Ow Mun Heng wrote: >On Mon, 2005-04-11 at 22:05 -0700, Peter Gordon wrote: > > >>Isn't that what the "-march=pentium-m" and "-mtune=pentium-m" flags are for in >>GCC 3.4? >> >> > >That's what it should be for. Friend of mine used 3.4 on a BSD machine >to compile apps using pentium-m and results were S-N-A-P-P-Y! :-) > >Doing a make world on the kernel though trashed. > >
Ok, since nobody is actually bothering to _read_ article that I linked to, let me quote a small piece: "Pentium M's Micro Ops Fusion, local branch prediction and general optimizations across integer division and register access are completely ignored by the compiler, even when setting - march=pentium-m, since most compilers (particularly anything before GCC 3.4.2) tend to just categorize Pentium M as a P6 processor with a higher clock." -Anandtech.com >From what I can tell from the change logs for GCC 3.4.2 and 3.4.3, nothing has changed in this regard. Anandtech.com might be completely wrong about GCC, but I would be _very_ surprised. The article has many benchmarks for different types of applications, if anyone is actually interested. http://www.anandtech.com/linux/showdoc.aspx?i=2308 -Richard -- gentoo-user@gentoo.org mailing list
