# Invocation command line: # /home/HPC2021F1.0.1/bin/harness/runhpc --reportable --config=6Ns_AMD_I204_O410.cfg --tune=base --pmodel=OMP --define model=omp --threads=8 --rank=32 --size=ref --iterations=3 tiny # output_root was not used for this run ############################################################################ #strict_rundir_verify=1 %ifndef %{label} # IF acctype is not set use mpi % define label I204_OMPI410_AMD %endif %ifndef %{model} # IF acctype is not set use mpi % define model mpi pmodel=MPI #% define acctype omp #% define acctype cuda %endif teeout = yes makeflags=-j 32 flagsurl000=http://www.spec.org/hpc2021/flags/Intel_compiler_flags.2021-10-20.xml label = %{label}_%{model} tune = base output_format = text use_submit_for_speed = 1 default: CC = mpicc CXX = mpicxx FC = mpifort CC_VERSION_OPTION = -V -c CXX_VERSION_OPTION = -V -c FC_VERSION_OPTION = -V -c submit = mpirun --allow-run-as-root --oversubscribe --bind-to numa -map-by numa -mca coll_hcoll_enable 1 -x HCOLL_ENABLE_NBC=1 -x HCOLL_MAIN_IB=mlx5_0:1 -mca pml ucx -hostfile /home/HPC2021K35/config/5nodes -npernode 128 -np $ranks $command %if %{model} eq 'omp' submit = mpirun --allow-run-as-root --oversubscribe -mca coll_hcoll_enable 1 -x HCOLL_ENABLE_NBC=1 -x HCOLL_MAIN_IB=mlx5_0:1 -mca pml ucx -hostfile /home/HPC2021K35/config/5nodes --map-by ppr:16:node:pe=8 -np $ranks $command %endif default=base=default: OPTIMIZE = -Ofast -no-prec-div -march=core-avx2 -ipo COPTIMIZE = -ansi-alias CXXOPTIMIZE = -ansi-alias #PORTABILITY = -DSPEC_LP64 #PORTABILITY += -std=c99 %if %{model} eq 'omp' pmodel = OMP OPTIMIZE += -qopenmp %endif #510.picongpu_t=default=default: #PORTABILITY += -DSPEC_NO_PIC_USE_MALLOCMC #CXXPORTABILITY += -DSPEC_NO_PIC_USE_MALLOCMC #LIBS = -lpthread -lm -ldl -lrt /usr/lib64/libz.so -L%{BOOST_DIR}/lib -L/opt/crtdc/cuda/10.1/lib64 #611.palm_s,711.palm_m=default=default: #PORTABILITY += -D__mpifh 613.soma_s=default=default: %if %{model} eq 'omp' PORTABILITY += -DSPEC_NO_VAR_ARRAY_REDUCE %endif 513.soma_t=default=default: %if %{model} eq 'omp' PORTABILITY += -DSPEC_NO_VAR_ARRAY_REDUCE %endif # The following section was added automatically, and contains settings that # did not appear in the original configuration file, but were added to the # raw file after the run. default: system_class = Homogenous sw_compiler = Intel C/C++/Fortran Compiler 20.4 sw_mpi_library = Open MPI 4.0.5 test_sponsor = Lenovo Global Technology license_num = 28 tester = Lenovo Global Technology hw_avail = Mar-2021 sw_avail = Oct-2020 prepared_by = Lenovo Global Technology system_vendor = Lenovo Global Technology system_name = ThinkSystem SR665 (AMD EPYC 7763) node_fileserver_syslbl = ThinkSystem SR665 node_fileserver_sw_state = Multi-User, run level 3 node_fileserver_sw_sharedfile = N/A node_fileserver_sw_other = None node_fileserver_sw_os = Red Hat Enterprise Linux Server release 8.3 node_fileserver_sw_localfile = xfs node_fileserver_purpose = Fileserver node_fileserver_order = 1 node_fileserver_hw_vendor = Lenovo Global Technology node_fileserver_hw_scache = 512 KB I+D on chip per core node_fileserver_hw_pcache = 32 KB I + 32 KB D on chip per core node_fileserver_hw_other = None node_fileserver_hw_ocache = None node_fileserver_hw_nthreadspercore = 1 node_fileserver_hw_ncpuorder = 1,2 chips node_fileserver_hw_ncoresperchip = 64 node_fileserver_hw_ncores = 128 node_fileserver_hw_nchips = 2 node_fileserver_hw_model = ThinkSystem SR665 node_fileserver_hw_memory = 512 GB (16 x 32 GB 2Rx8 PC4-3200A-R) node_fileserver_hw_disk = 1 x 480 GB 2.5" SSD node_fileserver_hw_cpu_name = AMD EPYC 7763 node_fileserver_hw_cpu_mhz = 2450 node_fileserver_hw_cpu_char = Max Boost Clock up to 3.5 GHz node_fileserver_hw_adapter_fs_slot_type = PCI-Express 4.0 x16 node_fileserver_hw_adapter_fs_ports_used = 1 node_fileserver_hw_adapter_fs_model = Mellanox ConnectX-6 HDR node_fileserver_hw_adapter_fs_interconnect = Nvidia Mellanox ConnectX-6 HDR node_fileserver_hw_adapter_fs_firmware = 20.28.1002 node_fileserver_hw_adapter_fs_driver = 5.2-1.0.4 node_fileserver_hw_adapter_fs_data_rate = 200 Gb/s node_fileserver_hw_adapter_fs_count = 1 node_fileserver_count = 1 node_compute_syslbl = ThinkSystem SR665 node_compute_sw_state = Multi-user, run level 3 node_compute_sw_sharedfile = NFS node_compute_sw_other = None node_compute_sw_localfile = xfs node_compute_purpose = Compute node_compute_order = 1 node_compute_hw_vendor = Lenovo Global Technology node_compute_hw_scache = 512 KB I+D on chip per core node_compute_hw_pcache = 32 KB I + 32 KB D on chip per core node_compute_hw_other = None node_compute_hw_ocache = None node_compute_hw_nthreadspercore = 1 node_compute_hw_ncpuorder = 1,2 chips node_compute_hw_ncoresperchip = 64 node_compute_hw_ncores = 128 node_compute_hw_nchips = 2 node_compute_hw_model = ThinkSystem SR665 node_compute_hw_memory = 512 GB (16 x 32 GB 2Rx8 PC4-3200A-R) node_compute_hw_disk = 1 x 480 GB 2.5" SSD node_compute_hw_cpu_name = AMD EPYC 7763 node_compute_hw_cpu_mhz = 2450 node_compute_hw_cpu_char = Max Boost Clock up to 3.5 GHz node_compute_hw_adapter_fs_slot_type = PCI-Express 4.0 x16 node_compute_hw_adapter_fs_ports_used = 1 node_compute_hw_adapter_fs_model = Mellanox ConnectX-6 HDR node_compute_hw_adapter_fs_interconnect = Nvidia Mellanox ConnectX-6 HDR node_compute_hw_adapter_fs_firmware = 20.28.1002 node_compute_hw_adapter_fs_driver = 5.2-1.0.4 node_compute_hw_adapter_fs_data_rate = 200 Gb/s node_compute_hw_adapter_fs_count = 1 node_compute_count = 2 interconnect_fs_syslbl = Nvidia Mellanox ConnectX-6 HDR interconnect_fs_purpose = MPI Traffic, NFS Access interconnect_fs_order = 0 interconnect_fs_label = Nvidia Mellanox ConnectX-6 HDR interconnect_fs_hw_vendor = Nvidia interconnect_fs_hw_topo = Mesh interconnect_fs_hw_switch_fs_ports = 40 interconnect_fs_hw_switch_fs_model = QM8700 Series interconnect_fs_hw_switch_fs_firmware = 3.9.0606 interconnect_fs_hw_switch_fs_data_rate = 200 Gb/s interconnect_fs_hw_switch_fs_count = 1 interconnect_fs_hw_model = Nvidia Mellanox ConnectX-6 HDR node_compute_hw_tcache000 = 256 MB I+D on chip per chip node_compute_hw_tcache001 = 32 MB shared / 8 cores node_compute_sw_os000 = Red Hat Enterprise Linux Server release 8.3, node_compute_sw_os001 = Kernel 4.18.0-193.el8.x86_64 node_fileserver_hw_tcache000 = 256 MB I+D on chip per chip node_fileserver_hw_tcache001 = 32 MB shared / 8 cores notes_000 =Environment variables set by runhpc before the start of the run: notes_005 =UCX_MEMTYPE_CACHE = "n" notes_010 =UCX_TLS = "self,shm,cuda_copy" notes_015 = notes_submit_000 = The config file option 'submit' was used. notes_submit_005 = submit = mpirun ${MPIRUN_OPTS} --allow-run-as-root --oversubscribe notes_submit_010 =--bind-to numa -map-by numa notes_submit_015 =-mca coll_hcoll_enable 1 -x HCOLL_ENABLE_NBC=1 notes_submit_020 =-x HCOLL_MAIN_IB=mlx5_0:1 -mca pml ucx notes_submit_025 =-hostfile /home/HPC2021K35/config/6nodes -npernode 128 -np $ranks $command