ECNU_sei_mfj的博客

#include <stdio.h> // For the CUDA runtime routines (prefixed with "cuda_") #include <cuda_runtime.h> #include<device_launch_parameters.h> #include <helper_cuda.h> #include<device_functions.h> #define imin(a,b) (a<b?a:b.

将矩阵分块进行转置 #include <stdio.h> #include<stdlib.h> #include <cuda_runtime.h> #include<device_launch_parameters.h> #include<device_functions.h> #define imin(a,b) (a<b?a:b) //const int N=33*1024; const int N = 16; const int