• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

What is it about Q3 and games based on that engine that makes them faster on systems w/big memory bandwidth?

F

fkloster

Diamond Member
O.k., we can all agree that the Q3 engine runs faster on P4's because of the i850's big memory bandwidth. But why? When Carmack is writing code, does he delibratly write stuff that sends instructions to the cpu from the video card and then back through the system memory pipeline; therfore games using this technique run faster on P4's because of the 3.2gb/s bandwidth? Please explain this phenomenon to me... 🙂
 
honestly, no-one knows why people do these things.

I suspect that the fact that his engine is 'efficient' (LOL, it requires 64 megs of RAM), means that you are able to see memory bandwidth making an effect, because it is the slowest component on the computer, at least when playing games (you need that amount of RAM in order to hold that massive engine).
 


<< ...honestly, no-one knows why people do these things... >>



I am totally serious. Does anyone have any insight?



<< I think they asked carmack this question and he even stated he wasn't sure why... >>



Uh oh, if Carmack doesn't know whats up, this thread may be useless 🙁
 
Think about it this way, if the guy who wrote the code for QIII
1. is John Carmack and
2. doesnt know
lets not bother.

Edit- just saw the edit above... yea...
 
I thought it was stated by anand and other editors that Q3 was coded with the scaling of memory bandwidth. I think backthen the best bandwidth you can get was RDRAM solution on the i820 or either the i840 but that might of came later.
 
Here's the quote from a while back:



<< If I had to hazard a wild guess, I would say that it is because much of Q3's structure is broken up into nice separate phases, like game, cgame, front end, back end. The P4 relies on a trace cache for best performance, and it would have effects in some ways like a smaller instruction cache. It may turn out to be something unrelated, like a better bus interface helping the graphics driver more. >>

- John Carmack

Source is from here.

Sounds like a guess, but there you go.
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top