Post your GPU scores - to prep for next gen cpu's I have 1080ti 3080ti 6900xt included

[spookywatcher]

First I'm doing this because one of the results is quite surprising. With next gen ryzen and alder lake not too far off, hopefully with higher single core performance, we'll be able to better leverage the GPU performance while in game. So I thought I'd throw out what kind of performance I'm getting in the Menu screen when it first launches. (the station is flying by from right to left). This ensures that during this scene I am not cpu limited so it's time to crank up the graphics settings and see how different GPU's fair. This is at open and until the big "spire" of the station starts entering the screen. I have 3 gpu's to test
1080ti
3080ti
6900xt

Graphics settings (we want to make it gpu bound):

Code: Select all

2560x1440 
MSAA 4x
Fullscreen
No vsync
colour correction off
Gamma 100
Graphics Quality Custom
Texture Quality high
shadows high
soft shadows on
ssao high
glow normal
chromatic aberation on
distortion on
LOD 100
Effect Distance 100
Radar high
Screen space reflection off - I thought this might be a cpu thing
volumetric Fog high
High quality video capture off

As always my test bench is my golden boy 6700k at 4.9 ghz with 4x8gb 3600 mhz cl 15 trident z

All GPU scores are stock settings...no overclocks or raising the power limits. My scores were practically identical in both windows and linux for each card.

1080ti

Code: Select all

1080ti (evga sc2)  = 120 fps - 125 fps as the spire starts to come on screen

3080ti

Code: Select all

3080ti (gigabyte aorus master) = 232 fps - 238 fps   this score looks right in line with what I thought it should be

6900xt

Code: Select all

6900 xt (amd reference) = 160 fps   :gruebel:  This was astonishing  I had to try it in windows and linux multiple times 
and the score was the same.  I calculated that it should have been at least 225 fps.

In game with those settings I'm still mostly cpu bound at around 150 fps in open space (no stations or ships nearby) and about 120 fps close to stations. So I hope to test the next batch of cpu's when they come out. Really interested in how x4 performs with ddr5 and next gen cpu's.

I'll test with 1080p in a little while and post those

[Panos]

First I'm doing this because one of the results is quite surprising. With next gen ryzen and alder lake not too far off, hopefully with higher single core performance, we'll be able to better leverage the GPU performance while in game. So I thought I'd throw out what kind of performance I'm getting in the Menu screen when it first launches. (the station is flying by from right to left). This ensures that during this scene I am not cpu limited so it's time to crank up the graphics settings and see how different GPU's fair. This is at open and until the big "spire" of the station starts entering the screen. I have 3 gpu's to test
1080ti
3080ti
6900xt

Graphics settings (we want to make it gpu bound):

Code: Select all

2560x1440 
MSAA 4x
Fullscreen
No vsync
colour correction off
Gamma 100
Graphics Quality Custom
Texture Quality high
shadows high
soft shadows on
ssao high
glow normal
chromatic aberation on
distortion on
LOD 100
Effect Distance 100
Radar high
Screen space reflection off - I thought this might be a cpu thing
volumetric Fog high
High quality video capture off

As always my test bench is my golden boy 6700k at 4.9 ghz with 4x8gb 3600 mhz cl 15 trident z

All GPU scores are stock settings...no overclocks or raising the power limits. My scores were practically identical in both windows and linux for each card.

1080ti

Code: Select all

1080ti (evga sc2)  = 120 fps - 125 fps as the spire starts to come on screen

3080ti

Code: Select all

3080ti (gigabyte aorus master) = 232 fps - 238 fps   this score looks right in line with what I thought it should be

6900xt

Code: Select all

6900 xt (amd reference) = 160 fps   :gruebel:  This was astonishing  I had to try it in windows and linux multiple times 
and the score was the same.  I calculated that it should have been at least 225 fps.

In game with those settings I'm still mostly cpu bound at around 150 fps in open space (no stations or ships nearby) and about 120 fps close to stations. So I hope to test the next batch of cpu's when they come out. Really interested in how x4 performs with ddr5 and next gen cpu's.

I'll test with 1080p in a little while and post those

6900XT check if Chill is activated on the driver settings.

[spookywatcher]

First I'm doing this because one of the results is quite surprising. With next gen ryzen and alder lake not too far off, hopefully with higher single core performance, we'll be able to better leverage the GPU performance while in game. So I thought I'd throw out what kind of performance I'm getting in the Menu screen when it first launches. (the station is flying by from right to left). This ensures that during this scene I am not cpu limited so it's time to crank up the graphics settings and see how different GPU's fair. This is at open and until the big "spire" of the station starts entering the screen. I have 3 gpu's to test
1080ti
3080ti
6900xt

Graphics settings (we want to make it gpu bound):

Code: Select all

2560x1440 
MSAA 4x
Fullscreen
No vsync
colour correction off
Gamma 100
Graphics Quality Custom
Texture Quality high
shadows high
soft shadows on
ssao high
glow normal
chromatic aberation on
distortion on
LOD 100
Effect Distance 100
Radar high
Screen space reflection off - I thought this might be a cpu thing
volumetric Fog high
High quality video capture off

As always my test bench is my golden boy 6700k at 4.9 ghz with 4x8gb 3600 mhz cl 15 trident z

All GPU scores are stock settings...no overclocks or raising the power limits. My scores were practically identical in both windows and linux for each card.

1080ti

Code: Select all

1080ti (evga sc2)  = 120 fps - 125 fps as the spire starts to come on screen

3080ti

Code: Select all

3080ti (gigabyte aorus master) = 232 fps - 238 fps   this score looks right in line with what I thought it should be

6900xt

Code: Select all

6900 xt (amd reference) = 160 fps   :gruebel:  This was astonishing  I had to try it in windows and linux multiple times 
and the score was the same.  I calculated that it should have been at least 225 fps.

In game with those settings I'm still mostly cpu bound at around 150 fps in open space (no stations or ships nearby) and about 120 fps close to stations. So I hope to test the next batch of cpu's when they come out. Really interested in how x4 performs with ddr5 and next gen cpu's.

I'll test with 1080p in a little while and post those

6900XT check if Chill is activated on the driver settings.

Yeah it seems to be stuck at factory 255 watts both in linux and windows and radeon settings not showing up in windows. I'm still working on it...

[Harrison_rus]

Oh. Will be nice to see tests with Alder Lake and DDR5. I very interesting as game will works. Anyway I plan waits next gen and upgrade to Raptor Lake.

[Panos]

Oh. Will be nice to see tests with Alder Lake and DDR5. I very interesting as game will works. Anyway I plan waits next gen and upgrade to Raptor Lake.

True but also the upcoming Zen3 with the 3D cache too.

[Panos]

Yeah it seems to be stuck at factory 255 watts both in linux and windows and radeon settings not showing up in windows. I'm still working on it...

I hope you used DDU in windows safe mode to clean up Nvidia & AMD drivers first yes?

[spookywatcher]

Yeah it seems to be stuck at factory 255 watts both in linux and windows and radeon settings not showing up in windows. I'm still working on it...

I hope you used DDU in windows safe mode to clean up Nvidia & AMD drivers first yes?

Of course. DDU in safe mode. Thing is ... both Linux and Windows are giving the exact same result of 160 fps locked at the 255 watt power limit. I'll be working on it today. Since I can't get radeon settings to show in windows, I'll focus on getting the power limit lifted in Linux. Have to append the secret sauce in grub then install either radeon profile or corectl. But again.. this was supposed to be out of the box plug and play numbers and in that arena RDNA 2 is meh. I'm going to have to test other games and see if there is this much of a gap in perf

I was most excited for the 6900xt. So hoping to get it performing where it should. I really wanted it to be my daily driver so I'll figure it out. If I can 225 fps in the rendered scene and bump my unigine super 1080p extreme score up it'll be my daily driver. Superposition score for the 6900xt was only 9686. 1080ti was 5733. 3080ti was 11457.

[Panos]

Yeah it seems to be stuck at factory 255 watts both in linux and windows and radeon settings not showing up in windows. I'm still working on it...

I hope you used DDU in windows safe mode to clean up Nvidia & AMD drivers first yes?

Of course. DDU in safe mode. Thing is ... both Linux and Windows are giving the exact same result of 160 fps locked at the 255 watt power limit. I'll be working on it today. Since I can't get radeon settings to show in windows, I'll focus on getting the power limit lifted in Linux. Have to append the secret sauce in grub then install either radeon profile or corectl. But again.. this was supposed to be out of the box plug and play numbers and in that arena RDNA 2 is meh. I'm going to have to test other games and see if there is this much of a gap in perf

I was most excited for the 6900xt. So hoping to get it performing where it should. I really wanted it to be my daily driver so I'll figure it out. If I can 225 fps in the rendered scene and bump my unigine super 1080p extreme score up it'll be my daily driver. Superposition score for the 6900xt was only 9686. 1080ti was 5733. 3080ti was 11457.

If you cannot open the radeon settings then you have problem with the drivers too.
Have you tried to install older or newer versions?

[spookywatcher]

I hope you used DDU in windows safe mode to clean up Nvidia & AMD drivers first yes?

Of course. DDU in safe mode. Thing is ... both Linux and Windows are giving the exact same result of 160 fps locked at the 255 watt power limit. I'll be working on it today. Since I can't get radeon settings to show in windows, I'll focus on getting the power limit lifted in Linux. Have to append the secret sauce in grub then install either radeon profile or corectl. But again.. this was supposed to be out of the box plug and play numbers and in that arena RDNA 2 is meh. I'm going to have to test other games and see if there is this much of a gap in perf

I was most excited for the 6900xt. So hoping to get it performing where it should. I really wanted it to be my daily driver so I'll figure it out. If I can 225 fps in the rendered scene and bump my unigine super 1080p extreme score up it'll be my daily driver. Superposition score for the 6900xt was only 9686. 1080ti was 5733. 3080ti was 11457.

If you cannot open the radeon settings then you have problem with the drivers too.
Have you tried to install older or newer versions?

Well...more testing done. Something is amiss with x4 and the 6900xt. The results are practically identical for the AMD reference 6900 xt in both windows and linux for me (within 3 fps in X4 and within 260 pts in superpostion). I would LOVE someone with a 6800xt or 6900xt to test to see what they get.

for the 6900xt I was able to raise the power limit to 293watts and apply as much overclock as possible. Boost clocks were about the same as when it was limited to 255 watts but were noticeably hanging out in the higher end.

So with the higher power limit of 293 watts and the overclock my 6900xt was regularly smashing 2555 mhz. Temps with custom speed of 74% were: 64c gpu, 82c junction/hotspot, 74c memory. This looks to be an Excellent piece of silicon!

Unigine Super went from 9984 to 10405 pts in windows. In linux it went from 9686 to 10140 with higher power and clocks. This is a 4% increase for both.

In X4 6900xt went from 160 fps to 163 fps in both Linux and Windows. What the heck?

In Unigine Super the 6900xt is getting 88% of the 3080ti score. So that should translate into getting aprox 88% of the 3080ti fps in X4. Around 212 fps. I'm getting no where near that obviously. So something is bottlenecking the 6900xt in X4 in BOTH windows and Linux

Again...if ANYONE who has a 6800xt or 6900xt can test and see what they get... Please weigh in!

[spookywatcher]

Very interesting review from KitGuruTechs. I thought I remembered something about this problem and it took me a while to find it. But here it is:
In their review Far Cry New Dawn showed clear bottle neck of 141 fps for 6800 6800xt & 6900xt at the 6:02 mark linked below.
https://www.youtube.com/watch?v=tWCO9sytpWc&t=362s

Granted this is a one off comparison but I'm wondering if something similar is happening here. Just spit balling.

Uhgg...Do I go buy the 5950x at MC for $719 to test it with it? Mamabear is gonna be pissed.

[Panos]

Well...more testing done. Something is amiss with x4 and the 6900xt. The results are practically identical for the AMD reference 6900 xt in both windows and linux for me (within 3 fps in X4 and within 260 pts in superpostion). I would LOVE someone with a 6800xt or 6900xt to test to see what they get.

for the 6900xt I was able to raise the power limit to 293watts and apply as much overclock as possible. Boost clocks were about the same as when it was limited to 255 watts but were noticeably hanging out in the higher end.

So with the higher power limit of 293 watts and the overclock my 6900xt was regularly smashing 2555 mhz. Temps with custom speed of 74% were: 64c gpu, 82c junction/hotspot, 74c memory. This looks to be an Excellent piece of silicon!

Unigine Super went from 9984 to 10405 pts in windows. In linux it went from 9686 to 10140 with higher power and clocks. This is a 4% increase for both.

In X4 6900xt went from 160 fps to 163 fps in both Linux and Windows. What the heck?

In Unigine Super the 6900xt is getting 88% of the 3080ti score. So that should translate into getting aprox 88% of the 3080ti fps in X4. Around 212 fps. I'm getting no where near that obviously. So something is bottlenecking the 6900xt in X4 in BOTH windows and Linux

Again...if ANYONE who has a 6800xt or 6900xt can test and see what they get... Please weigh in!

Very interesting review from KitGuruTechs. I thought I remembered something about this problem and it took me a while to find it. But here it is:
In their review Far Cry New Dawn showed clear bottle neck of 141 fps for 6800 6800xt & 6900xt at the 6:02 mark linked below.
https://www.youtube.com/watch?v=tWCO9sytpWc&t=362s

Granted this is a one off comparison but I'm wondering if something similar is happening here. Just spit balling.

Uhgg...Do I go buy the 5950x at MC for $719 to test it with it? Mamabear is gonna be pissed.

Because performance should have been in par if not better to the 3080Ti with the 6900XT

a) What is your current CPU & RAM speed + cas?
b) What resolution and settings do you play the game? Have you tried to raise SSAA higher to see if the card maintains the fps or tanks completely?
c) Deactivate Freesync on the 6900XT. Make sure Chill is not active. Check the game profile in the drivers not only the general profile.
d) Linux. Do you use MESA or the AMD drivers? On Linux opensource MESA are the best drivers to use.

[spookywatcher]

So this is to all who wonder if you should upgrade or not. First, I'll leave that up to you. Second, I reinstalled my gtx 1080ti and shelved the 3080ti and 6900xt.

WTH? Why? Well... as it stands with the settings I like to play with for my visual preferences, my trusty old 1080ti plays x4 perfectly at MSAA 2x. I am almost always CPU bound with those settings. I get the same FPS with the same settings except having to drop to MSAA 2x instead of MSAA 4x on the 3080ti. That's right...same FPS and I only lose 2x MSAA. Sure 4x looks better however it does not out weigh what I lose keeping the 3080ti installed. Let me explain further.

With the 3080ti installed I am pumping out 150 watts more into my ambient and it is very noticeable here in the summer months. In addition, installing the extremely thick 3080ti I lose ALL of my extra pcie slots if I install it into the top x16 pcie slot. I can install it on the bottom pcie at only x8 and I did for testing (which gave me my top slot back). And I did not notice any performance hit with it being in the pch x8 slot (maybe 2 fps??).

But for now... The venerable greatest (imo) of all time GTX 1080ti is staying by my side. So cheers 1080ti you are the best; ole good and faithful servant.

But wait...what about the 6900xt. I really thought she was going to be the daily driver. I still kept my bottom pcie slot available with it installed in the top slot, but performance just wasn't there. No matter what I tried, it just fell way short of the 3080ti. It did beat the 1080ti a little, but the main problem was/is my monitors. My main monitor, which I love dearly, is old school gsync only. Does not work with freesync. So I'd have to move my second monitor to the primary slot... And frankly I just don't enjoy staring at it for hours compared to my favorite monitor. Anyhow.. here's to waiting for next gen cpu's and ddr5.

[Panos]

So this is to all who wonder if you should upgrade or not. First, I'll leave that up to you. Second, I reinstalled my gtx 1080ti and shelved the 3080ti and 6900xt.

WTH? Why? Well... as it stands with the settings I like to play with for my visual preferences, my trusty old 1080ti plays x4 perfectly at MSAA 2x. I am almost always CPU bound with those settings. I get the same FPS with the same settings except having to drop to MSAA 2x instead of MSAA 4x on the 3080ti. That's right...same FPS and I only lose 2x MSAA. Sure 4x looks better however it does not out weigh what I lose keeping the 3080ti installed. Let me explain further.

With the 3080ti installed I am pumping out 150 watts more into my ambient and it is very noticeable here in the summer months. In addition, installing the extremely thick 3080ti I lose ALL of my extra pcie slots if I install it into the top x16 pcie slot. I can install it on the bottom pcie at only x8 and I did for testing (which gave me my top slot back). And I did not notice any performance hit with it being in the pch x8 slot (maybe 2 fps??).

But for now... The venerable greatest (imo) of all time GTX 1080ti is staying by my side. So cheers 1080ti you are the best; ole good and faithful servant.

But wait...what about the 6900xt. I really thought she was going to be the daily driver. I still kept my bottom pcie slot available with it installed in the top slot, but performance just wasn't there. No matter what I tried, it just fell way short of the 3080ti. It did beat the 1080ti a little, but the main problem was/is my monitors. My main monitor, which I love dearly, is old school gsync only. Does not work with freesync. So I'd have to move my second monitor to the primary slot... And frankly I just don't enjoy staring at it for hours compared to my favorite monitor. Anyhow.. here's to waiting for next gen cpu's and ddr5.

If you sell the 6900XT at MSRP let me know

[SirNukes]

With the 3080ti installed I am pumping out 150 watts more into my ambient and it is very noticeable here in the summer months.

In play, at same settings and cpu bound fps, I would expect the 3080ti to be able to run at lower power (maybe after some fiddling with the power limit or v/f curve).

[Tempest]

@ Spookywatcher

whats the reason for this test? is the menu background even GPU rendered and not some standard video?

your other thread seemed way more elaborate : viewtopic.php?t=427248

i should probably get off my arse and test the 5800x + 1080Ti even though the CPU is somewhat "old news" soon

[CBJ]

is the menu background even GPU rendered and not some standard video?

It is not a video. It's a scene built, and rendered, using the game engine. It's actually quite a good test of the GPU, as the CPU load for rendering it is a lot lower than in-game.

[Tempest]

is the menu background even GPU rendered and not some standard video?

It is not a video. It's a scene built, and rendered, using the game engine. It's actually quite a good test of the GPU, as the CPU load for rendering it is a lot lower than in-game.

Thank you, for confirming CBJ.

i spose there aren't any "rules" for the CPU at all? (PBO off for AMD etc.)

i'll have to take a look at MSI Afterburner and revert it to default clocks.

[spookywatcher]

If you sell the 6900XT at MSRP let me know

Sorry...it's in a glass showcase on my "I Love Me Wall". Took me 6 months of trying to get that thing. My favorite monitor is quite old so if it ever pops a cap and I got to get a new monitor... the 6900xt is going in. And I refuse to believe it's performance. I've a little bit of time today... hope to be able to work on it and get it working well.

[spookywatcher]

With the 3080ti installed I am pumping out 150 watts more into my ambient and it is very noticeable here in the summer months.

In play, at same settings and cpu bound fps, I would expect the 3080ti to be able to run at lower power (maybe after some fiddling with the power limit or v/f curve).

I could. However how I set my settings is as follows: I lower my graphics until there is basically no GPU load. Then fly around and see what and where my normal high cpu bottleneck is. e.g. near a busy station in busy sector. Then let's say my fps is 120 there. I'll then raise my graphics settings until I reach about 98% in that situation looking at the sun in black hole sun sectors. Because putting that directly in the crosshairs really loads the gpu up. Or the asteroid belt...etc you get the idea. So basically I have max cpu performance and max gpu in balance. I could set the same settings as the 1080ti but then...what's the point? So I just put the 1080ti back in. I'll probably put the 3080ti back in when the summer heat wave ends for us in socal.

[spookywatcher]

@ Spookywatcher

whats the reason for this test? is the menu background even GPU rendered and not some standard video?

your other thread seemed way more elaborate : viewtopic.php?t=427248

i should probably get off my arse and test the 5800x + 1080Ti even though the CPU is somewhat "old news" soon

Reason was.. I was lucky enough to be able to get two of the top of the line GPU's to compare with my old 1080ti. And when I saw the 6900xt choke at those settings and after confirming with multiple OS installs that it indeed was 160 fps I thought others should know. I still want the 6900xt to be my daily driver and will continue to work at it. Maybe with it being put in a 5950x system it'll be able to stretch it's legs. Hoping someone with that kind of setup lets us know what they are getting. Would save me $1100 for the cpu mobo combo.

And yes... I'm almost 100% positive the opening menu scene is a rendered scene with very little cpu overhead. And the results were very repeatable and didn't rely on savegames etc.

I think your 5800x and 1080ti are about the most perfect combo. I'm still tempted to go get the 5950x. Just still researching mobos and trying to find which one would best suit me and my goals for it.