This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
i386 backend
- To: <gcc at gcc dot gnu dot org>
- Subject: i386 backend
- From: "David Rasmussen" <pinkfloydhomer at yahoo dot com>
- Date: Mon, 19 Mar 2001 20:12:24 +0100
I have a question.
What is being done at the moment, to make the i386 backend more effecient
(and possibly other parts of the compiler that might be relevant)?
When comparing the assembler output of gcc with that of MSVC++ or the Intel
C++ Compiler, one finds that there are many relatively simple optimizations
that gcc lacks. Optimally, it would be cool if gcc supported such advanced
features as profiler directed compilation and other features that some
compilers have.
I like gcc, but I'm not using it anymore, since I need all the performance I
can get in my domain, and MSVC++ generated code is about 30% faster than
that of gcc, while Intel's is 40-50% faster.
What is being done to address these issues, if anything?
David Rasmussen