c++ - OpenCL 在调用 clGetPlatformIDs 时返回 -64

Question

编辑:错误代码如下

CL_INVALID_PROPERTY if context property name in properties is not a 
supported property name, if the value specified for a supported property 
name is not valid, or if the same property name is specified more than once.
However if the extension cl_khr_gl_sharing is enabled, then 
CL_INVALID_PROPERTY is returned if an attribute name other than those listed
in the table for properties above is specified in properties.

我正在使用 MinGW (x86) 和 x86 AMD OpenCL 库，以下代码在最终检查后返回 NULL:

cl_context CreateContext()
{
     cl_int errNum;
     cl_uint numPlatforms;
     cl_platform_id firstPlatformID;
     cl_context context=NULL;
     //Select an OpenCL platform

     errNum=clGetPlatformIDs(1, &firstPlatformID, &numPlatforms);
     if (errNum!=CL_SUCCESS||numPlatforms<=0)
     {
        cerr<<"Failed to find any OpenCL platforms."<<endl;
        return NULL;
     }

     cl_context_properties contextProperties[]=
     {
        CL_CONTEXT_PLATFORM,
        (cl_context_properties) firstPlatformID,
     };
     context=clCreateContextFromType(contextProperties, CL_DEVICE_TYPE_GPU, NULL, NULL, &errNum);
     cout << errNum << endl;
     if (errNum!=CL_SUCCESS)
     {
         cerr<<"Failed to create an OpenCL GPU context, trying CPU."<<endl;
         context=clCreateContextFromType(contextProperties,CL_DEVICE_TYPE_CPU, NULL, NULL, &errNum);

         if (errNum!=CL_SUCCESS)
         {
            cerr<<"Failed to create an OpenCL GPU or CPU context."<<endl;
            return NULL;
         }
     }
     return context;
}

它检测到 2 个平台(intel cpu、AMD gpu)，但无法创建上下文。 x64 库做同样的事情。有人知道怎么解决吗？

Answer 1

根据 clCreateContext 的文档您必须用零终止 cl_context_properties 列表。

通过以下更改代码适用于我:

cl_context_properties contextProperties[] =
{
    CL_CONTEXT_PLATFORM,
    (cl_context_properties)firstPlatformID, 
    0
};