spmv_csr_scalar_kernel(const int num_rows , const int * ptr , const int * indices , const float * data , const float * x, float * y) { int row = get_global_id(0); if(row < num_rows) { float dot = 0; int row_start = ptr[row]; int row_end = ptr[row+1]; for (int jj = row_start; jj < row_end; jj++) { dot += data[jj] * x[indices[jj]]; } y[row] += dot; } } Above is the Open Cl code for multiplying a sparse matrix in CSR format with a Column vector.It uses one global work item per for loop.Can anybody help me in using two work items in each for loop.I am new to open cl and get a lot of issues if I modify even the smallest thing.Please help me.This a part of my project.I made it this parallel but I wanna make it more parallel.Please help me if you can.plzzzz A single work item executes the for loop from row_start to row_end.I want that this row or for loop is further divided into two parts each executed by a single work item.How do I go on accomplishing that? This is what I could come up with but its returning the wrong output.plzz help __kernel void mykernel(__global int* colvector,__global int* val,__global int* result,__global int* index,__global int* rowptr,__global int* sync) { __global int vals[8]={0,0,0,0,0,0,0,0}; for(int i=0;i<4;i++) { result[i]=0; } barrier(CLK_GLOBAL_MEM_FENCE); int thread_id=get_global_id(0); int warp_id=thread_id/2; int lane=(thread_id)&1; int row=warp_id; if(row<4) { int row_start = rowptr[row]; int row_end = rowptr[row+1]; vals[thread_id]=0; for (int i = row_start+lane; i<row_end; i+=2) { vals[thread_id]+=val[i]*colvector[index[i]]; } vals[thread_id]+=vals[thread_id+1]; if(lane==0){ result[row] += vals[thread_id]; } } }