options

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

Global Metrics

Metricr0r1
Total Time (s)81.5184.26
Max (Thread Active Time) (s)18.4120.28
Average Active Time (s)17.3019.89
Activity Ratio (%)66.069.1
Average number of active threads13.58615.110
Affinity Stability (%)96.096.4
GFLOPS4.2053.735
Time in analyzed loops (%)79.578.7
Time in analyzed innermost loops (%)78.777.1
Time in user code (%)79.578.7
Compilation Options Score (%)100100
Array Access Efficiency (%)40.072.3
Potential Speedups
Perfect Flow Complexity1.001.00
Perfect OpenMP/MPI/Pthread/TBB1.071.13
Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution1.341.30
No Scalar IntegerPotential Speedup2.681.03
Nb Loops to get 80%12
FP VectorisedPotential Speedup1.231.37
Nb Loops to get 80%11
Fully VectorisedPotential Speedup2.602.66
Nb Loops to get 80%22
Only FP ArithmeticPotential Speedup1.371.06
Nb Loops to get 80%22

FLOPS Breakdown

Cumulated Speedup If No Scalar Integer

Cumulated Speedup If FP Vectorized

Cumulated Speedup If Fully Vectorized

Cumulated Speedup If Only FP Arithmetic

Loop Based Profiles

Innermost / Single Loops

Inbetween Loops

Outermost Loops

Cumulated Coverage With All Loops

Innermost Loop Based Profiles

Coverage

Count

Application Categorization

Time

Coverage

Compilation Options

Source ObjectIssue
kmeans-acfl-Ofast
main.cpp

Path Count Profiles

Coverage

Count

Low Iteration Count Profiles

Coverage

Count

Average Number of Active Threads

Run 1 - Neoverse V1 ACFL Ofast Manual Unroll ONLY (no Hoisting) (250 iterations, 64 threads)

Run 2 - Neoverse V1 ACFL Ofast Hoisting ONLY (no Unroll) (250 iterations, 64 threads)

Experiment Summaries

r0r1
Experiment NameK-Means single with 250 iterations on config acfl-Ofast (Manual unroll ONLY - no assignment hoist) and size 100000000K-Means single with 250 iterations on config acfl-Ofast (Assignment Hoist ONLY - no manual unroll) and size 100000000
Application./kmeans/kmeans-acfl-Ofastsame as r0
Timestamp2025-09-30 09:52:582025-09-30 09:57:51
Experiment TypeOpenMP; same as r0
Machineip-172-31-18-66same as r0
Architectureaarch64same as r0
Micro ArchitectureARM_NEOVERSE_V1same as r0
Model Name
Cache Size
Number of Cores
Maximal Frequency0 GHzsame as r0
OS VersionLinux 6.14.0-1012-aws #12~24.04.1-Ubuntu SMP Fri Aug 15 00:07:14 UTC 2025same as r0
Architecture used during static analysisaarch64same as r0
Micro Architecture used during static analysisARM_NEOVERSE_V1same as r0
Compilation Options kmeans-acfl-Ofast: Arm C/C++/Fortran Compiler version 24.10.1 (build number 4) (based on LLVM 19.1.0) /opt/arm/arm-linux-compiler-24.10.1_Ubuntu-20.04/llvm-bin/clang-19 --driver-mode=g++ -I . -MMD -MP -Wall -std=c++14 -g -fno-omit-frame-pointer -fopenmp -Ofast -grecord-command-line -march=native -mcpu=native -c -o main.o main.cpp same as r0
Number of processes observed1same as r0
Number of threads observed64same as r0
Frequency DriverNAsame as r0
Frequency GovernorNAsame as r0
Huge Pagesmadvisesame as r0
Hyperthreadingoffsame as r0
Number of sockets1same as r0
Number of cores per socket64same as r0
MAQAO version2025.1.2same as r0
MAQAO buildee78608affc6d6d67ff71a0d376ae286b36f9862::20250929-173943same as r0
CommentsK-MEANS AWS Graviton 3 (Neoverse V1) CPU, 64 threads run, 250 iterationssame as r0
×