Runtime failures on larger process counts about gpi-2 HOT 2 OPEN

//  mpicxx gaspi_segment.cpp -pthread -I$GPI2_HOME/include -L$GPI2_HOME/lib64 -lGPI2

#include <iostream>
#include <cassert>
#include <vector>
#include <mpi.h>
#include "GASPI.h"


inline gaspi_return_t CheckGaspiResult(gaspi_return_t result, const char* what)
{
  if (result != GASPI_SUCCESS && result != GASPI_TIMEOUT)
  {
    throw std::runtime_error(what);
  }
  return result;
}

#define GASPI_CHECK( X ) CheckGaspiResult((X), #X)


using RankIndexT = unsigned int;

struct GASPICommunicator
{
  gaspi_rank_t numProcs_;
  gaspi_rank_t ownRank_;
  gaspi_number_t maxReduceElems_;

  GASPICommunicator()
  {
    GASPI_CHECK(gaspi_allreduce_elem_max(&maxReduceElems_));
    GASPI_CHECK(gaspi_proc_rank(&ownRank_));
    GASPI_CHECK(gaspi_proc_num(&numProcs_));
  }

  void AllGatherValueImpl(const unsigned int* values, unsigned int* data)
  {
    std::fill_n(data, numProcs_, 0);
    std::copy(values, values + 1, data + ownRank_);
    gaspi_number_t remainingElems = gaspi_number_t(numProcs_);
    while (remainingElems > 0)
    {
      auto reduceEles = std::min(maxReduceElems_, remainingElems);
      GASPI_CHECK(gaspi_allreduce(data, data, reduceEles, GASPI_OP_SUM, GASPI_TYPE_UINT, GASPI_GROUP_ALL, GASPI_BLOCK));
      remainingElems -= reduceEles;
      data += reduceEles;
    }
  }
};

void CheckAllreduce()
{
  GASPICommunicator communicator;
  unsigned int value = communicator.ownRank_;
  std::vector<unsigned int> allData (communicator.numProcs_, -1);
  communicator.AllGatherValueImpl(&value, allData.data());
  for (int i = 0; i < communicator.numProcs_; ++i)
  {
    if (i != allData[i])
    {
      std::cout << "At rank " << value << " first fail at " << i << ", content is " << allData[i] << std::endl;
      return;
    }
  }
  std::cout << "At rank " << value << " all OK." << std::endl;
}


int main(int argc, char** argv)
{
  int provided_thread_level;
  int mpi_init_result = MPI_Init_thread(&argc, &argv, MPI_THREAD_SERIALIZED, &provided_thread_level);

  GASPI_CHECK(gaspi_proc_init(GASPI_BLOCK));

  CheckAllreduce();

  GASPI_CHECK(gaspi_proc_term(GASPI_BLOCK));
  MPI_Finalize();
}