[lkml]   [1998]   [Jun]   [23]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    SubjectRe: -malign-loops=2 -malign-jumps=2 -malign-functions=2, Why?
    On Mon, Jun 22, 1998 at 05:38:27PM +0200, Niels Kristian Bech Jensen wrote:
    > Hi,
    > What's the reason for using the compiler flags shown in the subj. line
    > when building a kernel for pentium(pro)s?

    no. could we solve this problem now? 4 byte alignment on pentiums is EVIL
    EVIL EVIL. its worse than either zero or 16. Its a total waste of space.

    On ppro and p-ii, alignment is a different issue. A fixed alignment there is,
    again, waste of space as improvements through alignment are seldom, and
    dependent on the number of fill bytes required (egcs is able to selectively
    add alignment).

    For the ppro & p-ii, an alignment of either 0 (for compact code) or 16
    is best.

    > Why aren't those flags used for 486 kernels? On my system a 2.1.106 kernel

    The 486 usually incurs a 2-3% speed penalty when not using 16 byte alignments
    (which are default with -m486), although its usually a different issue with
    the kernel.

    -----==- |
    ----==-- _ |
    ---==---(_)__ __ ____ __ Marc Lehmann +--
    --==---/ / _ \/ // /\ \/ / |e|
    -=====/_/_//_/\_,_/ /_/\_\ --+
    The choice of a GNU generation |

    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to

     \ /
      Last update: 2005-03-22 13:43    [W:0.028 / U:6.064 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site