cuda 学习笔记

 1#include <iostream>
 2#include <math.h>
 3
 4// function to add the elements of two arrays
 5void add(int n, float *x, float *y)
 6{
 7  for (int i = 0; i < n; i++)
 8      y[i] = x[i] + y[i];
 9}
10
11int main(void)
12{
13  int N = 1<<20; // 1M elements
14
15  float *x = new float[N];
16  float *y = new float[N];
17
18  // initialize x and y arrays on the host
19  for (int i = 0; i < N; i++) {
20    x[i] = 1.0f;
21    y[i] = 2.0f;
22  }

 1#include <iostream>
 2#include <math.h>
 3// Kernel function to add the elements of two arrays
 4__global__
 5void add(int n, float *x, float *y)
 6{
 7  for (int i = 0; i < n; i++)
 8    y[i] = x[i] + y[i];
 9}
10
11int main(void)
12{
13  int N = 1<<20;
14  float *x, *y;
15
16  // Allocate Unified Memory – accessible from CPU or GPU
17  cudaMallocManaged(&x, N*sizeof(float));
18  cudaMallocManaged(&y, N*sizeof(float));
19
20  // initialize x and y arrays on the host
21  for (int i = 0; i < N; i++) {
22    x[i] = 1.0f;
23    y[i] = 2.0f;
24  }
25
26  // Run kernel on 1M elements on the GPU
27  add<<<1, 1>>>(N, x, y);
28
29  // Wait for GPU to finish before accessing on host
30  cudaDeviceSynchronize();
31
32  // Check for errors (all values should be 3.0f)
33  float maxError = 0.0f;
34  for (int i = 0; i < N; i++)
35    maxError = fmax(maxError, fabs(y[i]-3.0f));
36  std::cout << "Max error: " << maxError << std::endl;
37
38  // Free memory
39  cudaFree(x);
40  cudaFree(y);
41
42  return 0;
43}

 1#include <cstdio>
 2#include <iostream>
 3#include <math.h>
 4// Kernel function to add the elements of two arrays
 5__global__
 6void add(int n, float *x, float *y)
 7{
 8    int index = blockIdx.x * blockDim.x + threadIdx.x;
 9    int stride = blockDim.x * gridDim.x;
10    printf(" %d %d",index,stride);
11    for ( int i = index ; i < n ; i += stride)
12        y[i] = x[i] + y[i];
13}
14
15int main(void)
16{
17    int N = 1<<20;
18    float *x, *y;
19
20    // Allocate Unified Memory – accessible from CPU or GPU
21    cudaMallocManaged(&x, N*sizeof(float));
22    cudaMallocManaged(&y, N*sizeof(float));
23
24    // initialize x and y arrays on the host
25    for (int i = 0; i < N; i++) {
26        x[i] = 1.0f;
27        y[i] = 2.0f;
28    }
29
30
31    int blockSize = 256;
32    int numBlocks = (N + blockSize - 1) / blockSize;
33    add<<<numBlocks, blockSize>>>(N, x, y);
34    // Wait for GPU to finish before accessing on host
35    cudaDeviceSynchronize();
36
37    // Check for errors (all values should be 3.0f)
38    float maxError = 0.0f;
39    for (int i = 0; i < N; i++)
40        maxError = fmax(maxError, fabs(y[i]-3.0f));
41//    std::cout << "Max error: " << maxError << std::endl;
42
43    // Free memory
44    cudaFree(x);
45    cudaFree(y);
46
47    return 0;
48}

 1➜ learn>nvprof ./add_cuda
 2==9312== NVPROF is profiling process 9312, command: ./add_cuda
 3Max error: 0
 4==9312== Profiling application: ./add_cuda
 5==9312== Profiling result:
 6Time(%)      Time     Calls       Avg       Min       Max  Name
 7100.00%  167.48ms         1  167.48ms  167.48ms  167.48ms  add(int, float*, float*)
 8
 9
10
11==9382== Profiling application: ./add_block
12==9382== Profiling result:
13Time(%)      Time     Calls       Avg       Min       Max  Name
14100.00%  3.5144ms         1  3.5144ms  3.5144ms  3.5144ms  add(int, float*, float*)
15
16
17
18
19==9447== Profiling application: ./add_grid
20==9447== Profiling result:
21Time(%)      Time     Calls       Avg       Min       Max  Name
22100.00%  1.8084ms         1  1.8084ms  1.8084ms  1.8084ms  add(int, float*, float*)