This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: i386 backend
David Rasmussen wrote:
> Even if I can't be very precise in pointing out _where_ the problems is, it
> should still be recognized as a problem. A very simplistic way of putting it
> is: "Why is gcc producing slower code than MSVC++ or Intel C++?". I know
> that it is not always the case, but from all the different types of programs
> I've compiled, and all the people who I have talked to, it is almost always
> the case. So there is room for improvement.
Last time I observed someone comparing GCC and MSVC++, GCC was faster by
about 20% IIRC (around 3 years ago). MSVC++ compiled much faster
though, so they still used it (the project required on-the-fly
compilation). Also MSVC++ produced much smaller executables for C++.
Work a few years earlier on video games showed MSVC coming out faster at
first, but later it seemed GCC was winning, so they switched from GCC to
MSVC to GCC..
Your question remains a good one, especially if you rephrase as "What
are MSVC++ and Intel C++ doing that produces better code?".
-----------
It's not very useful to simply claim that MSVC++ is better. Most people
here don't use Windows, so aren't able to compare the code.
If you have done comparisons, it would be very helpful if you could
illustrate what exactly MSVC++ and Intel C++ are doing better.
Perhaps you could provide assembly listings of the noticably faster
parts of your program?
-- Jamie