我尝试在CUDA 9中使用协作组(Cooperative Groups),但是编译时出现了错误。
有人知道解决方案吗?
开发环境如下:
- CUDA 9
- Kepler K80
- 计算能力:3.7
#include <cstdint>
#include <iostream>
#include <vector>
#include <cooperative_groups.h>
__global__
void kernel(uint32_t values[])
{
using namespace cooperative_groups;
grid_group g = this_grid();
}
int main(void)
{
constexpr uint32_t kNum = 1 << 24;
std::vector<uint32_t> h_values(kNum);
uint32_t *d_values;
cudaMalloc(&d_values, sizeof(uint32_t) * kNum);
cudaMemcpy(d_values, h_values.data(), sizeof(uint32_t) * kNum, cudaMemcpyHostToDevice);
const uint32_t thread_num = 256;
const dim3 block(thread_num);
const dim3 grid((kNum + block.x - 1) / block.x);
void *params[] = {&d_values};
cudaLaunchCooperativeKernel((void *)kernel, grid, block, params);
cudaMemcpy(h_values.data(), d_values, sizeof(uint32_t) * kNum, cudaMemcpyDeviceToHost);
cudaFree(d_values);
return 0;
}
$ nvcc -arch=sm_37 test.cu --std=c++11 -o test
test.cu(12): error: identifier "grid_group" is undefined
test.cu(12): error: identifier "this_grid" is undefined