《CUDA By Example》【Chapter 04】CUDA C 并行编程

概述

GPU计算的应用前景在很大程度上取决于能否从很多问题中发掘出大规模并行性。
本章介绍如何启动并行执行的设备核函数。

矢量求和（基于CPU和GPU）

add_loop_cpu.cu

#include "../common/book.h"

#define N   10

void add( int *a, int *b, int *c ) {
    int tid = 0;    // this is CPU zero, so we start at zero
    while (tid < N) {
        c[tid] = a[tid] + b[tid];
        tid += 1;   // we have one CPU, so we increment by one
    }
}

int main( void ) {
    int a[N], b[N], c[N];

    // fill the arrays 'a' and 'b' on the CPU
    for (int i=0; i<N; i++) {
        a[i] = -i;
        b[i] = i * i;
    }

    add( a, b, c );

    // display the results
    for (int i=0; i<N; i++) {
        printf( "%d + %d = %d\n", a[i], b[i], c[i] );
    }

    return 0;
}

add_loop_gpu.cu

#include "../common/book.h"

#define N   10

__global__ void add( int *a, int *b, int *c ) {
    int tid = blockIdx.x;    // this thread handles the data at its thread id
    if (tid < N)//在核函数内部检查下标，避免内存访问越界；
        c[tid] = a[tid] + b[tid];
}

int main(