London
1
Windows Server 2008 64 Bit
- Synopsis description of the problem
The code crashes.
- Detailed description of the problem
In the code below, the call to curandGenerateNormalDouble is failing as it is not returning the Success status.
If I change the 125000 to a smaller value, it runs okey. Is there a limitation of the curandGenerateNormalDouble function.
If I use curandGenerateUniformDouble, it runs okey.
If it is timeout, how could it fix it?
The card we have is GTX295 and running on windows server 2008.
cudaResult = cudaMalloc((void **)&data, 125000 * sizeof(double));
for (unsigned int i = 0; i <= 1000000 ; i++)
{
curandResult = curandGenerateNormalDouble(gen, data, 125000, mean, stddev);
}
- CUDA toolkit release version
V3.2
V3.2
- Compiler for CPU host code
Visual C++ from Visual Studio 2008
- System description including:
CPU type: I7
system RAM: 12G
video cards: GTX 295
Thanks
Yu
London
2
Windows Server 2008 64 Bit
- Synopsis description of the problem
The code crashes.
- Detailed description of the problem
In the code below, the call to curandGenerateNormalDouble is failing as it is not returning the Success status.
If I change the 125000 to a smaller value, it runs okey. Is there a limitation of the curandGenerateNormalDouble function.
If I use curandGenerateUniformDouble, it runs okey.
If it is timeout, how could it fix it?
The card we have is GTX295 and running on windows server 2008.
cudaResult = cudaMalloc((void **)&data, 125000 * sizeof(double));
for (unsigned int i = 0; i <= 1000000 ; i++)
{
curandResult = curandGenerateNormalDouble(gen, data, 125000, mean, stddev);
}
- CUDA toolkit release version
V3.2
V3.2
- Compiler for CPU host code
Visual C++ from Visual Studio 2008
- System description including:
CPU type: I7
system RAM: 12G
video cards: GTX 295
Thanks
Yu
Crankie
3
Try this on another GPU with more memory. I don’t think it’s a timeout problem.
Crankie
4
Try this on another GPU with more memory. I don’t think it’s a timeout problem.