SPEC® CFP2006 Result

Copyright 2006-2017 Standard Performance Evaluation Corporation

Lenovo Global Technology

ThinkSystem SR950
(2.70 GHz, Intel Xeon Platinum 8168)

CPU2006 license: 9017 Test date: Jul-2017
Test sponsor: Lenovo Global Technology Hardware Availability: Sep-2017
Tested by: Lenovo Global Technology Software Availability: Apr-2017
Benchmark results graph
Hardware
CPU Name: Intel Xeon Platinum 8168
CPU Characteristics: Intel Turbo Boost Technology up to 3.70 GHz
CPU MHz: 2700
FPU: Integrated
CPU(s) enabled: 96 cores, 4 chips, 24 cores/chip, 2 threads/core
CPU(s) orderable: 2,4 chips
Primary Cache: 32 KB I + 32 KB D on chip per core
Secondary Cache: 1 MB I+D on chip per core
L3 Cache: 33 MB I+D on chip per chip
Other Cache: None
Memory: 1536 GB (48 x 32 GB 2Rx4 PC4-2666V-R)
Disk Subsystem: 800 GB tmpfs
Other Hardware: None
Software
Operating System: Red Hat Enterprise Linux Server release 7.3
(Maipo)
Kernel 3.10.0-514.el7.x86_64
Compiler: C/C++: Version 17.0.3.191 of Intel C/C++
Compiler for Linux;
Fortran: Version 17.0.3.191 of Intel Fortran
Compiler for Linux
Auto Parallel: Yes
File System: tmpfs
System State: Run level 3 (multi-user)
Base Pointers: 32/64-bit
Peak Pointers: 32/64-bit
Other Software: None

Results Table

Benchmark Base Peak
Copies Seconds Ratio Seconds Ratio Seconds Ratio Copies Seconds Ratio Seconds Ratio Seconds Ratio
Results appear in the order in which they were run. Bold underlined text indicates a median measurement.
410.bwaves 192 1184 2200 1183 2200 1184 2200 96 580 2250 580 2250 580 2250
416.gamess 192 842 4470 842 4470 841 4470 192 816 4610 815 4610 817 4600
433.milc 192 832 2120 832 2120 832 2120 192 832 2120 832 2120 832 2120
434.zeusmp 192 463 3770 471 3710 465 3760 192 463 3770 471 3710 465 3760
435.gromacs 192 247 5540 248 5530 247 5560 192 246 5570 245 5600 245 5600
436.cactusADM 192 547 4190 547 4200 545 4210 192 547 4190 547 4200 545 4210
437.leslie3d 192 1124 1610 1123 1610 1122 1610 96 550 1640 564 1600 550 1640
444.namd 192 421 3660 420 3670 421 3650 192 415 3710 415 3710 415 3710
447.dealII 192 326 6740 330 6660 334 6570 192 326 6740 330 6660 334 6570
450.soplex 192 949 1690 942 1700 944 1700 96 403 1990 402 1990 402 1990
453.povray 192 165 6180 165 6190 165 6200 192 141 7250 141 7250 141 7220
454.calculix 192 231 6860 231 6850 231 6850 192 231 6860 231 6850 231 6850
459.GemsFDTD 192 1346 1510 1346 1510 1346 1510 96 694 1470 695 1470 695 1470
465.tonto 192 489 3860 491 3850 490 3850 192 464 4070 465 4070 470 4020
470.lbm 192 865 3050 865 3050 865 3050 192 865 3050 865 3050 865 3050
481.wrf 192 804 2670 802 2670 803 2670 192 804 2670 802 2670 803 2670
482.sphinx3 192 1195 3130 1188 3150 1190 3140 192 1195 3130 1188 3150 1190 3140

Submit Notes

 The numactl mechanism was used to bind copies to processors. The config file option 'submit'
 was used to generate numactl commands to bind each copy to a specific processor.
 For details, please see the config file.

Operating System Notes

 Stack size set to unlimited using "ulimit -s unlimited"
 Tmpfs filesystem can be set with:
  mount -t tmpfs -o size=800g tmpfs /home
 Process tuning setting:
  echo 50000     > /proc/sys/kernel/sched_cfs_bandwidth_slice_us
  echo 240000000 > /proc/sys/kernel/sched_latency_ns
  echo 5000000   > /proc/sys/kernel/sched_migration_cost_ns
  echo 100000000 > /proc/sys/kernel/sched_min_granularity_ns
  echo 150000000 > /proc/sys/kernel/sched_wakeup_granularity_ns

Platform Notes

BIOS configuration:
Choose Operating Mode set to Maximum Performance
SNC set to Enable
DCU Streamer Prefetcher set to Disable
Stale AtoS set to Enable
LLC dead line alloc set to Disable
 Sysinfo program /home/cpu2006-1.2-ic17.0u3/config/sysinfo.rev6993
 Revision 6993 of 2015-11-06 (b5e8d4b4eb51ed28d7f98696cbe290c1)
 running on Proton4S-RHEL7.3 Fri Jul 21 21:58:39 2017

 This section contains SUT (System Under Test) info as seen by
 some common utilities.  To remove or add to this section, see:
   http://www.spec.org/cpu2006/Docs/config.html#sysinfo

 From /proc/cpuinfo
    model name : Intel(R) Xeon(R) Platinum 8168 CPU @ 2.70GHz
       4 "physical id"s (chips)
       192 "processors"
    cores, siblings (Caution: counting these is hw and system dependent.  The
    following excerpts from /proc/cpuinfo might not be reliable.  Use with
    caution.)
       cpu cores : 24
       siblings  : 48
       physical 0: cores 0 1 2 3 4 5 8 9 10 11 12 13 16 17 18 19 20 21 24 25 26
       27 28 29
       physical 1: cores 0 1 2 3 4 5 8 9 10 11 12 13 16 17 18 19 20 21 24 25 26
       27 28 29
       physical 2: cores 0 1 2 3 4 5 8 9 10 11 12 13 16 17 18 19 20 21 24 25 26
       27 28 29
       physical 3: cores 0 1 2 3 4 5 8 9 10 11 12 13 16 17 18 19 20 21 24 25 26
       27 28 29
    cache size : 33792 KB

 From /proc/meminfo
    MemTotal:       1584770976 kB
    HugePages_Total:       0
    Hugepagesize:       2048 kB

 From /etc/*release* /etc/*version*
    os-release:
       NAME="Red Hat Enterprise Linux Server"
       VERSION="7.3 (Maipo)"
       ID="rhel"
       ID_LIKE="fedora"
       VERSION_ID="7.3"
       PRETTY_NAME="Red Hat Enterprise Linux Server 7.3 (Maipo)"
       ANSI_COLOR="0;31"
       CPE_NAME="cpe:/o:redhat:enterprise_linux:7.3:GA:server"
    redhat-release: Red Hat Enterprise Linux Server release 7.3 (Maipo)
    system-release: Red Hat Enterprise Linux Server release 7.3 (Maipo)
    system-release-cpe: cpe:/o:redhat:enterprise_linux:7.3:ga:server

 uname -a:
    Linux Proton4S-RHEL7.3 3.10.0-514.el7.x86_64 #1 SMP Wed Oct 19 11:24:13 EDT
    2016 x86_64 x86_64 x86_64 GNU/Linux

 run-level 3 Jul 21 21:56

 SPEC is set to: /home/cpu2006-1.2-ic17.0u3
    Filesystem     Type   Size  Used Avail Use% Mounted on
    tmpfs          tmpfs  800G  5.0G  796G   1% /home
 Additional information from dmidecode:

    Warning: Use caution when you interpret this section. The 'dmidecode' program
    reads system data which is "intended to allow hardware to be accurately
    determined", but the intent may not be met, as there are frequent changes to
    hardware, firmware, and the "DMTF SMBIOS" standard.

   BIOS Lenovo -[PSE105I-1.00]- 06/12/2017
   Memory:
    48x NO DIMM NO DIMM
    48x Samsung M393A4K40BB2-CTD 32 GB 2 rank 2666 MHz

 (End of data from sysinfo program)

General Notes

Environment variables set by runspec before the start of the run:
LD_LIBRARY_PATH = "/home/cpu2006-1.2-ic17.0u3/lib/ia32:/home/cpu2006-1.2-ic17.0u3/lib/intel64:/home/cpu2006-1.2-ic17.0u3/sh10.2"

 Binaries compiled on a system with 1x Intel Core i7-4790 CPU + 32GB RAM
 memory using Redhat Enterprise Linux 7.2
 Transparent Huge Pages enabled by default
 Filesystem page cache cleared with:
 shell invocation of 'sync; echo 3 > /proc/sys/vm/drop_caches' prior to run
 runspec command invoked through numactl i.e.:
 numactl --interleave=all runspec <etc>

Base Compiler Invocation

C benchmarks:

 icc -m64 

C++ benchmarks:

 icpc -m64 

Fortran benchmarks:

 ifort -m64 

Benchmarks using both Fortran and C:

 icc -m64   ifort -m64 

Base Portability Flags

410.bwaves:  -DSPEC_CPU_LP64 
416.gamess:  -DSPEC_CPU_LP64 
433.milc:  -DSPEC_CPU_LP64 
434.zeusmp:  -DSPEC_CPU_LP64 
435.gromacs:  -DSPEC_CPU_LP64   -nofor_main 
436.cactusADM:  -DSPEC_CPU_LP64   -nofor_main 
437.leslie3d:  -DSPEC_CPU_LP64 
444.namd:  -DSPEC_CPU_LP64 
447.dealII:  -DSPEC_CPU_LP64 
450.soplex:  -DSPEC_CPU_LP64 
453.povray:  -DSPEC_CPU_LP64 
454.calculix:  -DSPEC_CPU_LP64   -nofor_main 
459.GemsFDTD:  -DSPEC_CPU_LP64 
465.tonto:  -DSPEC_CPU_LP64 
470.lbm:  -DSPEC_CPU_LP64 
481.wrf:  -DSPEC_CPU_LP64   -DSPEC_CPU_CASE_FLAG   -DSPEC_CPU_LINUX 
482.sphinx3:  -DSPEC_CPU_LP64 

Base Optimization Flags

C benchmarks:

 -xCORE-AVX2   -ipo   -O3   -no-prec-div   -qopt-prefetch   -auto-p32   -qopt-mem-layout-trans=3 

C++ benchmarks:

 -xCORE-AVX2   -ipo   -O3   -no-prec-div   -qopt-prefetch   -auto-p32   -qopt-mem-layout-trans=3 

Fortran benchmarks:

 -xCORE-AVX2   -ipo   -O3   -no-prec-div   -qopt-prefetch 

Benchmarks using both Fortran and C:

 -xCORE-AVX2   -ipo   -O3   -no-prec-div   -qopt-prefetch   -auto-p32   -qopt-mem-layout-trans=3 

Peak Compiler Invocation

C benchmarks:

 icc -m64 

C++ benchmarks (except as noted below):

 icpc -m64 
450.soplex:  icpc -m32 -L/opt/intel/compilers_and_libraries_2017/linux/lib/ia32 

Fortran benchmarks:

 ifort -m64 

Benchmarks using both Fortran and C:

 icc -m64   ifort -m64 

Peak Portability Flags

410.bwaves:  -DSPEC_CPU_LP64 
416.gamess:  -DSPEC_CPU_LP64 
433.milc:  -DSPEC_CPU_LP64 
434.zeusmp:  -DSPEC_CPU_LP64 
435.gromacs:  -DSPEC_CPU_LP64   -nofor_main 
436.cactusADM:  -DSPEC_CPU_LP64   -nofor_main 
437.leslie3d:  -DSPEC_CPU_LP64 
444.namd:  -DSPEC_CPU_LP64 
447.dealII:  -DSPEC_CPU_LP64 
450.soplex:  -D_FILE_OFFSET_BITS=64 
453.povray:  -DSPEC_CPU_LP64 
454.calculix:  -DSPEC_CPU_LP64   -nofor_main 
459.GemsFDTD:  -DSPEC_CPU_LP64 
465.tonto:  -DSPEC_CPU_LP64 
470.lbm:  -DSPEC_CPU_LP64 
481.wrf:  -DSPEC_CPU_LP64   -DSPEC_CPU_CASE_FLAG   -DSPEC_CPU_LINUX 
482.sphinx3:  -DSPEC_CPU_LP64 

Peak Optimization Flags

C benchmarks:

433.milc:  basepeak = yes 
470.lbm:  basepeak = yes 
482.sphinx3:  basepeak = yes 

C++ benchmarks:

444.namd:  -prof-gen(pass 1)   -prof-use(pass 2)   -xCORE-AVX2(pass 2)   -par-num-threads=1(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -fno-alias   -auto-ilp32   -qopt-mem-layout-trans=3 
447.dealII:  basepeak = yes 
450.soplex:  -prof-gen(pass 1)   -prof-use(pass 2)   -xCORE-AVX2(pass 2)   -par-num-threads=1(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -qopt-malloc-options=3   -qopt-mem-layout-trans=3 
453.povray:  -prof-gen(pass 1)   -prof-use(pass 2)   -xCORE-AVX2(pass 2)   -par-num-threads=1(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -unroll4   -qopt-mem-layout-trans=3 

Fortran benchmarks:

410.bwaves:  -xCORE-AVX2   -ipo   -O3   -no-prec-div   -qopt-prefetch 
416.gamess:  -prof-gen(pass 1)   -prof-use(pass 2)   -xCORE-AVX2(pass 2)   -par-num-threads=1(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -unroll2   -inline-level=0   -scalar-rep- 
434.zeusmp:  basepeak = yes 
437.leslie3d:  Same as 410.bwaves 
459.GemsFDTD:  Same as 410.bwaves 
465.tonto:  -prof-gen(pass 1)   -prof-use(pass 2)   -xCORE-AVX2(pass 2)   -par-num-threads=1(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -unroll4   -auto   -inline-calloc   -qopt-malloc-options=3 

Benchmarks using both Fortran and C:

435.gromacs:  -prof-gen(pass 1)   -prof-use(pass 2)   -xCORE-AVX2(pass 2)   -par-num-threads=1(pass 1)   -qopt-prefetch   -auto-ilp32   -qopt-mem-layout-trans=3 
436.cactusADM:  basepeak = yes 
454.calculix:  basepeak = yes 
481.wrf:  basepeak = yes 

The flags files that were used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/Intel-ic17.0-official-linux64-revF.html,
http://www.spec.org/cpu2006/flags/Lenovo-Platform-Flags-V1.2-SKL-E.html.

You can also download the XML flags sources by saving the following links:
http://www.spec.org/cpu2006/flags/Intel-ic17.0-official-linux64-revF.xml,
http://www.spec.org/cpu2006/flags/Lenovo-Platform-Flags-V1.2-SKL-E.xml.