我正在尝试并行实现多个 top-k 选择,其中每个选择从 n 个元素的列表中选择 k 个元素,并且有 m 个这样的任务要并行执行。我用 cub 来做到这一点。我遇到了一个奇怪的错误,我不知道我在哪里做错了。我觉得我可能在理解上犯了一些明显的错误,有人可以帮我检查一下吗?
编辑:
我通过cudaDeviceSynchronize()
在包含free()
. 所以现在我的问题是,does 的free
行为不同于cudaFree
,因为异步调用立即进行是不允许的,这与我在这里问的另一个问题相反:异步调用后 cudaFree 是否有效?
// Assume dtop has size k x m and dmat has size n x m, where k < n
// Each column of dtop is supposed to obtain the top-k indices of
// elements from the corresponding column in dmat.
template<typename ValueType, typename IndexType>
void TopKPerColumn_cub_test(DenseMatrix<IndexType, MemDev> dtop,
DenseMatrix<ValueType, MemDev, Const> dmat);
template<typename T>
struct SelectLE {
T x_;
__device__ SelectLE(const T& x):x_(x){}
__device__ bool operator() (const T& a) {
return a > x_;
}
};
template<typename ValueType, typename IndexType>
__global__ void k_TopKPerColumn_cub_test(DenseMatrix<IndexType, MemDev> dtop,
DenseMatrix<ValueType, MemDev, Const> dmat) {
int n = dmat.num_rows();
int k = dtop.num_rows();
cub::DoubleBuffer<ValueType> keys;
keys.d_buffers[0] = reinterpret_cast<ValueType*>(
malloc(sizeof(ValueType) * n));
keys.d_buffers[1] = reinterpret_cast<ValueType*>(
malloc(sizeof(ValueType) * n));
memcpy(keys.d_buffers[keys.selector], dmat.get_col(blockIdx.x).data(),
sizeof(ValueType) * n);
void* temp_storage = 0;
size_t temp_storage_size = 0;
cub::DeviceRadixSort::SortKeysDescending(
temp_storage, temp_storage_size, keys, n);
temp_storage = malloc(temp_storage_size);
cub::DeviceRadixSort::SortKeysDescending(
temp_storage, temp_storage_size, keys, n);
ValueType kth = keys.Current()[k-1];
free(temp_storage);
free(keys.d_buffers[0]);
free(keys.d_buffers[1]);
temp_storage = 0;
temp_storage_size = 0;
int* nb_selected = reinterpret_cast<int*>(malloc(sizeof(int)));
SelectLE<ValueType> selector(kth);
cub::DeviceSelect::If(temp_storage, temp_storage_size,
const_cast<ValueType*>(dmat.get_col(blockIdx.x).data()),
dtop.get_col(blockIdx.x).data(),
nb_selected, n, selector);
temp_storage = malloc(temp_storage_size);
cub::DeviceSelect::If(temp_storage, temp_storage_size,
const_cast<ValueType*>(dmat.get_col(blockIdx.x).data()),
dtop.get_col(blockIdx.x).data(),
nb_selected, n, selector);
free(nb_selected);
free(temp_storage);
}
template<typename ValueType, typename IndexType>
void TopKPerColumn_cub_test(DenseMatrix<IndexType, MemDev> dtop,
DenseMatrix<ValueType, MemDev, Const> dmat) {
k_TopKPerColumn_cub_test<<<dtop.num_cols(), 1>>>(dtop, dmat);
}