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

TechPowerUp GPU-Z v2.52.0 Released

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
TechPowerUp today released the latest version of TechPowerUp GPU-Z, the popular PC graphics information, monitoring, and diagnostics utility. Version 2.52.0 adds support for AMD Radeon RX 7900 XTX, RX 7900 XT, RX 6300 OEM; NVIDIA GeForce RTX 4070 Ti, and a few rare "Ampere" based GPUs in circulation these days, including the RTX 3080 Ti 20 GB, RTX 3070 Ti based on GA102 silicon, RTX 3050 based on GA107, and the PCIe AIC version of the A800 80 GB accelerator. Detection is improved for the Xe LP-based iGPU of Intel Core "Raptor Lake" processors. NVIDIA GPUs with ECC memory now have ECC status reported in the Advanced panel. On GPUs where the boost frequency can't be read, the base frequency will be used to calculate fillrates. Clock speed detection for Intel Arc "Alchemist" GPUs has been improved. Vendor detection has been added for several new graphics card brands such as Corsair (gaming notebooks), Maxsun, and Wingtech.

DOWNLOAD: TechPowerUp GPU-Z v2.52.0



  • Added support for AMD Radeon RX 7900 XT and XTX (Navi 31)
  • Added support for NVIDIA GeForce RTX 4070 Ti, RTX 3080 Ti 20 GB, RTX 3070 Ti (GA102), RTX 3050 (GA107), A800 80 GB PCIe
  • Added support for Intel Raptor Lake IGP
  • Added support for AMD Radeon RX 6300
  • NVIDIA ECC memory status is now reported in Advanced Panel / General
  • If boost clock can't be read, base clocks are used to calculate fillrates
  • GPU clock reading on Intel Arc graphics has been improved
  • Improved VRAM size reporting in some edge cases
  • Added support for vendor detection of Corsair, Huqaqin, Maxsun and Wingtech

View at TechPowerUp Main Site
 
Thank you for the Software and the update.
 
Question...... I have few Matrox cards(P690,M9120,Xenia)and still using some as my second GPU to power my side panels but for some reason Gpu-Z was never able to recognized those cards so not sure if Matrox cards are at all in yours database or maybe is the problem on my side.....THX in advance
 
Question...... I have few Matrox cards(P690,M9120,Xenia)and still using some as my second GPU to power my side panels but for some reason Gpu-Z was never able to recognized those cards so not sure if Matrox cards are at all in yours database or maybe is the problem on my side.....THX in advance
Matrox isn't supported at all.. in a perfect world I'd love to support them, but really not enough time
 
Matrox isn't supported at all.. in a perfect world I'd love to support them, but really not enough time
Ok THX.....It's not a big deal as HW info actually can saw my Matrox card just wanted to ask if is supported by you guys.....cheers
 
Matrox isn't supported at all.. in a perfect world I'd love to support them, but really not enough time

Matrox is the benchmark for the best possible image quality ever in the PC industry.
I think Matrox definitely deserves a top priority for GPU-Z support.
 
Matrox is the benchmark for the best possible image quality ever in the PC industry.
I think Matrox definitely deserves a top priority for GPU-Z support.
If you have any contacts at Matrox that think so too, and are willing to provide developer documentation/support/hardware, let me know, would love to add them, if it only takes a few days of work, not weeks or months full-time.
 
3080 Ti 20 GB, 3050 (GA 107), RX 6300... wait, what? Did I miss something? :wtf:
 
Matrox is the benchmark for the best possible image quality ever in the PC industry.
I think Matrox definitely deserves a top priority for GPU-Z support.
I believe at one time they made their own chips, then used ATi, then Nvidia.

Now sure about now?
 
3080 Ti 20 GB, 3050 (GA 107), RX 6300... wait, what? Did I miss something? :wtf:
3080 Ti 20Gb version were discussed in previous release of GPU-Z. Hope i can check it again, but with this release and report back. Just to be sure everything is working fine.
 
3080 Ti 20Gb version were discussed in previous release of GPU-Z. Hope i can check it again, but with this release and report back. Just to be sure everything is working fine.
Thanks. To be fair, I'm more interested in the RX 6300. I can imagine it being a great, modern HTPC card in a passive and low profile version, just like my GT 1030. :) (if AMD can get the price right this time)
 
Here is screenshot from GPU-Z of RTX 3080 Ti with 20GB (GIGABYTE GV-N3080TAORUS X-20GB).

@W1zzard Need help. Here is two screenshots of modded driver. Template used of GeForce RTX 3080 Ti [2208]. No errors during driver installing, but result after installing you may see on screenshot #2.

Error from Nvidia control panel say: Nvidia display setting not availible. Used display not connected to NVIDIA GPU. And missed windows in GPU-Z.
 

Attachments

  • RTX_3080_Ti_20GB.jpg
    RTX_3080_Ti_20GB.jpg
    112.4 KB · Views: 128
  • 2208-1.jpg
    2208-1.jpg
    80.5 KB · Views: 137
  • 2208-2.jpg
    2208-2.jpg
    141.4 KB · Views: 116
There's a yellow bang in device manager, check GPU's properties/general tab for error code
Yeah, i saw it, but for some weird reason i didn't ask person to look for error (i help him over Telegram). Reason might be in "express" install of driver on top of previous version.

Anyway, i also decided to test second template - GeForce RTX 3090 [2204] and clean install.

This time everything worked nice! Modded driver installed, no errors in Device manager, possible to run FurMark and Superposition (test canceled since poor performance - connected via riser).
 

Attachments

  • RTX_3080_Ti_20GB_v527.56.jpg
    RTX_3080_Ti_20GB_v527.56.jpg
    158.8 KB · Views: 130
  • RTX_3080_Ti_20GB_v527.56_GPU-Z_Sensors.jpg
    RTX_3080_Ti_20GB_v527.56_GPU-Z_Sensors.jpg
    119.1 KB · Views: 78
  • RTX_3080_Ti_20GB_v527.56_Superposition-2.jpg
    RTX_3080_Ti_20GB_v527.56_Superposition-2.jpg
    94.7 KB · Views: 80
Yeah, i saw it, but for some weird reason i didn't ask person to look for error (i help him over Telegram). Reason might be in "express" install of driver on top of previous version.

Anyway, i also decided to test second template - GeForce RTX 3090 [2204] and clean install.

This time everything worked nice! Modded driver installed, no errors in Device manager, possible to run FurMark and Superposition (test canceled since poor performance - connected via riser).
I'm not sure what's more shocking... the fact that you got 1500 points in Superposition 4K with a 3080 Ti, or that you're running the card in an ancient Core 2 Duo system.
 
I'm not sure what's more shocking... the fact that you got 1500 points in Superposition 4K with a 3080 Ti, or that you're running the card in an ancient Core 2 Duo system.
Nah, it's not my GPU. In general i find this GPU on some kind of local flea market and it look interesting to buy, but since it required so much things to do i decided to just help seller with software part (drivers mod and GPU-Z (with W1zzard help too!)). I bought for myself RTX 3080 Ti FTW3 Ultra Gaming from EVGA.

But Superposition result and PC config look weird indeed. %)

If i can only install my GPU on Laptop via eGPU - it look even more weird (i did it with GTX 1080 Ti). But my laptop is no longer working (BIOS softlock). Maybe one day i will try to revive it.
 
3050 based on GA107? Is it going to be cheaper? ;)
 
3050 based on GA107? Is it going to be cheaper? ;)
No. It's a new chip in the desktop segment, so it's going to be more expensive. :D
 
Granted, it wasn't announced as fixed in the changelog, but DDR5 memory bandwidth is still reported as double what it should be.


4rs.png
 
Granted, it wasn't announced as fixed in the changelog, but DDR5 memory bandwidth is still reported as double what it should be.


4rs.png
How do you have the "PhysX" box ticked with AMD?
 
Back
Top