------- Comment #11 from pinskia at gcc dot gnu dot org 2005-11-03 02:40 ------- (In reply to comment #10) > I am not sure what kind of answer you expect here. > Speed and code size are not disjoint. Think about I-cache and I-TLB misses. But again who is using an pentiumpro machine any more. People who really care about preformance in code really should be tunning for their machine. Xterm is not a good example of a program which really needs more speed. Also you are going to get a lot of Icache missed anyways as the machine is going to be switching between processes more offten than actually doing anything with this instruction. Now if you can prove that using -march=pentium3 (or 4 depending on your target) will be worse then just maybe. But otherwise this is invalid. Yes most distros defaultly compile for pentiumpro (i686) but that is not GCC's fault as this is actually faster for the pentumpro.
-- pinskia at gcc dot gnu dot org changed: What |Removed |Added ---------------------------------------------------------------------------- Status|WAITING |RESOLVED Resolution| |INVALID http://gcc.gnu.org/bugzilla/show_bug.cgi?id=23523