常用 blas 函数

Y=alpha * X +beta*Y 

template <>
void caffe_cpu_axpby<float>(const int N, const float alpha, const float* X,
                            const float beta, float* Y) {
  cblas_saxpby(N, alpha, X, 1, beta, Y, 1);
}

template <>
void caffe_cpu_axpby<double>(const int N, const double alpha, const double* X,
                             const double beta, double* Y) {
  cblas_daxpby(N, alpha, X, 1, beta, Y, 1);
}

cblas_dscal(N, beta, Y, incY);  Y=Y*beta 
cblas_daxpy(N, alpha, X, incX, Y, incY);  Y= (alpha * X) + Y)

template <>
void caffe_axpy<float>(const int N, const float alpha, const float* X,
    float* Y) { cblas_saxpy(N, alpha, X, 1, Y, 1); }

template <>
void caffe_axpy<double>(const int N, const double alpha, const double* X,
    double* Y) { cblas_daxpy(N, alpha, X, 1, Y, 1); }

DEFINE_VSL_BINARY_FUNC(Add, y[i] = a[i] + b[i]);
DEFINE_VSL_BINARY_FUNC(Sub, y[i] = a[i] - b[i]);
DEFINE_VSL_BINARY_FUNC(Mul, y[i] = a[i] * b[i]);
DEFINE_VSL_BINARY_FUNC(Div, y[i] = a[i] / b[i]);


template <>
void caffe_add<float>(const int n, const float* a, const float* b,
float* y) {
vsAdd(n, a, b, y);
}

template <>
void caffe_add<double>(const int n, const double* a, const double* b,
double* y) {
vdAdd(n, a, b, y);
}