在设备上调用 printf() 的不完整输出

My gpu is GeForce GTX 550i, with compute capability 2.1

我的代码:

#include<stdio.h>
#include<stdlib.h>
#define N 4096

__global__ void Printcell(float *d_Array , int n){
    int k = 0;

    printf("
=========== data of d_Array on device==============
");
    for( k = 0; k < n; k++ ){
        printf("%f  ", d_Array[k]);
        if((k+1)%6 == 0) printf("
");
    }
    printf("

Totally %d elements has been printed", k);
}

int main(){

    int i =0;

    float Array[N] = {0}, rArray[N] = {0};
    float *d_Array;
    for(i=0;i<N;i++)
        Array[i] = i;


    cudaMalloc((void**)&d_Array, N*sizeof(float));
    cudaMemcpy(d_Array, Array, N*sizeof(float), cudaMemcpyHostToDevice);
    cudaDeviceSynchronize();
    Printcell<<<1,1>>>(d_Array, N);    //Print the device array by a kernel
    cudaDeviceSynchronize();

    /* Copy the device array back to host to see if it was correctly copied */   
    cudaMemcpy(rArray, d_Array, N*sizeof(float), cudaMemcpyDeviceToHost);

    printf("

");

    for(i=0;i<N;i++){
        printf("%f  ", rArray[i]);
        if((i+1)%6 == 0) printf("
");
    }
}

推荐答案

来自设备的 printf 队列有限.它适用于小规模调试式输出，而不是大规模输出.