• Global
  • Configurations
• Summary
• Functions
• Loops

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

Global Metrics

Metric		r0	r1	r2	r3	r4	r5
Total Time (s)		102.88	101.32	104.31	101.76	100.39	105.32
Max (Thread Active Time) (s)		101.38	99.04	102.08	100.19	98.45	102.95
Average Active Time (s)		100.74	98.88	101.96	99.89	98.30	102.86
Activity Ratio (%)		98.2	97.8	97.9	98.5	98.2	97.9
Average number of active threads		188.008	187.372	187.675	188.467	187.997	187.529
Affinity Stability (%)		98.3	98.0	98.0	98.6	98.3	98.1
GFLOPS		387.091	359.278	362.232	388.000	361.424	355.223
Time in analyzed loops (%)		93.1	92.4	93.3	93.3	93.1	93.0
Time in analyzed innermost loops (%)		89.6	89.4	90.8	89.8	89.8	89.0
Time in user code (%)		93.3	92.7	93.6	93.5	93.4	93.3
Compilation Options Score (%)		100	66.7	75.0	100	100	100
Array Access Efficiency (%)		55.3	51.9	56.6	55.3	52.0	56.3
Potential Speedups
Perfect Flow Complexity		2.01	4.54	4.65	1.98	4.60	4.95
Perfect OpenMP/MPI/Pthread/TBB		1.03	1.04	1.03	1.03	1.04	1.03
Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution		1.07	1.07	1.06	1.06	1.06	1.06
No Scalar Integer	Potential Speedup	1.18	1.26	1.38	1.19	1.26	1.40
	Nb Loops to get 80%	2	2	2	2	2	3
FP Vectorised	Potential Speedup	1.61	1.65	1.60	1.61	1.65	1.54
	Nb Loops to get 80%	3	3	3	3	3	3
Fully Vectorised	Potential Speedup	5.61	5.62	6.61	5.71	5.80	6.66
	Nb Loops to get 80%	6	7	7	6	7	8
Only FP Arithmetic	Potential Speedup	1.26	1.36	1.49	1.28	1.36	1.50
	Nb Loops to get 80%	4	3	3	4	3	4

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

r0r1r2r3r4r5

Source Object	Issue
▼exec–
▼lattice.cpp–
○
▼fix_nve.cpp–
○
▼verlet.cpp–
○
▼nbin.cpp–
○
▼pair.cpp–
○
▼nbin_standard.cpp–
○
▼create_atoms.cpp–
○
▼pair_eam.cpp–
○
▼memory.h–
○
▼atom.cpp–
○
▼comm_brick.cpp–
○
▼neighbor.cpp–
○
▼compute_temp.cpp–
○
▼atom_vec.cpp–
○
▼domain_omp.cpp–
○
▼npair_bin.cpp–
○

Source Object	Issue
▼exec–
▼stl_map.h–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼atom.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼platform.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼atom_vec.h–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼memory.h–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼npair_bin.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼fix_nve.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼verlet.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼pair.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼random_park.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼compute.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼atom_vec.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼nbin.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼utils.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼neighbor.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼group.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼comm_brick.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼domain.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼velocity.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼create_atoms.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼integrate.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼modify.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼timer.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼variable.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼pair_eam.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼compute_temp.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼comm.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼domain_omp.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼my_page.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼lattice.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼compute_pe.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼nbin_standard.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2
▼thermo.cpp–
○	-xHost or -march=native should not be used with Intel compilers while targeting (or compiling on) non-Intel processors, use -mavx2

Source Object	Issue
▼exec–
▼lattice.cpp–
○	-funroll-loops is missing.
▼fix_nve.cpp–
○	-funroll-loops is missing.
▼verlet.cpp–
○	-funroll-loops is missing.
▼nbin.cpp–
○	-funroll-loops is missing.
▼pair.cpp–
○	-funroll-loops is missing.
▼nbin_standard.cpp–
○	-funroll-loops is missing.
▼create_atoms.cpp–
○	-funroll-loops is missing.
▼pair_eam.cpp–
○	-funroll-loops is missing.
▼npair_bin.cpp–
○	-funroll-loops is missing.
▼atom.cpp–
○	-funroll-loops is missing.
▼platform.cpp–
○	-funroll-loops is missing.
▼neighbor.cpp–
○	-funroll-loops is missing.
▼domain_omp.cpp–
○	-funroll-loops is missing.
▼atom_vec.cpp–
○	-funroll-loops is missing.
▼compute_temp.cpp–
○	-funroll-loops is missing.
▼comm_brick.cpp–
○	-funroll-loops is missing.

Source Object	Issue
▼exec–
▼nbin.cpp–
○
▼atom.cpp–
○
▼neighbor.cpp–
○
▼compute_temp.cpp–
○
▼lattice.cpp–
○
▼fix_nve.cpp–
○
▼verlet.cpp–
○
▼modify.cpp–
○
▼pair_eam.cpp–
○
▼npair_bin.cpp–
○
▼pair.cpp–
○
▼create_atoms.cpp–
○
▼timer.cpp–
○
▼domain_omp.cpp–
○
▼atom_vec.cpp–
○
▼nbin_standard.cpp–
○
▼comm_brick.cpp–
○

Source Object	Issue
▼exec–
▼stl_map.h–
○
▼stl_tree.h–
○
▼atom.cpp–
○
▼platform.cpp–
○
▼domain_omp.cpp–
○
▼npair_bin.cpp–
○
▼fix_nve.cpp–
○
▼verlet.cpp–
○
▼pair.cpp–
○
▼random_park.cpp–
○
▼lammps.cpp–
○
▼compute.cpp–
○
▼atom_vec.cpp–
○
▼npair.cpp–
○
▼nbin.cpp–
○
▼utils.cpp–
○
▼neighbor.cpp–
○
▼group.cpp–
○
▼compute_temp.cpp–
○
▼new_allocator.h–
○
▼basic_string.h–
○
▼velocity.cpp–
○
▼neigh_list.cpp–
○
▼integrate.cpp–
○
▼modify.cpp–
○
▼comm_brick.cpp–
○
▼variable.cpp–
○
▼pair_eam.cpp–
○
▼finish.cpp–
○
▼comm.cpp–
○
▼lattice.cpp–
○
▼my_page.cpp–
○
▼memory.h–
○
▼timer.cpp–
○
▼nbin_standard.cpp–
○
▼create_atoms.cpp–
○

Source Object	Issue
▼exec–
▼npair_bin.cpp–
○
▼fix_nve.cpp–
○
▼verlet.cpp–
○
▼nbin.cpp–
○
▼pair.cpp–
○
▼nbin_standard.cpp–
○
▼lattice.cpp–
○
▼pair_eam.cpp–
○
▼compute_temp.cpp–
○
▼atom.cpp–
○
▼create_atoms.cpp–
○
▼neighbor.cpp–
○
▼domain_omp.cpp–
○
▼atom_vec.cpp–
○
▼comm_brick.cpp–
○
▼modify.cpp–
○

Path Count Profiles

Coverage

Count

Low Iteration Count Profiles

Coverage

Count

Average Number of Active Threads

Run 1 - orig_default

Run 2 - icx_default

Run 3 - gcc_default

Run 4 - aocc_1

Run 5 - icx_2

Run 6 - gcc_5