CUDA In Fedora 11

Step 1: Update the Kernel

[vivek@farpoint ~]$ uname -r
2.6.29.6-217.2.16.fc11.i686.PAE

Step 2: Get hold of the cuda driver, toolkit and SDK and install them as root, in this order, using

sh ./filename.run

(If you get a "could not load kernel module nvidia.ko" then follow this link to install the nVidia driver, without CUDA support first. Then reboot the system, make sure that driver works, and then come back here and continue from step 1.)

Step 3: Install some libraries required for CUDA:

yum install freeglut-devel libXi* libXmu*

Step 4: Modify the makefile (this step is due to http://forums.nvidia.com/index.php?showtopic=104525)

cd /opt/NVIDIA_GPU_Computing_SDK (or wherever your SDK is installed)

Edit ./common/common.mk

ADD one more flag to NVCCFLAGS
—compiler-options -fno-inline

As in gcc 4.4.x, check against inline function be declared as weak.

In Makefile, add two lines for clean

@make -C common -f Makefile_paramgl clean
@make -C common -f Makefile_rendercheckgl clean

(Use TAB and not the space bar to indent the new lines added.)

Step 5: Run Make!

Output on my system:

[root@farpoint NVIDIA_GPU_Computing_SDK]# cd C
[root@farpoint C]# make
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/common'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/common'
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/common'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/common'
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/common'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/common'
make -C src/MonteCarloMultiGPU/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/MonteCarloMultiGPU'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/MonteCarloMultiGPU'
make -C src/asyncAPI/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/asyncAPI'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/asyncAPI'
make -C src/simpleGL/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleGL'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleGL'
make -C src/dwtHaar1D/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/dwtHaar1D'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/dwtHaar1D'
make -C src/eigenvalues/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/eigenvalues'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/eigenvalues'
make -C src/SobolQRNG/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/SobolQRNG'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/SobolQRNG'
make -C src/simpleVoteIntrinsics/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleVoteIntrinsics'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleVoteIntrinsics'
make -C src/matrixMulDynlinkJIT/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/matrixMulDynlinkJIT'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/matrixMulDynlinkJIT'
make -C src/simpleCUFFT/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleCUFFT'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleCUFFT'
make -C src/MersenneTwister/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/MersenneTwister'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/MersenneTwister'
make -C src/transpose/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/transpose'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/transpose'
make -C src/sortingNetworks/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/sortingNetworks'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/sortingNetworks'
make -C src/recursiveGaussian/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/recursiveGaussian'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/recursiveGaussian'
make -C src/fastWalshTransform/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/fastWalshTransform'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/fastWalshTransform'
make -C src/convolutionFFT2D/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/convolutionFFT2D'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/convolutionFFT2D'
make -C src/bandwidthTest/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/bandwidthTest'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/bandwidthTest'
make -C src/matrixMul/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/matrixMul'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/matrixMul'
make -C src/deviceQueryDrv/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/deviceQueryDrv'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/deviceQueryDrv'
make -C src/quasirandomGenerator/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/quasirandomGenerator'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/quasirandomGenerator'
make -C src/scalarProd/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/scalarProd'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/scalarProd'
make -C src/scan/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/scan'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/scan'
make -C src/particles/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/particles'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/particles'
make -C src/fluidsGL/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/fluidsGL'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/fluidsGL'
make -C src/simpleStreams/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleStreams'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleStreams'
make -C src/clock/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/clock'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/clock'
make -C src/imageDenoising/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/imageDenoising'
imageDenoisingGL.cpp:46: warning: deprecated conversion from string constant to ‘char*’
imageDenoisingGL.cpp:54: warning: deprecated conversion from string constant to ‘char*’
imageDenoisingGL.cpp:54: warning: deprecated conversion from string constant to ‘char*’
imageDenoisingGL.cpp:54: warning: deprecated conversion from string constant to ‘char*’
imageDenoisingGL.cpp:54: warning: deprecated conversion from string constant to ‘char*’
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/imageDenoising'
make -C src/alignedTypes/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/alignedTypes'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/alignedTypes'
make -C src/dxtc/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/dxtc'
./dxtc.cu(101): Advisory: Loop was not unrolled, unexpected control flow construct
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/dxtc'
make -C src/simpleTemplates/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleTemplates'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleTemplates'
make -C src/BlackScholes/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/BlackScholes'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/BlackScholes'
make -C src/smokeParticles/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/smokeParticles'
particleDemo.cpp: In function ‘int main(int, char**)’:
particleDemo.cpp:844: warning: deprecated conversion from string constant to ‘char*’
particleDemo.cpp:845: warning: deprecated conversion from string constant to ‘char*’
ParticleSystem.cpp: In member function ‘void ParticleSystem::sphereEmitter(uint&, nv::vec3f, nv::vec3f, nv::vec3f, float, int, float, float)’:
ParticleSystem.cpp:322: warning: unused variable ‘dist’
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/smokeParticles'
make -C src/cppIntegration/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/cppIntegration'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/cppIntegration'
make -C src/oceanFFT/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/oceanFFT'
oceanFFT.cpp: In function ‘void runCudaTest(bool)’:
oceanFFT.cpp:460: warning: deprecated conversion from string constant to ‘char*’
oceanFFT.cpp:472: warning: deprecated conversion from string constant to ‘char*’
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/oceanFFT'
make -C src/simpleAtomicIntrinsics/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleAtomicIntrinsics'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleAtomicIntrinsics'
make -C src/postProcessGL/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/postProcessGL'
ptxas /tmp/tmpxft_0000142c_00000000-2_postProcessGL.ptx, line 330; warning : Double is not supported. Demoting to float
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/postProcessGL'
make -C src/simpleTexture/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleTexture'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleTexture'
make -C src/boxFilter/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/boxFilter'
boxFilter.cpp:48: warning: deprecated conversion from string constant to ‘char*’
boxFilter.cpp:69: warning: deprecated conversion from string constant to ‘char*’
boxFilter.cpp:515: warning: unused parameter ‘argc’
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/boxFilter'
make -C src/simpleCUBLAS/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleCUBLAS'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleCUBLAS'
make -C src/simpleZeroCopy/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleZeroCopy'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleZeroCopy'
make -C src/volumeRender/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/volumeRender'
volumeRender.cpp:61: warning: deprecated conversion from string constant to ‘char*’
volumeRender.cpp:217: warning: unused parameter ‘x’
volumeRender.cpp:217: warning: unused parameter ‘y’
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/volumeRender'
make -C src/bicubicTexture/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/bicubicTexture'
bicubicTexture.cpp:88: warning: deprecated conversion from string constant to ‘char*’
bicubicTexture.cpp:118: warning: deprecated conversion from string constant to ‘char*’
bicubicTexture.cpp:685: warning: unused parameter ‘argc’
bicubicTexture.cpp:574: warning: ‘shaderCode’ defined but not used
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/bicubicTexture'
make -C src/simpleTexture3D/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleTexture3D'
simpleTexture3D.cpp:190: warning: unused parameter ‘x’
simpleTexture3D.cpp:190: warning: unused parameter ‘y’
simpleTexture3D.cpp: In function ‘void runAutoTest(int, char**)’:
simpleTexture3D.cpp:316: warning: deprecated conversion from string constant to ‘char*’
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleTexture3D'
make -C src/threadMigration/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/threadMigration'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/threadMigration'
make -C src/convolutionSeparable/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/convolutionSeparable'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/convolutionSeparable'
make -C src/marchingCubes/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/marchingCubes'
marchingCubes.cpp:127: warning: deprecated conversion from string constant to ‘char*’
marchingCubes.cpp: In function ‘void runAutoTest(int, char**)’:
marchingCubes.cpp:317: warning: deprecated conversion from string constant to ‘char*’
marchingCubes.cpp:318: warning: deprecated conversion from string constant to ‘char*’
marchingCubes.cpp:319: warning: deprecated conversion from string constant to ‘char*’
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/marchingCubes'
make -C src/binomialOptions/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/binomialOptions'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/binomialOptions'
make -C src/simpleTextureDrv/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleTextureDrv'
simpleTextureDrv.cpp:37: warning: deprecated conversion from string constant to ‘char*’
simpleTextureDrv.cpp:38: warning: deprecated conversion from string constant to ‘char*’
simpleTextureDrv.cpp: In function ‘void showHelp()’:
simpleTextureDrv.cpp:64: warning: too many arguments for format
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleTextureDrv'
make -C src/dct8x8/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/dct8x8'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/dct8x8'
make -C src/convolutionTexture/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/convolutionTexture'
main.cpp: In function ‘int main(int, char**)’:
main.cpp:123: warning: comparison between signed and unsigned integer expressions
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/convolutionTexture'
make -C src/SobelFilter/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/SobelFilter'
In file included from SobelFilter.cpp:29:
SobelFilter_kernels.h:41: warning: deprecated conversion from string constant to ‘char*’
SobelFilter_kernels.h:41: warning: deprecated conversion from string constant to ‘char*’
SobelFilter_kernels.h:41: warning: deprecated conversion from string constant to ‘char*’
SobelFilter.cpp:46: warning: deprecated conversion from string constant to ‘char*’
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/SobelFilter'
make -C src/lineOfSight/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/lineOfSight'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/lineOfSight'
make -C src/transposeNew/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/transposeNew'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/transposeNew'
make -C src/matrixMulDrv/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/matrixMulDrv'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/matrixMulDrv'
make -C src/ptxjit/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/ptxjit'
ptxjit.cpp: In function ‘int main(int, char**)’:
ptxjit.cpp:83: warning: comparison between signed and unsigned integer expressions
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/ptxjit'
make -C src/Mandelbrot/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/Mandelbrot'
Mandelbrot.cpp:155: warning: deprecated conversion from string constant to ‘char*’
Mandelbrot.cpp: In function ‘void keyboardFunc(unsigned char, int, int)’:
Mandelbrot.cpp:641: warning: deprecated conversion from string constant to ‘char*’
ptxas /tmp/tmpxft_0000194f_00000000-2_Mandelbrot_sm11.ptx, line 1788; warning : Double is not supported. Demoting to float
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/Mandelbrot'
make -C src/radixSort/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/radixSort'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/radixSort'
make -C src/nbody/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/nbody'
nbody.cpp: In function ‘void initGL()’:
nbody.cpp:233: warning: deprecated conversion from string constant to ‘char*’
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/nbody'
make -C src/simpleMultiGPU/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleMultiGPU'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simpleMultiGPU'
make -C src/MonteCarlo/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/MonteCarlo'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/MonteCarlo'
make -C src/scanLargeArray/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/scanLargeArray'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/scanLargeArray'
make -C src/reduction/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/reduction'
ptxas /tmp/tmpxft_00001bc0_00000000-2_reduction_kernel_sm10.ptx, line 8281; warning : Double is not supported. Demoting to float
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/reduction'
make -C src/histogram/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/histogram'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/histogram'
make -C src/deviceQuery/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/deviceQuery'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/deviceQuery'
make -C src/simplePitchLinearTexture/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simplePitchLinearTexture'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/simplePitchLinearTexture'
make -C src/template/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/template'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/template'
make -C src/3DFD/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/3DFD'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/3DFD'
make -C src/threadFenceReduction/
make[1]: Entering directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/threadFenceReduction'
make[1]: Leaving directory `/opt/NVIDIA_GPU_Computing_SDK/C/src/threadFenceReduction'
Finished building all

Step 6: Run deviceQuery to confirm operation.

[vivek@farpoint release]$ ./deviceQuery
CUDA Device Query (Runtime API) version (CUDART static linking)
There are 2 devices supporting CUDA

Device 0: "GeForce GTX 295"
  CUDA Driver Version:                           2.30
  CUDA Runtime Version:                          2.30
  CUDA Capability Major revision number:         1
  CUDA Capability Minor revision number:         3
  Total amount of global memory:                 938803200 bytes
  Number of multiprocessors:                     30
  Number of cores:                               240
  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:                          262144 bytes
  Texture alignment:                             256 bytes
  Clock rate:                                    1.24 GHz
  Concurrent copy and execution:                 Yes
  Run time limit on kernels:                     Yes
  Integrated:                                    No
  Support host page-locked memory mapping:       Yes
  Compute mode:                                  Default (multiple host threads can use this device simultaneously)

Device 1: "GeForce GTX 295"
  CUDA Driver Version:                           2.30
  CUDA Runtime Version:                          2.30
  CUDA Capability Major revision number:         1
  CUDA Capability Minor revision number:         3
  Total amount of global memory:                 939261952 bytes
  Number of multiprocessors:                     30
  Number of cores:                               240
  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:                          262144 bytes
  Texture alignment:                             256 bytes
  Clock rate:                                    1.24 GHz
  Concurrent copy and execution:                 Yes
  Run time limit on kernels:                     No
  Integrated:                                    No
  Support host page-locked memory mapping:       Yes
  Compute mode:                                  Default (multiple host threads can use this device simultaneously)

Test PASSED

Press ENTER to exit...

[vivek@farpoint release]$
Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License