わかりましたので、cuda が動作するように 2D 配列を取得しようとしていますが、それは苦痛になってきています。エラーはタイトルにあり、cudaMemcpy2D で発生します。問題は訓練された目には明らかだと思います。助けてくれてありがとう、私は現在ポインターを学んでいる私のクラスよりも一歩先を行っています。
#include <cuda_runtime.h>
#include <iostream>
#pragma comment (lib, "cudart")
/* Program purpose: pass a 10 x 10 matrix and multiply it by another 10x10 matrix */
float matrix1_host[100][100];
float matrix2_host[100][100];
float* matrix1_device;
float* matrix2_device;
size_t pitch;
cudaError_t err;
__global__ void addMatrix(float* matrix1_device,float* matrix2_device, size_t pitch){
// How this works
// first we start to cycle through the rows by using the thread's ID
// then we calculate an address from the address of a point in the row, by adding the pitch (size of each row) and * it by
// the amount of rows we've already completed, then we can use that address of somewhere at a start of a row to get the colums
// in the row with a normal array grab.
int r = threadIdx.x;
float* rowofMat1 = (float*)((char*)matrix1_device + r * pitch);
float* rowofMat2 = (float*)((char*)matrix2_device + r * pitch);
for (int c = 0; c < 100; ++c) {
rowofMat1[c] += rowofMat2[c];
}
}
void initCuda(){
err = cudaMallocPitch((void**)matrix1_device, &pitch, 100 * sizeof(float), 100);
err = cudaMallocPitch((void**)matrix2_device, &pitch, 100 * sizeof(float), 100);
//err = cudaMemcpy(matrix1_device, matrix1_host, 100*100*sizeof(float), cudaMemcpyHostToDevice);
//err = cudaMemcpy(matrix2_device, matrix2_host, 100*100*sizeof(float), cudaMemcpyHostToDevice);
err = cudaMemcpy2D(matrix1_device, 100*sizeof(float), matrix1_host, pitch, 100*sizeof(float), 100, cudaMemcpyHostToDevice);
err = cudaMemcpy2D(matrix2_device, 100*sizeof(float), matrix2_host, pitch, 100*sizeof(float), 100, cudaMemcpyHostToDevice);
}
void populateArrays(){
for(int x = 0; x < 100; x++){
for(int y = 0; y < 100; y++){
matrix1_host[x][y] = (float) x + y;
matrix2_host[y][x] = (float) x + y;
}
}
}
void runCuda(){
dim3 dimBlock ( 100 );
dim3 dimGrid ( 1 );
addMatrix<<<dimGrid, dimBlock>>>(matrix1_device, matrix2_device, 100*sizeof(float));
//err = cudaMemcpy(matrix1_host, matrix1_device, 100*100*sizeof(float), cudaMemcpyDeviceToHost);
err = cudaMemcpy2D(matrix1_host, 100*sizeof(float), matrix1_device, pitch, 100*sizeof(float),100, cudaMemcpyDeviceToHost);
//cudaMemcpy(matrix1_host, matrix1_device, 100*100*sizeof(float), cudaMemcpyDeviceToHost);
}
void cleanCuda(){
err = cudaFree(matrix1_device);
err = cudaFree(matrix2_device);
err = cudaDeviceReset();
}
int main(){
populateArrays();
initCuda();
runCuda();
cleanCuda();
std::cout << cudaGetErrorString(cudaGetLastError());
system("pause");
return 0;
}