• 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
47,301 (7.52/day)
Location
Hyderabad, India
System Name RBMK-1000
Processor AMD Ryzen 7 5700G
Motherboard ASUS ROG Strix B450-E Gaming
Cooling DeepCool Gammax L240 V2
Memory 2x 8GB G.Skill Sniper X
Video Card(s) Palit GeForce RTX 2080 SUPER GameRock
Storage Western Digital Black NVMe 512GB
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
 
Joined
Aug 30, 2006
Messages
7,223 (1.08/day)
System Name ICE-QUAD // ICE-CRUNCH
Processor Q6600 // 2x Xeon 5472
Memory 2GB DDR // 8GB FB-DIMM
Video Card(s) HD3850-AGP // FireGL 3400
Display(s) 2 x Samsung 204Ts = 3200x1200
Audio Device(s) Audigy 2
Software Windows Server 2003 R2 as a Workstation now migrated to W10 with regrets.
So, not all RX 7900 XTX being sold are the same!? And significantly! Let me get my popcorn, will watch this with interest.
 
Joined
Feb 11, 2009
Messages
5,572 (0.96/day)
System Name Cyberline
Processor Intel Core i7 2600k -> 12600k
Motherboard Asus P8P67 LE Rev 3.0 -> Gigabyte Z690 Auros Elite DDR4
Cooling Tuniq Tower 120 -> Custom Watercoolingloop
Memory Corsair (4x2) 8gb 1600mhz -> Crucial (8x2) 16gb 3600mhz
Video Card(s) AMD RX480 -> RX7800XT
Storage Samsung 750 Evo 250gb SSD + WD 1tb x 2 + WD 2tb -> 2tb MVMe SSD
Display(s) Philips 32inch LPF5605H (television) -> Dell S3220DGF
Case antec 600 -> Thermaltake Tenor HTCP case
Audio Device(s) Focusrite 2i4 (USB)
Power Supply Seasonic 620watt 80+ Platinum
Mouse Elecom EX-G
Keyboard Rapoo V700
Software Windows 10 Pro 64bit
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?
 
Joined
Aug 30, 2006
Messages
7,223 (1.08/day)
System Name ICE-QUAD // ICE-CRUNCH
Processor Q6600 // 2x Xeon 5472
Memory 2GB DDR // 8GB FB-DIMM
Video Card(s) HD3850-AGP // FireGL 3400
Display(s) 2 x Samsung 204Ts = 3200x1200
Audio Device(s) Audigy 2
Software Windows Server 2003 R2 as a Workstation now migrated to W10 with regrets.
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.
 

Toothless

Tech, Games, and TPU!
Supporter
Joined
Mar 26, 2014
Messages
9,653 (2.46/day)
Location
Washington, USA
System Name Veral
Processor 7800x3D
Motherboard x670e Asus Crosshair Hero
Cooling Corsair H150i RGB Elite
Memory 2x24 Klevv Cras V RGB
Video Card(s) Powercolor 7900XTX Red Devil
Storage Crucial P5 Plus 1TB, Samsung 980 1TB, Teamgroup MP34 4TB
Display(s) Acer Nitro XZ342CK Pbmiiphx, 2x AOC 2425W, AOC I1601FWUX
Case Fractal Design Meshify Lite 2
Audio Device(s) Blue Yeti + SteelSeries Arctis 5 / Samsung HW-T550
Power Supply Corsair HX850
Mouse Corsair Nightsword
Keyboard Corsair K55
VR HMD HP Reverb G2
Software Windows 11 Professional
Benchmark Scores PEBCAK
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.
 
Joined
Nov 29, 2022
Messages
834 (1.10/day)
Processor Intel i7 77OOK
Motherboard Gigabyte Aorus something
Cooling Noctua NH-U12S dual fan
Memory Ballistix 32 Go
Video Card(s) MSI 3060 Gaming X
Storage Mixed bag of M2 SSD and SATA SSD
Display(s) MSI 34" 3440x1440 Artimys 343CQR
Case Old Corsair Obsidian something
Audio Device(s) Integrated
Power Supply Old Antec HCG 620 still running good
Mouse Steelseries something
Keyboard Steelseries someting too
Benchmark Scores bench ? no time to lose with bench ! :)
If the perfs are goods when gaming ... don't care about 3D Mark ... no ?
 
Joined
Dec 7, 2010
Messages
43 (0.01/day)
System Name sdfsdfsdf
Processor Core i5 750
Motherboard Asus P7P55D LE
Cooling Hyper 212 Plus
Memory 2x2gb Corsair xms3 1600mhz
Video Card(s) Gigabyte Gtx 560 Ti Windforce
Storage Sansung 320gb + Seagate 7200.12 500gb + WD Carviar Green 1tb
Case Cooler Master 690
Power Supply Corsair vx550w
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.
 
Joined
Mar 29, 2014
Messages
496 (0.13/day)
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.
 
Joined
Jul 13, 2016
Messages
3,335 (1.08/day)
Processor Ryzen 7800X3D
Motherboard ASRock X670E Taichi
Cooling Noctua NH-D15 Chromax
Memory 32GB DDR5 6000 CL30
Video Card(s) MSI RTX 4090 Trio
Storage Too much
Display(s) Acer Predator XB3 27" 240 Hz
Case Thermaltake Core X9
Audio Device(s) Topping DX5, DCA Aeon II
Power Supply Seasonic Prime Titanium 850w
Mouse G305
Keyboard Wooting HE60
VR HMD Valve Index
Software Win 10
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.
 

Space Lynx

Astronaut
Joined
Oct 17, 2014
Messages
17,427 (4.68/day)
Location
Kepler-186f
Processor 7800X3D -25 all core
Motherboard B650 Steel Legend
Cooling Frost Commander 140
Video Card(s) Merc 310 7900 XT @3100 core -.75v
Display(s) Agon 27" QD-OLED Glossy 240hz 1440p
Case NZXT H710 (Red/Black)
Audio Device(s) Asgard 2, Modi 3, HD58X
Power Supply Corsair RM850x Gold
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.
 
Joined
May 30, 2015
Messages
1,943 (0.56/day)
Location
Seattle, WA
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".
 
Joined
Apr 18, 2019
Messages
941 (0.45/day)
Location
The New England region of the United States
System Name Gaming Rig
Processor Ryzen 7 3800X
Motherboard Gigabyte X570 Aurus Pro Wifi
Cooling Noctua NH-D15 chromax.black
Memory 32GB(2x16GB) Patriot Viper DDR4-3200C16
Video Card(s) EVGA RTX 3060 Ti
Storage Samsung 970 EVO Plus 1TB (Boot/OS)|Hynix Platinum P41 2TB (Games)
Display(s) Gigabyte G27F
Case Corsair Graphite 600T w/mesh side
Audio Device(s) Logitech Z625 2.1 | cheapo gaming headset when mic is needed
Power Supply Corsair HX850i
Mouse Redragon M808-KS Storm Pro (Great Value)
Keyboard Redragon K512 Shiva replaced a Corsair K70 Lux - Blue on Black
VR HMD Nope
Software Windows 11 Pro x64
Benchmark Scores Nope
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.
 
Joined
May 30, 2015
Messages
1,943 (0.56/day)
Location
Seattle, WA
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.
 
Joined
Mar 25, 2020
Messages
1,710 (0.99/day)
Location
Over the Hill UK
System Name AMDWeapon
Processor Ryzen 7 7800X3D -20 CO
Motherboard X670E MSI Tomahawk WiFi
Cooling Thermalright Peerless Assassin 120 ARGB with Silverstone Air Blazer 2200rpm fans
Memory G-Skill Trident Z Neo RGB 6000 CL30 32GB@EXPO
Video Card(s) Powercolor 7900 GRE Red Devil minor undervolt
Storage Samsung 870 QVO 1TB x 2, Lexar 256 GB, TeamGroup MP44L 2TB, Crucial T700 1TB, Seagate Firecuda 2TB
Display(s) 32" LG UltraGear GN600-B
Case Montech 903 MAX AIR
Audio Device(s) SteelSeries Arctis Nova Pro Wireless
Power Supply MSI MPG AGF 850 watt gold
Mouse SteelSeries AeroX 5 l Forza Pad GameSir G7 SE l Razer Wolverine V3 TE for FPS (paddles)
Keyboard SteelSeries Apex 9 TKL
Software Windows 11 Pro 24H2
Benchmark Scores Enough for me
Just tried Time Spy out of curiosity and it will not make a full pass!

Got this error
Time Spy fail.png
 
Top