Re: gpu core temp readout problem

a very nice well-ordered display :)



odyssey bin # nvidia-smi -q -a

==============NVSMI LOG==============


Timestamp                       : Thu Jan  6 12:32:50 2011

Driver Version                  : 260.19.29


GPU 0:
        Product Name            : GeForce GTX 285
        PCI Device/Vendor ID    : 5e310de
        PCI Location ID         : 0:1:0
        Board Serial            : 3169719755757
        Display                 : Connected
        Temperature             : 65 C
        Fan Speed               : 100%
        Utilization
            GPU                 : 84%
            Memory              : 32%
GPU 1:
        Product Name            : GeForce GTX 295
        PCI Device/Vendor ID    : 5eb10de
        PCI Location ID         : 0:5:0
        Board Serial            : 3450956253542
        Display                 : Connected
        Temperature             : 55 C
        Fan Speed               : 100%
        Utilization
            GPU                 : 95%
            Memory              : 70%
GPU 2:
        Product Name            : GeForce GTX 295
        PCI Device/Vendor ID    : 5eb10de
        PCI Location ID         : 0:4:0
        Board Serial            : 843961436557
        Display                 : Not connected
        Temperature             : 59 C
        Utilization
            GPU                 : 97%
            Memory              : 72%






On Thursday, January 06, 2011, you wrote:
> On Thu, 6 Jan 2011 08:27:03 -0500
> Rio <[email protected]> wrote:
> 
> > Bill or whoever is now doing the code -
> > 
> > 
> > i found out what the problem is.. .nvidia changed the syntax on reading coretemps.. 
here 
> > is the info
> > 
> > ------------------------------------
> > You'll need to query the thermal sensors directly:
> > 
> > nvidia-settings -q [thermalsensor:0]/ThermalSensorReading
> > 
> > Each card has two thermal sensors, core and ambient, so thermal sensors 0,2,4 will be 
the 
> > core temperatures and 1,3,5 will be the ambient temperatures.
> > 
> > ---------------------------------------
> 
> Offhand I'm not sure what backwards compatibility complications there would
> be with changing to handle this new nvidia-settings api change.  It's something
> I'll have to investigate.
> 
> But there's an alternative I think I would rather promote.  I'm leaning towards using 
the
> nvidia-smi command as the primary way to get nvidia GPU temps since the nvidia-smi
> command executes much faster than nvidia-settings.
> 
> What output do you get from running:
> 
> 	nvidia-smi -q -a
> 
> Bill
> 
> ______________________________________________
> Gkrellm mailing list
> [email protected]
> Read archives-join-leave-set RSS feed:
> http://archive.lists.netservicesgroup.com
> This service is provided by The Network Services Group:
> http://www.netservicesgroup.com
> 
> 


-- 

Rio


______________________________________________
Gkrellm mailing list
[email protected]
Read archives-join-leave-set RSS feed:
http://archive.lists.netservicesgroup.com
This service is provided by The Network Services Group:
http://www.netservicesgroup.com