Help is available by moving the cursor above any symbol or by checking MAQAO website.
▶Filter Information
There is no filter information to display
Global Metrics
Total Time (s)
10.44
Max (Thread Active Time) (s)
2.87
Average Active Time (s)
2.81
Activity Ratio (%)
29.9
Average number of active threads
17.215
Affinity Stability (%)
95.6
Time in analyzed loops (%)
4.35
Time in analyzed innermost loops (%)
3.86
Time in user code (%)
4.47
Compilation Options Score (%)
74.9
Array Access Efficiency (%)
74.2
Potential Speedups
Perfect Flow Complexity
1.00
Perfect OpenMP/MPI/Pthread/TBB
1.03
Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution
1.06
No Scalar Integer
Potential Speedup
1.01
Nb Loops to get 80%
3
FP Vectorised
Potential Speedup
1.01
Nb Loops to get 80%
2
Fully Vectorised
Potential Speedup
1.03
Nb Loops to get 80%
2
FP Arithmetic Only
Potential Speedup
1.03
Nb Loops to get 80%
3
CQA Potential Speedups Summary
Average Active Threads Count⏎
Loop Based Profile⏎
Innermost Loop Based Profile⏎
Application Categorization⏎
Compilation Options⏎
Source Object
Issue
▼libllama.so–
○hashtable.h
-funroll-loops is missing.
○llama-vocab.cpp
-funroll-loops is missing.
○hashtable_policy.h
-funroll-loops is missing.
▼libggml-cpu.so–
○binary-ops.cpp
-funroll-loops is missing.
○ops.cpp
-funroll-loops is missing.
○vec.cpp
-funroll-loops is missing.
○ggml-cpu.c
-funroll-loops is missing.
○quants.c
-funroll-loops is missing.
▼libggml-base.so–
▼–
○
-g is missing for some functions (possibly ones added by the compiler), it is needed to have more accurate reports. Other recommended flags are: -O2/-O3, -march=(target)