Ashes of the Singularity User Benchmarks Thread

[TheELF]

Sure thing.

See if I did it correctly.

Thank you,yes awesome job,so after all dx11 is more threaded then dx12,as "advertised" any gain comes from the driver thread that is missing(well it is there but does 0 work) in dx12 you get the ~10% less cpu usage due to the missing driver,and probably the same 10% in speed if your CPU couldn't keep up with your GPU in dx11.
Will be interesting to see if they will be able to keep the perfect splitting of CPU work between the cores in the final game or if it is just because it is a benchmark.


(Lol...dafuq?!?! nvwgf2umx.dll is dx10? )

 

[Sabrewings]

Which made especially these two graphs as inconclusive as it could possible get:
http://www.extremetech.com/wp-content/uploads/2015/09/3qX42h4.png
http://www.extremetech.com/wp-content/uploads/2015/09/vevF50L.png
Just to pick two graphs which got abducted from this thread and ... got misinterpreted, because they mostly measured at lot of random noise. A+ for scientific method.

https://forum.beyond3d.com/threads/dx12-async-compute.57188/page-36

This made me laugh, as I have seen those graphs thrown around a lot in this thread.

Edit: Also...

Guys I hate to throw a wet blanket on this (I'm sort of amused that we have people messing around with GPUView voluntarily in their spare time

), but I think it's time to ask what the point in this exercise is? As a few people have sort of argued on the previous page, none of the results from synthetic workloads are going to generalize to "real" workloads here, as by its very nature this is all completely workload and architecture dependent. Trying to drill into specifics of the implementation on one piece of hardware (reverse engineering) is interesting from a curiosity point of view, but don't be under the illusion that these tests are going to be predictive of real workload performance, or even that one "real" async compute workload is going to be predictive of another. It's roughly like saying that one architecture is "good at compute" or some similarly general/meaningless statement.

Of course I don't realistically expect people to stop digging - as it is sort of fun - but just keep the limitations of this data in perspective and remember that fanboys all across the internet like to grab bits of data out of context from here to support whatever preconceived notions or brand loyalty they have

Let's not be those folks here at least.

 

[AtenRa]

Ok, here are the rest of the tests.

970+2500k cpu test with the same above frequencies.



And here are the 7950+2500k tests and graph





The 7950s score with the 2500k went up 1.5fps.

Thanks patrida,

What Catalyst did you use ??

 

[psolord]

The latest 15.8 my friend.

@TheElf or anyone that is interested.

Here are the DX11 and DX12 runs with process hacker monitoring, on my 7950+i7 860.



and here are the 970+2500k again for a refresher and ease of use.



I guess the 7950 DX12 gets more threads due to the 860 being hyper threaded?

 

[guskline]

Here is the latest benchmark for rig 1 below at 3440 x 1440 and crazy preset with the latest Nvidia drivers 386.69 and a Zotac GTX 1080 FE stock (EK water block)

 

[Bacon1]

Here is the latest benchmark for rig 1 below at 3440 x 1440 and crazy preset with the latest Nvidia drivers 386.69 and a Zotac GTX 1080 FE stock (EK water block)

Hey can you take some pictures of what the benchmark looks like? I'm wondering if they ever fixed the snow bug

 

[guskline]

It's a 3 minute benchmark. Do you have any idea approximately what time during the 3 minute bench the "snow bug" occurs?

 

[Bacon1]

It's a 3 minute benchmark. Do you have any idea approximately what time during the 3 minute bench the "snow bug" occurs?

http://videocardz.com/60860/amd-exp...ts-radeon-rx-480-cf-vs-gtx-1080-demonstration

Pretty much anything with mountains in them.