Hi,
I have installed an addtional graphics card in my PC. The idea is to use one for the monitor and to use one for CUDA.
I had expected that kernelExecTimeoutEnabled woould be 0 for the GPU which has no connected displays but this is not the case.
A device query shows the following info:
=> Nbr of CUDA enabled cards = 2
=> 0 - name: GeForce GTX 480
0 - totalGlobalMem: 1576468480 bytes ( 1.47 Gbytes)
0 - sharedMemPerBlock: 49152 bytes ( 48.00 Kbytes)
0 - regsPerBlock: 32768
0 - warpSize: 32
0 - memPitch: 2147483647
0 - maxThreadsPerBlock: 1024
0 - maxThreadsDim[0]: 1024
0 - maxThreadsDim[1]: 1024
0 - maxThreadsDim[2]: 64
0 - maxGridSize[0]: 65535
0 - maxGridSize[1]: 65535
0 - maxGridSize[2]: 1
0 - totalConstMem: 65536 bytes ( 64.00 Kbytes)
0 - compute capability: 2.0
0 - clockRate 1401000 kilohertz
0 - textureAlignment 512
0 - deviceOverlap 1
0 - multiProcessorCount 15
0 - kernelExecTimeoutEnabled 1
0 - integrated 0
0 - canMapHostMemory 1
0 - computeMode 0
=> 1 - name: GeForce GT 440
1 - totalGlobalMem: 1041825792 bytes ( 0.97 Gbytes)
1 - sharedMemPerBlock: 49152 bytes ( 48.00 Kbytes)
1 - regsPerBlock: 32768
1 - warpSize: 32
1 - memPitch: 2147483647
1 - maxThreadsPerBlock: 1024
1 - maxThreadsDim[0]: 1024
1 - maxThreadsDim[1]: 1024
1 - maxThreadsDim[2]: 64
1 - maxGridSize[0]: 65535
1 - maxGridSize[1]: 65535
1 - maxGridSize[2]: 1
1 - totalConstMem: 65536 bytes ( 64.00 Kbytes)
1 - compute capability: 2.1
1 - clockRate 1645000 kilohertz
1 - textureAlignment 512
1 - deviceOverlap 1
1 - multiProcessorCount 2
1 - kernelExecTimeoutEnabled 1
1 - integrated 0
1 - canMapHostMemory 1
1 - computeMode 0
How can I disable kernelExecTimeoutEnabled on card nbr 1?
I’m using windows 7, CUDA Driver = CUDART, CUDA Driver Version = 3.20, CUDA Runtime Version = 3.20.
Thanks and best regards,
Karel Deprez