Re:Optimizing matrix multiplication in C
by attractivechaos on Monday August 29, 2016 @10:12AM
(#12381939)
> 2. and then you compare performances without equal consideration of the problem size for n!
All the different implementations are compared on the same condition: same n, same compiler and same machine.
> are you aware that Blas uses Fortran
Wrong. uBLAS and Eigen are written purely in C++. OpenBLAS is a mixture of C and ASM. They have nothing to do with Fortran.
> you have also added debugging flags to the compilers further slowing the BLAS routines with more debugging cruft!?
By debugging flags, you mean "-g"? No, -g should not affect the performance (maybe a tiny bit on loading the executable, but that is negligible). Get rid of -g, and you will get essentially the same result.
> you dare use the word "primitive"
Yes, I dare, because uBLAS is just that bad and should be trashed. Prove me wrong with your benchmarks. Let number speak for itself.
All the different implementations are compared on the same condition: same n, same compiler and same machine.
> are you aware that Blas uses Fortran
Wrong. uBLAS and Eigen are written purely in C++. OpenBLAS is a mixture of C and ASM. They have nothing to do with Fortran.
> you have also added debugging flags to the compilers further slowing the BLAS routines with more debugging cruft!?
By debugging flags, you mean "-g"? No, -g should not affect the performance (maybe a tiny bit on loading the executable, but that is negligible). Get rid of -g, and you will get essentially the same result.
> you dare use the word "primitive"
Yes, I dare, because uBLAS is just that bad and should be trashed. Prove me wrong with your benchmarks. Let number speak for itself.