|
3608 | 3608 | <MAX_MPITASKS_PER_NODE compiler="oneapi-ifxgpu">12</MAX_MPITASKS_PER_NODE> |
3609 | 3609 | <PROJECT_REQUIRED>FALSE</PROJECT_REQUIRED> |
3610 | 3610 | <mpirun mpilib="default"> |
3611 | | - <executable>mpiexec</executable> |
3612 | | - <!--executable>numactl -m 2-3 mpiexec</executable--><!--for HBM runs--> |
3613 | | - <arguments> |
3614 | | - <arg name="total_num_tasks">-np {{ total_tasks }} --label</arg> |
3615 | | - <arg name="ranks_per_node">-ppn {{ tasks_per_node }}</arg> |
3616 | | - <arg name="ranks_bind">--cpu-bind $ENV{RANKS_BIND}</arg> |
3617 | | - <arg name="threads_per_rank">-d $ENV{OMP_NUM_THREADS}</arg> |
3618 | | - <arg name="gpu_maps">$ENV{GPU_TILE_COMPACT}</arg> |
3619 | | - </arguments> |
| 3611 | + <executable>mpiexec</executable> |
| 3612 | + <!--executable>numactl -m 2-3 mpiexec</executable--><!--for HBM runs--> |
| 3613 | + <arguments> |
| 3614 | + <arg name="total_num_tasks">-np {{ total_tasks }} --label</arg> |
| 3615 | + <arg name="ranks_per_node">-ppn {{ tasks_per_node }}</arg> |
| 3616 | + <arg name="ranks_bind">--cpu-bind $ENV{RANKS_BIND}</arg> |
| 3617 | + <arg name="threads_per_rank">-d $ENV{OMP_NUM_THREADS} $ENV{RLIMITS}</arg> |
| 3618 | + <arg name="gpu_maps">$ENV{GPU_TILE_COMPACT}</arg> |
| 3619 | + </arguments> |
3620 | 3620 | </mpirun> |
3621 | 3621 | <module_system type="module" allow_error="true"> |
3622 | | - <init_path lang="sh">/usr/share/lmod/lmod/init/sh</init_path> |
3623 | | - <init_path lang="csh">/usr/share/lmod/lmod/init/csh</init_path> |
3624 | | - <init_path lang="python">/usr/share/lmod/lmod/init/env_modules_python.py</init_path> |
3625 | | - <cmd_path lang="sh">module</cmd_path> |
3626 | | - <cmd_path lang="csh">module</cmd_path> |
3627 | | - <cmd_path lang="python">/usr/share/lmod/lmod/libexec/lmod python</cmd_path> |
3628 | | - <modules> |
3629 | | - <command name="load">cmake/3.30.5</command> |
3630 | | - <command name="load">oneapi/release/2025.0.5</command> |
3631 | | - </modules> |
3632 | | - </module_system> |
3633 | | - <RUNDIR>$CIME_OUTPUT_ROOT/$CASE/run</RUNDIR> |
3634 | | - <EXEROOT>$CIME_OUTPUT_ROOT/$CASE/bld</EXEROOT> |
3635 | | - <MAX_GB_OLD_TEST_DATA>0</MAX_GB_OLD_TEST_DATA> |
3636 | | - <environment_variables> |
| 3622 | + <init_path lang="sh">/usr/share/lmod/lmod/init/sh</init_path> |
| 3623 | + <init_path lang="csh">/usr/share/lmod/lmod/init/csh</init_path> |
| 3624 | + <init_path lang="python">/usr/share/lmod/lmod/init/env_modules_python.py</init_path> |
| 3625 | + <cmd_path lang="sh">module</cmd_path> |
| 3626 | + <cmd_path lang="csh">module</cmd_path> |
| 3627 | + <cmd_path lang="python">/usr/share/lmod/lmod/libexec/lmod python</cmd_path> |
| 3628 | + <modules> |
| 3629 | + <command name="load">cmake/3.30.5</command> |
| 3630 | + <command name="load">oneapi/release/2025.0.5</command> |
| 3631 | + <command name="load">mpich-config/collective-tuning/1024</command> |
| 3632 | + </modules> |
| 3633 | + </module_system> |
| 3634 | + <RUNDIR>$CIME_OUTPUT_ROOT/$CASE/run</RUNDIR> |
| 3635 | + <EXEROOT>$CIME_OUTPUT_ROOT/$CASE/bld</EXEROOT> |
| 3636 | + <MAX_GB_OLD_TEST_DATA>0</MAX_GB_OLD_TEST_DATA> |
| 3637 | + <environment_variables> |
3637 | 3638 | <env name="NETCDF_PATH">/lus/flare/projects/E3SM_Dec/soft/netcdf/4.9.2c-4.6.1f/oneapi.eng.2024.07.30.002</env> |
3638 | 3639 | <env name="PNETCDF_PATH">/lus/flare/projects/E3SM_Dec/soft/pnetcdf/1.14.0/oneapi.eng.2024.07.30.002</env> |
3639 | 3640 | <env name="LD_LIBRARY_PATH">/lus/flare/projects/E3SM_Dec/soft/pnetcdf/1.14.0/oneapi.eng.2024.07.30.002/lib:/lus/flare/projects/E3SM_Dec/soft/netcdf/4.9.2c-4.6.1f/oneapi.eng.2024.07.30.002/lib:$ENV{LD_LIBRARY_PATH}</env> |
3640 | 3641 | <env name="PATH">/lus/flare/projects/E3SM_Dec/soft/pnetcdf/1.14.0/oneapi.eng.2024.07.30.002/bin:/lus/flare/projects/E3SM_Dec/soft/netcdf/4.9.2c-4.6.1f/oneapi.eng.2024.07.30.002/bin:$ENV{PATH}</env> |
3641 | 3642 | <env name="FI_CXI_DEFAULT_CQ_SIZE">131072</env> |
3642 | 3643 | <env name="FI_CXI_CQ_FILL_PERCENT">20</env> |
| 3644 | + <env name="RLIMITS"> </env> |
3643 | 3645 | </environment_variables> |
3644 | 3646 | <environment_variables compiler="oneapi-ifxgpu"> |
3645 | 3647 | <env name="ONEAPI_DEVICE_SELECTOR">level_zero:gpu</env> |
3646 | | - <env name="MPIR_CVAR_CH4_COLL_SELECTION_TUNING_JSON_FILE"></env> |
3647 | | - <env name="MPIR_CVAR_COLL_SELECTION_TUNING_JSON_FILE"></env> |
3648 | | - <env name="MPIR_CVAR_CH4_POSIX_COLL_SELECTION_TUNING_JSON_FILE"></env> |
3649 | 3648 | <env name="UR_L0_USE_DRIVER_INORDER_LISTS">1</env> |
3650 | 3649 | <env name="UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS">1</env> |
3651 | 3650 | <env name="UR_L0_USE_COPY_ENGINE_FOR_IN_ORDER_QUEUE">1</env> |
3652 | | - <!--<env name="FI_PROVIDER">cxi</env>--> |
3653 | | - <env name="FI_MR_CACHE_MONITOR">disabled</env> |
| 3651 | + <env name="FI_MR_CACHE_MONITOR">disabled</env> |
3654 | 3652 | <env name="FI_CXI_OVFLOW_BUF_SIZE">8388608</env> |
3655 | 3653 | <env name="PALS_PING_PERIOD">240</env> |
3656 | 3654 | <env name="PALS_RPC_TIMEOUT">240</env> |
| 3655 | + <env name="SYCL_PI_LEVEL_ZERO_SINGLE_THREAD_MODE">1</env> |
| 3656 | + <env name="SYCL_PI_LEVEL_ZERO_DISABLE_USM_ALLOCATOR">1</env> |
| 3657 | + <env name="SYCL_PI_LEVEL_ZERO_USM_RESIDENT">0x001</env> |
| 3658 | + <env name="UR_L0_USE_DRIVER_INORDER_LISTS">1</env> |
| 3659 | + <env name="UR_L0_USE_COPY_ENGINE_FOR_IN_ORDER_QUEUE">1</env> |
3657 | 3660 |
|
3658 | | - <env name="MPIR_CVAR_ENABLE_GPU">1</env> |
| 3661 | + <env name="MPIR_CVAR_ENABLE_GPU">1</env> |
3659 | 3662 | <env name="romio_cb_read">disable</env> |
3660 | 3663 | <env name="romio_cb_write">disable</env> |
3661 | | - <env name="SYCL_CACHE_PERSISTENT">1</env> |
3662 | 3664 | <env name="GATOR_INITIAL_MB">4000MB</env> |
3663 | 3665 | <env name="GATOR_DISABLE">0</env> |
3664 | 3666 | <env name="GPU_TILE_COMPACT">/lus/flare/projects/E3SM_Dec/tools/mpi_wrapper_utils/gpu_tile_compact.sh</env> |
3665 | 3667 | <env name="RANKS_BIND">list:1-8:9-16:17-24:25-32:33-40:41-48:53-60:61-68:69-76:77-84:85-92:93-100 --gpu-bind list:0.0:0.1:1.0:1.1:2.0:2.1:3.0:3.1:4.0:4.1:5.0:5.1 --mem-bind list:0:0:0:0:0:0:1:1:1:1:1:1</env> |
3666 | 3668 | <env name="ZES_ENABLE_SYSMAN">1</env> |
3667 | | - <!-- default is ZE_FLAT_DEVICE_HIERARCHY=COMPOSITE: enable this to run 4 MPI/tile or 48 MPI/node |
3668 | | - <env name="ZEX_NUMBER_OF_CCS">0:4,1:4,2:4,3:4:4:4,5:4</env>--> |
3669 | | - <!-- <env name="ZE_FLAT_DEVICE_HIERARCHY">FLAT</env> |
3670 | | - <env name="ZEX_NUMBER_OF_CCS">0:4,1:4,2:4,3:4:4:4,5:4,6:4,7:4,8:4,9:4,10:4,11:4</env>--> |
| 3669 | + <!-- default is ZE_FLAT_DEVICE_HIERARCHY=COMPOSITE: enable this to run 4 MPI/tile or 48 MPI/node |
| 3670 | + <env name="ZEX_NUMBER_OF_CCS">0:4,1:4,2:4,3:4:4:4,5:4</env>--> |
| 3671 | + <!-- <env name="ZE_FLAT_DEVICE_HIERARCHY">FLAT</env> |
| 3672 | + <env name="ZEX_NUMBER_OF_CCS">0:4,1:4,2:4,3:4:4:4,5:4,6:4,7:4,8:4,9:4,10:4,11:4</env>--> |
3671 | 3673 | </environment_variables> |
3672 | 3674 | <environment_variables compiler="oneapi-ifx"> |
3673 | 3675 | <env name="LIBOMPTARGET_DEBUG">0</env><!--default 0, max 5 --> |
|
3680 | 3682 | <env name="KMP_AFFINITY">granularity=core,balanced</env> |
3681 | 3683 | <env name="OMP_STACKSIZE">128M</env> |
3682 | 3684 | </environment_variables> |
| 3685 | + <environment_variables DEBUG="TRUE"> |
| 3686 | + <env name="RLIMITS">--rlimits CORE</env> |
| 3687 | + </environment_variables> |
| 3688 | + <resource_limits DEBUG="TRUE"> |
| 3689 | + <resource name="RLIMIT_CORE">-1</resource> |
| 3690 | + </resource_limits> |
3683 | 3691 | <resource_limits> |
3684 | 3692 | <resource name="RLIMIT_STACK">-1</resource> |
3685 | 3693 | </resource_limits> |
|
0 commit comments