cuda 操作杂记

curand

curandState_t 用来控制产生不同的随机数，用seed来初始化
curand_init(seed, index, 0, &states[index]);
device float curand_uniform (curandState_t *state) 输出一个0到1的均匀分布，
device float curand_normal (curandState_t *state) 输出一个0到1的正太分布，

thrust

thrust :: host_vector <int > H (4);
// Copy host_vector H to device_vector D   
thrust :: device_vector <int > D = H;

thrust :: device_vector <int > D(10 , 1);  
// set the first seven elements of a vector to 9   
thrust :: fill (D. begin () , D. begin () + 7, 9);  
// initialize a host_vector with the first five elements of D   
thrust :: host_vector <int > H(D. begin () , D. begin () + 5);  
// set the elements of H to 0, 1, 2, 3, ...   
thrust :: sequence (H. begin () , H. end ());  
// copy all of H back to the beginning of D   
thrust :: copy (H. begin () , H. end () , D. begin ());  

thrust::raw_pointer_cast
//返回内部数据指针

比如，计算y=a * x + y，其中x、y为向量，a为常数。这其实就是我们所熟知的由BLAS提供的SAXPY（a*x+y）运算。如果我们在thrust中实现SAXPY我们有几个选择。

struct saxpy_functor
{
  const float a;

  saxpy_functor(float _a) : a(_a) {}

  __host__ __device__
  float operator()(const float& x, const float& y) const
  { 
    return a * x + y;
  }
};

void saxpy_fast(float A, thrust::device_vector<float>& X, thrust::device_vector<float>& Y)
{
  // Y <- A * X + Y
  thrust::transform(X.begin(), X.end(), Y.begin(), Y.begin(), saxpy_functor(A));
}

void saxpy_slow(float A, thrust::device_vector<float>& X, thrust::device_vector<float>& Y)
{
  thrust::device_vector<float> temp(X.size());

  // temp <- A
  thrust::fill(temp.begin(), temp.end(), A);

  // temp <- A * X
  thrust::transform(X.begin(), X.end(), temp.begin(), temp.begin(), thrust::multiplies<float>());

  // Y <- A * X + Y
  thrust::transform(temp.begin(), temp.end(), Y.begin(), Y.begin(), thrust::plus<float>());
}

make_zip_iterator

#include <thrust/iterator/zip_iterator.h>
...
// initialize vectors
thrust::device_vector<int>  A(3);
thrust::device_vector<char> B(3);
A[0] = 10;  A[1] = 20;  A[2] = 30;
B[0] = 'x'; B[1] = 'y'; B[2] = 'z';

// create iterator (type omitted)
first = thrust::make_zip_iterator(thrust::make_tuple(A.begin(), B.begin()));
last  = thrust::make_zip_iterator(thrust::make_tuple(A.end(),   B.end()));

first[0]   // returns tuple(10, 'x')
first[1]   // returns tuple(20, 'y')
first[2]   // returns tuple(30, 'z')

// maximum of [first, last)
thrust::maximum< thrust::tuple<int,char> > binary_op;
thrust::tuple<int,char> init = first[0];
thrust::reduce(first, last, init, binary_op); // returns tuple(30, 'z')