Author |
Message |
MarkJ Volunteer moderator Volunteer tester Send message
Joined: 24 Dec 08 Posts: 738 Credit: 200,909,904 RAC: 0 Level
Scientific publications
|
Beta drivers posted on the nvidia website, or click here. The release notes are shown below. The last point might be of interest.
This is a beta driver for GeForce 6, 7, 8, 9, 100, and 200-series desktop GPUs and ION desktop GPUs.
New in Version 191.03
Adds support for OpenGL 3.2 for GeForce 8, 9, 100, and 200-series GPUs and ION GPUs.
Accelerates performance in several gaming applications. The following are examples of improvements measured with version 191.03 drivers vs. version 190.62 drivers (results will vary depending on your GPU, system configuration, and game settings):
Up to 12% performance increase in ARMA 2
Up to 8% performance increase in Batman: Arkham Asylum with GPU PhysX enabled
Up to 50% performance increase in Call of Juarez: Blood in Bound with SLI enabled
Up to 14% performance increase in Fallout 3 (indoor scenes) with antialiasing enabled
Up to 10% performance increase in Far Cry 2 (DX9 version) with antialiasing enabled
Up to 34% performance increase in Prototype with antialiasing enabled
Adds SLI support for Darkfall, Dawn of Magic 2: Time of Shadows, Dreamkiller, Fuel, Majesty 2: The Fantasy Kingdom Sim, Need for Speed: Shift and more.
Includes numerous bug fixes, including the following key fix (additional bug fixes can be found in the release notes on the documentation tab): For graphics cards supporting multiple clock states, 3D clocks correctly return to 2D clocks after exiting a 3D application.
____________
BOINC blog |
|
|
|
Got 2 tasks for testing on GTX260 under Win 7 x64. May be it will finally work...
____________
From Siberia with love!
|
|
|
|
Well, seems like 191.03 drivers didn't solved an 260's bug:
<core_client_version>6.10.3</core_client_version>
<![CDATA[
<message>
- exit code 98 (0x62)
</message>
<stderr_txt>
# Using CUDA device 0
# There is 1 device supporting CUDA
# Device 0: "GeForce GTX 260"
# Clock rate: 1.24 GHz
# Total amount of global memory: 939524096 bytes
# Number of multiprocessors: 24
# Number of cores: 192
MDIO ERROR: cannot open file "restart.coor"
ERROR: c:\cygwin\home\speechserver\gpumd2\src\pme\CPME_cufft.cu, line 104: cufftExecC2R (gridcalc3)
called boinc_finish
</stderr_txt>
]]>
p.s. why this topic names "191.06 drivers released"? :-))
____________
From Siberia with love!
|
|
|
STE\/ESend message
Joined: 18 Sep 08 Posts: 368 Credit: 3,222,386,349 RAC: 50,650,979 Level
Scientific publications
|
The 191.03 Drivers don't fix anything as far as I can see, they work but don't Prevent the Down Clocking of the Cards. The one Box I tried them on already has reset it's self twice already to 300/100. That's worse than before, before it would reset to 300/400. Now the Wu just appears to stall and no Progression is seen. No error is given but the Wu stalls and if I suspend the Wu I can see the reset with GPU-Z ...
Back to Collatz, simple can't run these Wu's if the Cards are going to reset and Stall ... |
|
|
MarkJ Volunteer moderator Volunteer tester Send message
Joined: 24 Dec 08 Posts: 738 Credit: 200,909,904 RAC: 0 Level
Scientific publications
|
Well, seems like 191.03 drivers didn't solved an 260's bug:
<core_client_version>6.10.3</core_client_version>
<![CDATA[
<message>
- exit code 98 (0x62)
</message>
<stderr_txt>
# Using CUDA device 0
# There is 1 device supporting CUDA
# Device 0: "GeForce GTX 260"
# Clock rate: 1.24 GHz
# Total amount of global memory: 939524096 bytes
# Number of multiprocessors: 24
# Number of cores: 192
MDIO ERROR: cannot open file "restart.coor"
ERROR: c:\cygwin\home\speechserver\gpumd2\src\pme\CPME_cufft.cu, line 104: cufftExecC2R (gridcalc3)
called boinc_finish
</stderr_txt>
]]>
p.s. why this topic names "191.06 drivers released"? :-))
Well I didn't think it would solve the cuda fft bug on GTX260's. It might have made a difference to the cards downclocking. According to PoorBoy its worse than before.
As for the driver version number in the topic, that just my typing mistake.
____________
BOINC blog |
|
|
|
Well I didn't think it would solve the cuda fft bug on GTX260's.
Yep... But it could... Perhaps... In theory... :-)
____________
From Siberia with love!
|
|
|
STE\/ESend message
Joined: 18 Sep 08 Posts: 368 Credit: 3,222,386,349 RAC: 50,650,979 Level
Scientific publications
|
Well I didn't think it would solve the cuda fft bug on GTX260's. It might have made a difference to the cards downclocking. According to PoorBoy its worse than before
I have to believe it has something to do with the Grid Application/Wu it's self. I can run Collatz or SETI GPU Wu's for days on end with no Re-setting of the GPU but within a 1/2 Hour usually of running the Grid Wu's on a few cards they Re-set them self's ... |
|
|
zpm Send message
Joined: 2 Mar 09 Posts: 159 Credit: 13,639,818 RAC: 0 Level
Scientific publications
|
Well I didn't think it would solve the cuda fft bug on GTX260's. It might have made a difference to the cards downclocking. According to PoorBoy its worse than before
I have to believe it has something to do with the Grid Application/Wu it's self. I can run Collatz or SETI GPU Wu's for days on end with no Re-setting of the GPU but within a 1/2 Hour usually of running the Grid Wu's on a few cards they Re-set them self's ...
your right.... someone needs to go take a look at the line in the code and see if something looks different.
ERROR: c:\cygwin\home\speechserver\gpumd2\src\pme\CPME_cufft.cu, line 104: cufftExecC2R (gridcalc3)
SIDE NOTE: 191.06 beta didn't fix my p4's java/nvidia conflict.. 186.xx is where that computer is going to have to stay... |
|
|