g++ -c -g -O0 -funroll-all-loops -std=c++17 -Wall -pedantic -Wextra -Weffc++ -Woverloaded-virtual -Wfloat-equal -Wshadow -Wredundant-decls -Winline -fmax-errors=1  -flto -o main.o main.cpp
g++ -c -g -O0 -funroll-all-loops -std=c++17 -Wall -pedantic -Wextra -Weffc++ -Woverloaded-virtual -Wfloat-equal -Wshadow -Wredundant-decls -Winline -fmax-errors=1  -flto -o mylib.o mylib.cpp
g++ -c -g -O0 -funroll-all-loops -std=c++17 -Wall -pedantic -Wextra -Weffc++ -Woverloaded-virtual -Wfloat-equal -Wshadow -Wredundant-decls -Winline -fmax-errors=1  -flto -o benchmark.o benchmark.cpp
g++  main.o mylib.o benchmark.o  -g -O0  -llapack -lblas -flto -o main.GCC_
./main.GCC_ 

===== Benchmark A =====
<xA,yA> = 1.4e+06
Timing in sec. : 0.00893637
GFLOPS         : 0.291808
GiByte/s       : 2.33446

===== Benchmark B =====
340000
bytes: 2.31472e+07
Timing in sec. : 0.0133897
GFLOPS         : 0.402029
GiByte/s       : 1.61001

===== Benchmark C =====
7.37196e+07
bytes: 2.4e+07
Timing in sec. : 8.67235
GFLOPS         : 0.21478
GiByte/s       : 0.00257736

===== Benchmark D =====
10500
bytes: 3.20001e+07
Timing in sec. : 0.101087
GFLOPS         : 0.515935
GiByte/s       : 0.294821

===== Benchmark 5A =====
NORM = 150114
Timing in sec. : 0.00703533
GFLOPS         : 0.370658
GiByte/s       : 1.48263

===== Benchmark 5B =====
<xA,yA> = 1.4e+06
Timing in sec. : 0.0108377
GFLOPS         : 0.601533
GiByte/s       : 1.92491

===== Benchmark 5C =====
7.37196e+07
bytes: 2.4e+07
Timing in sec. : 15.2407
GFLOPS         : 0.122215
GiByte/s       : 0.00146658