#!/usr/bin/env python
# -*- coding: utf-8 -*-

from __future__ import absolute_import, print_function
import numpy as np
import pyopencl as cl

a_np = np.random.rand(50000).astype(np.float32)
b_np = np.random.rand(50000).astype(np.float32)

ctx = cl.create_some_context()
queue = cl.CommandQueue(ctx)

mf = cl.mem_flags
a_g = cl.Buffer(ctx, mf.READ_WRITE, a_np.nbytes)
b_g = cl.Buffer(ctx, mf.READ_WRITE, b_np.nbytes)

cl.enqueue_copy(queue, a_g, a_np)
cl.enqueue_copy(queue, b_g, b_np)

prg = cl.Program(ctx, """
__kernel void sum(
    __global const float *a_g, __global const float *b_g, __global float *res_g)
{
  int gid = get_global_id(0);
  res_g[gid] = a_g[gid] + b_g[gid];
}
""").build()

res_g = cl.Buffer(ctx, mf.WRITE_ONLY, a_np.nbytes)
prg.sum(queue, (500, 10), (16, 16), a_g, b_g, res_g, g_times_l=True)

res_np = np.empty_like(a_np)
cl.enqueue_copy(queue, res_np, res_g)

# Check on CPU with Numpy:
print(res_np - (a_np + b_np))
print(np.linalg.norm(res_np - (a_np + b_np)))