Faster encoding on 64bit?

[Tr!n!]

Hi,

Was just reading just articles about the new amd opteron and was wondering if 64-bit cpu's will be much faster in encoding.
Is encoding done with much floating point operations (fast on 64 bit) or is most done with 32bit integers?
And are there other factors to look at?

Greetings,
Trini

[int 21h]

http://forum.doom9.org/showthread.php?s=&threadid=51964

[Tr!n!]

Thanks for the link, but that was a benchmark on 32bit.
I was asking if some1 would compile a 64 bit xvid version and run it would it be much faster than the 32bit version?
I dont really know the encondig algoritm, but i guess some here do...
If it would be using 32bit integers (like 32bit colors) all the time there wouldnt be much improvment, right?

[int 21h]

I guess you didn't read down the entire thread, so I will just paste the relevant portion.


It may have encoded slower, but it also encoded with a higher accuracy There is a similar situation between MMX iDCT and SSE2 iDCT, the speed is nearly identical, but the SSE2 iDCT is leagues more accurate. When comparing SSE or even MMX to SSE2, the thing to keep in mind is that you're reaching an area of diminishing returns. SSE2 won't necessarily preform faster than SSE, but it will preform higher accuracy calculations at a higher speed than doing the same accuracy level in SSE. Eventually you reach the point where assembly is assembly, and disregarding any large branch mispredicts, the speed will be nearly identical for either version of the instructions... and that is where things get interesting for the two behemoths (AMD and Intel) since they both are moving towards radically different CPU models... In theory, SSE2 instructions should execute more quickly on an Opteron than a P4 because of the shorter pipeline.....