https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/unresolved-I-MPI-intel-fast-memcpy/m-p/880209#M9438 <P>Ok this one is solved:</P> <P>I put -lmpiif -lmpi -lmpgi -lrt instead of -lmpi -lmpi_mt -lrt.</P> <P>The requested routine is provided by the -lmpgi flag</P> <P>No I have the same Pb at execution for the dynamically and statically linked binaries!...</P> <P>[cli_2]: aborting job:<BR />Fatal error in MPI_Comm_size: Invalid communicator, error stack:<BR />MPI_Comm_size(110): MPI_Comm_size(comm=0x5b, size=0xbba858) failed<BR />MPI_Comm_size(69).: Invalid communicator<BR />rank 2 in job 73 clusteru_48585 caused collective abort of all ranks<BR /> exit status of rank 2: return code 13 <BR />[cli_1]: aborting job:<BR />Fatal error in MPI_Comm_size: Invalid communicator, error stack:<BR />MPI_Comm_size(110): MPI_Comm_size(comm=0x5b, size=0xbba858) failed<BR />MPI_Comm_size(69).: Invalid communicator<BR />rank 1 in job 73 clusteru_48585 caused collective abort of all ranks<BR /> exit status of rank 1: return code 13 <BR />rank 0 in job 73 clusteru_48585 caused collective abort of all ranks<BR /> exit status of rank 0: return code 13 <BR /></P> <P>As this Pb did not appear in test programs using only MPI, I think it comes from my code, allthough it works on another cluster... :-(</P> Fri, 30 May 2008 16:46:02 GMT md25 2008-05-30T16:46:02Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/unresolved-I-MPI-intel-fast-memcpy/m-p/880208#M9437 <P>Hi,</P> <P>I have a hard time trying to compile and run a code using the scalapack version included in Intel cluster toolkit :</P> <P>my LD_LIBRARY_PATH variable will give you the version numbers:</P> <P>/opt/intel/mkl/10.0.2.018/lib/em64t:/opt/intel/ict/3.0.1/mpi/3.0/lib64:/opt/intel/ict/3.0.1/cmkl/9.1/lib/em64t:/opt/intel/ict/3.0.1/itac/7.0.1/itac/slib_impi2:/opt/intel/fce/10.0.023/lib</P> <P>When I try to make a static link with ifort:</P> <P>ifort -C -Bstatic type.o modules.o interfaces_sca.o field_sca.o get_param33.o adin33.o fillmat33.o lu33.o calpol33.o solve_e033.o t33.o fillpol33.o rotate33.o propag33.o init_sca.o distrib_par.o matgen_sca.o lu_sca.o solve_sca.o derf.o -o Linux/bin/ifort/dfield -lmkl_scalapack_lp64 -lmkl_blacs_lp64 -L/opt/intel/ict/3.0.1/mpi/3.0/lib64 -lmpi -lmpi_mt -lrt -openmp -lmkl_lapack -Wl,--start-group -lmkl_intel_lp64 -lmkl_intel_thread -lmkl_core -Wl,--end-group -lpthread<BR /></P> <P>I get the following errors (just the beginning of it !!!):</P> <P>ipo: warning #11041: unresolved __I_MPI__intel_fast_memcpy<BR /> Referenced in libmpi.a(type_struct.o)<BR /> Referenced in libmpi.a(errutil.o)<BR /> Referenced in libmpi.a(helper_fns.o)<BR /> Referenced in libmpi.a(fx_heap_crsec_aligned.o)<BR /> Referenced in libmpi.a(mpid_datatype_contents.o)<BR /> Referenced in libmpi.a(ch3u_request.o)<BR /> Referenced in libmpi.a(type_create_indexed_block.o)<BR /> Referenced in libmpi.a(mpid_segment.o)<BR /> Referenced in libmpi.a(gen_dataloop.o)<BR /> Referenced in libmpi.a(mpidi_pg.o)<BR /> Referenced in libmpi.a(ch3_istartmsgv.o)<BR /> Referenced in libmpi.a(ch3_shm.o)<BR /> Referenced in libmpi.a(sock.o)<BR /> Referenced in libmpi.a(ch3u_buffer.o)<BR /> Referenced in libmpi.a(ch3u_comm_spawn_multiple.o)<BR /> Referenced in libmpi.a(gen_type_blockindexed.o)<BR /> Referenced in libmpi.a(ch3u_handle_recv_pkt.o)<BR /> Referenced in libmpi.a(ch3i_shm_bootstrapq.o)<BR /> Referenced in libmpi.a(I_MPI_wrap_dat.o)<BR /> Referenced in libmpi.a(rdma_iba.o)<BR /> Referenced in libmpi.a(rdma_iba_rendezwrite.o)<BR /> Referenced in libmpi.a(dapl_gather.o)<BR /> Referenced in libmpi.a(dapl_gatherv.o)<BR /> Referenced in libmpi.a(dapl_scatter.o)<BR /> Referenced in libmpi.a(dapl_scatterv.o)<BR /> Referenced in libmpi.a(dapl_allgather.o)<BR /> Referenced in libmpi.a(dapl_allgatherv.o)<BR /> Referenced in libmpi.a(dapl _alltoall.o)<BR /> Referenced in libmpi.a(dapl_alltoallv.o)<BR /> Referenced in libmpi.a(dapl_reduce.o)<BR /> Referenced in libmpi.a(dapl_allreduce.o)<BR /> Referenced in libmpi.a(dapl_red_scat.o)<BR /> Referenced in libmpi.a(dapl_scan.o)<BR /> Referenced in libmpi.a(type_indexed.o)<BR />ipo: warning #11041: unresolved __I_MPI__intel_fast_memset<BR /> Referenced in libmpi.a(initthread.o)<BR /> Referenced in libmpi.a(helper_fns.o)<BR /> Referenced in libmpi.a(fx_heap_crsec_aligned.o)<BR /> Referenced in libmpi.a(rdma_iba_init_d.o)<BR /> Referenced in libmpi.a(ch3u_comm_spawn_multiple.o)<BR /> Referenced in libmpi.a(dapl_utils.o)<BR />ipo: warning #11041: unresolved __I_MPI___intel_cpu_indicator<BR /> Referenced in libmpi.a(opmax.o)<BR /> Referenced in libmpi.a(opmin.o)<BR /> Referenced in libmpi.a(opsum.o)<BR /> Referenced in libmpi.a(opprod.o)<BR /></P> <P>Any Idea ???</P> <P>PS: I will tell in another post the problems I get when trying dynamic link with mpiifort...</P> Fri, 30 May 2008 13:51:13 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/unresolved-I-MPI-intel-fast-memcpy/m-p/880208#M9437 md25 2008-05-30T13:51:13Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/unresolved-I-MPI-intel-fast-memcpy/m-p/880209#M9438 <P>Ok this one is solved:</P> <P>I put -lmpiif -lmpi -lmpgi -lrt instead of -lmpi -lmpi_mt -lrt.</P> <P>The requested routine is provided by the -lmpgi flag</P> <P>No I have the same Pb at execution for the dynamically and statically linked binaries!...</P> <P>[cli_2]: aborting job:<BR />Fatal error in MPI_Comm_size: Invalid communicator, error stack:<BR />MPI_Comm_size(110): MPI_Comm_size(comm=0x5b, size=0xbba858) failed<BR />MPI_Comm_size(69).: Invalid communicator<BR />rank 2 in job 73 clusteru_48585 caused collective abort of all ranks<BR /> exit status of rank 2: return code 13 <BR />[cli_1]: aborting job:<BR />Fatal error in MPI_Comm_size: Invalid communicator, error stack:<BR />MPI_Comm_size(110): MPI_Comm_size(comm=0x5b, size=0xbba858) failed<BR />MPI_Comm_size(69).: Invalid communicator<BR />rank 1 in job 73 clusteru_48585 caused collective abort of all ranks<BR /> exit status of rank 1: return code 13 <BR />rank 0 in job 73 clusteru_48585 caused collective abort of all ranks<BR /> exit status of rank 0: return code 13 <BR /></P> <P>As this Pb did not appear in test programs using only MPI, I think it comes from my code, allthough it works on another cluster... :-(</P> Fri, 30 May 2008 16:46:02 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/unresolved-I-MPI-intel-fast-memcpy/m-p/880209#M9438 md25 2008-05-30T16:46:02Z