Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Segmentation fault with amdclang compiler on Frontier when OMP_NUM_THREADS > 1 #6756

Open
dqwu opened this issue Nov 18, 2024 · 0 comments
Open
Assignees
Labels
AMD-compiler Issues related to AMD Compiler Frontier mpas-seaice

Comments

@dqwu
Copy link
Contributor

dqwu commented Nov 18, 2024

Not reproducible when OMP_NUM_THREADS = 1
Similar issues on Crusher: #5227, #5320

Steps to Reproduce on Frontier

git clone https://github.com/E3SM-Project/E3SM.git
cd E3SM

git submodule update --init --recursive

cd cime/scripts

./create_newcase --machine=frontier --compiler=amdclang --case F2010_ne4_oQU240 --compset F2010 --res ne4_oQU240 --walltime 00:03:00
cd F2010_ne4_oQU240

./xmlchange STOP_N=1
./xmlchange LND_NTHRDS=2

./case.setup

./case.build

./case.submit

Backtrace of the Core Dump

(gdb) bt
#0  0x00007fffe678cdfe in local_copy_i8 () from /opt/rocm-5.4.0/llvm/bin/../lib/libflang.so
#1  0x00007fffe678e979 in f90_copy_f77_argl_i8 () from /opt/rocm-5.4.0/llvm/bin/../lib/libflang.so
#2  0x0000000003e9f501 in mpas_dmpar::mpas_dmpar_exch_group_start_send () at F2010_ne4_oQU240/bld/cmake-bld/framework/mpas_dmpar.f90:7668
#3  0x0000000003e9b11a in mpas_dmpar::mpas_dmpar_exch_group_full_halo_exch () at F2010_ne4_oQU240/bld/cmake-bld/framework/mpas_dmpar.f90:6941
#4  0x0000000003e9b573 in mpas_dmpar::mpas_dmpar_field_halo_exch () at F2010_ne4_oQU240/bld/cmake-bld/framework/mpas_dmpar.f90:7008
#5  0x0000000003f21214 in mpas_stream_manager::exch_all_halos () at F2010_ne4_oQU240/bld/cmake-bld/framework/mpas_stream_manager.f90:4738
#6  0x0000000003f1e31d in mpas_stream_manager::read_stream () at F2010_ne4_oQU240/bld/cmake-bld/framework/mpas_stream_manager.f90:4022
#7  0x0000000003f1afd4 in mpas_stream_manager::mpas_stream_mgr_read () at F2010_ne4_oQU240/bld/cmake-bld/framework/mpas_stream_manager.f90:3545
#8  0x0000000003cad23c in seaice_core::seaice_core_init () at F2010_ne4_oQU240/bld/cmake-bld/core_seaice/model_forward/mpas_seaice_core.f90:110
#9  0x0000000003249798 in ice_comp_mct::ice_init_mct () at F2010_ne4_oQU240/mpas-seaice/driver/ice_comp_mct.f90:632
#10 0x00000000007e8ba1 in component_mod::component_init_cc () at E3SM/driver-mct/main/component_mod.F90:257
#11 0x00000000007b4021 in cime_comp_mod::cime_init () at E3SM/driver-mct/main/cime_comp_mod.F90:1518
#12 0x00000000007e66b7 in cime_driver () at driver-mct/main/cime_driver.F90:122
@dqwu dqwu added mpas-seaice AMD-compiler Issues related to AMD Compiler Frontier labels Nov 18, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
AMD-compiler Issues related to AMD Compiler Frontier mpas-seaice
Projects
None yet
Development

No branches or pull requests

2 participants