PyOpenCL how to modify a matrix locally within the kernel function - python-3.x

Question

I am trying to modify a matrix (Pbis) locally within a pyOpenCL kernel function and when filling up this matrix with 0 it alters the result matrix R. When executing this code we obtain weird values in the R matrix. It is probably due to memory allocation but we cannot figure out how to fix it. Normally R should be exclusively composed of the init value.
program = cl.Program(context, """
__kernel void generate_paths(__global float *P, ushort const n,
ushort N, ushort init, __global float *R){
int i = get_global_id(0);
__private float* Pbis;
for (int k=0; k<n; k++){
Pbis[k] = 0;
}
for (int j=0; j<n; j++)
{
R[i*(n+1) + j] = init;
}
R[i*(n+1) + n] = init;
}
""").build()
The parameters for the generation are:
program.generate_paths(queue, res_np.shape, None, P_buf, np.uint16(n), np.uint16(N), np.uint16(init), res_buf)
Here is the entire code for reproducibility:
import numpy as np
import pyopencl as cl
import numpy.linalg as la
import os
os.environ['PYOPENCL_COMPILER_OUTPUT'] = '1'
os.environ['PYOPENCL_CTX'] = '1'
(n, N) = (3,6)
U = np.random.uniform(0,1, size=(n+1)*N)
U = U.astype(np.float32)
P = np.matrix([[0, 1/3, 1/3, 1/3], [1/3, 0, 1/3, 1/3], [1/3, 1/3, 0, 1/3], [1/3, 1/3, 1/3, 0]])
P = P.astype(np.float32)
res_np = np.zeros((N, n+1),dtype = np.float32)
platform = cl.get_platforms()[0]
device = platform.get_devices()[0]
context = cl.Context([device])
queue = cl.CommandQueue(context)
mf = cl.mem_flags
U_buf = cl.Buffer(context, mf.COPY_HOST_PTR | mf.COPY_HOST_PTR, hostbuf=U)
P_buf = cl.Buffer(context, mf.COPY_HOST_PTR | mf.COPY_HOST_PTR, hostbuf=P)
res_buf = cl.Buffer(context, mf.WRITE_ONLY, res_np.nbytes)
init = 0
program = cl.Program(context, """
__kernel void generate_paths(__global const float *U, __global float *P, ushort const n,
ushort N, ushort init, __global float *R){
int i = get_global_id(0);
int current = init;
__private float* Pbis;
for (int k=0; k<n; k++){
Pbis[k] = 0;
}
for (int j=0; j<n; j++)
{
R[i*(n+1) + j] = current;
}
R[i*(n+1) + n] = init;
}
""").build()
#prg.multiply(queue, c.shape, None,
# np.uint16(n), np.uint16(m), np.uint16(p),
# a_buf, b_buf, c_buf)
# a_mul_b = np.empty_like(c)
# cl.enqueue_copy(queue, a_mul_b, c_buf)
program.generate_paths(queue, res_np.shape, None, U_buf, P_buf, np.uint16(n), np.uint16(N), np.uint16(init), res_buf)
chem_gen = np.empty_like(res_np)
cl.enqueue_copy(queue, chem_gen, res_buf)
print("Platform Selected = %s" %platform.name)
print("Device Selected = %s" %device.name)
print("Generated Paths:")
print (chem_gen)