Thanks, but that did not work. It looks like this is just in MPIAIJ, but I am using SeqAIJ. ex2 (below) uses PETSC_COMM_SELF everywhere.
+ srun -G 1 -n 16 -c 1 --cpu-bind=cores --ntasks-per-core=2 /global/homes/m/madams/mps-wrapper.sh ../ex2 -dm_landau_device_type cuda -dm_mat_type aijcusparse -dm_vec_type cuda -log_view -pc_type gamg -ksp_type gmres -pc_gamg_reuse_interpolation *-matmatmult_backend_cpu -matptap_backend_cpu *-dm_landau_ion_masses .0005,1,1,1,1,1,1,1,1 -dm_landau_ion_charges 1,2,3,4,5,6,7,8,9 -dm_landau_thermal_temps 1,1,1,1,1,1,1,1,1,1 -dm_landau_n 1.000003,.5,1e-7,1e-7,1e-7,1e-7,1e-7,1e-7,1e-7,1e-7 0 starting nvidia-cuda-mps-control on cgpu17 mps ready: 2021-07-07T06:17:36-07:00 masses: e= 9.109e-31; ions in proton mass units: 5.000e-04 1.000e+00 ... charges: e=-1.602e-19; charges in elementary units: 1.000e+00 2.000e+00 thermal T (K): e= 1.160e+07 i= 1.160e+07 imp= 1.160e+07. v_0= 1.326e+07 n_0= 1.000e+20 t_0= 5.787e-06 domain= 5.000e+00 CalculateE j0=0. Ec = 0.050991 0 TS dt 1. time 0. 0) species-0: charge density= -1.6054532569865e+01 z-momentum= -1.9059929215360e-19 energy= 2.4178543516210e+04 0) species-1: charge density= 8.0258396545108e+00 z-momentum= 7.0660527288120e-20 energy= 1.2082380663859e+04 0) species-2: charge density= 6.3912608577597e-05 z-momentum= -1.1513901010709e-24 energy= 3.5799558195524e-01 0) species-3: charge density= 9.5868912866395e-05 z-momentum= -1.1513901010709e-24 energy= 3.5799558195524e-01 0) species-4: charge density= 1.2782521715519e-04 z-momentum= -1.1513901010709e-24 energy= 3.5799558195524e-01 [7]PETSC ERROR: --------------------- Error Message -------------------------------------------------------------- [7]PETSC ERROR: GPU resources unavailable [7]PETSC ERROR: CUDA error 2 (cudaErrorMemoryAllocation) : out of memory. Reports alloc failed; this indicates the GPU has run out resources [7]PETSC ERROR: See https://www.mcs.anl.gov/petsc/documentation/faq.html for trouble shooting. [7]PETSC ERROR: Petsc Development GIT revision: v3.15.1-569-g270a066c1e GIT Date: 2021-07-06 03:22:54 -0700 [7]PETSC ERROR: ../ex2 on a arch-cori-gpu-opt-gcc named cgpu17 by madams Wed Jul 7 06:17:38 2021 [7]PETSC ERROR: Configure options --with-mpi-dir=/usr/common/software/sles15_cgpu/openmpi/4.0.3/gcc --with-cuda-dir=/usr/common/software/sles15_cgpu/cuda/11.1.1 --CFLAGS=" -g -DLANDAU_DIM=2 -DLANDAU_MAX_SPECIES=10 -DLANDAU_MAX_Q=4" --CXXFLAGS=" -g -DLANDAU_DIM=2 -DLANDAU_MAX_SPECIES=10 -DLANDAU_MAX_Q=4" --CUDAFLAGS="-g -Xcompiler -rdynamic -DLANDAU_DIM=2 -DLANDAU_MAX_SPECIES=10 -DLANDAU_MAX_Q=4" --FFLAGS=" -g " --COPTFLAGS=" -O3" --CXXOPTFLAGS=" -O3" --FOPTFLAGS=" -O3" --download-fblaslapack=1 --with-debugging=0 --with-mpiexec="srun -G 1" --with-cuda-gencodearch=70 --with-batch=0 --with-cuda=1 --download-p4est=1 --download-hypre=1 --with-zlib=1 PETSC_ARCH=arch-cori-gpu-opt-gcc *[7]PETSC ERROR: #1 MatProductSymbolic_SeqAIJCUSPARSE_SeqAIJCUSPARSE() at /global/u2/m/madams/petsc/src/mat/impls/aij/seq/seqcusparse/aijcusparse.cu:2622 <http://aijcusparse.cu:2622>*[7]PETSC ERROR: #2 MatProductSymbolic_ABC_Basic() at /global/u2/m/madams/petsc/src/mat/interface/matproduct.c:1146 [7]PETSC ERROR: #3 MatProductSymbolic() at /global/u2/m/madams/petsc/src/mat/interface/matproduct.c:799 [7]PETSC ERROR: #4 MatPtAP() at /global/u2/m/madams/petsc/src/mat/interface/matrix.c:9626 [7]PETSC ERROR: #5 PCGAMGCreateLevel_GAMG() at /global/u2/m/madams/petsc/src/ksp/pc/impls/gamg/gamg.c:87 [7]PETSC ERROR: #6 PCSetUp_GAMG() at /global/u2/m/madams/petsc/src/ksp/pc/impls/gamg/gamg.c:663 [7]PETSC ERROR: #7 PCSetUp() at /global/u2/m/madams/petsc/src/ksp/pc/interface/precon.c:1014 [7]PETSC ERROR: #8 KSPSetUp() at /global/u2/m/madams/petsc/src/ksp/ksp/interface/itfunc.c:406 [7]PETSC ERROR: #9 KSPSolve_Private() at /global/u2/m/madams/petsc/src/ksp/ksp/interface/itfunc.c:850 [7]PETSC ERROR: #10 KSPSolve() at /global/u2/m/madams/petsc/src/ksp/ksp/interface/itfunc.c:1084 [7]PETSC ERROR: #11 SNESSolve_NEWTONLS() at /global/u2/m/madams/petsc/src/snes/impls/ls/ls.c:225 [7]PETSC ERROR: #12 SNESSolve() at /global/u2/m/madams/petsc/src/snes/interface/snes.c:4769 [7]PETSC ERROR: #13 TSTheta_SNESSolve() at /global/u2/m/madams/petsc/src/ts/impls/implicit/theta/theta.c:185 [7]PETSC ERROR: #14 TSStep_Theta() at /global/u2/m/madams/petsc/src/ts/impls/implicit/theta/theta.c:223 [7]PETSC ERROR: #15 TSStep() at /global/u2/m/madams/petsc/src/ts/interface/ts.c:3571 [7]PETSC ERROR: #16 TSSolve() at /global/u2/m/madams/petsc/src/ts/interface/ts.c:3968 [7]PETSC ERROR: #17 main() at ex2.c:699 [7]PETSC ERROR: PETSc Option Table entries: [7]PETSC ERROR: -dm_landau_amr_levels_max 0 [7]PETSC ERROR: -dm_landau_amr_post_refine 5 [7]PETSC ERROR: -dm_landau_device_type cuda [7]PETSC ERROR: -dm_landau_domain_radius 5 [7]PETSC ERROR: -dm_landau_Ez 0 [7]PETSC ERROR: -dm_landau_ion_charges 1,2,3,4,5,6,7,8,9 [7]PETSC ERROR: -dm_landau_ion_masses .0005,1,1,1,1,1,1,1,1 [7]PETSC ERROR: -dm_landau_n 1.000003,.5,1e-7,1e-7,1e-7,1e-7,1e-7,1e-7,1e-7,1e-7 [7]PETSC ERROR: -dm_landau_thermal_temps 1,1,1,1,1,1,1,1,1,1 [7]PETSC ERROR: -dm_landau_type p4est [7]PETSC ERROR: -dm_mat_type aijcusparse [7]PETSC ERROR: -dm_preallocate_only [7]PETSC ERROR: -dm_vec_type cuda [7]PETSC ERROR: -ex2_connor_e_field_units [7]PETSC ERROR: -ex2_impurity_index 1 [7]PETSC ERROR: -ex2_plot_dt 200 [7]PETSC ERROR: -ex2_test_type none [7]PETSC ERROR: -ksp_type gmres [7]PETSC ERROR: -log_view *[7]PETSC ERROR: -matmatmult_backend_cpu[7]PETSC ERROR: -matptap_backend_cpu* [7]PETSC ERROR: -pc_gamg_reuse_interpolation [7]PETSC ERROR: -pc_type gamg [7]PETSC ERROR: -petscspace_degree 1 [7]PETSC ERROR: -snes_max_it 15 [7]PETSC ERROR: -snes_rtol 1.e-6 [7]PETSC ERROR: -snes_stol 1.e-6 [7]PETSC ERROR: -ts_adapt_scale_solve_failed 0.5 [7]PETSC ERROR: -ts_adapt_time_step_increase_delay 5 [7]PETSC ERROR: -ts_dt 1 [7]PETSC ERROR: -ts_exact_final_time stepover [7]PETSC ERROR: -ts_max_snes_failures -1 [7]PETSC ERROR: -ts_max_steps 10 [7]PETSC ERROR: -ts_max_time 300 [7]PETSC ERROR: -ts_rtol 1e-2 [7]PETSC ERROR: -ts_type beuler On Wed, Jul 7, 2021 at 4:07 AM Stefano Zampini <[email protected]> wrote: > This will select the CPU path > > -matmatmult_backend_cpu -matptap_backend_cpu > > On Jul 7, 2021, at 2:43 AM, Mark Adams <[email protected]> wrote: > > Can I turn off using cuSprarse for RAP? > > On Tue, Jul 6, 2021 at 6:25 PM Barry Smith <[email protected]> wrote: > >> >> Stefano has mentioned this before. He reported cuSparse matrix-matrix >> vector products use a very amount of memory. >> >> On Jul 6, 2021, at 4:33 PM, Mark Adams <[email protected]> wrote: >> >> I am running out of memory in GAMG. It looks like this is from the new >> cuSparse RAP. >> I was able to run Hypre with twice as much work on the GPU as this run. >> Are there parameters to tweek for this perhaps or can I disable it? >> >> Thanks, >> Mark >> >> 0 SNES Function norm 5.442539952302e-04 >> [2]PETSC ERROR: --------------------- Error Message >> -------------------------------------------------------------- >> [2]PETSC ERROR: GPU resources unavailable >> [2]PETSC ERROR: CUDA error 2 (cudaErrorMemoryAllocation) : out of memory. >> Reports alloc failed; this indicates the GPU has run out resources >> [2]PETSC ERROR: See https://www.mcs.anl.gov/petsc/documentation/faq.html >> for trouble shooting. >> [2]PETSC ERROR: Petsc Development GIT revision: v3.15.1-569-g270a066c1e >> GIT Date: 2021-07-06 03:22:54 -0700 >> [2]PETSC ERROR: ../ex2 on a arch-cori-gpu-opt-gcc named cgpu11 by madams >> Tue Jul 6 13:37:43 2021 >> [2]PETSC ERROR: Configure options >> --with-mpi-dir=/usr/common/software/sles15_cgpu/openmpi/4.0.3/gcc >> --with-cuda-dir=/usr/common/software/sles15_cgpu/cuda/11.1.1 --CFLAGS=" >> -g -DLANDAU_DIM=2 -DLANDAU_MAX_SPECI >> ES=10 -DLANDAU_MAX_Q=4" --CXXFLAGS=" -g -DLANDAU_DIM=2 >> -DLANDAU_MAX_SPECIES=10 -DLANDAU_MAX_Q=4" --CUDAFLAGS="-g -Xcompiler >> -rdynamic -DLANDAU_DIM=2 -DLANDAU_MAX_SPECIES=10 -DLANDAU_MAX_Q=4" >> --FFLAGS=" -g " - >> -COPTFLAGS=" -O3" --CXXOPTFLAGS=" -O3" --FOPTFLAGS=" -O3" >> --download-fblaslapack=1 --with-debugging=0 --with-mpiexec="srun -G 1" >> --with-cuda-gencodearch=70 --with-batch=0 --with-cuda=1 --download-p4est=1 >> -- >> download-hypre=1 --with-zlib=1 PETSC_ARCH=arch-cori-gpu-opt-gcc >> [2]PETSC ERROR: #1 MatProductSymbolic_SeqAIJCUSPARSE_SeqAIJCUSPARSE() at >> /global/u2/m/madams/petsc/src/mat/impls/aij/seq/seqcusparse/ >> aijcusparse.cu:2622 >> [2]PETSC ERROR: #2 MatProductSymbolic_ABC_Basic() at >> /global/u2/m/madams/petsc/src/mat/interface/matproduct.c:1159 >> [2]PETSC ERROR: #3 MatProductSymbolic() at >> /global/u2/m/madams/petsc/src/mat/interface/matproduct.c:799 >> [2]PETSC ERROR: #4 MatPtAP() at >> /global/u2/m/madams/petsc/src/mat/interface/matrix.c:9626 >> [2]PETSC ERROR: #5 PCGAMGCreateLevel_GAMG() at >> /global/u2/m/madams/petsc/src/ksp/pc/impls/gamg/gamg.c:87 >> [2]PETSC ERROR: #6 PCSetUp_GAMG() at >> /global/u2/m/madams/petsc/src/ksp/pc/impls/gamg/gamg.c:663 >> [2]PETSC ERROR: #7 PCSetUp() at >> /global/u2/m/madams/petsc/src/ksp/pc/interface/precon.c:1014 >> [2]PETSC ERROR: #8 KSPSetUp() at >> /global/u2/m/madams/petsc/src/ksp/ksp/interface/itfunc.c:406 >> [2]PETSC ERROR: #9 KSPSolve_Private() at >> /global/u2/m/madams/petsc/src/ksp/ksp/interface/itfunc.c:850 >> [2]PETSC ERROR: #10 KSPSolve() at >> /global/u2/m/madams/petsc/src/ksp/ksp/interface/itfunc.c:1084 >> [2]PETSC ERROR: #11 SNESSolve_NEWTONLS() at >> /global/u2/m/madams/petsc/src/snes/impls/ls/ls.c:225 >> [2]PETSC ERROR: #12 SNESSolve() at >> /global/u2/m/madams/petsc/src/snes/interface/snes.c:4769 >> [2]PETSC ERROR: #13 TSTheta_SNESSolve() at >> /global/u2/m/madams/petsc/src/ts/impls/implicit/theta/theta.c:185 >> [2]PETSC ERROR: #14 TSStep_Theta() at >> /global/u2/m/madams/petsc/src/ts/impls/implicit/theta/theta.c:223 >> [2]PETSC ERROR: #15 TSStep() at >> /global/u2/m/madams/petsc/src/ts/interface/ts.c:3571 >> [2]PETSC ERROR: #16 TSSolve() at >> /global/u2/m/madams/petsc/src/ts/interface/ts.c:3968 >> [2]PETSC ERROR: #17 main() at ex2.c:699 >> >> >> >
