I am sorry wing people, my AMD laptop (6972907) is having driver problems. It runs the cpu tasks fine but the amd GPU driver keeps failing and restarting. When the GPU driver fails it stops the GPU task from completing. So I have resorted to aborting tasks that are past due. I hate it.

I have tried everything: pause / restart, upgrade / downgrade vid driver, upgrade / downgrade boinc, 1 core / 2 core.

I am at my wits end, I even tried to upgrade win 8 to 8.1, it failed.

oh, sorry, it's a HP Pavilion g6-2240nr, new last April/ May, it uses the:

Authentic AMD A6-4400M APU with Radeon(tm) HD Graphics [Family 21 Model 16 Stepping 1]
(2 processors)AMD AMD Radeon HD (unknown)(512MB) driver: 1.4.1741 OpenCL: 1.2 Microsoft Windows 8
Core x64 Edition, (06.02.9200.00)

---

http://allprojectstats.com/ts593244b0a.png

I just checked again - all my GPU tasks are failing.

---

http://allprojectstats.com/ts593244b0a.png

I'm asking you to update Boinc to a Boinc version that is likely to display what the GPU is, AMD doesn't have an api like Nvidia has, so the GPU has to be hard coded into Boinc, so new Boinc versions are required to display new AMD GPUs,
The Host details page only displays the CAL driver version, I did ask DA to display the the OpenCL driver version, he didn't do as I asked, he did something different instead and displayed the OpenCL version the GPU supported,
the OpenCL driver version is displayed in the Boinc startup, hence why I asked for the startup,
The AMD MBv7 apps have been quite sensitive to the APP runtime version, at the moment I can deduce you're got a Catalyst version of somewhere been Cat 12.6 and 13.4, with Cat 13.1 being the must avoid version,
I've already reported to the Boinc devs about app stderr.txt being not shown when a task is aborted, if Boinc 7.2.42 also does this i'll report it again,
At no point did I say that changing Boinc versions was going to fix it, I'm only trying to gather information, once we have the right information we can supply the correct fix.

If you don't want help, I won't help.

Claggy

The GPU is an HD 7520G which is rather slow.

Make sure you try a more recent driver version for the GPU.

Did you use driver sweeper or AMD uninstall utility to get rid of driver rests?

---

With each crime and every kindness we birth our future.

O.K. Claggy, I will make my message public. This is what I tried to pm you:

Claggy, I wish to say I am sorry for being rude to you, there is no excuse for it. The only thing that I can say is that I am extremely frustrated and I really have tried all version, but I understand you need more data - hence your request. I will go back to the current version per your request.

We have talked before about my new Xeon and you were a great help.

In my feeble defense I had come in from a Hosp visit for a 2nd degree burn on my hand and was really really cranky.

Be Well Claggy

---

http://allprojectstats.com/ts593244b0a.png

To further cloud this issue if I update the video driver from the hp site boinc does not even see the gpu. Upgrading from amd does not solve the problem.

Robert

---

http://allprojectstats.com/ts593244b0a.png

I did not use the driver sweep function, I will at your suggestion.

Robert

---

http://allprojectstats.com/ts593244b0a.png

I have resolved the stalled wu issue on my AMD laptop. My solution was to add a registry value called TdrDelay and adjust it from the default of 2 to a value of 8. I would still suggest that you make certain that your drivers are current as a start to resolve this issue.

The following is just some information that I found after reading from many sources.

Snips from the various Microsoft web pages:

.. snip...

Symptom
Your PC may temporarily hang or become unresponsive, and you receive the following error message:
Display driver stopped responding and has recovered

Resolution
To resolve this issue, follow the steps in the methods starting with method 1 and then proceeding with method 2 if that solution does not resolve the issue.
Method 1: Increase the GPU (Graphics Processing Unit) processing time by adjusting the Timeout Detection and Recovery registry value
Timeout Detection and Recovery is a Windows feature that can detect when video adapter hardware or a driver on your PC has taken longer than expected to complete an operation. When this happens, Windows attempts to recover and reset the graphics hardware. If the GPU is unable to recover and reset the graphics hardware in the time permitted (2 seconds), your system may become unresponsive, and display the error “Display driver stopped responding and has recovered.”

Giving the Timeout Detection and Recovery feature more time to complete this operation by adjusting the registry value, may resolve this issue.

..snip...

Limiting Repetitive GPU Hangs and Recoveries

Beginning with Windows Vista with Service Pack 1 (SP1) and Windows Server 2008, the user experience has been improved in situations where the GPU hangs frequently and rapidly. Repetitive GPU hangs indicate that the graphics hardware has not recovered successfully. In these situations, the end user must shut down and restart the operating system to fully reset the graphics hardware. If the operating system detects that six or more GPU hangs and subsequent recoveries occur within 1 minute, the operating system bug-checks the computer on the next GPU hang.

..snip...

Important This section, method, or task contains steps that tell you how to modify the registry. However, serious problems might occur if you modify the registry incorrectly. Therefore, make sure that you follow these steps carefully. For added protection, back up the registry before you modify it. Then, you can restore the registry if a problem occurs. For more information about how to back up the registry in Windows 7, see Back up the registry


TDR Registry Keys

You can use the following TDR-related registry keys for testing or debugging purposes only. That is, they should not be manipulated by any applications outside targeted testing or debugging.

TdrDelay

Specifies the number of seconds that the GPU can delay the preempt request from the GPU scheduler. This is effectively the timeout threshold. The default value is 2 seconds.


KeyPath : HKEY_LOCAL_MACHINE\System\CurrentControlSet\Control\GraphicsDrivers
KeyValue : TdrDelay
ValueType : REG_DWORD
ValueData : Number of seconds to delay. 2 seconds is the default value.

I would postulate that when we add a massive workload to gpu it takes longer than normal to report and the os sees this as a fault - thus we need to give it more time to report.

On a further information note - in my research I saw that this fault was not isolated to AMD APU's, I saw NVIDIA and AMD stand alone cards involved in the issue.

If this helps even 1 person I will be very happy.

Be Well
Robert

---

http://allprojectstats.com/ts593244b0a.png

Hmm, I will have to give this a try. I've had the same issue on occasion with my Nividia cards. It's sporadic which makes it even more annoying lol.

Thanks,

Chris

---

I have used the TdrLevel setting & disabled this feature. As I was having an issue when using uVNC that caused the video driver to crash.

---

SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[

Good idea Chris, I was surprised to find out that the issue was OS based and not APU/GPU driver related. Good Luck.

Robert

---

http://allprojectstats.com/ts593244b0a.png

Hi HAL9000, could you please post some details on your solution. It will help not just I but others that run across this thread. I thank you in advance.

Robert

---

http://allprojectstats.com/ts593244b0a.png

Hi HAL9000, could you please post some details on your solution. It will help not just I but others that run across this thread. I thank you in advance.

Robert

Here is the whole MS write up on the options for the video Timeout Detection & Recovery.
http://msdn.microsoft.com/en-us/library/windows/hardware/ff569918%28v=vs.85%29.aspx
I set TdrLevel to 0. Which basically just turns the whole thing off.

When I would VNC into my HTPC dwm.exe was fluctuating in memory use up to 300-400MB and back down to its normal amount. The graph on the performance tab looked like a sawtooth. Then after a few minutes I would get the display driver has stopped & been recovered message.

---

SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[

Hal9000, I took your advise and set TdrLevel to 0. And wanted to post so I can change title.

Robert