# Invocation command line: # /local/home/mcolgrove/ACCELv2b/bin/harness/runaccel -c nvhpc --reportable --define model=tgt accel # output_root was not used for this run ############################################################################ # Invocation command line: # runaccel -c nvhpc --reportable -T base --define model= accel # # MODEL may be one of the following options: # 1. "acc" - Use OpenACC (default) # 2. "lop" - Use OpenMP with "loop" construct # 3. "tgt" - Use OpenMP with "distribute" construct # 4. "smd" - Use OpenMP with "distribute" and inner "simd" construct # 5. "acp" - Use OpenACC with the "parallel" src.alt # 6. "lops" - Use OpenMP with "loop" construct src.alt (no metadirectives) # 7. "tgts" - Use OpenMP with "distribute" construct src.alt (no metadirectives) # 8. "smds" - Use OpenMP with "distribute" and inner "simd" construct src.alt (no metadirectives) # ############################################################################ # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 %ifndef %{model} # IF model is not set use acc % define model acc %endif #################################################################### # Tester information #################################################################### license_num = 9045 tester = NVIDIA Corporation test_sponsor = NVIDIA Corporation ###################################################################### # The header section of the config file. Must appear # before any instances of "default=" # # label = how the binaries you generated will be identified # tune = specify "base" or "peak" or "all" label = nvhpc tune = base output_format = txt,html,pdf teeout = yes teerunout = yes strict_rundir_verify=1 #output_root = /tmp/accel2023 flagsurl000=http://www.spec.org/accel2023/flags/nv2021_flags_v1.0.3.xml # Adjust the number of make jobs to use here makeflags=-j 40 #################################################################### # Hardware information #################################################################### #include: SUT.inc # ----- Begin inclusion of 'SUT.inc' ############################################################################ ##### SUT.inc #### ##### Example of required hardware information for the system under test (SUT) #### default: hw_avail = Feb-2018 sw_avail = Oct-2023 hw_cpu_name = CPU Name hw_cpu_max_mhz = 3700 hw_cpu_nominal_mhz = 2400 hw_nchips = 1 hw_ncores = 40 hw_nthreadspercore = 2 hw_ncpuorder = 2 chips hw_pcache = 32 KB I + 32 KB D on chip per core hw_scache = 1 MB I+D on chip per core hw_tcache = 28160 KB I+D on chip per chip hw_ocache = None hw_vendor = Supermicro hw_model = SuperServer SYS-1029GQ-TRT hw_disk = 1x NVME, 1000 GB, 99999 RPM hw_memory = 384 GB (12 x 32 GB 2Rx4 PC4-2666V-R) hw_other = None # Accelerator description hw_accel_connect = PCIe 3.0 x 16 hw_accel_desc = See Notes hw_accel_ecc = Yes hw_accel_model = Tesla V100 hw_accel_name = Tesla V100-PCIE-16GB hw_accel_type = GPU hw_accel_vendor = NVIDIA sw_accel_driver = NVIDIA UNIX x86_64 Kernel Module 465.19.01 # ---- End inclusion of '/local/home/mcolgrove/ACCELv2b/config/SUT.inc' #################################################################### # Software information #################################################################### default: CC = nvc CXX = nvc++ FC = nvfortran CC_VERSION_OPTION = -V CXX_VERSION_OPTION = -V FC_VERSION_OPTION = -V %if %{model} eq 'acc' pmodel=ACC OPTIMIZE = -fast -acc %endif %if %{model} eq 'acp' pmodel=ACC OPTIMIZE = -fast -acc 450.md,453.clvrleaf,455.seismic,456.spF,457.spC,459.miniGhost,463.swim,470.bt: srcalt=acc_parallel %endif %if %{model} eq 'lop' pmodel=LOP OPTIMIZE = -fast -mp=gpu 403.stencil: PORTABILITY += -DSPEC_NO_NOTHING %endif %if %{model} eq 'lops' pmodel=LOP OPTIMIZE = -fast -mp=gpu srcalt = omp_loop 403.stencil: PORTABILITY += -DSPEC_NO_NOTHING %endif %if %{model} eq 'tgt' OPTIMIZE = -fast -mp=gpu 403.stencil: PORTABILITY += -DSPEC_NO_NOTHING %endif %if %{model} eq 'tgts' pmodel=TGT OPTIMIZE = -fast -mp=gpu srcalt = omp_target 403.stencil: PORTABILITY += -DSPEC_NO_NOTHING %endif %if %{model} eq 'smd' pmodel=SMD OPTIMIZE = -fast -mp=gpu 403.stencil: PORTABILITY += -DSPEC_NO_NOTHING %endif %if %{model} eq 'smds' pmodel=SMD OPTIMIZE = -fast -mp=gpu srcalt = omp_inner_simd 403.stencil: PORTABILITY += -DSPEC_NO_NOTHING %endif 457.spC: PORTABILITY += -mcmodel=medium -Wl,--no-relax 459.miniGhost: EXTRA_LDFLAGS += -Mnomain # The following settings were obtained by running the sysinfo_program # 'specperl $[top]/bin/sysinfo' (sysinfo:SHA:ac6f2b38b7dec295b8795065d3a13319ea78b9367f95037a5e6ed5e46e487861) default: notes_plat_sysinfo_000 = notes_plat_sysinfo_005 = Sysinfo program /local/home/mcolgrove/ACCELv2b/bin/sysinfo notes_plat_sysinfo_010 = Rev: r6622 of 2021-04-07 b1a7d5f8f71be5aff70a755cad7211a0 notes_plat_sysinfo_015 = running on dev-sky5 Thu Oct 12 11:53:15 2023 notes_plat_sysinfo_020 = notes_plat_sysinfo_025 = SUT (System Under Test) info as seen by some common utilities. notes_plat_sysinfo_030 = For more information on this section, see notes_plat_sysinfo_035 = https://www.spec.org/cpu2017/Docs/config.html#sysinfo notes_plat_sysinfo_040 = notes_plat_sysinfo_045 = From /proc/cpuinfo notes_plat_sysinfo_050 = model name : Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz notes_plat_sysinfo_055 = 2 "physical id"s (chips) notes_plat_sysinfo_060 = 80 "processors" notes_plat_sysinfo_065 = cores, siblings (Caution: counting these is hw and system dependent. The following notes_plat_sysinfo_070 = excerpts from /proc/cpuinfo might not be reliable. Use with caution.) notes_plat_sysinfo_075 = cpu cores : 20 notes_plat_sysinfo_080 = siblings : 40 notes_plat_sysinfo_085 = physical 0: cores 0 1 2 3 4 8 9 10 11 12 16 17 18 19 20 24 25 26 27 28 notes_plat_sysinfo_090 = physical 1: cores 0 1 2 3 4 8 9 10 11 12 16 17 18 19 20 24 25 26 27 28 notes_plat_sysinfo_095 = notes_plat_sysinfo_100 = From lscpu from util-linux 2.31.1: notes_plat_sysinfo_105 = Architecture: x86_64 notes_plat_sysinfo_110 = CPU op-mode(s): 32-bit, 64-bit notes_plat_sysinfo_115 = Byte Order: Little Endian notes_plat_sysinfo_120 = CPU(s): 80 notes_plat_sysinfo_125 = On-line CPU(s) list: 0-79 notes_plat_sysinfo_130 = Thread(s) per core: 2 notes_plat_sysinfo_135 = Core(s) per socket: 20 notes_plat_sysinfo_140 = Socket(s): 2 notes_plat_sysinfo_145 = NUMA node(s): 2 notes_plat_sysinfo_150 = Vendor ID: GenuineIntel notes_plat_sysinfo_155 = CPU family: 6 notes_plat_sysinfo_160 = Model: 85 notes_plat_sysinfo_165 = Model name: Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz notes_plat_sysinfo_170 = Stepping: 4 notes_plat_sysinfo_175 = CPU MHz: 1000.909 notes_plat_sysinfo_180 = CPU max MHz: 2401.0000 notes_plat_sysinfo_185 = CPU min MHz: 1000.0000 notes_plat_sysinfo_190 = BogoMIPS: 4800.00 notes_plat_sysinfo_195 = Virtualization: VT-x notes_plat_sysinfo_200 = L1d cache: 32K notes_plat_sysinfo_205 = L1i cache: 32K notes_plat_sysinfo_210 = L2 cache: 1024K notes_plat_sysinfo_215 = L3 cache: 28160K notes_plat_sysinfo_220 = NUMA node0 CPU(s): 0-19,40-59 notes_plat_sysinfo_225 = NUMA node1 CPU(s): 20-39,60-79 notes_plat_sysinfo_230 = Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov notes_plat_sysinfo_235 = pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp notes_plat_sysinfo_240 = lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid notes_plat_sysinfo_245 = aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 notes_plat_sysinfo_250 = xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave notes_plat_sysinfo_255 = avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 notes_plat_sysinfo_260 = invpcid_single pti intel_ppin ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority notes_plat_sysinfo_265 = ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a notes_plat_sysinfo_270 = avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl notes_plat_sysinfo_275 = xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local notes_plat_sysinfo_280 = dtherm ida arat pln pts pku ospke md_clear flush_l1d notes_plat_sysinfo_285 = notes_plat_sysinfo_290 = /proc/cpuinfo cache data notes_plat_sysinfo_295 = cache size : 28160 KB notes_plat_sysinfo_300 = notes_plat_sysinfo_305 = Unable to get information from 'numactl --hardware' notes_plat_sysinfo_310 = Please verify numactl installation. notes_plat_sysinfo_315 = notes_plat_sysinfo_320 = From /proc/meminfo notes_plat_sysinfo_325 = MemTotal: 394882320 kB notes_plat_sysinfo_330 = HugePages_Total: 0 notes_plat_sysinfo_335 = Hugepagesize: 2048 kB notes_plat_sysinfo_340 = notes_plat_sysinfo_345 = /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor has notes_plat_sysinfo_350 = ondemand notes_plat_sysinfo_355 = notes_plat_sysinfo_360 = /usr/bin/lsb_release -d notes_plat_sysinfo_365 = Ubuntu 18.04.2 LTS notes_plat_sysinfo_370 = notes_plat_sysinfo_375 = From /etc/*release* /etc/*version* notes_plat_sysinfo_380 = debian_version: buster/sid notes_plat_sysinfo_385 = os-release: notes_plat_sysinfo_390 = NAME="Ubuntu" notes_plat_sysinfo_395 = VERSION="18.04.2 LTS (Bionic Beaver)" notes_plat_sysinfo_400 = ID=ubuntu notes_plat_sysinfo_405 = ID_LIKE=debian notes_plat_sysinfo_410 = PRETTY_NAME="Ubuntu 18.04.2 LTS" notes_plat_sysinfo_415 = VERSION_ID="18.04" notes_plat_sysinfo_420 = HOME_URL="https://www.ubuntu.com/" notes_plat_sysinfo_425 = SUPPORT_URL="https://help.ubuntu.com/" notes_plat_sysinfo_430 = notes_plat_sysinfo_435 = uname -a: notes_plat_sysinfo_440 = Linux dev-sky5 4.15.0-50-generic #54-Ubuntu SMP Mon May 6 18:46:08 UTC 2019 x86_64 notes_plat_sysinfo_445 = x86_64 x86_64 GNU/Linux notes_plat_sysinfo_450 = notes_plat_sysinfo_455 = Kernel self-reported vulnerability status: notes_plat_sysinfo_460 = notes_plat_sysinfo_465 = CVE-2018-12207 (iTLB Multihit): No status reported notes_plat_sysinfo_470 = CVE-2018-3620 (L1 Terminal Fault): Mitigation: PTE Inversion; VMX: notes_plat_sysinfo_475 = conditional cache flushes, SMT notes_plat_sysinfo_480 = vulnerable notes_plat_sysinfo_485 = Microarchitectural Data Sampling: Mitigation: Clear CPU buffers; SMT notes_plat_sysinfo_490 = vulnerable notes_plat_sysinfo_495 = CVE-2017-5754 (Meltdown): Mitigation: PTI notes_plat_sysinfo_500 = CVE-2018-3639 (Speculative Store Bypass): Mitigation: Speculative Store notes_plat_sysinfo_505 = Bypass disabled via prctl and notes_plat_sysinfo_510 = seccomp notes_plat_sysinfo_515 = CVE-2017-5753 (Spectre variant 1): Mitigation: __user pointer notes_plat_sysinfo_520 = sanitization notes_plat_sysinfo_525 = CVE-2017-5715 (Spectre variant 2): Mitigation: Full generic notes_plat_sysinfo_530 = retpoline, IBPB: conditional, notes_plat_sysinfo_535 = IBRS_FW, STIBP: conditional, RSB notes_plat_sysinfo_540 = filling notes_plat_sysinfo_545 = CVE-2020-0543 (Special Register Buffer Data Sampling): No status reported notes_plat_sysinfo_550 = CVE-2019-11135 (TSX Asynchronous Abort): No status reported notes_plat_sysinfo_555 = notes_plat_sysinfo_560 = run-level 5 Oct 12 10:32 notes_plat_sysinfo_565 = notes_plat_sysinfo_570 = SPEC is set to: /local/home/mcolgrove/ACCELv2b notes_plat_sysinfo_575 = Filesystem Type Size Used Avail Use% Mounted on notes_plat_sysinfo_580 = /dev/sda1 ext4 440G 281G 137G 68% / notes_plat_sysinfo_585 = notes_plat_sysinfo_590 = From /sys/devices/virtual/dmi/id notes_plat_sysinfo_595 = Vendor: Supermicro notes_plat_sysinfo_600 = Product: SYS-1029GQ-TRT notes_plat_sysinfo_605 = Product Family: SMC X11 notes_plat_sysinfo_610 = notes_plat_sysinfo_615 = Cannot run dmidecode; consider saying (as root) notes_plat_sysinfo_620 = chmod +s /usr/sbin/dmidecode notes_plat_sysinfo_625 = notes_plat_sysinfo_630 = BIOS: notes_plat_sysinfo_635 = BIOS Vendor: American Megatrends Inc. notes_plat_sysinfo_640 = BIOS Version: 3.2 notes_plat_sysinfo_645 = BIOS Date: 11/07/2019 notes_plat_sysinfo_650 = notes_plat_sysinfo_655 = (End of data from sysinfo program) hw_cpu_name = Intel Xeon Gold 6148 hw_disk = 440 GB SATA hw_nchips = 2 prepared_by = mcolgrove (is never output, only tags rawfile) sw_compiler = C/Fortran: Version 23.9 of NVIDIA NVHPC SDK fw_bios = American Megatrends Inc. 3.2 11/07/2019 sw_file = ext4 sw_os000 = Ubuntu 18.04.2 LTS sw_os001 = 4.15.0-50-generic sw_state = Run level 5 (multi-user) sw_other = None # End of settings added by sysinfo_program # 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: notes_plat_000 = Information from nvaccelinfo notes_plat_005 = CUDA Driver Version: 11030 notes_plat_010 = NVRM version: NVIDIA UNIX x86_64 Kernel Module 465.19.01 Fri Mar 19 07:44:41 UTC 2021 notes_plat_015 = Device Number: 0 notes_plat_020 = Device Name: NVIDIA Tesla V100-PCIE-16GB notes_plat_025 = Device Revision Number: 7.0 notes_plat_030 = Global Memory Size: 16945512448 notes_plat_035 = Number of Multiprocessors: 80 notes_plat_040 = Concurrent Copy and Execution: Yes notes_plat_045 = Total Constant Memory: 65536 notes_plat_050 = Total Shared Memory per Block: 49152 notes_plat_055 = Registers per Block: 65536 notes_plat_060 = Warp Size: 32 notes_plat_065 = Maximum Threads per Block: 1024 notes_plat_070 = Maximum Block Dimensions: 1024, 1024, 64 notes_plat_075 = Maximum Grid Dimensions: 2147483647 x 65535 x 65535 notes_plat_080 = Maximum Memory Pitch: 2147483647B notes_plat_085 = Texture Alignment: 512B notes_plat_090 = Clock Rate: 1380 MHz notes_plat_095 = Execution Timeout: No notes_plat_100 = Integrated Device: No notes_plat_105 = Can Map Host Memory: Yes notes_plat_110 = Compute Mode: default notes_plat_115 = Concurrent Kernels: Yes notes_plat_120 = ECC Enabled: Yes notes_plat_125 = Memory Clock Rate: 877 MHz notes_plat_130 = Memory Bus Width: 4096 bits notes_plat_135 = L2 Cache Size: 6291456 bytes notes_plat_140 = Max Threads Per SMP: 2048 notes_plat_145 = Async Engines: 7 notes_plat_150 = Unified Addressing: Yes notes_plat_155 = Managed Memory: Yes notes_plat_160 = Concurrent Managed Memory: Yes notes_plat_165 = Preemption Supported: Yes notes_plat_170 = Cooperative Launch: Yes notes_plat_175 = Default Target: cc70 notes_os_000 =Shell stacksize set to unlimited via "limit stacksize unlimited"