CUDA学习（一）：计算立方

cuda编程

VS2019+GPU

需要引入

再右键打开的项目–>生成依赖项–>生成自定义–>勾选CUDA v10.1。

再右键.cu文件–>文件属性设置为 CUDA c/c++

计算0到255的立方

“kernel.cu”

#include "cuda_runtime.h"  
#include "device_launch_parameters.h"  

__global__ void add(const int* a, const int* b, int* c, int size)
{
	int tid = threadIdx.x + blockIdx.x * blockDim.x;
	c[tid] = b[tid] *a[tid];
}

extern "C" void addKernel(const int* a, const int* b, int* c, int size)
{
	int* dev_a = 0;
	int* dev_b = 0;
	int* dev_c = 0;

	cudaSetDevice(0);
	cudaMalloc((void**)&dev_a, sizeof(int) * size);
	cudaMalloc((void**)&dev_b, sizeof(int) * size);
	cudaMalloc((void**)&dev_c, sizeof(int) * size);
	cudaMemcpy(dev_a, a, sizeof(int) * size, cudaMemcpyHostToDevice);
	cudaMemcpy(dev_b, b, sizeof(int) * size, cudaMemcpyHostToDevice);
	cudaMemcpy(dev_c, c, sizeof(int) * size, cudaMemcpyHostToDevice);

	add << <2, 128 >> > (dev_a, dev_b, dev_c, size);

	cudaMemcpy(c, dev_c, size * sizeof(int), cudaMemcpyDeviceToHost);

	cudaFree(dev_a);
	cudaFree(dev_b);
	cudaFree(dev_c);
}

“main.cpp”

#include <stdio.h>  
#include <stdlib.h>  
//#include "kernel.cu"  

#define N 256
extern "C" void addKernel(const int* a, const int* b, int* c, int size);

int main(int argc, char** argv)
{
	int a[N];
	int b[N];
	int c[N];

	for (int i = 0; i < N; i++)
	{
		a[i] = i;
		b[i] = i * i;
		c[i] = 0;
	}
	addKernel(a, b, c, N);
	for (int i = 0; i < N; i++)
	{
		printf("%d^3=%d\n", i, c[i]);
	}
	return 0;
}

结果如下

.
.
.

参考一
参考二