about latest versions

John W. Eaton jwe at octave.org
Sun Apr 19 11:03:34 CDT 2009


On 19-Apr-2009, MHELHEFNY wrote:

| As you mentioned that both  VC++/3.0.3/SSE2  and  MinGW/3.0.2/SSE2  on  your
| computer
| gave , the same performance of about 1350 MFLOPS , What astonishes  me is
| that MinGw/3.0.2
| on my computer gives a performance of  3600  MFLOPS  which is more than 2.5
| times more than
|  that you have mentioned  and which is also 5 times more than  that of
| Matlab (ver 6.5) which on my machine gave 660 MFLOPS  i.e. 1/5 of
| MinGw/3.0.2 .
| It is also  astonishing that Tatsuro's computer gave even more performance
| :-
| mingw(gcc-4.3.2-dw2-TDM)  MFLOPS = 4830.2 .

If you build Octave to link with an optimized BLAS library, you should
get good performance for basic linear algebra operations like matrix
multiplication, at least on the system for which the BLAS library was
designed.  But your optimized BLAS library that is tuned for one
system may not work well on another, different type of system (with a
different cache size, for example).

Since these performance problems you are seeing are not problems with
Octave itself, perhaps you could move this discussion somewhere else?

| May ,I dare to ask you , tatsuro and others what is more important in a
| mathematical software than performance?.

Getting a correct answer?

jwe


More information about the Bug-octave mailing list