one CUDA card unrecognized in 64bit Win7

[educnq]

I have 2 CUDA cards installed, one C1060 (device 0), the other GT430. Both of them work in Linux. However, in 64bit Win7, only C1060 is recognized as shown in deviceQuery’s results.

C:\ProgramData\NVIDIA Corporation\NVIDIA GPU Computing SDK 4.0\C\bin\win64\Release\deviceQuery.exe Starting…

CUDA Device Query (Runtime API) version (CUDART static linking)

There is 1 device supporting CUDA

Device 0: “Tesla C1060”

CUDA Driver Version / Runtime Version 4.0 / 4.0

CUDA Capability Major/Minor version number: 1.3

Total amount of global memory: 4096 MBytes (4294770688 bytes)

(30) Multiprocessors x ( 8) CUDA Cores/MP: 240 CUDA Cores

GPU Clock Speed: 1.30 GHz

Memory Clock rate: 800.00 Mhz

Memory Bus Width: 512-bit

Max Texture Dimension Size (x,y,z) 1D=(8192), 2D=(65536,32768), 3D=(2048,2048,2048)

Max Layered Texture Size (dim) x layers 1D=(8192) x 512, 2D=(8192,8192) x 512

Total amount of constant memory: 65536 bytes

Total amount of shared memory per block: 16384 bytes

Total number of registers available per block: 16384

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: 2147483647 bytes

Texture alignment: 256 bytes

Concurrent copy and execution: Yes with 1 copy engine(s)

Run time limit on kernels: No

Integrated GPU sharing Host Memory: No

Support host page-locked memory mapping: Yes

Concurrent kernel execution: No

Alignment requirement for Surfaces: Yes

Device has ECC support enabled: No

Device is using TCC driver mode: Yes

Device supports Unified Addressing (UVA): No

Device PCI Bus ID / PCI location ID: 131 / 0

Compute Mode:

 < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 4.0, CUDA Runtime Version = 4.0, NumDevs = 1, Device = Tesla C1060

Note it’s in TCC mode. Anyone knows how to fix it? Thanks.

Edit: Both cards can be seen in Device Manager.

[educnq]

Here is the Linux result:

[./deviceQuery] starting…

./deviceQuery Starting…

CUDA Device Query (Runtime API) version (CUDART static linking)

There are 2 devices supporting CUDA

Device 0: “Tesla C1060”

CUDA Driver Version / Runtime Version 4.0 / 4.0

CUDA Capability Major/Minor version number: 1.3

Total amount of global memory: 4096 MBytes (4294770688 bytes)

(30) Multiprocessors x ( 8) CUDA Cores/MP: 240 CUDA Cores

GPU Clock Speed: 1.30 GHz

Memory Clock rate: 800.00 Mhz

Memory Bus Width: 512-bit

Max Texture Dimension Size (x,y,z) 1D=(8192), 2D=(65536,32768), 3D=(2048,2048,2048)

Max Layered Texture Size (dim) x layers 1D=(8192) x 512, 2D=(8192,8192) x 512

Total amount of constant memory: 65536 bytes

Total amount of shared memory per block: 16384 bytes

Total number of registers available per block: 16384

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: 2147483647 bytes

Texture alignment: 256 bytes

Concurrent copy and execution: Yes with 1 copy engine(s)

Run time limit on kernels: No

Integrated GPU sharing Host Memory: No

Support host page-locked memory mapping: Yes

Concurrent kernel execution: No

Alignment requirement for Surfaces: Yes

Device has ECC support enabled: No

Device is using TCC driver mode: No

Device supports Unified Addressing (UVA): No

Device PCI Bus ID / PCI location ID: 131 / 0

Compute Mode:

 < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

Device 1: “GeForce GT 430”

CUDA Driver Version / Runtime Version 4.0 / 4.0

CUDA Capability Major/Minor version number: 2.1

Total amount of global memory: 1024 MBytes (1073414144 bytes)

( 2) Multiprocessors x (48) CUDA Cores/MP: 96 CUDA Cores

GPU Clock Speed: 1.40 GHz

Memory Clock rate: 667.00 Mhz

Memory Bus Width: 128-bit

L2 Cache Size: 131072 bytes

Max Texture Dimension Size (x,y,z) 1D=(65536), 2D=(65536,65535), 3D=(2048,2048,2048)

Max Layered Texture Size (dim) x layers 1D=(16384) x 2048, 2D=(16384,16384) x 2048

Total amount of constant memory: 65536 bytes

Total amount of shared memory per block: 49152 bytes

Total number of registers available per block: 32768

Warp size: 32

Maximum number of threads per block: 1024

Maximum sizes of each dimension of a block: 1024 x 1024 x 64

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

Maximum memory pitch: 2147483647 bytes

Texture alignment: 512 bytes

Concurrent copy and execution: Yes with 2 copy engine(s)

Run time limit on kernels: No

Integrated GPU sharing Host Memory: No

Support host page-locked memory mapping: Yes

Concurrent kernel execution: Yes

Alignment requirement for Surfaces: Yes

Device has ECC support enabled: No

Device is using TCC driver mode: No

Device supports Unified Addressing (UVA): Yes

Device PCI Bus ID / PCI location ID: 2 / 0

Compute Mode:

 < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 4.0, CUDA Runtime Version = 4.0, NumDevs = 2, Device = Tesla C1060, Device = GeForce GT 430

[./deviceQuery] test results…

PASSED

In both systems, I’m using latest 4.0 RC2 softwares and developer drivers.

[educnq]

Actually I have a third video card (Matrox G200eW) on the same workstation, which is not CUDA and used for display. Could it be the problem?

[brano]

Actually I have a third video card (Matrox G200eW) on the same workstation, which is not CUDA and used for display. Could it be the problem?

Yes indeed, that could be the problem.

I had the same problem on my machine. Try to plugin the monitor to the GTX card in see if it detects booth.

The tesla card works because it is in TCC mode. If you disable the TCC from the tesla not event this card will be recognized as a CUDA device.

[educnq]

Thanks brano. Using your method, I fixed the problem (see new Win7 results below). But before plugging the monitor into the GT430 card, some steps are needed. These include disabling onboard card driver in safe mode and setting boot video card priority in BIOS [BIOS → Advanced → PCI/PnP Configuration → Boots Graphic Adapter Priority → Select “Slot 6” instead of previous “Onboard VGA” (the NVIDIA GT430 card is on slot 6)].

C:\ProgramData\NVIDIA Corporation\NVIDIA GPU Computing SDK 4.0\C\bin\win64\Release\deviceQuery.exe Starting…

CUDA Device Query (Runtime API) version (CUDART static linking)

There are 2 devices supporting CUDA

Device 0: “Tesla C1060”

CUDA Driver Version / Runtime Version 4.0 / 4.0

CUDA Capability Major/Minor version number: 1.3

Total amount of global memory: 4096 MBytes (4294770688 bytes)

(30) Multiprocessors x ( 8) CUDA Cores/MP: 240 CUDA Cores

GPU Clock Speed: 1.30 GHz

Memory Clock rate: 800.00 Mhz

Memory Bus Width: 512-bit

Max Texture Dimension Size (x,y,z) 1D=(8192), 2D=(65536,32768), 3D=(2048,2048,2048)

Max Layered Texture Size (dim) x layers 1D=(8192) x 512, 2D=(8192,8192) x 512

Total amount of constant memory: 65536 bytes

Total amount of shared memory per block: 16384 bytes

Total number of registers available per block: 16384

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: 2147483647 bytes

Texture alignment: 256 bytes

Concurrent copy and execution: Yes with 1 copy engine(s)

Run time limit on kernels: No

Integrated GPU sharing Host Memory: No

Support host page-locked memory mapping: Yes

Concurrent kernel execution: No

Alignment requirement for Surfaces: Yes

Device has ECC support enabled: No

Device is using TCC driver mode: Yes

Device supports Unified Addressing (UVA): No

Device PCI Bus ID / PCI location ID: 131 / 0

Compute Mode:

 < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

Device 1: “GeForce GT 430”

CUDA Driver Version / Runtime Version 4.0 / 4.0

CUDA Capability Major/Minor version number: 2.1

Total amount of global memory: 993 MBytes (1041694720 bytes)

( 2) Multiprocessors x (48) CUDA Cores/MP: 96 CUDA Cores

GPU Clock Speed: 1.40 GHz

Memory Clock rate: 667.00 Mhz

Memory Bus Width: 128-bit

L2 Cache Size: 131072 bytes

Max Texture Dimension Size (x,y,z) 1D=(65536), 2D=(65536,65535), 3D=(2048,2048,2048)

Max Layered Texture Size (dim) x layers 1D=(16384) x 2048, 2D=(16384,16384) x 2048

Total amount of constant memory: 65536 bytes

Total amount of shared memory per block: 49152 bytes

Total number of registers available per block: 32768

Warp size: 32

Maximum number of threads per block: 1024

Maximum sizes of each dimension of a block: 1024 x 1024 x 64

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

Maximum memory pitch: 2147483647 bytes

Texture alignment: 512 bytes

Concurrent copy and execution: Yes with 2 copy engine(s)

Run time limit on kernels: Yes

Integrated GPU sharing Host Memory: No

Support host page-locked memory mapping: Yes

Concurrent kernel execution: Yes

Alignment requirement for Surfaces: Yes

Device has ECC support enabled: No

Device is using TCC driver mode: No

Device supports Unified Addressing (UVA): No

Device PCI Bus ID / PCI location ID: 2 / 0

Compute Mode:

 < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 4.0, CUDA Runtime Version = 4.0, NumDevs = 2, Device = Tesla C1060, Device = GeForce GT 430

[educnq]

The monitor does not plug into the card and the card is not recognized. This sounds like a bug. Anyway Linux has no this problem. NVIDIA may want to fix it.