It's never a processor limitation. If speed is not an issue, all the SIMD extensions to today's processors (chronologically MMX, 3DNow! [AMD only], SSE, SSE2, SSE3, Supplemental SSE3 and SSE4 [upcoming]) are completely useless. They run a single operation on sets of operands (e.g. vectors -- (ax, ay, az) + (bx, by, bz) = (cx, cy, cz)), thereby speeding up such calculations.
The "bad bone weight" error probably means that a "circumvention" of SSE2 (a "scenic route" -- using good ol' FPU and/or integer operations instead of SSE2, which is unavailable) returns an invalid result due to human error. We don't know why and whose error, though. ~~ Ondra On 10.11.07 21:21 Uhr, Devin Carlson wrote:
"Yes that is true. There are no problems hosting the Windows version on a P3/AMD Athlon. Drek" So it is not a processor limitation, ie because of processor support for FCMOV/SSE2 etc.... well that's good to know, thanks. I'll check back in a month or so to see if they have fixed the problem with their linux server.
_______________________________________________ To unsubscribe, edit your list preferences, or view the list archives, please visit: http://list.valvesoftware.com/mailman/listinfo/hlds_linux
