PyCuda学习二之矩阵的加法

矩阵的加法

1. 导入必要的库

   import numpy as np
   import pycuda.autoinit
   import pycuda.driver as cuda
   from pycuda.compiler import SourceModule
   

2. 编写核函数 注意: 三引号里面的语法是c/c++的语法

   mod = SourceModule("""
   	__global__ void gpu_add(float* x, float* y, size_t N)
   	{
   		int index = threadIdx.x + blockDim.x * blockIdx.x;
   		int stride = blockDim.x * gridDim.x;
   		for (int i = index; i < N; i += stride) {
   			y[i] = x[i] + y[i]
   		}
   	}
   """)
   
   

3. 编写测试函数

   
   def test(N):
     	a = np.empty(N, dtype=np.float32)
     	a[:] = 10.0
       b = np.empty(N, dtype=np.float32