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

3% of AMD Radeon Users May Experience Unusually Low 3DMark TimeSpy Performance, Driver Fix Underway

btarunr

Editor & Senior Moderator
Staff member
Joined
Oct 9, 2007
Messages
47,670 (7.43/day)
Location
Dublin, Ireland
System Name RBMK-1000
Processor AMD Ryzen 7 5700G
Motherboard Gigabyte B550 AORUS Elite V2
Cooling DeepCool Gammax L240 V2
Memory 2x 16GB DDR4-3200
Video Card(s) Galax RTX 4070 Ti EX
Storage Samsung 990 1TB
Display(s) BenQ 1440p 60 Hz 27-inch
Case Corsair Carbide 100R
Audio Device(s) ASUS SupremeFX S1220A
Power Supply Cooler Master MWE Gold 650W
Mouse ASUS ROG Strix Impact
Keyboard Gamdias Hermes E2
Software Windows 11 Pro
About 3% of AMD Radeon graphics card users may experience lower than usual 3DMark TimeSpy performance, says UL Benchmarks, developers of the 3DMark graphics benchmark suite. The issue came to light when a Google developer noticed that his RX 7900 XTX exhibited lower than expected performacne in TimeSpy, and took it up with UL. While the 3DMark developer hasn't been able to reproduce the issue on their end, it mentions that AMD is aware of it, has had more luck in reproducing it, and is working on a driver-level fix. For now, UL offers no solution other than to roll back to older driver versions and try testing again.



View at TechPowerUp Main Site | Source
 
So, not all RX 7900 XTX being sold are the same!? And significantly! Let me get my popcorn, will watch this with interest.
 
So, not all RX 7900 XTX being sold are the same!? And significantly! Let me get my popcorn, will watch this with interest.

How do you draw that conclusion?
 
The observation is drawn on the information given - however - if one goes "up the source path", it seems like there is a chinese whispers going on here. The 3% figure has been pulled from the 3DMark TimeSpy database but without proper context. Is this 3% relating to people with the same hardware setup ie 97% of similar systems are not affected whereas 3% are, suggesting there is something "wrong" with 3% of the identical systems, or is it that 100% of people with a certain setup are affected, but they represent 3% of the database.
 
The observation is drawn on the information given - however - if one goes "up the source path", it seems like there is a chinese whispers going on here. The 3% figure has been pulled from the 3DMark TimeSpy database but without proper context. Is this 3% relating to people with the same hardware setup ie 97% of similar systems are not affected whereas 3% are, suggesting there is something "wrong" with 3% of the identical systems, or is it that 100% of people with a certain setup are affected, but they represent 3% of the database.
Dude, it's a driver issue. Article didn't mention if it's only 7xxx or not so there is a chance it's other cards too.
 
If the perfs are goods when gaming ... don't care about 3D Mark ... no ?
 
If the perfs are goods when gaming ... don't care about 3D Mark ... no ?
Usually when something is wrong people focus on that even if everything else is right.
 
The observation is drawn on the information given - however - if one goes "up the source path", it seems like there is a chinese whispers going on here. The 3% figure has been pulled from the 3DMark TimeSpy database but without proper context. Is this 3% relating to people with the same hardware setup ie 97% of similar systems are not affected whereas 3% are, suggesting there is something "wrong" with 3% of the identical systems, or is it that 100% of people with a certain setup are affected, but they represent 3% of the database.

:laugh: Dude, just means UL nerfed the performance in the benchmark and users caught them.

These are the tools corrupt corporations use to influence buyers.
 
So, not all RX 7900 XTX being sold are the same!? And significantly! Let me get my popcorn, will watch this with interest.

About 3% of AMD Radeon graphics card users may experience lower than usual 3DMark TimeSpy performance, says UL Benchmarks, developers of the 3DMark graphics benchmark suite. The issue came to light when a Google developer noticed that his RX 7900 XTX exhibited lower than expected performacne in TimeSpy, and took it up with UL. While the 3DMark developer hasn't been able to reproduce the issue on their end, it mentions that AMD is aware of it, has had more luck in reproducing it, and is working on a driver-level fix. For now, UL offers no solution other than to roll back to older driver versions and try testing again.

First, not limited to the 7900 XTX.

Second, this is only in 3DMark

Third, it's fixable via a driver update.

Thus the trend of the first comments on an article being those that thought the least before posting continues.
 
First, not limited to the 7900 XTX.

Second, this is only in 3DMark

Third, it's fixable via a driver update.

Thus the trend of the first comments on an article being those that thought the least before posting continues.

indeed. haven't used 3dmark once since i built my system, drivers have been great for everything i do. people overreact as usual.
 
Missing context that this ONLY happens on Windows 11 Beta Channel builds 10.0.22624 and 10.0.22621 with the latest Moment 2 patches.

Quote from UL developer:
Note that release preview channel Windows is not officially supported by us. We only test on it with a single system so any hardware-specific issues are not visible to us unless they occur with the "live" version of Windows.

In other news, AMD has apparently reproduced this internally and it is starting to look more and more like a driver issue, so at this time I can only offer "rollback to previous or ignore and wait for future driver fixes".
 
Tell me I'm not the only person who's first thought was why the hell are they wasting time and money on this? Who gives a rat's ass if the performance is 3% lower in a synthetic benchmark? The driver developers could otherwise be putting that effort towards optimizing for something that actually matters.
 
Tell me I'm not the only person who's first thought was why the hell are they wasting time and money on this? Who gives a rat's ass if the performance is 3% lower in a synthetic benchmark? The driver developers could otherwise be putting that effort towards optimizing for something that actually matters.

Wrong 3%. 3% of users on Windows 11 preview are experiencing performance drop by as much as 50%, so a tiny portion of a tiny portion but the performance impact is massive. That said even if we assume dismal sales figures if that 3% translated to ALL owners of RDNA3 cards that's thousands of people. Worth putting in efforts to squash any bug they can now instead of let it slip through into the final release of the next Windows update.
 
Just tried Time Spy out of curiosity and it will not make a full pass!

Got this error
Time Spy fail.png
 
Back
Top