There is no device supporting CUDA
I have a machine with Red Hat Enterprise Linux 4 installed. The machine has 3 8800 GTX in it. I installed the drivers, toolkit and SDK and compiled all the sample code.

When I try and run something in debug or release (meaning, on the GPU), I get this error.

[quote]NVIDIA: could not open the device file /dev/nvidia1 (Input/output error).
There is no device supporting CUDA.
[/quote]

In case this is informative:
[quote]ls /dev/nvidia*
/dev/nvidia0  /dev/nvidia1  /dev/nvidia2  /dev/nvidiactl
[/quote]

What should I do to fix this?
I have a machine with Red Hat Enterprise Linux 4 installed. The machine has 3 8800 GTX in it. I installed the drivers, toolkit and SDK and compiled all the sample code.



When I try and run something in debug or release (meaning, on the GPU), I get this error.



NVIDIA: could not open the device file /dev/nvidia1 (Input/output error).

There is no device supporting CUDA.





In case this is informative:

ls /dev/nvidia*

/dev/nvidia0  /dev/nvidia1  /dev/nvidia2  /dev/nvidiactl





What should I do to fix this?

#1
Posted 09/26/2007 03:15 PM   
Specifically which drivers did you install?
Did you start X first?
Specifically which drivers did you install?

Did you start X first?

#2
Posted 09/26/2007 03:16 PM   
[quote name='netllama' date='Sep 26 2007, 11:16 AM']Specifically which drivers did you install?
Did you start X first?
[right][snapback]256975[/snapback][/right]
[/quote]

I installed the ones off the website. The file is called NVIDIA-Linux-x86-100.14.11.pkg1.run. I am guessing that means I installed 100.14.11

X is running.
[quote name='netllama' date='Sep 26 2007, 11:16 AM']Specifically which drivers did you install?

Did you start X first?

[snapback]256975[/snapback]






I installed the ones off the website. The file is called NVIDIA-Linux-x86-100.14.11.pkg1.run. I am guessing that means I installed 100.14.11



X is running.

#3
Posted 09/26/2007 03:35 PM   
What is the output of "ls -l /dev/nv*"?
What is the output of "ls -l /dev/nv*"?

#4
Posted 09/26/2007 03:42 PM   
[quote name='mfatica' date='Sep 26 2007, 11:42 AM']What is the output of "ls -l /dev/nv*"?
[right][snapback]256992[/snapback][/right]
[/quote]

[cudauser@cuda3-linux ~]$ ls -l /dev/nv*
crw------- 1 cudauser root 195, 0 Sep 26 07:39 /dev/nvidia0
crw------- 1 cudauser root 195, 1 Sep 26 07:39 /dev/nvidia1
crw------- 1 cudauser root 195, 2 Sep 26 07:39 /dev/nvidia2
crw------- 1 cudauser root 195, 255 Sep 26 07:39 /dev/nvidiactl
[quote name='mfatica' date='Sep 26 2007, 11:42 AM']What is the output of "ls -l /dev/nv*"?

[snapback]256992[/snapback]






[cudauser@cuda3-linux ~]$ ls -l /dev/nv*

crw------- 1 cudauser root 195, 0 Sep 26 07:39 /dev/nvidia0

crw------- 1 cudauser root 195, 1 Sep 26 07:39 /dev/nvidia1

crw------- 1 cudauser root 195, 2 Sep 26 07:39 /dev/nvidia2

crw------- 1 cudauser root 195, 255 Sep 26 07:39 /dev/nvidiactl

#5
Posted 09/26/2007 03:46 PM   
Permissions are ok.
If you try to run deviceQuery, what is the output?
Do you have some old Cuda installation on your system?
Check with ldd that you are pointing to the new runtime.
Permissions are ok.

If you try to run deviceQuery, what is the output?

Do you have some old Cuda installation on your system?

Check with ldd that you are pointing to the new runtime.

#6
Posted 09/26/2007 03:53 PM   
[quote name='mfatica' date='Sep 26 2007, 11:53 AM']Permissions are ok.
If you try to run deviceQuery, what is the output?
Do you have some old Cuda installation on your system?
Check with ldd that you are pointing to the new runtime.
[right][snapback]256999[/snapback][/right]
[/quote]

The install is brand new. No previous versions of CUDA.

Can you elaborate on deviceQuery and ldd?

Is deviceQuery a CUDA function?
[quote name='mfatica' date='Sep 26 2007, 11:53 AM']Permissions are ok.

If you try to run deviceQuery, what is the output?

Do you have some old Cuda installation on your system?

Check with ldd that you are pointing to the new runtime.

[snapback]256999[/snapback]






The install is brand new. No previous versions of CUDA.



Can you elaborate on deviceQuery and ldd?



Is deviceQuery a CUDA function?

#7
Posted 09/26/2007 03:58 PM   
Here is the output from ldd in the /usr/local/cuda/lib directory. Not sure if this is what you meant.
[quote][cudauser@cuda3-linux lib]$ ldd *.1.0
libcublasemu.so.1.0:
        libtlshook.so (0x00819000)
        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x004dc000)
        libcuda.so (0x004ee000)
        libcudart.so (0x00917000)
        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x00a6f000)
        libm.so.6 => /lib/tls/libm.so.6 (0x00a0d000)
        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x003b6000)
        libc.so.6 => /lib/tls/libc.so.6 (0x00cd9000)
        /lib/ld-linux.so.2 (0x007c8000)
        libdl.so.2 => /lib/libdl.so.2 (0x003c0000)
        libz.so.1 => /usr/lib/libz.so.1 (0x006f6000)
libcublas.so.1.0:
        libtlshook.so (0x00658000)
        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x004aa000)
        libcuda.so (0x00111000)
        libcudart.so (0x002a0000)
        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x002cc000)
        libm.so.6 => /lib/tls/libm.so.6 (0x00394000)
        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x00da7000)
        libc.so.6 => /lib/tls/libc.so.6 (0x004bc000)
        /lib/ld-linux.so.2 (0x00c48000)
        libdl.so.2 => /lib/libdl.so.2 (0x003b7000)
        libz.so.1 => /usr/lib/libz.so.1 (0x003bb000)
libcudart.so.1.0:
        libcuda.so (0x00368000)
        libtlshook.so (0x00e10000)
        libdl.so.2 => /lib/libdl.so.2 (0x0034d000)
        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x00111000)
        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x008a9000)
        libm.so.6 => /lib/tls/libm.so.6 (0x00123000)
        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x00146000)
        libc.so.6 => /lib/tls/libc.so.6 (0x00b65000)
        libz.so.1 => /usr/lib/libz.so.1 (0x00150000)
        /lib/ld-linux.so.2 (0x00617000)
libcuda.so.1.0:
        libdl.so.2 => /lib/libdl.so.2 (0x0038d000)
        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x00534000)
        libz.so.1 => /usr/lib/libz.so.1 (0x004da000)
        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x008e4000)
        libm.so.6 => /lib/tls/libm.so.6 (0x00831000)
        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x003cc000)
        libc.so.6 => /lib/tls/libc.so.6 (0x00d7d000)
        /lib/ld-linux.so.2 (0x003e4000)
libcufftemu.so.1.0:
        libtlshook.so (0x003f2000)
        libdl.so.2 => /lib/libdl.so.2 (0x004ae000)
        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x00111000)
        libcuda.so (0x00123000)
        libcudart.so (0x006f1000)
        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x00ce6000)
        libm.so.6 => /lib/tls/libm.so.6 (0x005c8000)
        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x002b2000)
        libc.so.6 => /lib/tls/libc.so.6 (0x002bc000)
        /lib/ld-linux.so.2 (0x00b4a000)
        libz.so.1 => /usr/lib/libz.so.1 (0x003f4000)
libcufft.so.1.0:
        libtlshook.so (0x00dfe000)
        libdl.so.2 => /lib/libdl.so.2 (0x00f8a000)
        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x00b81000)
        libcuda.so (0x00111000)
        libcudart.so (0x002a0000)
        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x004ab000)
        libm.so.6 => /lib/tls/libm.so.6 (0x006eb000)
        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x00b51000)
        libc.so.6 => /lib/tls/libc.so.6 (0x002cc000)
        /lib/ld-linux.so.2 (0x00e9d000)
        libz.so.1 => /usr/lib/libz.so.1 (0x003f8000)
libtlshook.so.1.0:
        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x00c1b000)
        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x00e70000)
        libm.so.6 => /lib/tls/libm.so.6 (0x0017e000)
        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x00875000)
        libc.so.6 => /lib/tls/libc.so.6 (0x006f2000)
        /lib/ld-linux.so.2 (0x00d17000)
[/quote]
Here is the output from ldd in the /usr/local/cuda/lib directory. Not sure if this is what you meant.

[cudauser@cuda3-linux lib]$ ldd *.1.0

libcublasemu.so.1.0:

        libtlshook.so (0x00819000)

        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x004dc000)

        libcuda.so (0x004ee000)

        libcudart.so (0x00917000)

        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x00a6f000)

        libm.so.6 => /lib/tls/libm.so.6 (0x00a0d000)

        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x003b6000)

        libc.so.6 => /lib/tls/libc.so.6 (0x00cd9000)

        /lib/ld-linux.so.2 (0x007c8000)

        libdl.so.2 => /lib/libdl.so.2 (0x003c0000)

        libz.so.1 => /usr/lib/libz.so.1 (0x006f6000)

libcublas.so.1.0:

        libtlshook.so (0x00658000)

        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x004aa000)

        libcuda.so (0x00111000)

        libcudart.so (0x002a0000)

        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x002cc000)

        libm.so.6 => /lib/tls/libm.so.6 (0x00394000)

        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x00da7000)

        libc.so.6 => /lib/tls/libc.so.6 (0x004bc000)

        /lib/ld-linux.so.2 (0x00c48000)

        libdl.so.2 => /lib/libdl.so.2 (0x003b7000)

        libz.so.1 => /usr/lib/libz.so.1 (0x003bb000)

libcudart.so.1.0:

        libcuda.so (0x00368000)

        libtlshook.so (0x00e10000)

        libdl.so.2 => /lib/libdl.so.2 (0x0034d000)

        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x00111000)

        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x008a9000)

        libm.so.6 => /lib/tls/libm.so.6 (0x00123000)

        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x00146000)

        libc.so.6 => /lib/tls/libc.so.6 (0x00b65000)

        libz.so.1 => /usr/lib/libz.so.1 (0x00150000)

        /lib/ld-linux.so.2 (0x00617000)

libcuda.so.1.0:

        libdl.so.2 => /lib/libdl.so.2 (0x0038d000)

        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x00534000)

        libz.so.1 => /usr/lib/libz.so.1 (0x004da000)

        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x008e4000)

        libm.so.6 => /lib/tls/libm.so.6 (0x00831000)

        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x003cc000)

        libc.so.6 => /lib/tls/libc.so.6 (0x00d7d000)

        /lib/ld-linux.so.2 (0x003e4000)

libcufftemu.so.1.0:

        libtlshook.so (0x003f2000)

        libdl.so.2 => /lib/libdl.so.2 (0x004ae000)

        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x00111000)

        libcuda.so (0x00123000)

        libcudart.so (0x006f1000)

        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x00ce6000)

        libm.so.6 => /lib/tls/libm.so.6 (0x005c8000)

        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x002b2000)

        libc.so.6 => /lib/tls/libc.so.6 (0x002bc000)

        /lib/ld-linux.so.2 (0x00b4a000)

        libz.so.1 => /usr/lib/libz.so.1 (0x003f4000)

libcufft.so.1.0:

        libtlshook.so (0x00dfe000)

        libdl.so.2 => /lib/libdl.so.2 (0x00f8a000)

        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x00b81000)

        libcuda.so (0x00111000)

        libcudart.so (0x002a0000)

        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x004ab000)

        libm.so.6 => /lib/tls/libm.so.6 (0x006eb000)

        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x00b51000)

        libc.so.6 => /lib/tls/libc.so.6 (0x002cc000)

        /lib/ld-linux.so.2 (0x00e9d000)

        libz.so.1 => /usr/lib/libz.so.1 (0x003f8000)

libtlshook.so.1.0:

        libpthread.so.0 => /lib/tls/libpthread.so.0 (0x00c1b000)

        libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x00e70000)

        libm.so.6 => /lib/tls/libm.so.6 (0x0017e000)

        libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x00875000)

        libc.so.6 => /lib/tls/libc.so.6 (0x006f2000)

        /lib/ld-linux.so.2 (0x00d17000)

#8
Posted 09/26/2007 04:04 PM   
Sorry, I "found" deviceQuery. Here is the output from release, emurelease, emudebug:

[quote][cudauser@cuda3-linux release]$ ./deviceQuery
NVIDIA: could not open the device file /dev/nvidia1 (Input/output error).
There is no device supporting CUDA.

Device 0: "Device Emulation (CPU)"
  Major revision number:                        -1
  Minor revision number:                        -1
  Total amount of global memory:                2147483647 bytes
  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:                                    32
  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:                                    1350000 kilohertz

Test PASSED
[/quote]

BUT, if I run it in debug mode:
[quote][cudauser@cuda3-linux debug]$ ./deviceQuery
NVIDIA: could not open the device file /dev/nvidia1 (Input/output error).
Cuda error in file 'deviceQuery.cu' in line 53 : initialization error.
[/quote]
Sorry, I "found" deviceQuery. Here is the output from release, emurelease, emudebug:



[cudauser@cuda3-linux release]$ ./deviceQuery

NVIDIA: could not open the device file /dev/nvidia1 (Input/output error).

There is no device supporting CUDA.



Device 0: "Device Emulation (CPU)"

  Major revision number:                        -1

  Minor revision number:                        -1

  Total amount of global memory:                2147483647 bytes

  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:                                    32

  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:                                    1350000 kilohertz



Test PASSED





BUT, if I run it in debug mode:

[cudauser@cuda3-linux debug]$ ./deviceQuery

NVIDIA: could not open the device file /dev/nvidia1 (Input/output error).

Cuda error in file 'deviceQuery.cu' in line 53 : initialization error.

#9
Posted 09/26/2007 04:24 PM   
Problem solved!

Looking in /var/log/nvidia-installer.log, there was something about things failing because "out of vmalloc space". With this hint, I found a thread
[url="http://forums.nvidia.com/index.php?showtopic=28975&hl=vmalloc"]http://forums.nvidia.com/index.php?showtop...8975&hl=vmalloc[/url]
where someone has solved this problem.

You need to edit your grub to make it like the one below. For me, that meant adding the uppermem, vmalloc and pci parts. Now I have three GPUs.
[quote]title Red Hat Desktop (2.6.9-42.ELsmp) (Dual GPU SLI CUDA)
root (hd0,0)
uppermem 524288
kernel /vmlinuz-2.6.9-42.ELsmp ro root=LABEL=/1 rhgb quiet vmalloc=256MB
pci=nommconf
initrd /initrd-2.6.9-42.ELsmp.img
[/quote]

Thanks everyone for your help and quick responses.
Problem solved!



Looking in /var/log/nvidia-installer.log, there was something about things failing because "out of vmalloc space". With this hint, I found a thread

http://forums.nvidia.com/index.php?showtop...8975&hl=vmalloc

where someone has solved this problem.



You need to edit your grub to make it like the one below. For me, that meant adding the uppermem, vmalloc and pci parts. Now I have three GPUs.

title Red Hat Desktop (2.6.9-42.ELsmp) (Dual GPU SLI CUDA)

root (hd0,0)

uppermem 524288

kernel /vmlinuz-2.6.9-42.ELsmp ro root=LABEL=/1 rhgb quiet vmalloc=256MB

pci=nommconf

initrd /initrd-2.6.9-42.ELsmp.img





Thanks everyone for your help and quick responses.

#10
Posted 09/26/2007 07:31 PM   
Hi,

I'm running openSUSE 10.3 (AMD64) and GeForce 8800 GT. I managed to compile some examples in the SDK after having performed an installation according to [url="http://developer.download.nvidia.com/compute/cuda/1_1/CUDA_SDK_release_notes_linux.txt"]http://developer.download.nvidia.com/compu...notes_linux.txt[/url], along with some previously posted instructions (concerning gcc-4.2->4.1 and glut).

When I execute for example matrixMul I get "There is no device supporting CUDA". Make and execution of deviceQuery yields:
[quote]There is no device supporting CUDA.

Device 0: "Device Emulation (CPU)"
  Major revision number:                        -1
  Minor revision number:                        -1
  Total amount of global memory:                -1 bytes
  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:                                    32
  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:                                    1350000 kilohertz

Test PASSED

Press ENTER to exit...
[/quote]
There is one difference in the output compared to the previous post in this thread:
[quote]  Total amount of global memory:                -1 bytes
[/quote]
That doesn't sound to good ... but I do not know how to fix it. Can someone help me solve this? See also the attached nvidia-bug-report.log (extension changed to .txt due to upload restrictions).
Hi,



I'm running openSUSE 10.3 (AMD64) and GeForce 8800 GT. I managed to compile some examples in the SDK after having performed an installation according to http://developer.download.nvidia.com/compu...notes_linux.txt, along with some previously posted instructions (concerning gcc-4.2->4.1 and glut).



When I execute for example matrixMul I get "There is no device supporting CUDA". Make and execution of deviceQuery yields:

There is no device supporting CUDA.



Device 0: "Device Emulation (CPU)"

  Major revision number:                        -1

  Minor revision number:                        -1

  Total amount of global memory:                -1 bytes

  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:                                    32

  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:                                    1350000 kilohertz



Test PASSED



Press ENTER to exit...



There is one difference in the output compared to the previous post in this thread:

  Total amount of global memory:                -1 bytes



That doesn't sound to good ... but I do not know how to fix it. Can someone help me solve this? See also the attached nvidia-bug-report.log (extension changed to .txt due to upload restrictions).
Attachments

nvidia_bug_report.txt

#11
Posted 04/23/2008 09:14 PM   
[quote name='matuno' date='Apr 23 2008, 11:14 PM']Hi,

I'm running openSUSE 10.3 (AMD64) and GeForce 8800 GT. I managed to compile some examples in the SDK after having performed an installation according to [url="http://developer.download.nvidia.com/compute/cuda/1_1/CUDA_SDK_release_notes_linux.txt"]http://developer.download.nvidia.com/compu...notes_linux.txt[/url], along with some previously posted instructions (concerning gcc-4.2->4.1 and glut).

When I execute for example matrixMul I get "There is no device supporting CUDA". Make and execution of deviceQuery yields:

There is one difference in the output compared to the previous post in this thread:

That doesn't sound to good ... but I do not know how to fix it. Can someone help me solve this? See also the attached nvidia-bug-report.log (extension changed to .txt due to upload restrictions).
[right][snapback]367465[/snapback][/right]
[/quote]

I decided to try Fedora 7 instead, and it worked fine. A possible explanation to my suse troubles could be that I did not kill X before installing the nvidia driver.
[quote name='matuno' date='Apr 23 2008, 11:14 PM']Hi,



I'm running openSUSE 10.3 (AMD64) and GeForce 8800 GT. I managed to compile some examples in the SDK after having performed an installation according to http://developer.download.nvidia.com/compu...notes_linux.txt, along with some previously posted instructions (concerning gcc-4.2->4.1 and glut).



When I execute for example matrixMul I get "There is no device supporting CUDA". Make and execution of deviceQuery yields:



There is one difference in the output compared to the previous post in this thread:



That doesn't sound to good ... but I do not know how to fix it. Can someone help me solve this? See also the attached nvidia-bug-report.log (extension changed to .txt due to upload restrictions).

[snapback]367465[/snapback]






I decided to try Fedora 7 instead, and it worked fine. A possible explanation to my suse troubles could be that I did not kill X before installing the nvidia driver.

#12
Posted 04/24/2008 10:58 AM   
Scroll To Top