import pycuda.driver as cuda
import pycuda.autoinit
from pycuda.compiler import SourceModule
import numpy
a = numpy.random.randn(4,4)
a = a.astype(numpy.float32)
a_gpu = cuda.mem_alloc(a.nbytes)
cuda.memcpy_htod(a_gpu,a)

mod = SourceModule("""
__global__ void doublify(float *a)
{
int idx = threadIdx.x + threadIdx.y * 4;
a[idx] *= 2;
}
""")

import os
os.system("vcvarsamd64.bat")

import pycuda.gpuarray as gpuarray
import pycuda.driver as cuda
import pycuda.autoinit
import numpy
a_gpu = gpuarray.to_gpu(numpy.random.randn(4, 4))
print "a_gpu ="
print a_gpu
a_doubled = (2*a_gpu).get()
print
print "a_doubled ="
print a_doubled

COMPILER-BINDIR = C:Program Files (x86)Microsoft Visual Studio 10.0VCbinamd64