Hi, > > not too long ago I read on this list that you have to be extra careful > > about using floating point in the kernel. Is the same true for MMX? If > > so, would it be dangerous to compile a kernel module with -march=athlon? > > AFAIK gcc-3.2 generates MMX instructions if the target CPU supports > > them. > > If so, the kernel will crash, eventually. However, I thought that gcc > wouldn't use MMX on its own (ie that you have to use the MMX data types to > get MMX operations). Not true?
Not. gcc (3.1+) will use MMX for integer, SSE for float code, even with normal instructions, if both - code optimization enabled (so it will recognize normal array operations (example: for(i=0;i<15;i++) y[i]+=x[i];) and replace them with SIMD) - SIMD usage enabled (-msse, -mmmx, -msse2, -m3dnow, -mfpmath=sse (use SSE for float) / -mfpmath=sse,387 (use SSE and FPU in parallel for float) so, by default it won't use SIMD. > Many other architectures use a compiler flag like "-msoft-float" or > "-mno-fpu" to explicitly tell gcc that it cannot use the FP unit. If gcc > starts using MMX on its own, we'll have to find the switch that tells it it has -mno-mmx, -mno-sse etc. > not to do that. You might want to ask some gcc people about it.. ehh. i'm not gcc people... :) (but i did RTFM :) A'rpi / Astral & ESP-team -- Developer of MPlayer, the Movie Player for Linux - http://www.MPlayerHQ.hu ------------------------------------------------------- This sf.net email is sponsored by:ThinkGeek Welcome to geek heaven. http://thinkgeek.com/sf _______________________________________________ Dri-devel mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/dri-devel
