Tom's Hardware Superposition Benchmark Thread

[EquineHero]

That is an insane score. Tempting but my system runs well as is and I like the pretty colors lol

But I have pretty colors too. The higher end GTX 1070s have RGB lights.

I wish my cards had that, as the Neutron shows off the graphics card.

The PNY Geforce GTX 1080 XLR8 has LED fans. So jelly. I'm gonna mod my EVGA 1070 with LEDs at some point.

Here's my GTX 1050Ti, a LOT of R&D went into making that card a beast (sold for $225):

 

[logainofhades]

I am getting a 980ti FTW, from a friend. I would like to mod it somehow. Wish one of the newer ACX 3.0 LED coolers would just fit it, and make my life easier.

 

[EquineHero]

I am getting a 980ti FTW, from a friend. I would like to mod it somehow. Wish one of the newer ACX 3.0 LED coolers would just fit it, and make my life easier.

The GTX 1070 cooler should fit, they share the same die mounting holes. As long as the die is in the same relative position to the PCI slot you should be fine.

My 1070 has the solder points for the RGB lighting though, you'd have to do a custom job like I did.

 

[logainofhades]

I think the PCB is setup different for the backplate and fans assembly.

 

[EquineHero]

I think the PCB is setup different for the backplate and fans assembly.

Nope, 980Ti backplate assembly is the same across all 10xx cards. The 4-pin PWM fan header is also exactly the same.

 

[logainofhades]

vs

 

[EquineHero]

vs

That 1070 is wider than the 980Ti but the PNY XLR8 GTX 1070 I have matches that 980Ti PERFECTLY. So does my GTX 1070 Superclocked.

 

[bjornl]

New single card champ.

So a new run on a different video card. I experimented to see which gave the bigger boost GPU or RAM and overclocking the ram had the greatest impact. I think this explains the AMD cards generally doing quite well.

This was done on a stock Gigabyte AORUS GeForce GTX 1080 Ti with the factory air cooler. I raised the power limit in MSI afterburner by 15%. I did not raise the voltage. I overclocked the GPU by 75hz and the memory by 1ghz.

 

[Rogue Leader]

New single card champ.

So a new run on a different video card. I experimented to see which gave the bigger boost GPU or RAM and overclocking the ram had the greatest impact. I think this explains the AMD cards generally doing quite well.

Yep explains the fact I gained like 700 points by turning on HBCC.

 

[EquineHero]

New single card champ.

So a new run on a different video card. I experimented to see which gave the bigger boost GPU or RAM and overclocking the ram had the greatest impact. I think this explains the AMD cards generally doing quite well.

Yep explains the fact I gained like 700 points by turning on HBCC.

Yeah but doesn't power draw increase a lot and it gets hotter?

Also I can OC my 1070s by 500MHz, so that's 1GHz effective (4500Mhz *2=9000MHz)

So in terms of SLI, I've got another 2GHz on memory, some Kepler and even Maxwell cards don't even get memory to 2GHz ahahahaha

 

[Rogue Leader]

New single card champ.

So a new run on a different video card. I experimented to see which gave the bigger boost GPU or RAM and overclocking the ram had the greatest impact. I think this explains the AMD cards generally doing quite well.

Yep explains the fact I gained like 700 points by turning on HBCC.

Yeah but doesn't power draw increase a lot and it gets hotter?

Also I can OC my 1070s by 500MHz, so that's 1GHz effective (4500Mhz *2=9000MHz)

So in terms of SLI, I've got another 2GHz on memory, some Kepler and even Maxwell cards don't even get memory to 2GHz ahahahaha

My own unscientific monitoring saw some spikes about 50w higher than normal. Temps were the same, card never gets over about 70 degrees, but the fact its on an AIO helps that.

 

[ddinarte]

Guys, I just did and upgrade, but before that, I've ran the Superposition benchmark on my old machine for comparison reasons. The result with both kits was extremely close, what should not happen... Here are the two screenshoots:

First with an overclocked Phenom II X6 1090t + GTX1060 6GB

Then with an Ryzen 7 1800x @stock + GTX1060 6GB

Any ideas on how could this be possible?

Thanks in advance.

 

[Rogue Leader]

Guys, I just did and upgrade, but before that, I've ran the Superposition benchmark on my old machine for comparison reasons. The result with both kits was extremely close, what should not happen... Here are the two screenshoots:

First with an overclocked Phenom II X6 1090t + GTX1060 6GB


Then with an Ryzen 7 1800x @stock + GTX1060 6GB


Any ideas on how could this be possible?

Thanks in advance.

Superposition is extremely GPU biased. The 1090T is still a very capable CPU.

Run it at 1080p Extreme to get a comparable score to everyone else, also that should show more of a difference in your two systems.

 

[Vellinious]

Actually, running it at a lower setting would push more frame rate, and put more pressure on the CPU. Unigine benchmarks are notorious for being lightly threaded, which is why Valley is nothing more than a CPU benchmark any more. Bottlenecking the CPU intentionally, by running lower settings, and pushing the frame rates higher will show a bigger difference in the scores. By running a test with higher settings, or a higher resolution, you'd be taking the onus off of the CPU, and putting it more on the GPU. I would think that 1080 Extreme or 4k you'd see extremely similar scores between the two systems.

That said....it's a synthetic. Compare frame rates between a lightly threaded DX11 game, or a heavily threaded DX12 game, and you'll see a HUGE difference between them. Assuming, of course, the 1090T can run DX12.....I'm not really sure about that.

 

[Rogue Leader]

Actually, running it at a lower setting would push more frame rate, and put more pressure on the CPU. Unigine benchmarks are notorious for being lightly threaded, which is why Valley is nothing more than a CPU benchmark any more. Bottlenecking the CPU intentionally, by running lower settings, and pushing the frame rates higher will show a bigger difference in the scores. By running a test with higher settings, or a higher resolution, you'd be taking the onus off of the CPU, and putting it more on the GPU. I would think that 1080 Extreme or 4k you'd see extremely similar scores between the two systems.

That said....it's a synthetic. Compare frame rates between a lightly threaded DX11 game, or a heavily threaded DX12 game, and you'll see a HUGE difference between them. Assuming, of course, the 1090T can run DX12.....I'm not really sure about that.

No, running it at a higher setting would push the GPU to its maximum making it the bottleneck and therefore any performance differences between the two would be CPU only (being he is using the same GPU). Your theory would be correct if the CPU was being stressed here but its not. Increased frame rate does not necessarily cause the CPU to have to work harder.

There is nothing preventing a 1090T or any other CPU made in the past 7 or 8 years from running DX12, it has little to do with the CPU.

 

[EquineHero]

Guys, I just did and upgrade, but before that, I've ran the Superposition benchmark on my old machine for comparison reasons. The result with both kits was extremely close, what should not happen... Here are the two screenshoots:

First with an overclocked Phenom II X6 1090t + GTX1060 6GB

Then with an Ryzen 7 1800x @stock + GTX1060 6GB

Any ideas on how could this be possible?

Thanks in advance.

Unigine Superposition is designed to take advantage of GPU power wherever possible. Any effects that are usually handled by the CPU are done by the GPU instead, one reason why Superposition is so crippling to older GPUs.

I'd have the same score with my SB Xeon as I would with an 8700K.

Your scores were not added to the table because you did not run the 1080P Extreme test.

A rule I need to append is that for GPUs that cannot run Superposition is that 35% of the 1080p Medium score is used instead - GPUs with only 2GB or 1GB of vRAM.

 

[EquineHero]

Don't mind me, just casually destroying every GPU on the leaderboards except the Titan V and a nitro cooled 1080Ti

If you think my temperatures are fake, I just happened to be outside with my PC at 3:00AM in -20 degree weather. I got my CPU to -4C!

"SLI is dead and-" I'mma let you finish, but

 

[ddinarte]

Guys, I just did and upgrade, but before that, I've ran the Superposition benchmark on my old machine for comparison reasons. The result with both kits was extremely close, what should not happen... Here are the two screenshoots:

First with an overclocked Phenom II X6 1090t + GTX1060 6GB


Then with an Ryzen 7 1800x @stock + GTX1060 6GB


Any ideas on how could this be possible?

Thanks in advance.

Superposition is extremely GPU biased. The 1090T is still a very capable CPU.

Run it at 1080p Extreme to get a comparable score to everyone else, also that should show more of a difference in your two systems.

Thanks for the explanation.

I've run at 1080p Extreme and the results was yet more confused to me. I know that the 1090T is still a capable processor (i've skipped the fx series cause it wasn't worth buying compared to my phenom) but I was expecting better results from the Ryzen 7.

1080P Extreme with Phenom:

1080P Extreme with Ryzen 7 (I used the built-in "Performance Mode" function from the ASUS BIOS, what pushed the processor frequency to 3843mhz):

The results with Ryzen 7 were worse than my very old 1090T. Maybe it's just the way that Superposition Benchmark uses the CPU. Anyway, I'll keep testing in games to see if my performance will increase better.

Thanks for the attention.

 

[bignastyid]

ddinarte, superpositoion is a gpu benchmark so the cpu is almost complexity inconsequential as very little cpu power is used by the benchmark. If you want to see a the performance difference between the Phenon and Ryzen you need to run a cpu benchmark like cinebench or passmark. If you want something that tests cpu and gpu get something like 3dmark..

 

[jankerson]

Ran it again yesterday myself, OCed as before, higher memory clock this time.

And here is it at 1080P High Setting just for a laugh, was stock speed for this.

 

[EquineHero]

Ran it again yesterday myself, OCed as before, higher memory clock this time.

And here is it at 1080P High Setting just for a laugh, was stock speed for this.

I'll add your extreme score later, I'm out of the house right now.

My 1080 High score was about 16,000

 

[jankerson]

Ran it again yesterday myself, OCed as before, higher memory clock this time.

And here is it at 1080P High Setting just for a laugh, was stock speed for this.

I'll add your extreme score later, I'm out of the house right now.

No hurry.

Was at 6K Memory clock this time (12 GBS Effective).

 

[EquineHero]

Ran it again yesterday myself, OCed as before, higher memory clock this time.

And here is it at 1080P High Setting just for a laugh, was stock speed for this.

I'll add your extreme score later, I'm out of the house right now.

No hurry.

Was at 6K Memory clock this time (12 GBS Effective).

I can barely scratch 4000 with a single GTX 1070, but two of them destroys. If you want a chance at being on top of everyone else, you can SLI some 1080s.

Also, Superposition says your 7700K is not overclocked. It does the same for my Xeon, even though I have the BCLK at 105.8.

How are you getting your memory so high? My 1070s max out at around 4500MHz if I drop my core overclock (power mgmt issue).

The first 1070 I have on the chart had an 8 and a 6 pin and the shunt mod so I could get +400 on mem along with a good +200 on core, but I haven't hardmodded either of my 1070s yet.

I have Word open now. I can't add your new score, it's not 200 marks or 5% above your last one. Every time I update my score I make sure it is. My previous best was 7340, then I got 7605. Pretty big boost +350 on memory gives.

 

[bjornl]

So why did you remove my 1080ti score? It remains the single card record for this site at 6225.

The 1080ti easily allowed 1ghz OC on ram. I'd take it higher, but afterburner doesn't allow it.

 

[EquineHero]

So why did you remove my 1080ti score? It remains the single card record for this site at 6225.

The 1080ti easily allowed 1ghz OC on ram. I'd take it higher, but afterburner doesn't allow it.

Just a mistake, I'm fixing it now.