• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

GameTechBench GPU benchmark is already out!

Joined
Jul 5, 2013
Messages
30,245 (7.03/day)
One last thing, please: how would you make that key/license be usable once or in only one PC?
To me, when I buy a piece of software, you're selling it to me, not my PC.
(also coded into the internal checksum algorithm, to validate it if the key matches the buyer's PC)
Drop that. Forget the idea of hardware matching. You're selling a copy to a PC. You're selling a copy of this software to a person. That person is the owner of that copy, not the PC, or PC's, it's used on.
however, this would be a little slow because I would need to have a private keygen, receive the user's PC 'signature' (he should need to use another little software to generate it and report it to me)
Again, don't do that. Generate a CDKey that authenticates based on the user-name and or email. Don't waste your time, our ours, on hardware sigs/profiles.
But maybe you know an easier/faster approach.
Yeah, just use the username/email as the auth checksum key. If the CDKey matches the username check, the CDkey is rendered valid and an install for the advanced version proceeds.

Remember, portability is important.
 
Joined
Sep 26, 2022
Messages
2,491 (2.68/day)
Location
Braziguay
System Name G-Station 2.0 "YGUAZU"
Processor AMD Ryzen 7 5700X3D
Motherboard Gigabyte X470 Aorus Gaming 7 WiFi
Cooling Freezemod: Pump, Reservoir, 360mm Radiator, Fittings / Bykski: Blocks / Barrow: Meters
Memory Asgard Bragi DDR4-3600CL14 2x16GB
Video Card(s) Sapphire PULSE RX 7900 XTX
Storage 240GB Samsung 840 Evo, 1TB Asgard AN2, 2TB Hiksemi FUTURE-LITE, 320GB+1TB 7200RPM HDD
Display(s) Samsung 34" Odyssey OLED G8
Case Lian Li Lancool 216
Audio Device(s) Astro A40 TR + MixAmp
Power Supply Cougar GEX X2 1000W
Mouse Razer Viper Ultimate
Keyboard Razer Huntsman Elite (Red)
Software Windows 11 Pro, Garuda Linux
To me, when I buy a piece of software, you're selling it to me, not my PC.

Drop that. Forget the idea of hardware matching. You're selling a copy to a PC. You're selling a copy of this software to a person. That person is the owner of that copy, not the PC, or PC's, it's used on.

Again, don't do that. Generate a CDKey that authenticates based on the user-name and or email. Don't waste your time, our ours, on hardware sigs/profiles.

Yeah, just use the username/email as the auth checksum key. If the CDKey matches the username check, the CDkey is rendered valid and an install for the advanced version proceeds.

Remember, portability is important.
This is especially important for people who test varied hardware.
 
Joined
Jul 5, 2013
Messages
30,245 (7.03/day)
This is especially important for people who test varied hardware.
Exactly. Having to install, and then reinstall for every different change is a level tedium than just won't fly.

For example, Unigine Valley, Heaven and Superposition as completely portable in this way. If those had a fee/price, but were otherwise just as portable, I would absolutely pay for my copies!
 
Joined
Sep 29, 2020
Messages
156 (0.09/day)
Thank you again @lexluthermiester , but that wouldn't need, then, an internet connection to check the database of allowed usernames? And what would avoid unlimited users using the same key and username, to skip the validation?
 
Joined
Jul 5, 2013
Messages
30,245 (7.03/day)
but that wouldn't need, then, an internet connection to check the database of allowed usernames?
Not at all. The issued CDKey would be generated based on the binary checksum, a specific salt that you define and the user data. Then during install, the user inputs their info and the CDKey and the binary uses your salt hash to reverse the compare process. If the result is valid, the install proceed with the advanced features, if not the basic version is installed.

This assumes you even bother such methods. I personally wouldn't. I'd keep the basic version free for all and keep the advanced version behind a paywall. Pay for a copy, get a download link. But that's me keeping things simple.

And what would avoid unlimited users using the same key and username, to skip the validation?
Nothing, but then code crackers of the world do that anyway. Trying to stop that is a waste of your time & effort. It's like attempting to stuff an angry cat into a wet paper bag.
 
Joined
Jan 29, 2013
Messages
142 (0.03/day)
+10% power limit

GameTechBench-Win64-Shipping_2025_03_08_23_54_35_255.jpg
 
Joined
Sep 20, 2021
Messages
679 (0.52/day)
Processor Ryzen 7 9700x
Motherboard Asrock B650E PG Riptide WiFi
Cooling Underfloor CPU cooling
Memory 2x32GB 6200MT/s
Video Card(s) ASUS Prime Radeon RX 9070 XT OC Edition
Storage Kingston Fury Renegade 1TB, Seagate Exos 12TB
Display(s) MSI Optix MAG301RF 2560x1080@200Hz
Case Phanteks Enthoo Pro
Power Supply NZXT C850 850W Gold
Mouse Bloody W95 Max Naraka
Ryzen 9700x PBO
2x32GB DDR5 @ 6200MHz, 28-36-32-48-80
RX 9070 XT +10% PL
Win 11 24H2 (26100)

GameTech_2k_Raster.png
GameTech_2k_RT.png
GameTech_FHD_Raster.png
GameTech_FHD_RT.png
 
Joined
Sep 29, 2020
Messages
156 (0.09/day)
Not at all. The issued CDKey would be generated based on the binary checksum, a specific salt that you define and the user data. Then during install, the user inputs their info and the CDKey and the binary uses your salt hash to reverse the compare process. If the result is valid, the install proceed with the advanced features, if not the basic version is installed.

This assumes you even bother such methods. I personally wouldn't. I'd keep the basic version free for all and keep the advanced version behind a paywall. Pay for a copy, get a download link. But that's me keeping things simple.


Nothing, but then code crackers of the world do that anyway. Trying to stop that is a waste of your time & effort. It's like attempting to stuff an angry cat into a wet paper bag.

Thank you @lexluthermiester , I will consider all of that.

PS: Of course crackers will be able to bypass it, no doubt! But if that moment comes, it will be a good sign for me that the tool has already achieved success, but I don’t think they would put in the effort before that.

Yes, I bought this graphics card while in China.

Great acquisition! Please, could you pass it at 1080 and 1440 too?


And much did you improve the results? ;)

Ryzen 9700x PBO
2x32GB DDR5 @ 6200MHz, 28-36-32-48-80
RX 9070 XT +10% PL
Win 11 24H2 (26100)

View attachment 388603View attachment 388604View attachment 388605View attachment 388606

Great acquisition over here, too! Could you pass it at 4k and in full Path Tracing too, please?


Thank you all!!
 
Last edited:
Joined
Sep 21, 2020
Messages
1,822 (1.09/day)
Processor 5800X3D -30 CO
Motherboard MSI B550 Tomahawk
Cooling DeepCool Assassin III
Memory 32GB G.SKILL Ripjaws V @ 3800 CL14
Video Card(s) ASRock MBA 7900XTX
Storage 1TB WD SN850X + 1TB ADATA SX8200 Pro
Display(s) Dell S2721QS 4K60
Case Cooler Master CM690 II Advanced USB 3.0
Audio Device(s) Audiotrak Prodigy Cube Black (JRC MUSES 8820D) + CAL (recabled)
Power Supply Seasonic Prime TX-750
Mouse Logitech Cordless Desktop Wave
Keyboard Logitech Cordless Desktop Wave
Software Windows 10 Pro
RX 9070 XT +10% PL
10-11% faster with SW Lumen and 39-43% faster with HW than a stock 7900XTX (1080p / 1440p). In 2160p HW Lumen is 33% faster.
Wow :eek:
 
Last edited:
Joined
Sep 20, 2021
Messages
679 (0.52/day)
Processor Ryzen 7 9700x
Motherboard Asrock B650E PG Riptide WiFi
Cooling Underfloor CPU cooling
Memory 2x32GB 6200MT/s
Video Card(s) ASUS Prime Radeon RX 9070 XT OC Edition
Storage Kingston Fury Renegade 1TB, Seagate Exos 12TB
Display(s) MSI Optix MAG301RF 2560x1080@200Hz
Case Phanteks Enthoo Pro
Power Supply NZXT C850 850W Gold
Mouse Bloody W95 Max Naraka
Great acquisition over here, too! Could you pass it at 4k and in full Path Tracing too, please?

Thank you all!!
I'm going to do 4k, but Path Trace is crashing and I still can't figure out why :(
 
Joined
Sep 20, 2021
Messages
679 (0.52/day)
Processor Ryzen 7 9700x
Motherboard Asrock B650E PG Riptide WiFi
Cooling Underfloor CPU cooling
Memory 2x32GB 6200MT/s
Video Card(s) ASUS Prime Radeon RX 9070 XT OC Edition
Storage Kingston Fury Renegade 1TB, Seagate Exos 12TB
Display(s) MSI Optix MAG301RF 2560x1080@200Hz
Case Phanteks Enthoo Pro
Power Supply NZXT C850 850W Gold
Mouse Bloody W95 Max Naraka
Path Trace just crashed with this error:
I tried even the one with low VRAM.

Screenshot 2025-03-09 160342.png


4k RT/Raster.

GameTech_4k_Raster_2076.png
GameTech_4k_RT_1884.png
 
Joined
Jul 31, 2023
Messages
61 (0.10/day)
Went back and ran the path tracing bench again on my 4090. Widdled down the 5090 lead a little more. 5090 sometimes is quite a lot faster, sometimes like in this case, doesn't seem to be. Forgot to take a screenshot of the results screen.

1741547166730.png
 
Joined
Sep 29, 2020
Messages
156 (0.09/day)
simple oc of 7900XTX can reach oc 9070xt in SW lumen

View attachment 388693

for HW its around 20% if both are OC :)
Thank you for sharing it, under same conditions :)

Path Trace just crashed with this error:
I tried even the one with low VRAM.

View attachment 388698
@AVATARAT , please, could you report it to AMD? I have recently made a different UE5 project (very basic, with no Lumen, no Nanite, etc) and some AMD cards are crashing too, so it seems to be something related to the latest UE5 version and/or AMD Drivers (Nvidia is working as expected). Thank you!

Went back and ran the path tracing bench again on my 4090. Widdled down the 5090 lead a little more. 5090 sometimes is quite a lot faster, sometimes like in this case, doesn't seem to be. Forgot to take a screenshot of the results screen.

View attachment 388730
Stunning score! Very OCed?

@AVATARAT , I have updated the tool and it integrates an Unreal update released last night, so maybe it could help. Please, could you try?
 
Last edited:
Joined
Sep 20, 2021
Messages
679 (0.52/day)
Processor Ryzen 7 9700x
Motherboard Asrock B650E PG Riptide WiFi
Cooling Underfloor CPU cooling
Memory 2x32GB 6200MT/s
Video Card(s) ASUS Prime Radeon RX 9070 XT OC Edition
Storage Kingston Fury Renegade 1TB, Seagate Exos 12TB
Display(s) MSI Optix MAG301RF 2560x1080@200Hz
Case Phanteks Enthoo Pro
Power Supply NZXT C850 850W Gold
Mouse Bloody W95 Max Naraka
Joined
Sep 21, 2020
Messages
1,822 (1.09/day)
Processor 5800X3D -30 CO
Motherboard MSI B550 Tomahawk
Cooling DeepCool Assassin III
Memory 32GB G.SKILL Ripjaws V @ 3800 CL14
Video Card(s) ASRock MBA 7900XTX
Storage 1TB WD SN850X + 1TB ADATA SX8200 Pro
Display(s) Dell S2721QS 4K60
Case Cooler Master CM690 II Advanced USB 3.0
Audio Device(s) Audiotrak Prodigy Cube Black (JRC MUSES 8820D) + CAL (recabled)
Power Supply Seasonic Prime TX-750
Mouse Logitech Cordless Desktop Wave
Keyboard Logitech Cordless Desktop Wave
Software Windows 10 Pro
Pleased to report that with v1.15 Pro I'm getting a dark gray background instead of a blindig white one in the main menu.
 
Joined
Sep 20, 2021
Messages
679 (0.52/day)
Processor Ryzen 7 9700x
Motherboard Asrock B650E PG Riptide WiFi
Cooling Underfloor CPU cooling
Memory 2x32GB 6200MT/s
Video Card(s) ASUS Prime Radeon RX 9070 XT OC Edition
Storage Kingston Fury Renegade 1TB, Seagate Exos 12TB
Display(s) MSI Optix MAG301RF 2560x1080@200Hz
Case Phanteks Enthoo Pro
Power Supply NZXT C850 850W Gold
Mouse Bloody W95 Max Naraka
@AVATARAT , I have updated the tool and it integrates an Unreal update released last night, so maybe it could help. Please, could you try?
The update is installed, I also reinstalled the Radeon driver but it's still the same, crashes :(
 
Joined
Sep 29, 2020
Messages
156 (0.09/day)
Pleased to report that with v1.15 Pro I'm getting a dark gray background instead of a blindig white one in the main menu.
Haha, yes! But that's because I made a fixed grey background for AMD users. Nvidia users still can see the animated one :(. But at least you won't get blind now!
The update is installed, I also reinstalled the Radeon driver but it's still the same, crashes :(
Oh... that's a pity! I'm contacting AMD to see if they can fix anything via Driver. But let's see if they even reply me.

PS: Raster leaderboards has been added! (Mini-update already available). Let's contribute to fill them all!! (it may take some more seconds to retrieve all of them now, but some people asked for them)
 
Joined
Sep 21, 2020
Messages
1,822 (1.09/day)
Processor 5800X3D -30 CO
Motherboard MSI B550 Tomahawk
Cooling DeepCool Assassin III
Memory 32GB G.SKILL Ripjaws V @ 3800 CL14
Video Card(s) ASRock MBA 7900XTX
Storage 1TB WD SN850X + 1TB ADATA SX8200 Pro
Display(s) Dell S2721QS 4K60
Case Cooler Master CM690 II Advanced USB 3.0
Audio Device(s) Audiotrak Prodigy Cube Black (JRC MUSES 8820D) + CAL (recabled)
Power Supply Seasonic Prime TX-750
Mouse Logitech Cordless Desktop Wave
Keyboard Logitech Cordless Desktop Wave
Software Windows 10 Pro
It's good to see leaderboards for raster as well. Now the benchmark is complete!

I'm still unable to finish the PT test on a 6600XT though. It launches, but then sits on a black screen after the warm up phase. I can exit it still, so at least the app doesn't hang.

I've also tried to run both 4320p tests on the same card :roll:
Raster crashes repeatedly, with an "unable to allocate VRAM" error. Incredibly, the RT test completed (with up to 22 GB VRAM usage on an 8 GB card!), but the score was apparently not enough for the charts. Instead of a number, I got "result below the minimum".
 
Joined
Sep 29, 2020
Messages
156 (0.09/day)
It's good to see leaderboards for raster as well. Now the benchmark is complete!

I'm still unable to finish the PT test on a 6600XT though. It launches, but then sits on a black screen after the warm up phase. I can exit it still, so at least the app doesn't hang.

I've also tried to run both 4320p tests on the same card :roll:
Raster crashes repeatedly, with an "unable to allocate VRAM" error. Incredibly, the RT test completed (with up to 22 GB VRAM usage on an 8 GB card!), but the score was apparently not enough for the charts. Instead of a number, I got "result below the minimum".
Thank you for re-running in raster!

Have you tried the low VRAM option for the PT test? It might could help. I think some issues must be related to AMD drivers combined with latest Unreal version, because it has no other explanation why Nvidia cards doesn't have any issues :(

Hahaha, 4320p is a brutal test even for a 5090. Better to only run it with very high end GPUs with +24GB VRAM. Did you get the allocation warning only during this test (which consumes huge VRAM amount)? In that case, it might be understandable, at least.

Thanks!
 
Joined
Sep 20, 2021
Messages
679 (0.52/day)
Processor Ryzen 7 9700x
Motherboard Asrock B650E PG Riptide WiFi
Cooling Underfloor CPU cooling
Memory 2x32GB 6200MT/s
Video Card(s) ASUS Prime Radeon RX 9070 XT OC Edition
Storage Kingston Fury Renegade 1TB, Seagate Exos 12TB
Display(s) MSI Optix MAG301RF 2560x1080@200Hz
Case Phanteks Enthoo Pro
Power Supply NZXT C850 850W Gold
Mouse Bloody W95 Max Naraka
I've also tried to run both 4320p tests on the same card :roll:
Raster crashes repeatedly, with an "unable to allocate VRAM" error. Incredibly, the RT test completed (with up to 22 GB VRAM usage on an 8 GB card!), but the score was apparently not enough for the charts. Instead of a number, I got "result below the minimum".
If you're talking about the 7900 XTX, reboot the computer when it boots, close every program that uses VRAM, run a benchmark and select 4320p, this should be the first run, the test is on the edge of VRAM capacity and if there are leftovers in VRAM it will crash.
 
Joined
Sep 21, 2020
Messages
1,822 (1.09/day)
Processor 5800X3D -30 CO
Motherboard MSI B550 Tomahawk
Cooling DeepCool Assassin III
Memory 32GB G.SKILL Ripjaws V @ 3800 CL14
Video Card(s) ASRock MBA 7900XTX
Storage 1TB WD SN850X + 1TB ADATA SX8200 Pro
Display(s) Dell S2721QS 4K60
Case Cooler Master CM690 II Advanced USB 3.0
Audio Device(s) Audiotrak Prodigy Cube Black (JRC MUSES 8820D) + CAL (recabled)
Power Supply Seasonic Prime TX-750
Mouse Logitech Cordless Desktop Wave
Keyboard Logitech Cordless Desktop Wave
Software Windows 10 Pro
Have you tried the low VRAM option for the PT test?
Yep, tried both options. I've never been able to complete the PT test on the 6600XT.

Hahaha, 4320p is a brutal test even for a 5090. Better to only run it with very high end GPUs with +24GB VRAM. Did you get the allocation warning only during this test (which consumes huge VRAM amount)?
The only test that actually crashes for me (with an allocation error) on the 6600XT is raster 4320p. Miraculously, even 4320p + RT finished normally.
 
Joined
May 13, 2008
Messages
1,134 (0.18/day)
System Name HTPC whhaaaat?
Processor 2600k @ 4500mhz
Motherboard Asus Maximus IV gene-z gen3
Cooling Noctua NH-C14
Memory Gskill Ripjaw 2x4gb
Video Card(s) EVGA 1080 FTW @ 2037/11016
Storage 2x512GB MX100/1x Agility 3 128gb ssds, Seagate 3TB HDD
Display(s) Vizio P 65'' 4k tv
Case Lian Li pc-c50b
Audio Device(s) Denon 3311
Power Supply Corsair 620HX
First of all, this is a very cool bench and I thank the creator for making it. It's an easy way to show these limitations to people and I appreciate it; especially the 1%, .1%, and minimums. Awesome!
I honestly wish W1z would include something exactly like this in his suite. You're doing great work and it helps simplify things for a lot of people, I think! :rockout:

I appreciate ya'll posting the 1080p SW/HW Lumen results for 9070xt/7900xtx. I was curious if my theory would hold up about both being able to keep ~60fps mins in most any rational sitch...and AFAIK it does.

Obviously that requires overclocking on the 7900xtx, and UV on the 9070 xt, but still...I think it holds up? Should be able to keep 1080p (or 1440p 'quality' up-scaling) and 60fps mins AFAIK; in software if not hw.

If only those XTX owners could get FSR4 and/or AMD would improve 'performance' up-scaling...That part will stay pretty great imo (especially if you're a native 4k native user and/or can use the extra ram/compute).
Not to say it isn't still great at 4k native for raster...but YKWIM. It could be a nice catch-all if that were to happen; worse-case scenario of having upscale from 1080pRT and the compute/ram should help it.
Even over a 9070 xt (or even better) potentially, at least in some (perhaps weird to people that don't run a 4k display) situations.

Just curious AVA, did you UV at all to increase the clock? I'm kind of curious what it would take to keep 60mins in a sitch like where HW Lumen is used (Where you have 58.5).
I think that's similar to many things also limited by RT (say Spider-man 2 max RT or Wukong at 1080p)...should be very similar. I know you saw my post in the other thread about ~100 in Time Spy or 20k in Unigine.

Not perfect allegories, but close approximations. This would probably work much better for closer to definitive I think.

FWIW, I think core/ram equalization is something like ~3136/20000, and I don't *think* you'd need to overclock the ram to keep 60fps? I could be wrong. Shouldn't take much to get ~2.5%.
Trying to figure it out bc I think it helps a lot of people when you can say "adjust to roughly [x clock]", especially if it's just a UV on the core (which again, you might need bw...IDK your clock you have right now).
I think a lot of people are making the mistake of trying to run the core too hard and don't understand the cache only gives bandwidth (it's main limitation) at ~1/2 the rate of the memory; so it helps to adjust both. Look at Roman's video, for instance, where he has his set up pretty perfectly (something like 3369/21488), but I know all can't run that high, and frankly, I don't think they *need* to and could save power.

Considering 1440p quality up-scaling obviously performs a *little* better than 1080p native, and already would keep 60 where 1080p is slightly lower (as Wukong or your bench shows), it'd be a nice catch-all to know that approximate level of required perf for both 1080p and 1440p users to keep 60mins. And, ofc, if people can save a little power by lowering power limit to keep that level stable.

If you don't have the time, I totally get it. And again, perhaps I am wrong and it's not possible on all cards (1440p quality up-scaling should still keep 60 mins), I was just trying to figure out average power in worse-case 1080p60 scenario, as I think a lot of cards in the future will scale off approx whatever that required speed is. Ofc, they may also scale off quality up-scaling too (in which case it should already be fine).

Thanks again to all of you. :toast:
 
Last edited:
Top