> Change : 0.82 times faster <------- ;-)
On my system, PPro 180, gcc-2.7.2.3 I get Richards asm
code to be 1.15 times faster than your patched C code.
What were you using?
That's still pretty good, though. According to my tests,
that makes your unrolled C code faster than the i386 asm
we have in the kernel now (by about 15%).
-- There's really no way to fix this, and still keep Perl pathologically eclectic-- Erik Corry erik@arbat.com Ceterum censeo, Microsoftem esse delendam!- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/