调用GPU的本质其实是调用CUDA的dll
如果你对CUDA编程不熟悉,可以参考CUDA并行编程概述
生成CUDA dll
调用显卡的方法是调用CUDA的dll,因此首先要使用CUDA生成dll
下面是示例CUDA代码
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
| #include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <stdio.h>
#include <iostream>
using namespace std;
__global__ void DoInKernel(int* a, int* b, int* c, int num) {
int i = blockIdx.x * 1024 + threadIdx.x;
if (i >= num) return;
c[i] = a[i] + b[i];
}
extern "C" _declspec(dllexport) void Add(int* ori_a, int* ori_b, int* ori_c, int num) {
int* dev_a;
int* dev_b;
int* dev_c;
int size = num * sizeof(int);
cudaMalloc((void**)&dev_a, size);
cudaMalloc((void**)&dev_b, size);
cudaMalloc((void**)&dev_c, size);
cudaMemcpy(dev_a, ori_a, size, cudaMemcpyHostToDevice);
cudaMemcpy(dev_b, ori_b, size, cudaMemcpyHostToDevice);
DoInKernel << <num / 1024 + 1, 1024 >> > (dev_a, dev_b, dev_c, num);
cudaMemcpy(ori_c, dev_c, size, cudaMemcpyDeviceToHost);
cudaFree(dev_a);
cudaFree(dev_b);
cudaFree(dev_c);
}
|
它的作用是将 ori_a 和 ori_b 数组内的数组相加,并保存到 ori_c
编译后得到CUDA.dll文件
调用dll
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
| import ctypes
import random
length = 4096
dll_path = r"C:\Users\Administrator\桌面\CUDA.dll"
dll = ctypes.cdll.LoadLibrary(dll_path)
c_int = ctypes.c_int * length
array_a = c_int()
array_b = c_int()
array_c = c_int()
i = 0
while i < length:
array_a[i] = random.randint(0,1000)
array_b[i] = random.randint(0,1000)
i = i + 1
dll.Add(array_a, array_b, array_c, 4096)
i = 0
while i < length:
print(array_a[i],"+",array_b[i],"=",array_c[i])
i = i + 1
|
运行结果
