Dolphin, the GameCube and Wii emulator - Forums

Retested with the GTX 660:

OS: Win 8 Professional x64
CPU: Intel Core i5 3570K (stock, 3.7 GHz with turbo boost)
GPU: Nvidia GTX 660
Ram: 2 x 4GB (8GB) DDR3 1600 MHz
Dolphin build: 64 bit
Game region: NTSC







Scene 1: 231-251%
Scene 2: 191-203%
Scene 3: 276-316%

As you can see the delta increases as the speed gets higher. That's because at 300% speed a 1% difference in speed changes the counter by 3%.

GPU testing:
I did some additional testing at different resolutions as well. I'm not going to bother clogging up the thread with a zillion images so I'm just including the 1x images above.

Number inside parenthesis indicates the actual IR relative to native. % are the average. They are not calculated in any accurate way but are simply my estimations based on observation.

1x (1x):
241%
198%
296%

2x (4x):
241%
198%
296%

2x shows no difference compared to 1x.

3x (9x):
235%
198%
296%

3x shows no difference compared to 2x.

2x + 4xSSAA (16x):
235%
198%
296%

2x + 4xSSAA shows no difference from 3x.

3x + 4xSSAA (36x):
195%
195%
195%

Very odd results but they are accurate. All three now run at 195% speed average with almost no wavering up/down. Scenes 1 and 3 took a fairly large plummet while scene 2 stayed the same. Do keep in mind though that the game is still running at twice the native speed.

3x + 9xSSAA (81x):
88%
130%
88%

Big plummet in scenes 1 and 3, moderate plummet in scene 2. We're now below fullspeed. This confirms that scenes 1 and 3 are much more demanding on the GPU than scene 2.

And just for shits and giggles
3x + 9xSSAA + per-pixel lighting:
88%
130%
88%

Ok this is weird. Considering how high my internal resolution is and how few polygons are in these three scenes per-pixel lighting should be WAY slower than per-vertex lighting according to common sense. So either it's not working or my understanding of the option is flawed. Perhaps it is because dolphins video backends are limited entirely by video memory bandwidth and not shader throughput on modern GPUs as I have always suspected.

I'll post openGL and d3d11 results soon.

Edit: The results are in.

D3d11 1x:
242%
198%
300%

D3d11 2x:
242%
198%
300%

D3d11 3x:
242%
198%
300%

OpenGL 1x:
241%
197%
298%

OpenGL 2x:
241%
197%
298%

OpenGL 3x:
241%
197%
298%

They are all exactly the same. 1x, 2x, or 3x. D3d9, d3d11, or openGL. All yield the exact same results +/- 1 or 2%. This is because the GPU is not being bottlenecked with any of them. I need to test with 5x or higher to truly see how the three backends perform. I could stress it with MSAA both those results would not be comparable to SSAA.

Edit 2: The results with max MSAA/CSAA are exactly the same in d3d11 and openGL. It still isn't pushing the card hard enough.

Wonderfull, congratulations..

im a newer dolphin user, i still dont understand 100% of this sources, but im trying to do so.

When a game run in more than 100% speed, it means ecxatly what?

When a game run in 100% its the full speed?

When its under the game is slow and not full speed?

When a game is using more than 1920x1080 resolution it means That its more beautifull or doesnt matter because nome TVS have this resolution?

When you improve the ssaa + and + what you ecxatly obtain?

is Wind waker ONE of the most demanding gc games?

What means this Max msaa?

Really thank you

For this Wind Waker benchmark, it does not matter that you understand the settings since you're supposed to leave them as they are for the benchmark.

Nevertheless, I'll answer your questions:

100% speed means the game runs just like it would on a console. Something like 50% would be half the speed while 200% would be twice the speed.

More than 1920x1080 would not make a difference on an 1080p HDTV, but there are quite a few PC monitors that run at 2560x1440.

SSAA removes aliasing and/or "jaggies" by rendering at a higher resolution (such as 3840x2160) and then downscaling the resulting image to your current resolution.

Wind Waker is NOT one of the most demanding GC games - that would have to go to F-Zero GX.

MSAA is another way to remove aliasing and/or "jaggies", but instead is more complicated and optimized and therefore can give considerably better peformance. In general, instead of rendering the entire view at a higher resolution, it only renders the polygon models at a higher resolution, and then downsizes them to fit your resolution.

@NV
The last time we argue about Intel HD 4000 and 1x IR (I can't find that thread)
I said something like a dedicated GPU will get more FPS than Intel HD 4000 even if you use the minimum settings
I know I'm right lol
WindWaker is a lightweight game but you can see that much difference between a dedicated GPU & Intel HD 4000 !

Nintendo Maniac 64 Wrote:More than 1920x1080 would not make a difference on an 1080p HDTV

It certainly does make a difference. Sharper textures and less aliasing.

admin89 Wrote:@NV
The last time we argue about Intel HD 4000 and 1x IR (I can't find that thread)
I said something like a dedicated GPU will get more FPS than Intel HD 4000 even if you use the minimum settings
I know I'm right lol
WindWaker is a lightweight game but you can see that much difference between a dedicated GPU & Intel HD 4000 !

In lightweight games like WW I get the exact same speeds at 1x on both the HD 4000 and GTX 660.

In heavier games like SMG2 there is a performance difference even at 1x.

For most games though I see the same performance on both. Their are very few games that the HD 4000 cannot run fullspeed at 1x, in fact SMG/SMG2 are the only ones that I've encountered so far. I would still recommend a discrete GPU obviously, even at 1x.

(01-28-2013, 08:47 AM)NaturalViolence Wrote: [ -> ]

Nintendo Maniac 64 Wrote:More than 1920x1080 would not make a difference on an 1080p HDTV

It certainly does make a difference. Sharper textures and less aliasing.

I'm referring purely to a video output resolution of 1920x1080 and not factoring in the concept of SSAA. In fact most 1080p HDTVs probably wouldn't even accept a video signal that's larger than 1920x1080.

Really thanks the explanations.

So when you all Talk about FUll SPEED, its not 150 200 250 300%, its just the game is running at 100% ( the console speed )

my TV is full HD 32" can i see visual diference between 3ir and 4ir?

Quote:In lightweight games like WW I get the exact same speeds at 1x on both the HD 4000 and GTX 660.

But your benchmark result show :
Intel HD 4000 : 64-55-82
Nvidia GT 660 : 73-59-89
Did I miss something ?

Nintendo Maniac 64 Wrote:I'm referring purely to a video output resolution of 1920x1080 and not factoring in the concept of SSAA. In fact most 1080p HDTVs probably wouldn't even accept a video signal that's higher-res than 1920x1080.

Ah. You're referring to video output (external) resolution. I was referring to internal resolution.

rafael Wrote:MT TV is full HD 32" can i see visual diference between 3ir and 4ir?

Yes but it will be a small difference.

admin89 Wrote:But your benchmark result show :
Intel HD 4000 : 64-55-82
Nvidia GT 660 : 73-59-89
Did I miss something ?

Is that fps or vps? Are you using the results from before or after I installed the faster ram?

I'm comparing the gamespeed from after getting the new ram against the GTX 660 gamespeed.

ima do this benchmark tomorrow at several speeds. if anybody want to add any to the list let me know.

i plan on testing my 3570k @ 4.5ghz , 4.8ghz, 5ghz

also on stock ram speeds(1333mhz 9-9-9-24), 1600 speeds (with same ram settings), 1600 8-9-8-24 (my max stable ram overclock) speeds.

if theres insuffient data on previous overclocks let me know and ill run my 3570k at those clocks as well.

after doing the PCSX2 benchmark for cpus ive found overclocking ram has been useful in that emulation(i saw a 1 fps gain just from going from 1333mhz to 1600mhz speeds) so i want to test it with dolphin as well.

i really wanna see what my cpu is truly made of

chao for now

-venom

Edit: i decided to do the basic Test @ 4.5ghz tonight with stock ram speeds.


heres my results









test 1 - 90
test 2 - 74
test 3 - 113

will do the others tommorow!

im a bit surprised of the gains i have over a stock clocked 3570k from the previous user.

i cant wait to try mine even overclocked more!>