Here is part of the output for the run with MKL_VERBOSE=1: The core files can be later inspected using gdb: 'gdb -c core', after which you can examine threads, produce backtraces, etc, as usual.įor the last two options to work best, it would be preferrable to compiler WIEN2k with debug information so that the stack traces are more informative. For this to work, you need to execute 'ulimit -c unlimited' (bash) or 'limit coredumpsize unlimited' (csh) in your shell. If this does not work for you, a yet another option is to set a custom XERBLA function and call abort() from it producing core file(s). It probably should be grepped for DGEMM to reduce the size: mpirun | grep DGEMM > mkl_verbose.txtĪnother option is to run the MPI job under GDBs and set a breakpoint at mkl_serv_xerbla so that you can obtain a stack trace leading to a faulty function. Can you plese run it with MKL_VERBOSE=1 and paste here the part of the output just before the error? This actually looks like a ScaLAPACK or an application issue. The error you see indicates an invalid value of LDA passed to DGEMM.
15.0.1.1 intel centrino wireless n 2230 update#
Mpiifort for the Intel(R) MPI Library 5.0 Update 3 for Linux*Ĭopyright(C) 2003-2015, Intel Corporation. RP_LIBS = -lfftw3_mpi -lfftw3 -lmkl_scalapack_lp64 -lmkl_blacs_intelmpi_lp64 $(R_LIBS)
LDFLAGS = $(FOPT) -L$(MKLROOT)/lib/$(MKL_TARGET_ARCH) -pthread
I used the following option for compilation:įOPT = -FR -mp1 -w -prec_div -pc80 -pad -ip -DINTEL_VML -traceback -assume buffered_ioįPOPT = -FR -mp1 -w -prec_div -pc80 -pad -ip -DINTEL_VML -traceback -assume buffered_io -DFFTW3 -I/usr/local/include Intel MKL ERROR: Parameter 8 was incorrect on entry to DGEMM However, for the MPI version, I got a run-time error as The sequential version of the package runs properly. I have installed a package (WIEN2k) on a cluster which requires MKL.