Discussion in 'General Software' started by Aleksander, May 4, 2010.
Well, the more powerful the card, the more difference between results you get.
Yeah, I'm sure they got that. I also know what I've seen in my own testing. I was trying to find my spreadsheet earlier with the results on it, but it's gone awol. I'll ask my friend to email me his copy and I'll show you the results.
The NVIDIA benchmarks were on a more powerful card than the ATI benchmarks (higher FPS across the board). NVIDIA showed virtually no difference whereas ATI did. ATI may have been lacking driver optimizations for Vista/7. That may have changed since the benchmark was performed, however.
You sure it wasn't a DX9 vs DX10 thing? DX10 is faster than DX9 so long as all the settings are the same (and usually, they're not).
Publish them if you want to prove it, cuz mine is nvidia and it did show 250 points difference which for this card is a lot.
250 points in 3Dmark06 is nothing. It's almost within margin of error.
Quite sure, as TrackMania is a DX9 game. I used it, because it has a really easy to use and repeatable benchmark mode that doesn't take very long to run.
Anyway, I've now received the results spreadsheet from my friend and attached it to this post. It was about a year ago we did this, so it's XP SP3 v Vista SP1. Both operating systems were 32-bit and fully patched, had the latest DX update and drivers applied.
We tested a HD3850 512MB & a HD4870 512MB on an E8400 at the stock 3GHz. The performance loss with Vista averaged a large 30%, with the 4870 actually taking a bigger hit.
Windows 7 isn't any better, either. I did a couple of bench quickies with Windows 7 recently and the results don't change much. nvidia takes a slightly smaller hit, if I remember correctly, but I didn't bother to write the results down.
In short, if you want the best DX9 gaming performance, stick to XP 32-bit and that applies to the latest hardware, too. Our friend Aleksander Dishnica is right when he says he gets better 3D performance on XP.
The Athlon 64 results are there to quantify just how much faster the E8400 is compared to the Athlon 64. As you can see, it's way faster, as you'd expect. Interestingly, you can see how the system with the faster CPU & slower graphics card can sometimes beat the system with the slower CPU & faster graphics card, depending on the exact bench parameters.
Oh and finally, TrackMania is awesome.
Actually he says he gets better performance using x64 xp compared to x32 xp and win7.
I must add smth else. I get more performance on xp x86 (not x32!!!! as pepper wrote! )
than windows 7. From the bench all can see that in xp x64 i got better results than x32.
So summing up:
Windows 7 x86 < Windows XP x86 < Windows XP x64 (Performance)
This is at least for games.
x86 is x32
Never heard of those. You mean x86-64?
I'm going to go with something in the game coding that is causing that 30% difference, not the operating system. If it were the operating system, that large of difference would be uniform accross all benchmarks and it isn't.
"x32" doesn't exist. It's x86 (also known as IA-32), x86-64 (x86 w/ 64-bit extension, sometimes abreviated x64, technically is AMD64 or EM64T), or IA-64 (Intel 64-bit architecture).
I thought you also said that XP gives better performance than Vista or 7 on this thread?? With almost 90 posts here, it's a bit too long to start trawling through it to check this, to be honest.
Ok guys. Conclusion is Windows XP 64-bit is the best performer of all OS (windows tested only)
So, yes qubit. Vista is worse than windows 7. Actually reading between the lines your question gets an yes as answer.
x86 = 32-bit
x64 = 64-bit
Vista/Windows 7 is faster at networking than XP when there is a domain server on the intranet. Transfers between Windows 7 computers are "OMFG" faster than XP.
Game performance is about equal, slight advantage to XP; except the odd title out that is heavily biased towards XP.
Yes, it is better at networking, I've seen that myself. But this isn't about networking performance. Did you look at my results spreadsheet? The game I tested with actually gives fairly typical results compared to the other games I've seen. I just did some formal testing with this one to nail some numbers down, because the benchmarking mode is very quick and easy to do. There's no "heavy bias towards XP" with this game.
I think there is a mix up since I have a habit of incorrectly calling it x32 instead of x86.
I see difference in xp 32-bit even in most wanted, imagine in other games. What about the 64 bit xp?
Windows 7 is worse than Xp for games. That is for sure. That is why it needs more ram in system requirements. It has its downsides too, so dont be that optimistic, as it costs more than xp
Gamers just get directx 11 which again is a downside as it is not a concern for the moment.
Windows 7 gets more space in HDD or SSD. That means more space, less performance in games, costs more. I am not interested on it, sorry!!!
There is no x32, so i understand you mean 32-bit
Well you stick with XP if you like but Win 7 and DX11 are the way fowards.
I addressed that in the post above saying I've been incorrectly referring it x32 out of bad habit.
XP's good for DX9 games and also preventing advancement in computer gaming. Windows 7 are for real gamers who want the industry to move forward rather than to be happy with what they've got.
I think money make the real advancement, not OS or direct x11
They money that is used to buy the new os and DX11 hardware is.
I'm guessing you updated your video drivers to a newer/better version than you were using on your x86 installation.
its ok pepper. I hate it when people corre t me personally. zomg bro x86-32bit. ya i know. but everyone else in the universe understands when I say x32 or x64
I honestly still don't understand the point of the thread, are we asking for proof here other than 3DMark scores?
But don't you want to be technically correct? People that don't know that x32 is actually x86 are misinformed.
Your benchmarking clearly shows there is.
There's some games that perform better in XP (TrackMania being an example as well as ARMA II).
There's others that show virtually no preference like Call of Duty 4, Left 4 Dead, Fallout 3, and Dawn of War II.
And some that perform better in Vista/7 like Crysis, Far Cry 2, S.T.A.L.K.E.R.: Clear Sky, and Resident Evil V.
If you're looking for a gaming performance upgrade, the answer isn't a different OS (except in the case of tesselation on DX11). A better GPU will generally increase the FPS no matter the OS.
Separate names with a comma.