Functions | |
| template<typename T > | |
| void | reduce_single_sum (T *out, const T *in, const raft::comms::comms_t &comm, cudaStream_t stream, int root=0) |
| template<typename T > | |
| void | allreduce_single_sum (T *out, const T *in, const raft::comms::comms_t &comm, cudaStream_t stream) |
| void MLCommon::opg::allreduce_single_sum | ( | T * | out, |
| const T * | in, | ||
| const raft::comms::comms_t & | comm, | ||
| cudaStream_t | stream | ||
| ) |
all-reduce single float numbers across workers in Comm
| void MLCommon::opg::reduce_single_sum | ( | T * | out, |
| const T * | in, | ||
| const raft::comms::comms_t & | comm, | ||
| cudaStream_t | stream, | ||
| int | root = 0 |
||
| ) |
sum-reduce single float numbers across workers