| CPU2006 license: | 3 | Test date: | Oct-2016 |
|---|---|---|---|
| Test sponsor: | HPE | Hardware Availability: | Aug-2016 |
| Tested by: | HPE | Software Availability: | Sep-2016 |
| Hardware | |
|---|---|
| CPU Name: | Intel Xeon E7-8891 v3 |
| CPU Characteristics: | Intel Turbo Boost Technology up to 3.50 GHz |
| CPU MHz: | 2800 |
| FPU: | Integrated |
| CPU(s) enabled: | 80 cores, 8 chips, 10 cores/chip, 2 threads/core |
| CPU(s) orderable: | 2 to 16 chips |
| Primary Cache: | 32 KB I + 32 KB D on chip per core |
| Secondary Cache: | 256 KB I+D on chip per core |
| L3 Cache: | 45 MB I+D on chip per chip |
| Other Cache: | None |
| Memory: | 2 TB (64 x 32 GB 4Rx4 PC4-2133P-L, running at 1600 MHz) |
| Disk Subsystem: | 8 x C8S59A, 900 GB 10 K RPM SAS |
| Other Hardware: | None |
| Software | |
|---|---|
| Operating System: | SUSE Linux Enterprise Server 12 (x86_64) SP1 Kernel 3.12.49-11-default |
| Compiler: | C/C++: Version 17.0.0.098 of Intel C/C++ Compiler for Linux |
| Auto Parallel: | No |
| File System: | xfs |
| System State: | Run level 5 (multi-user, w/GUI) |
| Base Pointers: | 32-bit |
| Peak Pointers: | 32/64-bit |
| Other Software: | Microquill SmartHeap V10.2 |
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. | ||||||||||||||
| 400.perlbench | 160 | 553 | 2830 | 553 | 2830 | 553 | 2830 | 160 | 473 | 3300 | 477 | 3270 | 476 | 3290 |
| 401.bzip2 | 160 | 782 | 1970 | 782 | 1970 | 783 | 1970 | 160 | 739 | 2090 | 739 | 2090 | 740 | 2090 |
| 403.gcc | 160 | 461 | 2800 | 457 | 2820 | 461 | 2800 | 160 | 455 | 2830 | 454 | 2830 | 458 | 2810 |
| 429.mcf | 160 | 302 | 4840 | 303 | 4820 | 303 | 4820 | 160 | 302 | 4840 | 303 | 4820 | 303 | 4820 |
| 445.gobmk | 160 | 638 | 2630 | 638 | 2630 | 641 | 2620 | 160 | 630 | 2670 | 631 | 2660 | 631 | 2660 |
| 456.hmmer | 160 | 258 | 5790 | 258 | 5790 | 258 | 5770 | 160 | 223 | 6700 | 223 | 6680 | 223 | 6690 |
| 458.sjeng | 160 | 714 | 2710 | 713 | 2720 | 713 | 2720 | 160 | 671 | 2880 | 672 | 2880 | 671 | 2880 |
| 462.libquantum | 160 | 85.5 | 38800 | 85.5 | 38800 | 85.4 | 38800 | 160 | 85.5 | 38800 | 85.5 | 38800 | 85.4 | 38800 |
| 464.h264ref | 160 | 729 | 4860 | 755 | 4690 | 726 | 4880 | 160 | 702 | 5040 | 723 | 4900 | 690 | 5130 |
| 471.omnetpp | 160 | 575 | 1740 | 574 | 1740 | 576 | 1740 | 160 | 529 | 1890 | 530 | 1890 | 530 | 1890 |
| 473.astar | 160 | 515 | 2180 | 512 | 2190 | 511 | 2200 | 160 | 515 | 2180 | 512 | 2190 | 511 | 2200 |
| 483.xalancbmk | 160 | 231 | 4790 | 231 | 4780 | 231 | 4780 | 160 | 231 | 4790 | 231 | 4780 | 231 | 4780 |
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" Transparent Huge Pages enabled with: echo always > /sys/kernel/mm/transparent_hugepage/enabled Filesystem page cache cleared with: echo 1 > /proc/sys/vm/drop_caches runspec command invoked through numactl i.e.: numactl --interleave=all runspec <etc> Power profile set with: cpupower -c all frequency-set -g performance Setting the value of perf-bias: cpupower set -b 0 Tuned profile set with: tuned-adm profile throughput-performance
Platform Notes
Firmware settings: Memory RAS Configuration set to Maximum Performance Sysinfo program /home/cpu17/config/sysinfo.rev6993 Revision 6993 of 2015-11-06 (b5e8d4b4eb51ed28d7f98696cbe290c1) running on gh10 Sat Oct 8 22:46:13 2016 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) CPU E7-8891 v3 @ 2.80GHz 8 "physical id"s (chips) 160 "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 : 10 siblings : 20 physical 0: cores 0 1 2 4 6 8 17 19 20 23 physical 1: cores 0 1 2 4 6 8 17 19 20 23 physical 2: cores 0 1 2 4 6 8 17 19 20 23 physical 3: cores 0 1 2 4 6 8 17 19 20 23 physical 4: cores 0 1 2 4 6 8 17 19 20 23 physical 5: cores 0 1 2 4 6 8 17 19 20 23 physical 6: cores 0 1 2 4 6 8 17 19 20 23 physical 7: cores 0 1 2 4 6 8 17 19 20 23 cache size : 46080 KB From /proc/meminfo MemTotal: 2117603700 kB HugePages_Total: 0 Hugepagesize: 2048 kB /usr/bin/lsb_release -d SUSE Linux Enterprise Server 12 SP1 From /etc/*release* /etc/*version* SuSE-release: SUSE Linux Enterprise Server 12 (x86_64) VERSION = 12 PATCHLEVEL = 1 # This file is deprecated and will be removed in a future service pack or release. # Please check /etc/os-release for details about this release. os-release: NAME="SLES" VERSION="12-SP1" VERSION_ID="12.1" PRETTY_NAME="SUSE Linux Enterprise Server 12 SP1" ID="sles" ANSI_COLOR="0;32" CPE_NAME="cpe:/o:suse:sles:12:sp1" uname -a: Linux gh10 3.12.49-11-default #1 SMP Wed Nov 11 20:52:43 UTC 2015 (8d714a0) x86_64 x86_64 x86_64 GNU/Linux run-level 5 Oct 8 22:13 SPEC is set to: /home/cpu17 Filesystem Type Size Used Avail Use% Mounted on /dev/mapper/3600c0ff0002626a42792985701000000-part4 xfs 1.8T 285G 1.5T 16% /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 HP Bundle: 008.004.084 SFW: 043.025.000 08/16/2016 Memory: 64x HP M386A4G40DM0-CPB 32 GB 4 rank 2133 MHz, configured at 1600 MHz 128x not defined not defined (End of data from sysinfo program) Regarding the sysinfo display about the memory installed, the correct amount of memory is 2 TB and the dmidecode description should have one line reading as: 64x HP M386A4G40DM0-CPB 32 GB 4 rank 2133 MHz, configured at 1600 MHz
General Notes
Environment variables set by runspec before the start of the run: LD_LIBRARY_PATH = "/home/cpu17/libs/32:/home/cpu17/libs/64:/home/cpu17/sh10.2" Binaries compiled on a system with 1x Intel Core i7-4790 CPU + 32GB RAM memory using Redhat Enterprise Linux 7.2
Base Compiler Invocation
C benchmarks:
| icc -m32 -L/opt/intel/compilers_and_libraries_2017/linux/lib/ia32 |
C++ benchmarks:
| icpc -m32 -L/opt/intel/compilers_and_libraries_2017/linux/lib/ia32 |
Base Portability Flags
| 400.perlbench: | -D_FILE_OFFSET_BITS=64 -DSPEC_CPU_LINUX_IA32 |
| 401.bzip2: | -D_FILE_OFFSET_BITS=64 |
| 403.gcc: | -D_FILE_OFFSET_BITS=64 |
| 429.mcf: | -D_FILE_OFFSET_BITS=64 |
| 445.gobmk: | -D_FILE_OFFSET_BITS=64 |
| 456.hmmer: | -D_FILE_OFFSET_BITS=64 |
| 458.sjeng: | -D_FILE_OFFSET_BITS=64 |
| 462.libquantum: | -D_FILE_OFFSET_BITS=64 -DSPEC_CPU_LINUX |
| 464.h264ref: | -D_FILE_OFFSET_BITS=64 |
| 471.omnetpp: | -D_FILE_OFFSET_BITS=64 |
| 473.astar: | -D_FILE_OFFSET_BITS=64 |
| 483.xalancbmk: | -D_FILE_OFFSET_BITS=64 -DSPEC_CPU_LINUX |
Base Optimization Flags
C benchmarks:
| -xCORE-AVX2 -ipo -O3 -no-prec-div -qopt-prefetch -qopt-mem-layout-trans=3 |
C++ benchmarks:
| -xCORE-AVX2 -ipo -O3 -no-prec-div -qopt-prefetch -qopt-mem-layout-trans=3 -Wl,-z,muldefs -L/sh10.2 -lsmartheap |
Peak Compiler Invocation
C benchmarks (except as noted below):
| icc -m32 -L/opt/intel/compilers_and_libraries_2017/linux/lib/ia32 | |
| 400.perlbench: | icc -m64 |
| 401.bzip2: | icc -m64 |
| 456.hmmer: | icc -m64 |
| 458.sjeng: | icc -m64 |
C++ benchmarks:
| icpc -m32 -L/opt/intel/compilers_and_libraries_2017/linux/lib/ia32 |
Peak Portability Flags
| 400.perlbench: | -DSPEC_CPU_LP64 -DSPEC_CPU_LINUX_X64 |
| 401.bzip2: | -DSPEC_CPU_LP64 |
| 403.gcc: | -D_FILE_OFFSET_BITS=64 |
| 429.mcf: | -D_FILE_OFFSET_BITS=64 |
| 445.gobmk: | -D_FILE_OFFSET_BITS=64 |
| 456.hmmer: | -DSPEC_CPU_LP64 |
| 458.sjeng: | -DSPEC_CPU_LP64 |
| 462.libquantum: | -D_FILE_OFFSET_BITS=64 -DSPEC_CPU_LINUX |
| 464.h264ref: | -D_FILE_OFFSET_BITS=64 |
| 471.omnetpp: | -D_FILE_OFFSET_BITS=64 |
| 473.astar: | -D_FILE_OFFSET_BITS=64 |
| 483.xalancbmk: | -D_FILE_OFFSET_BITS=64 -DSPEC_CPU_LINUX |
Peak Optimization Flags
C benchmarks:
C++ benchmarks:
| 471.omnetpp: | -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-ra-region-strategy=block -qopt-mem-layout-trans=3 -Wl,-z,muldefs -L/sh10.2 -lsmartheap |
| 473.astar: | basepeak = yes |
| 483.xalancbmk: | basepeak = yes |