Installing the Cuda NVIDIA Graphics Driver

Question

I have two laptops: the Sony vaio z-series (vocz1) and the S series. The first has a Geforce with a GT330M cuda, and the second has a GT 640M LE. When I try to install the CUDA Geforce driver from this site http://developer.nvidia.com/cuda/cuda-downloads I get below error in Windows. I am wondering if you can offer me a solution to solve this problem? all my graphics cards are already installed

Nvidia Installer Cannot Continue This video card could not find compatible graphics hardware.

I'm starting to program with CUDA, I want to know if I can compile and run my CUDA program without installing the Nividia driver? The Cuda Toolkit and SDK have been successfully installed on my machine, but when I run my program, I cannot install my Cuda device. Does this mean that I need to install the Nividia driver?

cudaError_t cudaStatus1; int deviceCount; cudaGetDeviceCount(&deviceCount); int device; for (device = 0; device < 10; ++device) { cudaDeviceProp deviceProp; cudaGetDeviceProperties(&deviceProp, device); // Choose which GPU to run on, change this on a multi-GPU system. cudaStatus1 = cudaSetDevice(device); printf("Device %d has compute capability %d.%d. - %d\n", device, deviceProp.major, deviceProp.minor,cudaStatus1 ); } 

exit:

 Device 0 has compute capability 3137268.3137268. - 35 Device 1 has compute capability 3137268.3137268. - 35 Device 2 has compute capability 3137268.3137268. - 35 Device 3 has compute capability 3137268.3137268. - 35 Device 4 has compute capability 3137268.3137268. - 35 Device 5 has compute capability 3137268.3137268. - 35 Device 6 has compute capability 3137268.3137268. - 35 Device 7 has compute capability 3137268.3137268. - 35 Device 8 has compute capability 3137268.3137268. - 35 Device 9 has compute capability 3137268.3137268. - 35 

35 means that it is not installed on the device, if it became 0, means a set of devices.

after running deviceQuery below the information i got:

Microsoft Windows [Version 6.1.7601] Copyright (c) 2009 Microsoft Corporation. All rights reserved.
C: \ Users \ xx> "C: \ ProgramData \ NVIDIA Corporation \ NVIDIA GPU Computing SDK 4.2 \ C \ bin \ win64 \ Release \ deviceQuery.exe" [deviceQuery.exe] start ... C: \ ProgramData \ NVIDIA Corporation \ NVIDIA GPU Computing SDK 4.2 \ C \ bin \ win64 \ Releasea se \ deviceQuery.exe Launch ... CUDA Device Query version (Runtime API) (static link CUDART) Found 1 CUDA Possible devices Device 0: "GeForce GT 640M LE" CUDA Driver Version / Runtime Version 4.2 / 4.2 Features of CUDA Major / minor version number: 3.0 Total global memory capacity:
1024 MB (1073741824 bytes) (2) Multiprocessors x (192) CUDA Cores / MP: 384 CUDA Cores GPU Clock frequency:
405 MHz (0.41 GHz) Memory frequency:
Bus Width 900 Mhz: 128-bit L2 Cache Size: 262144 bytes Maximum Texture Dimension (x, y, z) 1D = (65536), 2D = (65536, 655536), 3 D = (4096.4096.40.4096) Maximum layered texture size (dim) x layers
1D = (16384) x 2048, 2D = (16384.16 384) x 2048 Total number of constants memory: 65536 bytes Total shared memory per block: 49152 bytes Total number of available registers block: 65536 Deformation size: 32
Maximum number of threads per multiprocessor: 2048 Maximum number of threads per block: 1024 Maximum dimensions of each block dimension: 1024 x 1024 x 64 Maximum dimensions of each dimension grid: 2147483647 x 65535 x 65535 Maximum memory step:
2147483647 bytes Texture Alignment: 512 bytes Parallel Copy and Execution: Yes with 1 copy Engine Timing on cores: Yes
Integrated GPU Sharing Host Memory: No Host Support Memory Matching with Page Lock: Yes Kernel parallel execution:
Yes Leveling requirements for surfaces: Yes The device has ECC support enabled: No device uses the TCC mode driver: No Device does not support Unified Addressing (UVA):
No bus ID PCI ID / PCI ID: 1/0 Calculate Mode: <By default (multiple host threads can use :: cudaSetDevice () with the device at the same time)> deviceQuery, CUDA Driver = CUDART, CUDA Driver version = 4.2, CUDA Runtime Versi on = 4.2, NumDevs = 1, Device = Test Results GeForce GT 640M LE [deviceQuery.exe] ... PASSED

in 3 seconds: 3 ... 2 ... 1 ... done!

Answer 1

I want to know if I can compile and run my CUDA program without installing Nividia Driver? The Cuda Toolkit and SDK have been successfully installed on my machine, but when I run my program, I cannot install my Cuda device. Does this mean that I need to install the Nividia driver?

You will definitely need drivers to run the program. You tried running deviceQuery.exe with binaries. This should give you a good starting point as to what is going wrong.

Answer 2

I also have a VAIO, and I have the same problem. Do not download the laptop version, try the Desktop version of the Nvidia driver. I also had to disable another graphics card (Intel). It worked for me.

Answer 3

Unfortunately, there are many NVIDIA GPUs for which a driver from the NVIDIA website will not be installed (especially for GPU versions specifically designed for Sony, Lenovo, etc., and OEM wants to control the driver’s experience). Most likely, this applies to you.

In these cases, you can edit the .inf file to add your GPU to the list of GPUs for which the driver will be installed. However, this is a bit complicated, and you usually need to edit 3 different sections of the INF file. You can find information on how to create NVIDIA inf files; There are a number of sites that do this.

Of course, you must have the appropriate CUDA driver before you can run CUDA. So, first first ... you need to install the driver.