NVIDIA高性能计算——基于共享内存的线程同步

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

#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include "device_functions.h"
//#include "GL/GLU.h"
//#include "GL/glut.h"

#define DIM 1024
#define PI 3.1415926535897932f

__global__ void kernel( unsigned char *ptr ) {
    // map from threadIdx/BlockIdx to pixel position
    int x = threadIdx.x + blockIdx.x * blockDim.x;
    int y = threadIdx.y + blockIdx.y * blockDim.y;
    int offset = x + y * blockDim.x * gridDim.x;

    __shared__ float    shared[16][16];

    // now calculate the value at that position
    const float period = 128.0f;

    shared[threadIdx.x][threadIdx.y] =
            255 * (sinf(x*2.0f*PI/ period) + 1.0f) *
                  (sinf(y*2.0f*PI/ period) + 1.0f) / 4.0f;


    __syncthreads();

	ptr[offset*4 + 0] = 0;
	ptr[offset*4 &