Answer to Question #196301 in C++ for Jordan

Question

 Write a program using OpenCL to do the following: Host code. O Create two STL vectors, named vecl and vec2. Initialise their contents as follows: vecl: A vector of ints that contains 32 elements. Initialise the elements with random values between 10 and 20. vec2: A vector of ints that contains 16 elements. Initialise the first half of the vector with values from 2 to 9 and the second half with values from -9 to -2. Create and initialise the necessary memory objects to pass vecl and vec2 as input to the kernel, and another memory object for kernel output. o Enqueue the kernel such that each work-item will process 8-elements from vecl, respectively, i.e. work-item 1 will refer to elements 0-7, work-item 2 will refer to elements 8-15, etc. After kernel execution, obtain the output from the kernel and display the results on O o screen. 

Answer 1

int in_vec_size = 100;
int out_vec_size = 100;

vector<vector<float>> in_vec(10,vector<float>(10));
vector<vector<float>> out_vec(10, vector<float>(10));
int k = 0;

//initialize the input vec
for (int i=0; i < 10;i++)
{
    for (int j = 0; j < 10;j++)
    {
        in_vec[i][j] = k++;
        out_vec[i][j] = 0;
    }
}

//creating bufferes
cl::Buffer inBuff(context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR, in_vec_size*4, &in_vec[0][0]);
cl::Buffer outBuff(context, CL_MEM_WRITE_ONLY, out_vec_size*4, NULL);

//set kernal args
kernal.setArg(0, inBuff);
kernal.setArg(1, outBuff);
kernal.setArg(2, in_vec_size);

cl::CommandQueue queue(context, devices_gpu[0]);

queue.enqueueTask(kernal);
queue.enqueueWriteBuffer(inBuff, CL_TRUE, 0, in_vec_size*4, &in_vec[0][0]);
queue.enqueueReadBuffer(outBuff, CL_TRUE, 0, out_vec_size*4, &out_vec[0][0]);

for (int i = 0; i < 10; i++)
{
    for (int j = 0; j < 10; j++)
    {
        cout << out_vec[i][j] << endl;
    }
}

__kernel void add(__global float*in,__global float*out,int x) 
{
   // i=get_global_id(0);
   for(int i=0;i<x;i++)
   {
      out[i] = in[i]+10;
   }
}