• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

**Official 3DMark API Overhead Leaderboard**

Is it normal for 280X's to be detected as 7900 series by Windows 10? Seems to be downloading drivers for 7900 series.

e0c23218b135d58db12863bceae5b6d0.png
 
Last edited:
Scurburg said:
[email protected] - 280x xfire@1175/1700 - Win7

Seems res doesn't make much difference (all around 26 million with mantle for me which seems odd tbh) Anyway, here are the results:
Click to expand...

All that means, is that you have hit the ceiling of what your cpu and the rendering engine can push to the card, or what the card can process.

Try overclocking cpu to see which. If a cpu overclock pushes it up, then its cpu bound. If not, its the gpu hitting its max at its clock.
 
290X CrossFire@1000/[email protected]

720p:

DX11 Multi-threaded draw calls per second975593.9
DX11 Single-threaded draw calls per second1077746.2
Mantle draw calls per second1.75453678E7
DX11 Multi-threaded draw calls per frame32256.0
DX11 Single-threaded draw calls per frame33792.0
Mantle draw calls per frame540672.0
DX11 Multi-threaded final fps30.25 fps
DX11 Single-threaded final fps31.89 fps
Mantle final fps32.45 fps

http://www.3dmark.com/3dm/6416409

1080p:

DX11 Multi-threaded draw calls per second990571.5
DX11 Single-threaded draw calls per second1031901.7
Mantle draw calls per second1.7411889E7
DX11 Multi-threaded draw calls per frame32256.0
DX11 Single-threaded draw calls per frame35328.0
Mantle draw calls per frame540672.0
DX11 Multi-threaded final fps30.71 fps
DX11 Single-threaded final fps29.21 fps
Mantle final fps32.2 fps

http://www.3dmark.com/3dm/6416497

1440p:

DX11 Single-threaded draw calls per second1073126.7
Mantle draw calls per second1.79782907E7
DX11 Single-threaded draw calls per frame35328.0
Mantle draw calls per frame540672.0
DX11 Single-threaded final fps30.38 fps
Mantle final fps33.25 fps

http://www.3dmark.com/3dm/6416564

4K:

DX11 Multi-threaded draw calls per second969705.5
DX11 Single-threaded draw calls per second1044883.1
Mantle draw calls per second1.75176338E7
DX11 Multi-threaded draw calls per frame32256.0
DX11 Single-threaded draw calls per frame33792.0
Mantle draw calls per frame565248.0
DX11 Multi-threaded final fps30.06 fps
DX11 Single-threaded final fps30.92 fps
Mantle final fps30.99 fps

http://www.3dmark.com/3dm/6416610
 
I'm adding DX11 to this but removing all resolutions above 720P.
As we found out higher resolutions make no difference to scores.
its also far too cluttered with so many resolutions.
Its better to make room for DX11 and clean it up so that people can actually see whats going on.

i will post back when i have made the changes. thanks :)
 
LegitReviews said:
“When moving over to the Sapphire Radeon R9 290X video card with AMD CATALYST 15.200.1012.2 drivers we are finally able to see Mantle versus DirectX 12! We got the highest number of draw calls per second with AMD Mantle! We hit 20.61M draw calls per second with the Radeon R9 290X and the AMD Mantle API with the Intel Core i7-5960X processor and HT disabled! This is more 3.85M more draw calls per second than the GeForce GTX 980 could reach”
Click to expand...

Source
http://www.legitreviews.com/looking...mance-3dmark-api-overhead-feature-test_160936

Forbes said:
“Above, my test results for an AMD Radeon 260x. We’re talking a 1200% uplift in draw calls per second!” – This was 2-5x the uplift of any other graphics ASIC tested by Forbes.
Click to expand...

Source
http://www.forbes.com/fdc/welcome_mjx.shtml
 
And in what actually matters for gamers today is DX11 performance where Nvidia's DX11 MT is nearly 300% faster than AMD.


We can worry about DX12 when it is officially released. Better yet we can benchmark actual games, because evidently the 980 is not 300% faster than a 290X which just shows how utterly meaningless this data is.
 
Late entry, but though it might be of interest as this old machine is severely hampered by its cpu let alone the gpu ;) No surprises in the result as it matches the pattern we have already seen, but it is still interesting to note the huge gap in the results between the api's.

Opteron 180 @2880
R7 250 1100/1200
Catalyst 15.4 beta / Windows 7 64bit

DX11 Multithreaded: 245,424
Dx11 Single Threaded: 251,074
Mantle: 2,432,038
 
MadMatty said:
Late entry, but though it might be of interest as this old machine is severely hampered by its cpu let alone the gpu ;) No surprises in the result as it matches the pattern we have already seen, but it is still interesting to note the huge gap in the results between the api's.

Opteron 180 @2880
R7 250 1100/1200
Catalyst 15.4 beta / Windows 7 64bit

DX11 Multithreaded: 245,424
Dx11 Single Threaded: 251,074
Mantle: 2,432,038
Click to expand...

Good Entry, why should they all be Uber Systems... :)

Done.
 
You must log in or register to reply here.
Back
Top Bottom