS=8 MAIN=bt FLINKFLAGS="
-dynamic
-openmp"
Run
- export PATH=$PATH:/apps/daint/5.2.UP02/maqao/2.1.1/bin
maqao/2.2.0_rc3
- export OMP_NUM_THREADS=1
- aprun -n8 -d1
maqao lprof --
./bt-mz_C.8 - maqao
--list-modules
MODULE ALIAS LOCATION ============================================================================== madras madras built-in analyze analyse built-in cqa cqa built-in mil mil1 built-in perfeval lprof built-in mil2 instrument built-in
Old version, do not use
- aprun -n8 -d1
maqao.intel64 perfeval --
./bt-mz_C.8
maqao.intel64 --list-modules MODULE ALIAS LOCATION ============================================================================== madras madras built-in cqa cqa built-in mil mil1 built-in analyze analyze built-in perfeval perf built-in grouping built-in mil2 instrument built-in
Analyze
Html report
- maqao lprof xp=maqao_052620151946 d=SFX
of=html
Text report
- maqao lprof xp=maqao_052620151946 d=SFX
CATEGORIZATION ################################################################################################################## # | Binary | MPI | OMP | MATH | System | Pthread | IO | String | Memory | Others # ################################################################################################################## # TOTAL | 78.01 | 1.43 | 0.00 | 0.00 | 19.84 | 0.00 | 0.00 | 0.69 | 0.00 | 0.02 # ################################################################################################################## HOTSPOTS SUMMARY ########################################################################################################################################################## # Function Name | Time Average (%) | Time Min(s) [TID] | Time Max(s) [TID] | Time Average(s) | Module # ########################################################################################################################################################## # binvcrhs_ | 30.80 | 5.26 [16234] | 6.42 [16233] | 5.89 | bt-mz_C.8 # # z_solve_ | 12.80 | 2.14 [16231] | 2.66 [16240] | 2.45 | bt-mz_C.8 # # y_solve_ | 10.14 | 1.64 [16243] | 2.32 [16231] | 1.94 | bt-mz_C.8 # # x_solve_ | 9.80 | 1.72 [16231] | 2.16 [16234] | 1.88 | bt-mz_C.8 # # compute_rhs_ | 9.63 | 1.42 [16240] | 2.04 [16241] | 1.84 | bt-mz_C.8 # # matmul_sub_ | 8.02 | 0.98 [16233] | 1.78 [16234] | 1.54 | bt-mz_C.8 # # MPIDI_CH3I_Progress | 5.88 | 0.44 [16234] | 1.44 [16243] | 1.12 | libmpich_intel.so.3.0.1 # # matvec_sub_ | 4.73 | 0.76 [16243] | 1.04 [16239] | 0.90 | bt-mz_C.8 # # exact_solution_ | 0.84 | 0.10 [16240] | 0.20 [16231] | 0.16 | bt-mz_C.8 #
-
reporter - changed title to MAQAO:LPROF
- Log in to comment