《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( void ) {
    int a[N], b[N], c[N];
    int *dev_a, *dev_b, *dev_c;

    // allocate the memory on the GPU
    HANDLE_ERROR( cudaMalloc( (void**)&dev_a, N * sizeof(int) ) );
    HANDLE_ERROR( cudaMalloc( (void**)&dev_b, N * sizeof(int) ) );
    HANDLE_ERROR( cudaMalloc( (void**)&dev_c, N * sizeof(int) ) );

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

    // copy the arrays 'a' and 'b' to the GPU
    HANDLE_ERROR( cudaMemcpy( dev_a, a, N * sizeof(int),
                              cudaMemcpyHostToDevice ) );
    HANDLE_ERROR( cudaMemcpy( dev_b, b, N * sizeof(int),
                              cudaMemcpyHostToDevice ) );

    add<<<N,1>>>( dev_a, dev_b, dev_c );
    //第一个参数，表示设备执行核函数时运行的并行线程的数量；
    //每一个并行执行环境称为线程块(Block)，有N个线程块；
    //并行线程块称为*线程格(Grid)*,这里为需要一维线程格，共N个线程块；

    // copy the array 'c' back from the GPU to the CPU
    HANDLE_ERROR( cudaMemcpy( c, dev_c, N * sizeof(int),
                              cudaMemcpyDeviceToHost ) );

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

    // free the memory allocated on the GPU
    HANDLE_ERROR( cudaFree( dev_a ) );
    //避免内存泄漏，使用cudaFree()释放内存；
    HANDLE_ERROR( cudaFree( dev_b ) );
    HANDLE_ERROR( cudaFree( dev_c ) );

    return 0;
}

绘制Julia集曲线（CPU&GPU）

julia_cpu.cu

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

#define DIM 1000

struct cuComplex {
    float   r;
    float   i;
    cuComplex( float a, float b ) : r(a), i(b)  {}
    float magnitude2( void ) { return r * r + i * i; }
    cuComplex operator*(const cuComplex& a) {
        return cuComplex(r*a.r - i*a.i, i*a.r + r*a.i);
    }
    cuComplex operator+(const cuComplex& a) {
        return cuComplex(r+a.r, i+a.i);
    }
};

int julia( int x, int y ) { 
    const float scale = 1.5;
    float jx = scale * (float)(DIM/2 - x)/(DIM/2);
    float jy = scale * (float)(DIM/2 - y)/(DIM/2);

    cuComplex c(-0.8, 0.156);
    cuComplex a(jx, jy);

    int i = 0;
    for (i=0; i<200; i++) {
        a = a * a + c;
        if (a.magnitude2() > 1000)
            return 0;
    }

    return 1;
}

void kernel( unsigned char *ptr ){
    for (int y=0; y<DIM; y++) {
        for (int x=0; x<DIM; x++) {
            int offset = x + y * DIM;

            int juliaValue = julia( x, y );
            ptr[offset*4 + 0] = 255 * juliaValue;
            ptr[offset*4 + 1] = 0;
            ptr[offset*4 + 2] = 0;
            ptr[offset*4 + 3] = 255;
        }
    }
 }

int main( void ) {
    CPUBitmap bitmap( DIM, DIM );
    unsigned char *ptr = bitmap.get_ptr();

    kernel( ptr );

    bitmap.display_and_exit();
}

julia_gpu.cu

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

#define DIM 1000

struct cuComplex {
    float   r;
    float   i;
    cuComplex( float a, float b ) : r(a), i(b)  {}
    __device__ float magnitude2( void ) {
        return r * r + i * i;
    }
    __device__ cuComplex operator*(const cuComplex& a) {
        return cuComplex(r*a.r - i*a.i, i*a.r + r*a.i);
    }
    __device__ cuComplex operator+(const cuComplex& a) {
        return cuComplex(r+a.r, i+a.i);
    }
};

__device__ int julia( int x, int y ) {
    const float scale = 1.5;
    float jx = scale * (float)(DIM/2 - x)/(DIM/2);
    float jy = scale * (float)(DIM/2 - y)/(DIM/2);

    cuComplex c(-0.8, 0.156);
    cuComplex a(jx, jy);

    int i = 0;
    for (i=0; i<200; i++) {
        a = a * a + c;
        if (a.magnitude2() > 1000)
            return 0;
    }

    return 1;
}

__global__ void kernel( unsigned char *ptr ) {
    // map from blockIdx to pixel position
    int x = blockIdx.x;
    int y = blockIdx.y;
    //二维线程格的x，y参数使用方式；
    int offset = x + y * gridDim.x;

    // now calculate the value at that position
    int juliaValue = julia( x, y );
    ptr[offset*4 + 0] = 255 * juliaValue;
    ptr[offset*4 + 1] = 0;
    ptr[offset*4 + 2] = 0;
    ptr[offset*4 + 3] = 255;
}

// globals needed by the update routine
struct DataBlock {
    unsigned char   *dev_bitmap;
};

int main( void ) {
    DataBlock   data;
    CPUBitmap bitmap( DIM, DIM, &data );
    unsigned char    *dev_bitmap;

    HANDLE_ERROR( cudaMalloc( (void**)&dev_bitmap, bitmap.image_size() ) );
    data.dev_bitmap = dev_bitmap;

    dim3    grid(DIM,DIM);//二维的线程格；
    //dim3是一个三维数组，明明需要的是二维的线程格：因为CUDA以后会支持三维线程格，现在默认第三维永远为1，等价于二维；
    kernel<<<grid,1>>>( dev_bitmap );

    HANDLE_ERROR( cudaMemcpy( bitmap.get_ptr(), dev_bitmap,
                              bitmap.image_size(),
                              cudaMemcpyDeviceToHost ) );

    HANDLE_ERROR( cudaFree( dev_bitmap ) );

    bitmap.display_and_exit();
}