options

exec - 2025-04-03 17:11:06 - MAQAO 2.21.1

Help is available by moving the cursor above any symbol or by checking MAQAO website.

Global Metrics

Total Time (s)129.96
Max (Thread Active Time) (s)127.77
Average Active Time (s)127.66
Activity Ratio (%)98.6
Average number of active threads70.725
Affinity Stability (%)99.8
GFLOPS58.894
Time in analyzed loops (%)96.1
Time in analyzed innermost loops (%)96.0
Time in user code (%)97.2
Compilation Options Score (%)50.0
Array Access Efficiency (%)94.4
Potential Speedups
Perfect Flow Complexity1.18
Perfect OpenMP + MPI + Pthread1.01
Perfect OpenMP + MPI + Pthread + Perfect Load Distribution1.02
No Scalar IntegerPotential Speedup1.08
Nb Loops to get 80%5
FP VectorisedPotential Speedup1.22
Nb Loops to get 80%9
Fully VectorisedPotential Speedup2.06
Nb Loops to get 80%21
FP Arithmetic OnlyPotential Speedup1.22
Nb Loops to get 80%13

CQA Potential Speedups Summary

Average Active Threads Count

Loop Based Profile

Innermost Loop Based Profile

Application Categorization

Compilation Options

Source ObjectIssue
exec
calc_dt.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.
advec_cell.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.
accelerate.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.
pack_kernel.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.
reset_field.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.
revert.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.
viscosity.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.
initialise_chunk.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.
ideal_gas.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.
PdV.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.
generate_chunk.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.
field_summary.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.
advec_mom.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.
flux_calc.cpp
-march=x86-64 is used but it should be replaced by a more architecture specific option or -march=native.
-funroll-loops is missing.

Loop Path Count Profile

Cumulated Speedup If No Scalar Integer

Cumulated Speedup If FP Vectorized

Cumulated Speedup If Fully Vectorized

Cumulated Speedup If FP Arithmetic Only

Experiment Summary

Application/beegfs/hackathon/users/eoseret/qaas_runs_CPU_8360Y/174-369-0250/intel/CloverLeaf2.0-CXX/run/base_runs/defaults/gcc/exec
Timestamp2025-04-03 17:11:06 Universal Timestamp1743693066
Number of processes observed2 Number of threads observed72
Experiment TypeMPI; OpenMP;
Machineicp01.benchmarkcenter.megware.com
Model NameIntel(R) Xeon(R) Platinum 8360Y CPU @ 2.40GHz
Architecturex86_64 Micro ArchitectureICELAKE_SP
Cache Size55296 KB Number of Cores36
OS VersionLinux 5.14.0-503.16.1.el9_5.x86_64 #1 SMP PREEMPT_DYNAMIC Fri Dec 13 01:47:05 EST 2024
Architecture used during static analysisx86_64 Micro Architecture used during static analysisICELAKE_SP
Frequency Driverintel_pstate Frequency Governorperformance
Huge Pagesalways Hyperthreadingon
Number of sockets2 Number of cores per socket36
Compilation Optionsexec: GNU C++17 14.2.0 -mtune=generic -march=x86-64 -g -O3 -std=c++17 -fno-omit-frame-pointer -fcf-protection=none -fopenmp

Configuration Summary

Dataset
Run Command<executable>
MPI Commandmpirun -n <number_processes>
Number Processes2
Number Nodes1
FilterNot Used
Profile StartNot Used
×