我有一个程序,它包含 3 个文件,一个.c
文件和两个.cu
文件,nn.cu
以及parallel.cu
. 主要功能位于一个.cu
文件中,nn.cu
文件.c
( utils.c
) 我extern "C"
在parallel.cu
. 我想进一步并行化程序(在没有 的情况下完美运行cilk
),所以我考虑cilk
了 ,_Cilk_spawn
和_Cilk_sync
:
int main(int argc, char* argv[] ) {
clock_t begin = clock();
srand((unsigned)time(NULL));
int n_inputs = atoi(argv[2]);
int n_hidden = atoi(argv[3]);
int n_outputs = atoi(argv[4]);
// Build output layer
NeuralNet nn = buildNeuralNet(n_inputs, n_outputs, n_hidden);
// Build training samples
int _p1[] = {0,0};
Pattern p1 = makePatternSingleOutput(_p1, 0);
int _p2[] = {0,1};
Pattern p2 = makePatternSingleOutput(_p2, 1);
int _p3[] = {1,1};
Pattern p3 = makePatternSingleOutput(_p3, 1);
int _p4[] = {1,0};
Pattern p4 = makePatternSingleOutput(_p4, 1);
Pattern patterns[] = {p3, p2, p1, p4};
// Train the network
_Cilk_spawn train_network(patterns, 4, atoi(argv[1]), nn);
printf("\n\nTesting the network\n");
_Cilk_sync;
_Cilk_spawn update_pattern(p2, nn);
for (int i=0; i < nn.n_outputs; i++) {
printf("Output: %f, expected: %i\n", nn.out_output[i], p2.result[i]);
printf("NN Error : %f\n", 1.0f - nn.out_output[i]);
}
cudaDeviceReset();
_Cilk_sync;
clock_t end = clock();
double time_spent = (double)(end - begin) / CLOCKS_PER_SEC;
printf("Runtime : %f\n", time_spent);
return 0;
}
问题是当我尝试将所有这些编译在一起时nvcc
:
$ nvcc -Wno-deprecated-gpu-targets -o my_nn_cilk nn.cu parallel.cu -lm
nn.cu(241): error: identifier "_Cilk_spawn" is undefined
nn.cu(241): error: expected a ")"
nn.cu(245): error: identifier "_Cilk_sync" is undefined
nn.cu(247): error: identifier "_Cilk_spawn" is undefined
nn.cu(247): error: expected a ")"
5 errors detected in the compilation of "/tmp/tmpxft_00003b52_00000000-14_nn.cpp1.ii".
_Cilk_spawn
我称之为所需CUDA
内核的两个函数。即使我将nvcc
参数添加到命令中-lcilkrts
,错误也是一样的。另外,我#include "cilk/cilk.h"
在代码的开头。
你能帮我么?为什么它会显示这些错误并且无法编译?先感谢您!