options

attention-icx-skl512 - 2026-06-24 16:29:58 - MAQAO 2026.0.1

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

Global Metrics

Total Time (s)13.81
Max (Thread Active Time) (s)13.80
Average Active Time (s)13.80
Activity Ratio (%)99.9
Average number of active threads0.999
Affinity Stability (%)60.3
GFLOPS2.507
Time in analyzed loops (%)98.9
Time in analyzed innermost loops (%)72.6
Time in user code (%)98.8
Compilation Options Score (%)99.8
Array Access Efficiency (%)31.3
Potential Speedups
Perfect Flow Complexity1.00
Perfect OpenMP/MPI/Pthread/TBB1.00
Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution1.00
No Scalar IntegerPotential Speedup1.07
Nb Loops to get 80%7
FP VectorisedPotential Speedup1.03
Nb Loops to get 80%6
Fully VectorisedPotential Speedup1.70
Nb Loops to get 80%9
FP Arithmetic OnlyPotential Speedup2.01
Nb Loops to get 80%9

CQA Potential Speedups Summary

FLOPS Breakdown

Loop Based Profile

Innermost Loop Based Profile

Application Categorization

Compilation Options

Source ObjectIssue
libstdc++.so.6.0.35
-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)
-O2, -O3 or -Ofast is missing.
-march=(target) is missing.
attention-icx-skl512
attention_v2.cpp
libc.so.6
-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)
-O2, -O3 or -Ofast is missing.
-march=(target) 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./attention-icx-skl512
Timestamp2026-06-24 16:29:58 Universal Timestamp1782311398
Number of processes observed1 Number of threads observed1
Experiment TypeSequential
Machineskylake
Model NameIntel(R) Xeon(R) Platinum 8170 CPU @ 2.10GHz
Architecturex86_64 Micro ArchitectureSKYLAKE
Cache Size36608 KB Number of Cores26
OS VersionLinux 6.19.8-arch1-1 #1 SMP PREEMPT_DYNAMIC Sat, 14 Mar 2026 01:07:43 +0000
Architecture used during static analysisx86_64 Micro Architecture used during static analysisSKYLAKE
Frequency Driverintel_cpufreq Frequency Governorschedutil
Huge Pagesalways Hyperthreadingoff
Number of sockets2 Number of cores per socket26
Compilation Optionsattention-icx-skl512: --driver-mode=g++ --intel -O3 -g -grecord-command-line -fno-omit-frame-pointer -march=native -mprefer-vector-width=512 -fapprox-func -fno-math-errno -ffinite-math-only -fassociative-math -fno-signed-zeros attention_v2.cpp -o attention-icx-skl512 -fveclib=SVML -faltmathlib=SVML -fheinous-gnu-extensions -dumpdir attention-icx-skl512-
libc.so.6: N/A + libstdc++.so.6.0.35: N/A

Configuration Summary

Dataset
Run Command<executable> 128 32 10000
FilterNot Used
Profile StartNot Used
Profile StopNot Used
×