Closed diehlpk closed 1 year ago
The DWD run should finish
However, we get a floating point exception using the more block branch.
Start execution the solver... ----------------------------------------------- checking for refinement regridding Regridded tree in 0.954963 seconds rebalancing 11849 nodes with 10368 leaves Rebalanced tree in 0.979901 seconds forming tree connections 7288 amr boundaries Formed tree in 7.751028 seconds solving gravity regrid done in 23.843107 seconds --------------------------------------- OMEGA = 9.681361e-01, output_dt = 4.000000e-02 0.000000e+00 4.000000e-02 dwd step... [l01-0209c:00103] *** Process received signal *** [l01-0209c:00103] Signal: Floating point exception (8) [l01-0209c:00103] Signal code: (14) [l01-0209c:00103] Failing at address: 0x400000ddb3ac [l01-0209c:00103] [ 0] linux-vdso.so.1(__kernel_rt_sigreturn+0x0)[0x4000000707a0] [l01-0209c:00103] [ 1] /vol0003/mdt0/data/hp210311/u10393/OctoTigerBuildChain/build/octotiger/build/libhpx_hydrolib.so(_Z25cell_reconstruct_ppm_simdIN3sve12experimental14parallelism_v24simdIdNS2_8simd_abi7sve_abiEEENS2_9simd_maskIdS5_EEEvPdPKdbbSB_iiiii+0xb8c)[0x400000ddb3ac] [l01-0209c:00103] [ 2] /vol0003/mdt0/data/hp210311/u10393/OctoTigerBuildChain/build/octotiger/build/libhpx_hydrolib.so(_Z35cell_reconstruct_inner_loop_p1_simdIN3sve12experimental14parallelism_v24simdIdNS2_8simd_abi7sve_abiEEENS2_9simd_maskIdS5_EEEvmiPKiSA_PdPKdSB_dSD_iiiii+0xa04)[0x400000ddc404] [l01-0209c:00103] [ 3] /vol0003/mdt0/data/hp210311/u10393/OctoTigerBuildChain/build/octotiger/build/libhpx_hydrolib.so(_ZZNK6Kokkos4Impl11ParallelForIZ23reconstruct_no_amc_implIN3sve12experimental14parallelism_v24simdIdNS5_8simd_abi7sve_abiEEENS5_9simd_maskIdS8_EENS_12Experimental3HPXEN8recycler24aggregated_recycled_viewINS_4ViewIPdJNS_11LayoutRightENS_9HostSpaceENS_12MemoryTraitsILj1EEEEEE15Allocator_SliceIdSaIdEN3hpx6kokkos8executorISD_EEEdEENSF_INSG_IPiJSI_SJ_SL_EEESN_IiSaIiESS_EiEEEvRNSR_IT1_EERN19Aggregated_ExecutorIS11_E14Executor_SliceEdiiRKT3_S19_RT2_RKS1A_S1B_S1B_S1D_S1D_iiimmEUlRKNS0_13HPXTeamMemberEE_NS_10TeamPolicyIJSD_EEESD_E12execute_taskEvENKUliE_clEi+0x190)[0x400000dde0b0] [l01-0209c:00103] [ 4] /vol0003/mdt0/data/hp210311/u10393/OctoTigerBuildChain/build/octotiger/build/libhpx_hydrolib.so(_ZN6Kokkos12parallel_forINS_10TeamPolicyIJNS_12Experimental3HPXEEEEZ23reconstruct_no_amc_implIN3sve12experimental14parallelism_v24simdIdNS8_8simd_abi7sve_abiEEENS8_9simd_maskIdSB_EES3_N8recycler24aggregated_recycled_viewINS_4ViewIPdJNS_11LayoutRightENS_9HostSpaceENS_12MemoryTraitsILj1EEEEEE15Allocator_SliceIdSaIdEN3hpx6kokkos8executorIS3_EEEdEENSG_INSH_IPiJSJ_SK_SM_EEESO_IiSaIiEST_EiEEEvRNSS_IT1_EERN19Aggregated_ExecutorIS12_E14Executor_SliceEdiiRKT3_S1A_RT2_RKS1B_S1C_S1C_S1E_S1E_iiimmEUlRKNS_4Impl13HPXTeamMemberEE_vEEvRKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_+0x3f4)[0x400000dde634] [l01-0209c:00103] [ 5] /vol0003/mdt0/data/hp210311/u10393/OctoTigerBuildChain/build/octotiger/build/libhpx_hydrolib.so(_ZZ27launch_hydro_kokkos_kernelsIN3hpx6kokkos8executorIN6Kokkos12Experimental3HPXEEEE10timestep_tRK14hydro_computerILi3ELi8E7physicsILi3EEERKSt6vectorISE_IdSaIdEESaISG_EESK_dmRT_RSE_I13hydro_state_tISG_ESaISO_EEENKUlOSL_E_clINS0_6futureIN19Aggregated_ExecutorIS6_E14Executor_SliceEEEEEDaSS_+0x27c4)[0x400000df51c4] [l01-0209c:00103] [ 6] /vol0003/mdt0/data/hp210311/u10393/OctoTigerBuildChain/build/octotiger/build/libhpx_hydrolib.so(_ZN3hpx4lcos6detail19invoke_continuationINS_6detail18annotated_functionIZ27launch_hydro_kokkos_kernelsINS_6kokkos8executorIN6Kokkos12Experimental3HPXEEEE10timestep_tRK14hydro_computerILi3ELi8E7physicsILi3EEERKSt6vectorISJ_IdSaIdEESaISL_EESP_dmRT_RSJ_I13hydro_state_tISL_ESaIST_EEEUlOSQ_E_EENS_6futureIN19Aggregated_ExecutorISB_E14Executor_SliceEEENS1_12continuationIS14_SZ_SC_EEEENSt9enable_ifIXntsrNS_6traits6detail16is_unique_futureINS_4util13invoke_resultISQ_JT0_EE4typeEvEE5valueEvE4typeESR_OS1D_RT1_+0x278)[0x400000df5898] [l01-0209c:00103] [ 7] /vol0003/mdt0/data/hp210311/u10393/OctoTigerBuildChain/build/octotiger/build/libhpx_hydrolib.so(_ZN3hpx4util6detail15callable_vtableIFSt4pairINS_7threads21thread_schedule_stateENS4_9thread_idEENS4_20thread_restart_stateEEE7_invokeINS4_6detail23thread_function_nullaryIZNS_4lcos6detail12continuationINS_6futureIN19Aggregated_ExecutorINS_6kokkos8executorIN6Kokkos12Experimental3HPXEEEE14Executor_SliceEEENS_6detail18annotated_functionIZ27launch_hydro_kokkos_kernelsISO_E10timestep_tRK14hydro_computerILi3ELi8E7physicsILi3EEERKSt6vectorIS12_IdSaIdEESaIS14_EES18_dmRT_RS12_I13hydro_state_tIS14_ESaIS1C_EEEUlOS19_E_EESV_E5asyncINSF_19post_policy_spawnerEEEvONS_13intrusive_ptrINSF_16future_data_baseISQ_EEEES1G_RNS_10error_codeEEUlvE_EEEES7_PvOS8_+0x6c)[0x400000dc332c] [l01-0209c:00103] [ 8] /vol0003/mdt0/data/hp210311/u10393/OctoTigerBuildChain/build/hpx/lib64/libhpx_core.so(_ZN3hpx7threads10coroutines6detail14coroutine_implclEv+0xf4)[0x400001996714] [l01-0209c:00103] [ 9] /vol0003/mdt0/data/hp210311/u10393/OctoTigerBuildChain/build/hpx/lib64/libhpx_core.so(+0x115e38)[0x400001995e38] [l01-0209c:00103] [10] /vol0003/mdt0/data/hp210311/u10393/OctoTigerBuildChain/build/boost/lib/libboost_context.so.1.79.0(make_fcontext+0x18)[0x400001e70b9c] [l01-0209c:00103] *** End of error message ***
... Please be as specific as possible while describing how to reproduce your problem.
... Please describe your environment
I can reproduce this on Perlmutter for dwd and v1309.
Ok, compiling without-simd and the bug is gone.
without-simd
cc @srinivasyadav18
This bug does not appear with the latest version and can be closed.
Expected Behavior
The DWD run should finish
Actual Behavior
However, we get a floating point exception using the more block branch.
Steps to Reproduce the Problem
... Please be as specific as possible while describing how to reproduce your problem.
Specifications
... Please describe your environment