OV - Compare Index

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

▶Compared Reports

r0: run_1_thread
r1: run_2_threads
r2: run_4_threads - option thread_filter-threshold (1%) discards 1 threads, cumulating 0.01 seconds CPU time.
r3: run_8_threads - option thread_filter-threshold (1%) discards 3 threads, cumulating 0.08 seconds CPU time.
r4: run_16_threads - option thread_filter-threshold (1%) discards 12 threads, cumulating 0.55 seconds CPU time.
r5: run_32_threads - option thread_filter-threshold (1%) discards 5 threads, cumulating 0.18 seconds CPU time.
r6: run_48_threads - option thread_filter-threshold (1%) discards 6 threads, cumulating 0.24 seconds CPU time.
r7: run_64_threads - option thread_filter-threshold (1%) discards 7 threads, cumulating 0.28 seconds CPU time.
r8: run_80_threads - option thread_filter-threshold (1%) discards 4 threads, cumulating 0.21 seconds CPU time.
r9: run_96_threads

Global Metrics

Metric		r0	r1	r2	r3	r4	r5	r6	r7	r8	r9
Total Time (s)		81.93	44.69	26.06	16.74	12.10	9.81	9.05	8.68	8.51	8.86
Max (Thread Active Time) (s)		7.39	7.39	7.39	7.39	7.43	7.49	7.45	7.56	7.48	7.98
Average Active Time (s)		7.39	7.39	7.39	7.39	3.75	0.43	0.38	0.40	0.45	0.88
Activity Ratio (%)		9.02	16.5	28.3	44.1	31.0	4.41	4.24	4.65	5.32	9.96
Average number of active threads		90.2 E-3	0.165	0.283	0.441	0.621	1.189	1.778	2.601	3.930	9.445
Affinity Stability (%)		96.1	96.4	96.8	97.4	49.0	66.9	79.6	83.8	87.8	91.8
GFLOPS		61.1 E-3	0.113	0.201	0.351	0.937	4.401	8.253	14.321	23.158	48.240
Time in analyzed loops (%)		100.0	100.0	100.0	99.9	99.9	100.0	100.0	100.0	100.0	99.9
Time in analyzed innermost loops (%)		100.0	100.0	99.9	99.8	99.4	97.4	96.4	95.4	94.5	93.4
Time in user code (%)		100	100	100	99.9	99.9	100.0	100	100	100	99.9
Compilation Options Score (%)		87.5	87.5	87.5	87.5	87.5	87.5	87.5	87.5	87.5	87.5
Array Access Efficiency (%)		41.7	41.7	41.7	41.7	41.7	41.7	41.7	41.7	41.7	41.7

Potential Speedups
Perfect Flow Complexity		1.00	1.00	1.00	1.00	1.03	1.17	1.26	1.34	1.41	1.52
Perfect OpenMP/MPI/Pthread/TBB		1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00
Perfect OpenMP/MPI/Pthread/TBB + Perfect Load Distribution		1.00	1.00	1.00	1.00	1.98	17.3	19.4	18.7	16.5	9.07
Scalability - Gap		1.00	0.55	0.32	0.20	0.30	3.23	4.64	5.94	7.68	10.27
No Scalar Integer	Potential Speedup	1.57	1.57	1.57	1.58	1.64	1.94	2.15	2.36	2.53	2.82
No Scalar Integer	Nb Loops to get 80%	1	1	1	1	2	2	2	2	2	1
FP Vectorised	Potential Speedup	1.14	1.14	1.14	1.14	1.16	1.24	1.29	1.34	1.37	1.42
FP Vectorised	Nb Loops to get 80%	1	1	1	1	2	2	2	1	1	1
Fully Vectorised	Potential Speedup	1.76	1.76	1.76	1.76	1.74	1.69	1.67	1.65	1.63	1.61
Fully Vectorised	Nb Loops to get 80%	1	1	1	1	1	2	2	2	2	1
Only FP Arithmetic	Potential Speedup	5.49	5.48	5.44	5.29	4.40	2.65	2.17	1.89	1.73	1.54
Only FP Arithmetic	Nb Loops to get 80%	1	1	1	1	1	2	2	2	2	2

Scalability Speedup

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 Object	Issue
▼kmeans-gcc-O3-all–
▼main.cpp–
○	-O3 or -Ofast is missing.

Path Count Profiles

Coverage

Count

Low Iteration Count Profiles

Coverage

Count

Average Number of Active Threads

Run 1 - run_1_thread

Run 2 - run_2_threads

Run 3 - run_4_threads

Run 4 - run_8_threads

Run 5 - run_16_threads

Run 6 - run_32_threads

Run 7 - run_48_threads

Run 8 - run_64_threads

Run 9 - run_80_threads

Run 10 - run_96_threads

Experiment Summaries

	r0	r1	r2	r3	r4	r5	r6	r7	r8	r9
Experiment Name	K-Means scalability gcc-O3-all 100000000	K-Means scalability gcc-O3-all 100000000	K-Means scalability gcc-O3-all 100000000	K-Means scalability gcc-O3-all 100000000	K-Means scalability gcc-O3-all 100000000	K-Means scalability gcc-O3-all 100000000	K-Means scalability gcc-O3-all 100000000	K-Means scalability gcc-O3-all 100000000	K-Means scalability gcc-O3-all 100000000	K-Means scalability gcc-O3-all 100000000
Application	./kmeans/kmeans-gcc-O3-all	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Timestamp	2025-07-10 12:04:59	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Experiment Type	Sequential	same as r0	same as r0	same as r0	OpenMP;	same as r4	same as r4	same as r4	same as r4	same as r4
Machine	ip-172-31-47-249.ec2.internal	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Architecture	aarch64	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Micro Architecture	ARM_NEOVERSE_V2	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Model Name
Cache Size
Number of Cores
Maximal Frequency	0 GHz	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
OS Version	Linux 6.1.109-118.189.amzn2023.aarch64 #1 SMP Tue Sep 10 08:58:40 UTC 2024	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Architecture used during static analysis	aarch64	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Micro Architecture used during static analysis	ARM_NEOVERSE_V2	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Compilation Options	kmeans-gcc-O3-all: GNU C++14 14.2.0 -mlittle-endian -mabi=lp64 -mcpu=neoverse-v2+crc+sve2-aes+sve2-sha3+nossbs -g -O3 -std=c++14 -fno-omit-frame-pointer -fopenmp -ftree-vectorize -funroll-loops -ffast-math GNU C17 14.2.0 -mlittle-endian -mabi=lp64 -g -g -g -O2 -O2 -O2 -fbuilding-libgcc -fno-stack-protector -fPIC	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Number of processes observed	1	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Number of threads observed	1	same as r0	same as r0	same as r0	2	27	42	56	74	95
Frequency Driver	NA	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Frequency Governor	NA	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Huge Pages	madvise	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Hyperthreading	off	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Number of sockets	1	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Number of cores per socket	96	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
MAQAO version	2025.1.1	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
MAQAO build	f763b230967252184a5e61875ae92196728ac8f6::20250710-120157	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0
Comments	AWS Graviton 4 (Neoverse V2) CPU, 1-96 threads runs	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0	same as r0

Report Configuration

▶Compared Reports

Global Metrics

Scalability Speedup

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

Path Count Profiles

Coverage

Count

Low Iteration Count Profiles

Coverage

Count

Average Number of Active Threads

Run 1 - run_1_thread

Run 2 - run_2_threads

Run 3 - run_4_threads

Run 4 - run_8_threads

Run 5 - run_16_threads

Run 6 - run_32_threads

Run 7 - run_48_threads

Run 8 - run_64_threads

Run 9 - run_80_threads

Run 10 - run_96_threads

Experiment Summaries