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. : 0.000900578
GFLOPS         : 2.89559
GiByte/s       : 23.1647

===== Benchmark B =====
1.7e+07
bytes: 2.31472e+07
Timing in sec. : 0.000687268
GFLOPS         : 7.83252
GiByte/s       : 31.3669

===== Benchmark C =====
bytes: 2.4e+07
Timing in sec. : 0.0151789
GFLOPS         : 122.713
GiByte/s       : 1.47255