Input Output Error 9600 Gx2 nvidiact2 9600gx2 cuda input/output error

Accelerated Computing CUDA CUDA Programming and Performance
1

Hello All,

I am attempting to run CUDA 2.0 with Driver version x86-177.73-pkg1 on a OpenSuse 10.3 32 bit System. However I dont seem to be able to see the devices as shown below. I have changed from a 8800gtx to a 9600gx2, I reinstalled the drivers and ToolKit and sdk

When i do a ./deviceQuery

NVIDIA: could not open the device file /dev/nvidia2 (Input/output error).

There is no device supporting CUDA.

[codebox]

Device 0: “Device Emulation (CPU)”

Major revision number: 9999

Minor revision number: 9999

Total amount of global memory: 4294967295 bytes

Number of multiprocessors: 16

Number of cores: 128

Total amount of constant memory: 65536 bytes

Total amount of shared memory per block: 16384 bytes

Total number of registers available per block: 8192

Warp size: 1

Maximum number of threads per block: 512

Maximum sizes of each dimension of a block: 512 x 512 x 64

Maximum sizes of each dimension of a grid: 65535 x 65535 x 1

Maximum memory pitch: 262144 bytes

Texture alignment: 256 bytes

Clock rate: 1.35 GHz

Concurrent copy and execution: No

Test PASSED

[/codebox]

I used to have a similar problem previously when I used to run with a 8800GTX when some one told me to

do chmod 0666 /dev/nvidia* as root

I did the same this time too but no luck. However when I move back to the 8800gtx it seems to work fine.

I can can see my 9800gx2 as well when I can do a lspci | grep -i nvidia as well

[codebox]

00:00.0 Host bridge: nVidia Corporation Unknown device 0071 (rev c1)

00:00.1 RAM memory: nVidia Corporation Unknown device 007f (rev a1)

00:00.2 RAM memory: nVidia Corporation Unknown device 0075 (rev a1)

00:00.3 RAM memory: nVidia Corporation Unknown device 006f (rev a1)

00:00.4 RAM memory: nVidia Corporation Unknown device 00b4 (rev a1)

00:01.0 RAM memory: nVidia Corporation Unknown device 0076 (rev a1)

00:01.1 RAM memory: nVidia Corporation Unknown device 0078 (rev a1)

00:01.2 RAM memory: nVidia Corporation Unknown device 0079 (rev a1)

00:01.3 RAM memory: nVidia Corporation Unknown device 007a (rev a1)

00:01.4 RAM memory: nVidia Corporation Unknown device 007b (rev a1)

00:01.5 RAM memory: nVidia Corporation Unknown device 007c (rev a1)

00:01.6 RAM memory: nVidia Corporation Unknown device 007d (rev a1)

00:02.0 PCI bridge: nVidia Corporation Unknown device 007e (rev a2)

00:04.0 PCI bridge: nVidia Corporation Unknown device 007e (rev a2)

00:05.0 PCI bridge: nVidia Corporation Unknown device 007e (rev a2)

00:09.0 RAM memory: nVidia Corporation MCP55 Memory Controller (rev a2)

00:0a.0 ISA bridge: nVidia Corporation MCP55 LPC Bridge (rev a3)

00:0a.1 SMBus: nVidia Corporation MCP55 SMBus (rev a3)

00:0b.0 USB Controller: nVidia Corporation MCP55 USB Controller (rev a1)

00:0b.1 USB Controller: nVidia Corporation MCP55 USB Controller (rev a2)

00:0d.0 IDE interface: nVidia Corporation MCP55 IDE (rev a1)

00:0e.0 RAID bus controller: nVidia Corporation MCP55 SATA Controller (rev a3)

00:0e.1 RAID bus controller: nVidia Corporation MCP55 SATA Controller (rev a4)

00:0e.2 RAID bus controller: nVidia Corporation MCP55 SATA Controller (rev a5)

00:0f.0 PCI bridge: nVidia Corporation MCP55 PCI bridge (rev a2)

00:0f.1 Audio device: nVidia Corporation MCP55 High Definition Audio (rev a2)

00:13.0 PCI bridge: nVidia Corporation MCP55 PCI Express bridge (rev a3)

00:18.0 PCI bridge: nVidia Corporation MCP55 PCI Express bridge (rev a3)

01:00.0 VGA compatible controller: nVidia Corporation G70 [GeForce 7300 GT] (rev a1)

06:00.0 PCI bridge: nVidia Corporation PCI express bridge for Quadro Plex S4 / Tesla S870 / Tesla S1070 (rev a2)

07:00.0 PCI bridge: nVidia Corporation PCI express bridge for Quadro Plex S4 / Tesla S870 / Tesla S1070 (rev a2)

07:02.0 PCI bridge: nVidia Corporation PCI express bridge for Quadro Plex S4 / Tesla S870 / Tesla S1070 (rev a2)

08:00.0 3D controller: nVidia Corporation GeForce 9800 GX2 (rev a2)

09:00.0 VGA compatible controller: nVidia Corporation GeForce 9800 GX2 (rev a2)

[/codebox]

Any help would be really appreciated.

Just for the record, Another thing I noticed when I use the 9800gx2

[codebox]

pmistry@pino:~/NVIDIA_CUDA_SDK/bin/linux/release> nvidia-smi

Gpus found in probe:

Found Gpuid 0x1000

Found Gpuid 0x8000

Found Gpuid 0x9000

Attaching all probed Gpus…NVIDIA: could not open the device file /dev/nvidia2 (Input/output error).

Failed to attach gpu

Could not allocate resources!

[/codebox]

I know that the gx2 has two gpus on it, does the sli or how it’s setup matter?

Thanks,

Perhaad

2

This is expected behavior if you’ve not started X with the nvidia X driver.

3

Thanks for replying, However I am not clear on what you mean by started X with the “nvidia X driver”,

In my case when I installed the driver I recieved the message it said something about configuring using nvidia-xconfig.

After I installed the driver I did do a “startx” after which installed CUDA and so on. As I mentioned the problem seems specific to the 9600gx2 that I am using, When I go back to using the 8800gtx everything works fine. Since I am not using the 9600gx2 or my older 8800gtx for display purposes, (Have a old 7300gt for that) I dont even see them in my xorg.conf.

Thanks for all your help.

–

Perhaad

4

Please generate and attach an nvidia-bug-report.log while this problem is present.

5

Hello Netllama.

I have attached a bug report, I did a new install with my 9600gx2 right from start, Driver, Start X-Server, CUDA, CUDA SDK

I still get a

[codebox]

NVIDIA: could not open the device file /dev/nvidia2 (Input/output error).

There is no device supporting CUDA.

Device 0: “Device Emulation (CPU)”

Major revision number: 9999

Minor revision number: 9999

and so on…

[/codebox]

Thanks for all your efforts, I was happy using the 8800gtx but I needed atomic ops for an exam :)

Perhaad
nvidia_bug_report.txt (204 KB)

6

(EE) NVIDIA(GPU-2): Failed to initialize the NVIDIA graphics device PCI:9:0:0.
(EE) NVIDIA(GPU-2): Please see the COMMON PROBLEMS section in the README for
(EE) NVIDIA(GPU-2): additional information.
(WW) NVIDIA(GPU-2): Failed to initialize NVIDIA graphics device on GPU PCI:9:0:0!
allocation failed: out of vmalloc space - use vmalloc= to increase size.
NVRM: failed to map registers!!
NVRM: RmInitAdapter failed! (0x10:0x32:1365)
NVRM: rm_init_adapter(2) failed

177.80 is no longer supported. I’d suggest installing the latest released driver package and seeing the README for further assistance. This is not a CUDA issue.