Help is available by moving the cursor above any symbol or by checking MAQAO website.
▶Filter Information
24 threads covering less than 1% of profiled time ( = Max (Thread Active Time)) were discarded, cumulating 0.33 seconds CPU time. You can adjust the threshold below which a thread will be discarded with the thread-filter-threshold option.
Global Metrics
Total Time (s)
39.29
Max (Thread Active Time) (s)
33.00
Average Active Time (s)
32.93
Activity Ratio (%)
83.8
Average number of active threads
53.627
Affinity Stability
27.3
Time in analyzed loops (%)
95.3
Time in analyzed innermost loops (%)
66.2
Time in user code (%)
95.3
Compilation Options Score (%)
100
Array Access Efficiency (%)
56.2
Potential Speedups
Perfect Flow Complexity
1.00
Perfect OpenMP + MPI + Pthread
1.02
Perfect OpenMP + MPI + Pthread + Perfect Load Distribution
1.05
No Scalar Integer
Potential Speedup
1.75
Nb Loops to get 80%
2
FP Vectorised
Potential Speedup
1.52
Nb Loops to get 80%
2
Fully Vectorised
Potential Speedup
3.27
Nb Loops to get 80%
5
FP Arithmetic Only
Potential Speedup
1.40
Nb Loops to get 80%
2
CQA Potential Speedups Summary
Loop Based Profile⏎
Innermost Loop Based Profile⏎
Application Categorization⏎
Compilation Options⏎
Source Object
Issue
▼lbc–
○lb_init.F90
○mpl_set.F90
○tools.F90
○lbc.F90
○lbm_functions.F90
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
./../lbc/lbc
Timestamp
2024-11-27 15:18:57
Universal Timestamp
1732720737
Number of processes observed
64
Number of threads observed
64
Experiment Type
MPI; OpenMP;
Machine
ip-172-31-42-13
Architecture
aarch64
Micro Architecture
ARM_NEOVERSE_V1
OS Version
Linux 6.8.0-1016-aws #17~22.04.2-Ubuntu SMP Thu Sep 26 18:55:31 UTC 2024
symbol or by checking MAQAO website.