在GPU上提前

我试图使用OpenCL作为我提前编译的目标。在我的Halide内核中，我有一个名为norm的函数，我这样编译:

...
 // Start with a default target
Target target = get_host_target();
// Set opencl
target.set_feature(Target::OpenCL);
// Compile
std::vector<Argument> args1(2);
args1[0] = input;
args1[1] = n;
norm.compile_to_file("norm", args1, target);

g++ -o mavg kernel.cpp -I /opt/intel/intel-opencl-1.2-5.0.0.43/opencl-1.2-sdk-5.0.0.43/include -I Halide/include -L Halide/lib -lHalide -lOpenCL

然后我有一个自动生成的(Python)库包装器，它调用我编译的内核:

#include <stdio.h>
#include <CL/cl.h>
#include <stdlib.h>
#include "norm.h"
#if defined(WIN32) || defined(_WIN32) || defined(__WIN32)
    #define LIBRARY_API extern "C" __declspec(dllexport)
#else
    #define LIBRARY_API extern "C"
#endif
// Compiled with the following values
// float* arg0 (float32) arg0 = <numpy.core._internal._ctypes object at 0x7f8b5e54a790>
// int arg1 (<type 'int'>) arg1 = c_int(5)
// float* arg2 (float32) arg2 = <numpy.core._internal._ctypes object at 0x7f8b5e54a690>
// int arg0_h (<type 'int'>) arg0_h = c_int(768)
// int arg0_w (<type 'int'>) arg0_w = c_int(1024)
// int arg0_nd (<type 'int'>) arg0_nd = c_int(3)
// int arg0_n (<type 'int'>) arg0_n = c_int(1)
// int arg2_h (<type 'int'>) arg2_h = c_int(768)
// int arg2_w (<type 'int'>) arg2_w = c_int(1024)
// int arg2_nd (<type 'int'>) arg2_nd = c_int(3)
// int arg2_n (<type 'int'>) arg2_n = c_int(1)
LIBRARY_API int run(float* arg0, int arg1, 
                    float* arg2, int arg0_h, int arg0_w, int arg0_nd, int arg0_n, int arg2_h, int arg2_w, int arg2_nd, int arg2_n)
{
    buffer_t buf_arg0 = {0};
    buf_arg0.extent[0] = arg0_w; // buffer width
    buf_arg0.extent[1] = arg0_h; // buffer height
    buf_arg0.extent[2] = 3; // buffer depth
    buf_arg0.stride[0] = 1;  // spacing in memory between adjacent values of x
    buf_arg0.stride[1] = arg0_w; // spacing in memory between adjacent values of y
    buf_arg0.stride[2] = arg0_w*arg0_h; // buffer depth
    buf_arg0.elem_size = arg0_n * sizeof(float); // bytes per element
    buf_arg0.host = (uint8_t*) arg0; // host buffer
    buffer_t buf_arg2 = {0};
    buf_arg2.extent[0] = arg2_w; // buffer width
    buf_arg2.extent[1] = arg2_h; // buffer height
    buf_arg2.extent[2] = 3; // buffer depth
    buf_arg2.stride[0] = 1;  // spacing in memory between adjacent values of x
    buf_arg2.stride[1] = arg2_w; // spacing in memory between adjacent values of y
    buf_arg2.stride[2] = arg2_w*arg2_h; // buffer depth
    buf_arg2.elem_size = arg2_n * sizeof(float); // bytes per element
    buf_arg2.host = (uint8_t*) arg2; // host buffer
    norm(&buf_arg0, arg1, &buf_arg2);
    return 0;
}

然后得到

undefined symbol: clBuildProgram

当我试图调用我的库使用ctypes在Python。是否支持OpenCL AOT编译，如果是，知道问题可能是什么吗?

谢谢。