Error while executing "particles"

Accelerated Computing CUDA CUDA Setup and Installation
1

Getting error while executing “particles” while following nivdia cuda starter guide.
C:\NVIDIA\CUDA\CUDASamples\Bin\win64\Release>particles
CUDA Particles Simulation Starting…

grid: 64 x 64 x 64 = 262144 cells
particles: 16384
CUDA error at d:/bld/rel/gpgpu/toolkit/r5.5/samples/5_Simulations/particles/part
icleSystem_cuda.cu:85 code=46(cudaErrorDevicesUnavailable) “cudaGraphicsGLRegist
erBuffer(cuda_vbo_resource, vbo, cudaGraphicsMapFlagsNone)”
completely new to this env - installed toolkit on windows 8.1

2

Is this an Optimus laptop? Are you able to run deviceQuery? Seems like CUDA isn’t finding your graphics card or it’s being used by another program/device: “cudaErrorDevicesUnavailable”

3

Hi, its an ACER V3 laptop…Yes device query works fine attached below is the results:
in case this helps for u to find any problems in my laptop…Thanks again for the help…let me check for the graphics card drivers…
C:\NVIDIA\CUDA\CUDASamples\Bin\win64\Release>devicequery
devicequery Starting…

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

Detected 1 CUDA Capable device(s)

Device 0: “GeForce GTX 760M”
CUDA Driver Version / Runtime Version 5.5 / 5.5
CUDA Capability Major/Minor version number: 3.0
Total amount of global memory: 2048 MBytes (2147483648 bytes)
( 4) Multiprocessors, (192) CUDA Cores/MP: 768 CUDA Cores
GPU Clock rate: 719 MHz (0.72 GHz)
Memory Clock rate: 2004 Mhz
Memory Bus Width: 128-bit
L2 Cache Size: 262144 bytes
Maximum Texture Dimension Size (x,y,z) 1D=(65536), 2D=(65536, 65536),
3D=(4096, 4096, 4096)
Maximum Layered 1D Texture Size, (num) layers 1D=(16384), 2048 layers
Maximum Layered 2D Texture Size, (num) layers 2D=(16384, 16384), 2048 layers
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 2048
Maximum number of threads per block: 1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and kernel execution: Yes with 1 copy engine(s)
Run time limit on kernels: Yes
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Disabled
CUDA Device Driver Mode (TCC or WDDM): WDDM (Windows Display Driver Mo
del)
Device supports Unified Addressing (UVA): Yes
Device PCI Bus ID / PCI location ID: 1 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simu
ltaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 5.5, CUDA Runtime Versi
on = 5.5, NumDevs = 1, Device0 = GeForce GTX 760M
Result = PASS

4

My only suggestion is a restart… not sure what else would trigger a ‘cudaErrorDevicesUnavailable’ otherwise… perhaps try updating the NVIDIA GPU drivers to the newest ones as well and doing a clean install of them

5

Did you get any success. I am having similar error message for other samples too.
Mine is CUDA 5.5 on ACER AspireV with GeForce 720M Windows 8.1. Can you please post here what you found.

6

I have this problem as well. It happens in a large number of the samples. I system is a Thinkpad t430 running ubuntu 13.10.

I have run all the samples and collected the errors:

CUDA error at bicubicTexture_cuda.cu:37 code=46(cudaErrorDevicesUnavailable) "cudaMallocArray(&d_imageArray, &channelDesc, imageWidth, imageHeight)" 
CUDA error at bilateral_kernel.cu:159 code=46(cudaErrorDevicesUnavailable) "cudaMemcpyToSymbol(cGaussian, fGaussian, sizeof(float)*(2*radius+1))" 
CUDA error at bindlessTexture.cpp:236 code=46(cudaErrorDevicesUnavailable) "cudaGraphicsGLRegisterBuffer(&cuda_pbo_resource, pbo, cudaGraphicsMapFlagsWriteDiscard)" 
CUDA error at boxFilter.cpp:286 code=46(cudaErrorDevicesUnavailable) "cudaMalloc((void **) &d_img, (width * height * sizeof(unsigned int)))" 
Unified Memory not supported on this device
checkCudaErrors() Driver API error = 0999 "CUDA_ERROR_UNKNOWN" from file <videoDecodeGL.cpp>, line 423.
   OpenGL device is Available
fluidsGL_kernels.cu(52) : getLastCudaError() CUDA error : cudaMalloc failed : (46) all CUDA-capable devices are busy or unavailable.
CUDA Capable Device 0, meets minimum required specs.
CUDA error at FunctionPointers_kernels.cu:309 code=46(cudaErrorDevicesUnavailable) "cudaMallocArray(&array, &desc, iw, ih)" 
CUDA error at GrabcutMain.cpp:649 code=46(cudaErrorDevicesUnavailable) "cudaGraphicsGLRegisterBuffer(&pbo_resource, pbo, cudaGraphicsMapFlagsNone)" 
CUDA error at imageDenoisingGL.cpp:556 code=46(cudaErrorDevicesUnavailable) "CUDA_MallocArray(&h_Src, imageW, imageH)" 
CUDA error at Mandelbrot.cpp:971 code=46(cudaErrorDevicesUnavailable) "cudaGraphicsGLRegisterBuffer(&cuda_pbo_resource, gl_PBO, cudaGraphicsMapFlagsWriteDiscard)" 
CUDA error at marchingCubes.cpp:475 code=46(cudaErrorDevicesUnavailable) "cudaMalloc((void **) &d_volume, size)" 
CUDA error at bodysystemcuda_impl.h:156 code=46(cudaErrorDevicesUnavailable) "cudaEventCreate(&m_deviceData[0].event)" 
CUDA error at particleSystem_cuda.cu:85 code=46(cudaErrorDevicesUnavailable) "cudaGraphicsGLRegisterBuffer(cuda_vbo_resource, vbo, cudaGraphicsMapFlagsNone)" 
CUDA error at main.cpp:276 code=46(cudaErrorDevicesUnavailable) "cudaGraphicsGLRegisterBuffer(pbo_resource, *pbo, cudaGraphicsMapFlagsNone)" 
CUDA error at recursiveGaussian.cpp:290 code=46(cudaErrorDevicesUnavailable) "cudaMalloc((void **) &d_img, size)" 
CUDA error at main.cpp:487 code=46(cudaErrorDevicesUnavailable) "cudaGraphicsGLRegisterImage(&cuda_tex_result_resource, *tex_cudaResult, GL_TEXTURE_2D, cudaGraphicsMapFlagsWriteDiscard)" 
CUDA error at simpleGL.cu:494 code=46(cudaErrorDevicesUnavailable) "cudaGraphicsGLRegisterBuffer(vbo_res, *vbo, vbo_res_flags)" 
CUDA error at simpleTexture3D.cpp:248 code=46(cudaErrorDevicesUnavailable) "cudaGraphicsGLRegisterBuffer(&cuda_pbo_resource, pbo, cudaGraphicsMapFlagsWriteDiscard)" 
SobelFilter_kernels.cu(223) : CUDA Runtime API error 46: all CUDA-capable devices are busy or unavailable.
CUDA error at volume.cpp:24 code=46(cudaErrorDevicesUnavailable) "cudaMalloc3DArray(&vol->content, &vol->channelDesc, dataSize, allowStore ? cudaArraySurfaceLoadStore : 0)" 
CUDA error at volumeRender_kernel.cu:190 code=46(cudaErrorDevicesUnavailable) "cudaMalloc3DArray(&d_volumeArray, &channelDesc, volumeSize)"

It seems that that everything with a GUI (but not limited to) crashes. Every time with the “cudaErrorDevicesUnavailable”. The actual CUDA call differs although “cudaGraphicsGLRegisterBuffer” and “cudaMallocArray” reoccur quite a lot. Strangely i got the “nbody” sample works by passing the “hostmem” option.

Edit: I should just add that my laptop runs optimus. The installation guide here http://docs.nvidia.com/cuda/pdf/CUDA_Getting_Started_Linux.pdf mentioned that if you have both an integrated and discreet GPU you should use the --no-opengl-libs option. I assumed this meant optimus.

My device query for refrence:

./deviceQuery Starting...

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

Detected 1 CUDA Capable device(s)

Device 0: "NVS 5400M"
  CUDA Driver Version / Runtime Version          6.0 / 6.0
  CUDA Capability Major/Minor version number:    2.1
  Total amount of global memory:                 1024 MBytes (1073414144 bytes)
  ( 2) Multiprocessors, ( 48) CUDA Cores/MP:     96 CUDA Cores
  GPU Clock rate:                                950 MHz (0.95 GHz)
  Memory Clock rate:                             900 Mhz
  Memory Bus Width:                              128-bit
  L2 Cache Size:                                 131072 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(65536), 2D=(65536, 65535), 3D=(2048, 2048, 2048)
  Maximum Layered 1D Texture Size, (num) layers  1D=(16384), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(16384, 16384), 2048 layers
  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 multiprocessor:  1536
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (65535, 65535, 65535)
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             512 bytes
  Concurrent copy and kernel 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
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        Disabled
  Device supports Unified Addressing (UVA):      Yes
  Device PCI Bus ID / PCI location ID:           1 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 6.0, CUDA Runtime Version = 6.0, NumDevs = 1, Device0 = NVS 5400M
Result = PASS