import numpy as np
import pyopencl as cl
import pyopencl.array as cl_array


deviceID = 0
platformID = 0
workGroup=(1,1)

N = 10
testData = np.zeros(N, dtype=cl_array.vec.float4)

dev = cl.get_platforms()[platformID].get_devices()[deviceID]

ctx = cl.Context([dev])
queue = cl.CommandQueue(ctx)
mf = cl.mem_flags
Data_In = cl.Buffer(ctx, mf.READ_WRITE, testData.nbytes)


prg = cl.Program(ctx, """

__kernel void   Pack_Cmplx( __global float4* Data_In, int  N)
{
  int gid = get_global_id(0);

  Data_In[gid] = 1;
}
 """).build()

prg.Pack_Cmplx(queue, (N,1), workGroup, Data_In, np.int32(N))
cl.enqueue_copy(queue, testData, Data_In)


print testData