ABINIT with MKL+MAGMA, GPU enabled gives segmentation fault

option, parallelism,...

Moderators: jbeuken, Jordan, pouillon

Forum rules
Please have a look at ~abinit/doc/config/build-config.ac in the source package for detailed and up-to-date information about the configuration of Abinit builds.
For a video explanation on how to build Abinit for Linux, please go to: http://www.youtube.com/watch?v=DppLQ-KQA68.
IMPORTANT: when an answer solves your problem, please check the little green V-like button on its upper-right corner to accept it.
Post Reply
Posts: 2
Joined: Thu Jul 04, 2019 12:58 pm

ABINIT with MKL+MAGMA, GPU enabled gives segmentation fault

Post by Naga » Fri Jul 05, 2019 9:15 am


I have compiled abinit with linalg as mkl+magma and enabled cuda. When I run abinit on a sample input, i get a segmentation fault in mkl routines. I have used lp64 libraries of mkl rather than ilp64. Any leads to resolve this? Please find the gdb dump below:

getcut: wavevector= 0.0000 0.0000 0.0000 ngfft= 36 36 40
ecut(hartree)= 40.000 => boxcut(ratio)= 2.10014

vtorho : nnsclo_now=2, note that nnsclo,dbl_nnsclo,istep=0 0 1

Program received signal SIGSEGV, Segmentation fault.
0x00002aab5e869fcb in mkl_blas_avx2_xzdotc ()
from /cm/shared/apps/intel/compilers_and_libraries_2016/linux/mkl/lib/intel64/libmkl_avx2.so
Missing separate debuginfos, use: debuginfo-install glibc-2.17-222.el7.x86_64 libibverbs-41mlnx1-OFED. libmlx4-41mlnx1-OFED. libmlx5-41mlnx1-OFED. libnl3-3.2.28-4.el7.x86_64 libpciaccess-0.14-1.el7.x86_64 librdmacm-41mlnx1-OFED. librxe-41mlnx1-OFED. munge-libs-0.5.11-3.el7.x86_64 numactl-libs-2.0.9-7.el7.x86_64
(gdb) bt
#0 0x00002aab5e869fcb in mkl_blas_avx2_xzdotc ()
from /cm/shared/apps/intel/compilers_and_libraries_2016/linux/mkl/lib/intel64/libmkl_avx2.so
#1 0x00002aaaab93b5e9 in zdotc_ ()
from /cm/shared/apps/intel/compilers_and_libraries_2016/linux/mkl/lib/intel64/libmkl_intel_lp64.so
#2 0x0000000001205562 in __m_cgtools_MOD_cg_zdotc ()
#3 0x0000000001205701 in __m_cgtools_MOD_dotprod_g ()
#4 0x000000000093f231 in cgwf_ ()
#5 0x0000000000511f91 in vtowfk_ ()
#6 0x00000000004fb750 in vtorho_ ()
#7 0x00000000004da136 in scfcv_ ()
#8 0x00000000004d0ccb in __m_scfcv_MOD_scfcv_scfcv ()
#9 0x00000000004a6a82 in gstate_ ()
#10 0x00000000004297f5 in gstateimg_ ()
#11 0x0000000000414780 in driver_ ()
#12 0x000000000040c02d in MAIN__ ()
#13 0x00000000004085ad in main ()


Post Reply