weixin_45806592的博客

一D卷积#include<cuda_runtime.h>#include<device_launch_parameters.h>#include<iostream>using namespace std;__global__ void juan(int* a, int* b, int* c, int m, int n) { int id = blockIdx.x * blockDim.x + threadIdx.x; int sum = 0; int k

原始#include<cuda_runtime.h>#include<device_launch_parameters.h>#include<iostream>using namespace std;__global__ void jia(int a[2][2], int b[2][2], int c[2][2],int n) { int idx = threadIdx.x + blockIdx.x * blockDim.x; int idy

#include<cuda_runtime_api.h>#include<cuda_runtime.h>#include<device_launch_parameters.h>#include<iostream>#include<Windows.h>#include<time.h>#include<math.h>#include<device_functions.h>using namespace

归约

什么是cudacuda是带有并行内核的串行代码，全部由c/c++编写，串行代码在host端串行执行，并行内核代码在device短的多线程中执行。cuda是用于在英伟达gpu上编程的编译器和工具支持gpu的异构计算cuda API扩展了c/c++编程语言快速SIMD并行性从硬件上提供了高级别的抽象cuda编程流程从host端将数据拷贝到device端呼叫gpu告诉gpu启动在gpu上运行计算将计算完后的device上的数据拷贝到host端kernel是CUDA中一个重要的概念