我在 CUDA 机器上使用 CUSP 库进行稀疏矩阵乘法。我目前的代码是
#include <cusp/coo_matrix.h>
#include <cusp/multiply.h>
#include <cusp/print.h>
#include <cusp/transpose.h>
#include<stdio.h>
#define CATAGORY_PER_SCAN 1000
#define TOTAL_CATAGORY 100000
#define MAX_SIZE 1000000
#define ELEMENTS_PER_CATAGORY 10000
#define ELEMENTS_PER_TEST_CATAGORY 1000
#define INPUT_VECTOR 1000
#define TOTAL_ELEMENTS ELEMENTS_PER_CATAGORY * CATAGORY_PER_SCAN
#define TOTAL_TEST_ELEMENTS ELEMENTS_PER_TEST_CATAGORY * INPUT_VECTOR
int main(void)
{
cudaEvent_t start, stop;
cudaEventCreate(&start);
cudaEventCreate(&stop);
cudaEventRecord(start, 0);
cusp::coo_matrix<long long int, double, cusp::host_memory> A(CATAGORY_PER_SCAN,MAX_SIZE,TOTAL_ELEMENTS);
cusp::coo_matrix<long long int, double, cusp::host_memory> B(MAX_SIZE,INPUT_VECTOR,TOTAL_TEST_ELEMENTS);
for(int i=0; i< ELEMENTS_PER_TEST_CATAGORY;i++){
for(int j = 0;j< INPUT_VECTOR ; j++){
int index = i * INPUT_VECTOR + j ;
B.row_indices[index] = i; B.column_indices[ index ] = j; B.values[index ] = i;
}
}
for(int i = 0;i < CATAGORY_PER_SCAN; i++){
for(int j=0; j< ELEMENTS_PER_CATAGORY;j++){
int index = i * ELEMENTS_PER_CATAGORY + j ;
A.row_indices[index] = i; A.column_indices[ index ] = j; A.values[index ] = i;
}
}
/*cusp::print(A);
cusp::print(B); */
//test vector
cusp::coo_matrix<long int, double, cusp::device_memory> A_d = A;
cusp::coo_matrix<long int, double, cusp::device_memory> B_d = B;
// allocate output vector
cusp::coo_matrix<int, double, cusp::device_memory> y_d(CATAGORY_PER_SCAN, INPUT_VECTOR ,CATAGORY_PER_SCAN * INPUT_VECTOR);
cusp::multiply(A_d, B_d, y_d);
cusp::coo_matrix<int, double, cusp::host_memory> y=y_d;
cudaEventRecord(stop, 0);
cudaEventSynchronize(stop);
float elapsedTime;
cudaEventElapsedTime(&elapsedTime, start, stop); // that's our time!
printf("time elaplsed %f ms\n",elapsedTime);
return 0;
}
cusp::multiply 函数仅使用 1 个 GPU(据我了解)。
- 如何使用 setDevice() 在两个 GPU 上运行相同的程序(每个 GPU 一个 cusp::multiply)。
- 准确测量总时间。
- 我如何在这个库中使用零拷贝固定内存,因为我自己可以使用 malloc。