|
SGI |
SPECompG_base2012 = 6.27 |
|
SGI ICE X (Intel Xeon E5-2690 v2, 3.0 GHz) |
SPECompG_peak2012 = 6.75 |
| OMP2012 license: | 4 | Test date: | Nov-2013 |
|---|---|---|---|
| Test sponsor: | SGI | Hardware Availability: | Sep-2013 |
| Tested by: | SGI | Software Availability: | Oct-2013 |
| Hardware | |
|---|---|
| CPU Name: | Intel Xeon E5-2690 v2 |
| CPU Characteristics: | Ten Core, 3.0 GHz, 8.0 GT/s QPI Intel Turbo Boost Technology up to 3.60 GHz Hyper-Threading Technology enabled |
| CPU MHz: | 3000 |
| CPU MHz Maximum: | 3600 |
| FPU: | Integrated |
| CPU(s) enabled: | 20 cores, 2 chips, 10 cores/chip, 2 threads/core |
| CPU(s) orderable: | 1,2 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: | 25 MB I+D on chip per chip |
| Other Cache: | None |
| Memory: | 64 GB (8 x 8 GB 2Rx4 PC3-14900R-13, ECC) |
| Disk Subsystem: | 64.8 TB RAID 6 72 x 900 GB SAS (Western Digital, 10K RPM) |
| Other Hardware: | -- |
| Base Threads Run: | 40 |
| Minimum Peak Threads: | 20 |
| Maximum Peak Threads: | 40 |
| Software | |
|---|---|
| Operating System: | SUSE Linux Enterprise Server 11 SP2, Kernel 3.0.80-0.7-default |
| Compiler: | C/C++/Fortran: Version 14.0.1.106 of Intel Composer XE 2013 for Linux, Build 20131008 |
| Auto Parallel: | No |
| File System: | NFSv3 IPoIB |
| System State: | Run level 3 ( Multi-user ) |
| Base Pointers: | 64-bit |
| Peak Pointers: | 64-bit |
| Other Software: | SGI Tempo Compute Node 2.7.3, Build 708rp14.sles11sp2-1305311204 |
Results Table
| Benchmark | Base | Peak | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Threads | Seconds | Ratio | Seconds | Ratio | Seconds | Ratio | Threads | Seconds | Ratio | Seconds | Ratio | Seconds | Ratio | |
| Results appear in the order in which they were run. Bold underlined text indicates a median measurement. | ||||||||||||||
| 350.md | 40 | 640 | 7.23 | 643 | 7.20 | 643 | 7.20 | 40 | 519 | 8.93 | 519 | 8.92 | 522 | 8.88 |
| 351.bwaves | 40 | 539 | 8.41 | 538 | 8.42 | 538 | 8.43 | 20 | 478 | 9.49 | 477 | 9.50 | 476 | 9.51 |
| 352.nab | 40 | 669 | 5.81 | 687 | 5.66 | 685 | 5.68 | 40 | 606 | 6.42 | 605 | 6.43 | 623 | 6.25 |
| 357.bt331 | 40 | 546 | 8.67 | 548 | 8.65 | 544 | 8.72 | 40 | 535 | 8.87 | 530 | 8.94 | 526 | 9.01 |
| 358.botsalgn | 40 | 937 | 4.64 | 938 | 4.64 | 938 | 4.64 | 40 | 939 | 4.63 | 938 | 4.64 | 939 | 4.63 |
| 359.botsspar | 40 | 1354 | 3.88 | 1365 | 3.85 | 1368 | 3.84 | 20 | 1100 | 4.77 | 1100 | 4.77 | 1100 | 4.77 |
| 360.ilbdc | 40 | 658 | 5.41 | 657 | 5.42 | 657 | 5.41 | 40 | 656 | 5.43 | 657 | 5.41 | 656 | 5.42 |
| 362.fma3d | 40 | 689 | 5.52 | 691 | 5.50 | 684 | 5.56 | 40 | 689 | 5.52 | 691 | 5.50 | 684 | 5.56 |
| 363.swim | 40 | 694 | 6.53 | 696 | 6.51 | 699 | 6.48 | 20 | 617 | 7.34 | 616 | 7.36 | 619 | 7.32 |
| 367.imagick | 40 | 835 | 8.42 | 829 | 8.48 | 822 | 8.55 | 40 | 835 | 8.42 | 829 | 8.48 | 822 | 8.55 |
| 370.mgrid331 | 40 | 740 | 5.97 | 742 | 5.96 | 740 | 5.97 | 20 | 707 | 6.26 | 707 | 6.25 | 707 | 6.25 |
| 371.applu331 | 40 | 870 | 6.96 | 867 | 6.99 | 871 | 6.96 | 40 | 870 | 6.96 | 867 | 6.99 | 871 | 6.96 |
| 372.smithwa | 40 | 820 | 6.54 | 815 | 6.58 | 813 | 6.59 | 20 | 693 | 7.73 | 705 | 7.61 | 688 | 7.79 |
| 376.kdtree | 40 | 747 | 6.02 | 745 | 6.04 | 750 | 6.00 | 40 | 747 | 6.02 | 745 | 6.04 | 750 | 6.00 |
Operating System Notes
BIOS settings notes:
Intel Turbo Boost Technology (Turbo) : Enabled
Transparent Hugepage : disabled
Transparent Hugepage is disabled by
echo never > /sys/kernel/mm/transparent_hugepage/enabled
Software Environment:
export KMP_LIBRARY=turnaround
export KMP_STACKSIZE=256M
export KMP_BLOCKTIME=infinite
export OMP_DYNAMIC=FALSE
export OMP_NESTED=FALSE
ulimit -s unlimited
Platform Notes
Sysinfo program /store/hfeng/omp2012/Docs/sysinfo $Rev: 395 $ $Date:: 2012-07-25 #$ 8f8c0fe9e19c658963a1e67685e50647 running on r1i2n14 Tue Nov 19 14:04:03 2013 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/omp2012/Docs/config.html#sysinfo From /proc/cpuinfo model name : Intel(R) Xeon(R) CPU E5-2690 v2 @ 3.00GHz 2 "physical id"s (chips) 40 "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 3 4 8 9 10 11 12 physical 1: cores 0 1 2 3 4 8 9 10 11 12 cache size : 25600 KB From /proc/meminfo MemTotal: 65979536 kB HugePages_Total: 0 Hugepagesize: 2048 kB From /etc/*release* /etc/*version* SuSE-release: SUSE Linux Enterprise Server 11 (x86_64) VERSION = 11 PATCHLEVEL = 2 sgi-compute-node-release: SGI Tempo Compute Node 2.7.3, Build 708rp14.sles11sp2-1305311204 uname -a: Linux r1i2n14 3.0.80-0.7-default #1 SMP Tue Jun 25 18:32:49 UTC 2013 (25740f8) x86_64 x86_64 x86_64 GNU/Linux run-level 3 Nov 15 22:04 last=S SPEC is set to: /store/hfeng/omp2012 Filesystem Type Size Used Avail Use% Mounted on 10.149.133.200:/mnt/data nfs 45T 9.3T 35T 21% /nas Cannot run dmidecode; consider saying 'chmod +s /usr/sbin/dmidecode' (End of data from sysinfo program)
General Notes
======================================================================== General base OMP Library Settings ENV_KMP_AFFINITY=compact,0 ======================================================================== General peak OMP Library Settings ENV_KMP_AFFINITY=compact,0 ======================================================================== Per benchmark peak OMP Library Settings ======================================================================== 351.bwaves:peak: ENV_KMP_AFFINITY=compact,1 ======================================================================== 359.botsspar:peak: ENV_KMP_AFFINITY=compact,1 ======================================================================== 362.fma3d basepeak=1 ======================================================================== 363.swim:peak: ENV_KMP_AFFINITY=compact,1 ======================================================================== 367.imagick basepeak=1 ======================================================================== 371.applu331:peak: basepeak=1 ======================================================================== 372.smithwa:peak: ENV_KMP_AFFINITY=compact,1 ======================================================================== 376.kdtree:peak: basepeak=1
Base Portability Flags
| 350.md: | -FR |
| 357.bt331: | -mcmodel=medium |
| 363.swim: | -mcmodel=medium |
| 367.imagick: | -std=c99 |
Base Optimization Flags
C benchmarks:
| -O2 -openmp -ipo -xAVX -ansi-alias |
C++ benchmarks:
| -O2 -openmp -ipo -xAVX -ansi-alias |
Fortran benchmarks:
| -O2 -openmp -ipo -xAVX |
Peak Portability Flags
| 350.md: | -FR |
| 357.bt331: | -mcmodel=medium |
| 363.swim: | -mcmodel=medium |
| 367.imagick: | -std=c99 |
Peak Optimization Flags
C benchmarks:
| 352.nab: | -O3 -openmp -ipo -xAVX -fno-alias -opt-malloc-options=1 -opt-calloc -fp-model fast=2 -no-prec-div -no-prec-sqrt -ansi-alias |
| 358.botsalgn: | -O3 -openmp -ipo -xSSE4.2 -fno-alias -ansi-alias |
| 359.botsspar: | -O3 -openmp -ipo -xAVX -fno-alias -ansi-alias |
| 367.imagick: | basepeak = yes |
| 372.smithwa: | -O2 -openmp -ipo -xSSE4.2 -fno-alias -opt-streaming-stores always -opt-malloc-options=1 -ansi-alias |
C++ benchmarks:
| 376.kdtree: | basepeak = yes |
Fortran benchmarks:
| 350.md: | -O2 -openmp -ipo -xAVX -fno-alias -opt-malloc-options=1 -fp-model fast=2 -no-prec-div -no-prec-sqrt |
| 351.bwaves: | -O3 -openmp -ipo -xAVX -fno-alias -fp-model fast=2 -no-prec-div -no-prec-sqrt |
| 357.bt331: | Same as 351.bwaves |
| 360.ilbdc: | -O3 -openmp -ipo -xAVX -opt-malloc-options=1 |
| 362.fma3d: | basepeak = yes |
| 363.swim: | -O3 -openmp -ipo -xSSE4.2 -fno-alias -opt-streaming-stores always -opt-malloc-options=3 |
| 370.mgrid331: | -O2 -openmp -ipo -xSSE4.2 -fno-alias -opt-malloc-options=3 |
| 371.applu331: | basepeak = yes |