• Holger Lubitz's avatar
    SSE4 version of 4x4 idct · e9fbd8db
    Holger Lubitz authored
    27->24 clocks on Nehalem.
    This is really just an excuse to use "movsd" in a real function.
    Add some comments to subsum-related macros in x86util.
    e9fbd8db
dct.c 23.8 KB