OpenCL异构计算资料收集

如果你对python熟，可以用 PyOpenCL, 兼顾 host 端的简洁与 device 端的高效。
kernel 函数可以写在单独的 *.cl 文件里， 一句 python 命令就可以 load + build:
 prg_src = open( 'kernel_test1.cl', 'r').read()
 prg = cl.Program(ctx, prg_src).build()

 #!/usr/bin/env python

 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_ONLY | mf.COPY_HOST_PTR, hostbuf=a_np)
 b_g = cl.Buffer(ctx, mf.READ_ONLY | mf.COPY_HOST_PTR, hostbuf=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, 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(res_np - (a_np + b_np))
 print(np.linalg.norm(res_np - (a_np + b_np)))