gistfile1.py

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

import numpy as np
import pyopencl as cl
from mako.template import Template

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_ONLY | mf.COPY_HOST_PTR, hostbuf=a_np)
b_g = cl.Buffer(ctx, mf.READ_ONLY | mf.COPY_HOST_PTR, hostbuf=b_np)


class Parameters:
    loops = 2
    factor = 3

parameters = Parameters()


tmpl = Template("""
__kernel void sum(__global const float *a_g, __global const float *b_g, __global float *res_g) {
  int gid = get_global_id(0);
  float a = a_g[gid];
  float b = b_g[gid];

  %for i in range(parameters.loops):
  a += b * ${parameters.factor};
  %endfor

  res_g[gid] = a;
}
""")

src = tmpl.render(parameters=parameters)

prg = cl.Program(ctx, src).build()

res_g = cl.Buffer(ctx, mf.WRITE_ONLY, a_np.nbytes)
prg.sum(queue, a_np.shape, None, a_g, b_g, res_g)

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

# Check on CPU with Numpy:
print(np.allclose(res_np, a_np + b_np * parameters.factor * parameters.loops))