#include<cuda.h>
#include<cuda_runtime.h>
#include<time.h>
using namespace std;
const int N=500;
__global__ void test(int* a,int n)
{
const int tid=blockIdx.x*blockDim.x+threadIdx.x;
int i=blockDim.x*gridDim.x*n+tid;
if(i<N)
{
if(a[i]<200)
{
printf("%d--1 ",a[i]);
}
if(a[i]<400&&a[i]>=200)
{
printf("%d--2 ",a[i]);
}
if(a[i]<600&&a[i]>=400)
{
printf("%d--3 ",a[i]);
}
if(a[i]<800&&a[i]>=600)
{
printf("%d--4 ",a[i]);
}
if(a[i]<1000&&a[i]>=800)
{
printf("%d--5 ",a[i]);
}
__syncthreads();
}
}
int main(void)
{
int a[N],*da;
cudaMalloc((void**)&da,N*sizeof(int));
srand(time(NULL));
for(int i=0;i<N;i++)
{
a[i]=rand()%1000;
cout<<a[i]<<" ";
}
cout<<endl<<endl<<endl;
cudaMemcpy(da,a,N*sizeof(int),cudaMemcpyHostToDevice);
for(int i=0;i<4;i++)
{
test<<<5,32>>>(da,i);
cudaDeviceSynchronize();
cout<<endl<<endl<<endl;
for(int z=0;z<100000000;z++)
;
}
return 0;
}
#include<iostream>
#include<cuda.h>
#include<cuda_runtime.h>
#include<time.h>
using namespace std;
const int N=500;
__global__ void test(int* a,int n)
{
const int tid=blockIdx.x*blockDim.x+threadIdx.x;
int i=blockDim.x*gridDim.x*n+tid;
if(i<N)
{
if(a[i]<200)
{
printf("%d--1 ",a[i]);
}
else
{
if(a[i]<400&&a[i]>=200)
printf("%d--2 ",a[i]);
else
{
if(a[i]<600&&a[i]>=400)
printf("%d--3 ",a[i]);
else
{
if(a[i]<800&&a[i]>=600)
printf("%d--4 ",a[i]);
else//(a[i]<1000&&a[i]>=800)
{
printf("%d--5 ",a[i]);
}
}
}
}
__syncthreads();
//if(tid==0)
// printf("\n------------ ");
}
}
int main(void)
{
int a[N],*da;
cudaMalloc((void**)&da,N*sizeof(int));
srand(time(NULL));
for(int i=0;i<N;i++)
{
a[i]=rand()%1000;
cout<<a[i]<<" ";
}
cout<<endl<<endl<<endl;
cudaMemcpy(da,a,N*sizeof(int),cudaMemcpyHostToDevice);
for(int i=0;i<4;i++)
{
test<<<5,32>>>(da,i);
cudaDeviceSynchronize();
cout<<endl<<endl<<endl;
for(int z=0;z<100000000;z++)
;
}
return 0;
}