Mersenne Twister giving bad uniform then bad Normal Distribution

I test the SDK examples Mersenne Twister (oclMersenneTwister)
If i compute the mean and standard deviation of the random number (N(0,1)) after the Box Muller, for example the first 4096 random numbers, i have a very poor mean 0.2 and a very poor std deviation 1.58, even with all the random numbers (2000000) the mean and std are not very well (0.0001 and 0.97…) (same problem with the CUDA example)
However, if i take the mersenne twister SDK of AMD and i run it on my CPU, the N(0,1) numbers are quite good compare to the SDK example of NVIDIA
It’s a problem of initialization of the data of the mersenne Twister algorithm.
Do you have a fix for this SDK examples ?