Saturday, January 21st 2012

TechPowerUp GPU-Z 0.5.8 Released

TechPowerUp today released the latest version of GPU-Z, our popular video subsystem information and diagnostic utility that provides you with accurate information about the graphics hardware installed, and lets you monitor their clock speeds, fan speeds, voltages, VRAM consumption, etc., in real-time. Version 0.5.8 introduces two new features. The first one is a render test that applies sufficient load (not stress) on the GPU to pull it out of PCI-Express link-state power-management, to ensure the Bus information is accurate. If you find the PCI-Express bus link speed or PCIe version displayed incorrectly, simply click on the "?" button next to the field to launch the load test.

The next new feature is ASIC quality, designed for NVIDIA Fermi (GF10x and GF11x GPUs) and AMD Southern Islands (HD 7800 series and above), aimed at advanced users, hardware manufacturers, and the likes. We've found the ways in which AMD and NVIDIA segregate their freshly-made GPU ASICs based on the electrical leakages the chips produce (to increase yield by allotting them in different SKUs and performance bins), and we've found ways in which ASIC quality can be quantified and displayed. Find this feature in the context menu of GPU-Z. We're working on implementing this feature on older AMD Radeon GPUs.
DOWNLOAD: TechPowerUp GPU-Z 0.5.8, TechPowerUp GPU-Z 0.5.8 ASUS ROG Themed

The full change-log follows.

  • Added explanation about PCI-Express power savings and 3D render test to accurately measure bus config under load
  • Added function to display ASIC quality for Fermi and Southern Islands. (Located in the GPU-Z system menu)
  • Fixed crash on older ATI cards
  • Added voltage monitoring for HD 7970
  • Improved real-time clock monitoring for HD 7970
  • Fixed OpenCL detection for AMD Antilles, Whistler, Seymour, Blackcomb
  • Improved default clock reading for AMD HD 7970 and Fusion
  • Added support for AMD FirePro V7900, HD 6930, HD 7690M, HD 6410D
  • Fixed Intel Sandy Bridge IGP to be DirectX 10.1, 32 nm
  • Added support for NVIDIA Tesla C2075, GeForce GT 630M
Add your own comment

135 Comments on TechPowerUp GPU-Z 0.5.8 Released

#2
Steven B
BTW right now Ivy bridge has an issue where the leakage is just crazy, so its air/water clocks are coming out like SB. but on LN2 its like amazing compared to all previous intel platforms IMO. .
Posted on Reply
#3
cristian.a
my radeon hd 6670 gddr5, say popup "ASIC quality reading not supported on this card." :wtf:

Why, why, why ????????

edit:
Posted on Reply
#4
claylomax
Jstn7477 said:
Which one? The ASIC percentage is simply read off the chip.
And how do you do that? When I click the question mark I get the window to start the test, I just want to get the ASIC reading.
Posted on Reply
#6
erocker


Stock volts. I've been running it like this since I got it. Water block should be here next week, hopefully it likes some extra volts. :)
Posted on Reply
#7
Jstn7477
claylomax said:
And how do you do that? When I click the question mark I get the window to start the test, I just want to get the ASIC reading.
Right click the title bar of the window (where it says TechPowerUp GPU-Z 0.5.8) to open a context menu that has the ASIC reading option.
Posted on Reply
#9
jaredpace
Can you get vrm temperature sensor readings for the 7970 in gpuz?
Posted on Reply
#10
Maban
So, who's got the lowest ASIC quality? My first 470 reads a massive 36.9%, which sounds about right. It was never a strong overclocker. Default VID of 1.037V can be overclocked to 725/1800 at stock volts or 775/1900 at 1.087V. Nothing too spectacular. Best I've ever gotten it was 850/1900 at I think 1.15V. It wasn't 100% stable and the card alone drew more than 400W in Furmark. (Don't worry I had the AXP on it and it never got above 75°C, worry about the VRMs though.)

My other 470 with a quality of 60.9% is a little better. Default VID is 0.975V. 725/1800 at 0.975V and 775/1900 at 1.037V.
Posted on Reply
#11
radrok
It doesn't work for me on 6990s, it says "ASIC quality reading not supported on this card."
Same on an ASUS 6970 DirectCU II
Posted on Reply
#12
sanadanosa
cristian.a said:
my radeon hd 6670 gddr5, say popup "ASIC quality reading not supported on this card." :wtf:

Why, why, why ????????

edit:
radrok said:
It doesn't work for me on 6990s, it says "ASIC quality reading not supported on this card."
Same on an ASUS 6970 DirectCU II
Didn't you read this? "The next new feature is ASIC quality, designed for NVIDIA Fermi (GF10x and GF11x GPUs) and AMD Southern Islands (HD 7800 series and above),"
Posted on Reply
#13
radrok
Nope sorry, totally missed it :)
Posted on Reply
#14
Freedom4556
I got 97.4% on an EVGA GTX 560 Ti 448 Core FTW
Currently running factory overclocked 797/975/1594 @ 1.013 V

This seems exceptionally good, am I right? Which would seem to support EVGA doing binning.
Posted on Reply
#15
mad1394
Freedom4556 said:
I got 97.4% on an EVGA GTX 560 Ti 448 Core FTW
Currently running factory overclocked 797/975/1594 @ 1.013 V

This seems exceptionally good, am I right? Which would seem to support EVGA doing binning.
Yea well my POS Gigabyte gtx 460 which has given me a lot of headaches has an ASIC quality of 110.3%. :ohwell:
Posted on Reply
#16
Disruptor4
ASIC quality reading is not supported on this card.
:(
Posted on Reply
#17
Freedom4556
mad1394 said:
Yea well my POS Gigabyte gtx 460 which has given me a lot of headaches has an ASIC quality of 110.3%. :ohwell:
I wonder where Wizz is pulling this number from and what it was originally meant to represent?
Posted on Reply
#18
W1zzard
Freedom4556 said:
I wonder where Wizz is pulling this number from and what it was originally meant to represent?
it's from the gpu silicon, and it's used to calculate the gpu voltage.

"bad" gpus get a higher voltage so they make the default clock. "good" gpus can do it with lower voltage

as you've seen in this thread, the scale for nvidia isnt perfect yet, so i'll apply some fixes once I have more data that suggests the typical ranges of gpu leakages
Posted on Reply
#19
trickson
OH, I have such a headache
W1zzard said:
it's from the gpu silicon, and it's used to calculate the gpu voltage.

"bad" gpus get a higher voltage so they make the default clock. "good" gpus can do it with lower voltage

as you've seen in this thread, the scale for nvidia isnt perfect yet, so i'll apply some fixes once I have more data that suggests the typical ranges of gpu leakages
Any chance for some old card support ? Like the HD5770 ?
Posted on Reply
#20
HammerON
The Watchful Moderator
Curious to see what my two GTX 580's would show:



Looks like my second card should oc better than my first one in the SLI setup.

Thanks W1zz for this nice little enhancement:toast:
Posted on Reply
#21
jaredpace
wiz any word on AMD 7900 series vrm temperature sensor readings in the next gpuz
Posted on Reply
#22
W1zzard
trickson said:
Any chance for some old card support ? Like the HD5770 ?
hd 6000: probably
hd 5000 ... rv610: maybe
Posted on Reply
#23
cristian.a
W1zzard said:
hd 6000: probably
hd 5000 ... rv610: maybe
Yes !!! i want to play too !!!!
Posted on Reply
#24
trickson
OH, I have such a headache
cristian.a said:
Yes !!! i want to play too !!!!
Me too . :respect::cry:
Posted on Reply
#25
The Von Matrices
Lol, I have two of the worst cards of the bunch. It could explain my really high power consumption.

GTX 470 #1: 50.6%
GTX 470 #2: 58.0%

I guess NVidia really needed to sell the worst chips when they created the 470.
Posted on Reply
Add your own comment