CUDA内核调用的参数超过256字节的想法 [英] Ideas for CUDA kernel calls with parameters exceeding 256 bytes

问题描述

我有两个结构，总计超过256个字节的大小允许作为参数传递到内核调用。

这两个结构已经被分配和复制

1）如何在这些结构的同一内核中使用，而不作为参数传递？

更多详情。单独地，这些结构可以作为参数传递。例如，在不同的内核中。但是：

2）如何在同一个内核中使用这两个结构？

解决方案

正如罗伯特·克罗维拉在他的评论中建议的，你应该能够传递一个指针到这些区域。
我在opencl中也有类似的问题
这是我如何实现struct：

（我的内核和主机函数都在opencl，

以下两个在我的Mapper.c - >主机函数中定义

p>

  typedef struct data 
 {
 double dattr [10]; 
 int d_id; 
 int bestCent; 
} Data; 
 
 
 typedef struct cent 
 {
 double cattr [5]; 
 int c_id; 
} Cent; 
 
 Data * dataNode; 
 Cent * centNode; 
  

在设备的全局内存上分配内存后，我传输了数据。
我必须在我的其他内核函数中重新定义结构体定义，如下所示：

mapper.cl：

  #pragma OPENCL EXTENSION cl_khr_fp64：enable 
 typedef struct data 
 {
 double dattr [10]; 
 int d_id; 
 int bestCent; 
} Data; 
 
 
 typedef struct cent 
 {
 double cattr [5]; 
 int c_id; 
} Cent; 
 
 __kernel void mapper（__ global int * keyMobj，__global int * valueMobj，__ global Data * dataMobj，__ global Cent * centMobj）
 {
 int i = get_global_id（0）; 
 int j，k，color = 0; 
 double dmin = 1000000.0，dx; 
 for（j = 0; j <2; j ++）//这里2是考虑的质心数量
 {
 dx = 0.0; 
 for（k = 0; k <2; k ++）
 {
 dx + =（（centMobj [j] .cattr [k]） - （dataMobj [i] .dattr [k] ））*（（centMobj [j] .cattr [k]） - （dataMobj [i] .dattr [k]）） 
} 
 if（dx  {color = j; 
 dmin = dx; 
} 
} 
 keyMobj [i] = color; 
 valueMobj [i] = dataMobj [i]。d_id; 
 
} 
  

你可以看到我只传递了指向这些区域的指针.. ie keyMobj和valueMobj。

  kernel = clCreateKernel（program，mapper，& ret）; 
 ret = clSetKernelArg（kernel，0，sizeof（cl_mem），（void *）& keyMobj）; 
 ret = clSetKernelArg（kernel，1，sizeof（cl_mem），（void *）& valueMobj）; 
 ret = clSetKernelArg（kernel，2，sizeof（cl_mem），（void *）& dataMobj）; 
 ret = clSetKernelArg（kernel，3，sizeof（cl_mem），（void *）& centMobj）; 
 

上面的代码行属于主机端函数（mapper.c），它创建内核函数.cl）..接下来的4行（clSetKernelArg ..）将参数传递给内核函数。

I have a couple of structures that summed up exceed the 256 bytes size allowed to be passed as parameters in a kernel call.

Both structures are already allocated and copied to device global memory.

1) How can I make use in the same kernel of these structures without being passed as parameters?

More details. Separately, these structures can be passed as parameters. For example, in different kernels. But:

2) How can I use both structures in the same kernel?

解决方案

As Robert Crovella suggested in his comment, you should just be able to pass a pointer to those areas. I have had similar problem in opencl.. This is how I implemented the struct:

(My kernel and host functions are in opencl, syntax can be the issue for you..but the context is same.!)

Following two are defined in my 'Mapper.c'--> Host function

typedef struct data
{
  double dattr[10];
  int d_id;
  int bestCent;
}Data;


typedef struct cent
{
  double cattr[5];
  int c_id;
}Cent;

Data *dataNode;
Cent *centNode;

After allocating memory on Device's global memory, I transferred the data. I had to redefine the struct definitions in my other kernel function as below:

mapper.cl:

#pragma OPENCL EXTENSION cl_khr_fp64 : enable
typedef struct data
{
  double dattr[10];
  int d_id;
  int bestCent;
}Data;


typedef struct cent
{
  double cattr[5];
  int c_id;
}Cent;

__kernel void mapper(__global int *keyMobj, __global int *valueMobj,__global Data *dataMobj,__global Cent *centMobj)
{
    int i= get_global_id(0);
    int j,k,color=0;
    double dmin=1000000.0, dx;
    for(j=0; j<2; j++)      //here 2 is number of centroids considered
     {
        dx = 0.0;
        for(k=0; k<2; k++)
        {
           dx+= ((centMobj[j].cattr[k])-(dataMobj[i].dattr[k])) * ((centMobj[j].cattr[k])-(dataMobj[i].dattr[k]));
        }  
        if(dx<dmin)            
        {  color = j;   
           dmin = dx;
        }
     }  
     keyMobj[i] = color;
     valueMobj[i] = dataMobj[i].d_id;

}

You can see that I have passed only pointer to those areas.. i.e. keyMobj and valueMobj.

kernel = clCreateKernel(program, "mapper", &ret);
ret = clSetKernelArg(kernel, 0, sizeof(cl_mem), (void *)&keyMobj);
ret = clSetKernelArg(kernel, 1, sizeof(cl_mem), (void *)&valueMobj);
ret = clSetKernelArg(kernel, 2, sizeof(cl_mem), (void *)&dataMobj);
ret = clSetKernelArg(kernel, 3, sizeof(cl_mem), (void *)&centMobj);

Above lines of code is belongs to host side function(mapper.c) which creates kernel function(mapper.cl)..and next 4 lines (clSetKernelArg..) passes the arguments to the kernel function.

这篇关于CUDA内核调用的参数超过256字节的想法的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！