SPEC® CFP2006 Result

Copyright 2006-2017 Standard Performance Evaluation Corporation

ASUSTeK Computer Inc. (Test Sponsor: Advanced Micro Devices)

Asus RS700A-E9,
AMD EPYC 7551

CPU2006 license: 49 Test date: Jul-2017
Test sponsor: Advanced Micro Devices Hardware Availability: Sep-2017
Tested by: Advanced Micro Devices Software Availability: Apr-2016
Benchmark results graph
Hardware
CPU Name: AMD EPYC 7551
CPU Characteristics: AMD Turbo CORE technology up to 3.00 GHz
CPU MHz: 2000
FPU: Integrated
CPU(s) enabled: 64 cores, 2 chips, 32 cores/chip, 2 threads/core
CPU(s) orderable: 1,2 chips
Primary Cache: 64 KB I + 32 KB D on chip per core
Secondary Cache: 512 KB I+D on chip per core
L3 Cache: 64 MB I+D on chip per chip, 8 MB shared / 4 cores
Other Cache: None
Memory: 512 GB (16 x 32 GB 2Rx4 PC4-2667V-R, running at
2400)
Disk Subsystem: 1 x 1 TB SSD
Other Hardware: None
Software
Operating System: Ubuntu 16.04.2 LTS,
Kernel 4.4.0-83-generic
Compiler: C/C++/Fortran: Version 4.5.2.1 of x86 Open64
Compiler Suite (from AMD)
Auto Parallel: No
File System: ext4
System State: Run level 3 (Full multiuser with network)
Base Pointers: 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 128 1437 1210 1439 1210 1439 1210 128 1409 1230 1409 1230 1409 1230
416.gamess 128 1249 2010 1249 2010 1246 2010 128 1110 2260 1112 2250 1110 2260
433.milc 128 1180 996 1181 995 1180 996 128 985 1190 985 1190 985 1190
434.zeusmp 128 534 2180 535 2180 534 2180 128 527 2210 529 2200 527 2210
435.gromacs 128 459 1990 461 1980 466 1960 128 341 2680 341 2680 341 2680
436.cactusADM 128 647 2360 650 2350 651 2350 128 631 2430 632 2420 634 2410
437.leslie3d 128 1362 883 1365 881 1364 882 128 1068 1130 1069 1130 1069 1130
444.namd 128 578 1780 579 1770 579 1770 128 482 2130 482 2130 481 2130
447.dealII 128 429 3410 432 3390 440 3330 128 392 3730 390 3760 393 3730
450.soplex 128 1133 942 1134 941 1134 942 128 1057 1010 1057 1010 1056 1010
453.povray 128 272 2500 271 2510 273 2500 128 217 3130 217 3140 218 3120
454.calculix 128 386 2730 385 2740 385 2740 128 386 2730 385 2740 385 2740
459.GemsFDTD 128 1719 790 1718 790 1719 790 128 1598 850 1591 853 1594 852
465.tonto 128 665 1890 670 1880 668 1890 128 613 2050 611 2060 612 2060
470.lbm 128 982 1790 981 1790 980 1790 128 981 1790 980 1790 979 1800
481.wrf 128 936 1530 938 1520 936 1530 128 935 1530 936 1530 935 1530
482.sphinx3 128 1950 1280 1950 1280 1947 1280 128 1754 1420 1753 1420 1759 1420

Submit Notes

The config file option 'submit' was used.
'numactl' was used to bind copies to the cores.
See the configuration file for details.

Operating System Notes

'ulimit -s unlimited' was used to set environment stack size
'ulimit -l 2097152' was used to set environment locked pages in memory limit

runspec command invoked through numactl i.e.:
numactl --interleave=all runspec <etc>

Set dirty_ratio=8 to limit dirty cache to 8% of memory
Set swappiness=1 to swap only if necessary
Set zone_reclaim_mode=1 to free local node memory and avoid remote memory
sync then drop_caches=3 to reset caches before invoking runcpu

Transparent huge pages were enabled for this run (OS default)

Set vm/nr_hugepages=114688 in /etc/sysctl.conf
mount -t hugetlbfs nodev /mnt/hugepages

Platform Notes

The Linux run level was 3; sysinfo run-level is incorrect.
The dmidecode memory speed information is incorrect.

General Notes

Environment variables set by runspec before the start of the run:
HUGETLB_LIMIT = "896"
LD_LIBRARY_PATH = "/root/work/cpu2006/amd1603-rate-libs-revA/32:/root/work/cpu2006/amd1603-rate-libs-revA/64"

The binaries were built with the AMD supported x86 Open64 Compiler Suite,
which is only available from AMD at
http://developer.amd.com/tools-and-sdks/cpu-development/x86-open64-compiler-suite/
Binaries were compiled on a system with 2x AMD Opteron 6378 chips + 128GB Memory using RHEL 6.3

Submitted_by: "Smith, Van" <Van.Smith@amd.com>
Submitted: Mon Aug  7 23:02:43 EDT 2017
Submission: cpu2006-20170807-48141.sub

Base Compiler Invocation

C benchmarks:

 opencc 

C++ benchmarks:

 openCC 

Fortran benchmarks:

 openf95 

Benchmarks using both Fortran and C:

 opencc   openf95 

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 
436.cactusADM:  -DSPEC_CPU_LP64   -fno-second-underscore 
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 
459.GemsFDTD:  -DSPEC_CPU_LP64 
465.tonto:  -DSPEC_CPU_LP64 
470.lbm:  -DSPEC_CPU_LP64 
481.wrf:  -DSPEC_CPU_LINUX   -DSPEC_CPU_CASE_FLAG   -DSPEC_CPU_LP64   -fno-second-underscore 
482.sphinx3:  -DSPEC_CPU_LP64 

Base Optimization Flags

C benchmarks:

 -Ofast   -OPT:malloc_alg=1   -HP:bd=2m:heap=2m   -IPA:plimit=8000   -IPA:small_pu=100   -mso   -march=bdver1   -mno-fma4   -mno-xop   -mno-tbm   -WB,   -Wl,   -z,muldefs 

C++ benchmarks:

 -Ofast   -static   -CG:load_exe=0   -OPT:malloc_alg=1   -INLINE:aggressive=on   -HP:bd=2m:heap=2m   -D__OPEN64_FAST_SET   -march=bdver2   -mno-fma4   -mno-xop   -mno-tbm   -WB,   -Wl,   -z,muldefs 

Fortran benchmarks:

 -Ofast   -LNO:blocking=off   -LNO:simd_peel_align=on   -OPT:rsqrt=2   -OPT:unroll_size=256   -HP:bd=2m:heap=2m   -mso   -march=bdver1   -mno-fma4   -mno-xop   -mno-tbm   -WB,   -Wl,   -z,muldefs 

Benchmarks using both Fortran and C:

 -Ofast   -OPT:malloc_alg=1   -HP:bd=2m:heap=2m   -IPA:plimit=8000   -IPA:small_pu=100   -mso   -march=bdver1   -mno-fma4   -mno-xop   -mno-tbm   -WB,   -Wl,   -z,muldefs   -LNO:blocking=off   -LNO:simd_peel_align=on   -OPT:rsqrt=2   -OPT:unroll_size=256 

Peak Compiler Invocation

C benchmarks:

 opencc 

C++ benchmarks:

 openCC 

Fortran benchmarks:

 openf95 

Benchmarks using both Fortran and C:

 opencc   openf95 

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 
436.cactusADM:  -DSPEC_CPU_LP64   -fno-second-underscore 
437.leslie3d:  -DSPEC_CPU_LP64 
444.namd:  -DSPEC_CPU_LP64 
453.povray:  -DSPEC_CPU_LP64 
454.calculix:  -DSPEC_CPU_LP64 
459.GemsFDTD:  -DSPEC_CPU_LP64 
465.tonto:  -DSPEC_CPU_LP64 
470.lbm:  -DSPEC_CPU_LP64 
481.wrf:  -DSPEC_CPU_LINUX   -DSPEC_CPU_CASE_FLAG   -DSPEC_CPU_LP64   -fno-second-underscore 

Peak Optimization Flags

C benchmarks:

433.milc:  -Ofast   -CG:movnti=1   -CG:locs_best=on   -HP:bdt=2m:heap=2m   -IPA:plimit=7000   -IPA:callee_limit=1200   -OPT:struct_array_copy=2   -OPT:alias=field_sensitive   -mso   -march=bdver1   -mno-fma4 
470.lbm:  -Ofast   -CG:cmp_peep=on   -OPT:keep_ext=on   -HP:bdt=2m:heap=2m   -IPA:plimit=8000   -IPA:small_pu=100   -march=bdver1   -mno-fma4   -mso 
482.sphinx3:  -Ofast   -m32   -IPA:plimit=1000   -OPT:malloc_alg=2   -CG:cmp_peep=on   -CG:p2align=0   -CG:load_exe=1   -CG:dsched=on   -INLINE:aggressive=on   -LNO:prefetch=2   -LNO:prefetch_ahead=4   -mso   -march=bdver2   -WB,   -mno-fma4   -mno-tbm   -mno-xop 

C++ benchmarks:

444.namd:  -Ofast   -IPA:plimit=3000   -LNO:ignore_feedback=off   -CG:local_sched_alg=0   -CG:load_exe=0   -OPT:unroll_size=256   -fno-exceptions   -HP:bdt=2m:heap=2m   -LNO:if_select_conv=1   -OPT:alias=disjoint   -LNO:psimd_iso_unroll=ON   -march=bdver2   -mno-fma4   -WB,   -mno-xop   -mno-tbm 
447.dealII:  -Ofast   -D__OPEN64_FAST_SET   -static   -INLINE:aggressive=on   -LNO:opt=1   -LNO:simd=2   -fno-emit-exceptions   -m32   -OPT:unroll_times_max=8   -OPT:unroll_size=256   -OPT:unroll_level=2   -HP:bdt=2m:heap=2m   -GRA:unspill=on   -CG:cmp_peep=on   -CG:movext_icmp=off   -TENV:frame_pointer=off   -march=bdver1   -mno-fma4 
450.soplex:  -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -O3   -LNO:ignore_feedback=off   -INLINE:aggressive=on   -OPT:RO=1   -OPT:IEEE_arith=3   -OPT:IEEE_NaN_Inf=off   -OPT:fold_unsigned_relops=on   -fno-exceptions   -CG:p2align=0   -m32   -mno-fma4   -HP:bdt=2m:heap=2m   -WOPT:sib=on   -march=bdver1 
453.povray:  -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -Ofast   -CG:pre_local_sched=off   -CG:p2align=0   -CG:p2align_split=on   -CG:dsched=on   -INLINE:aggressive=on   -HP:bd=2m:heap=2m   -OPT:transform=2   -OPT:alias=disjoint   -WOPT:aggcm=0   -march=bdver2   -mno-fma4   -WB,   -mno-xop   -mno-tbm   -Wl,   -z,muldefs 

Fortran benchmarks:

410.bwaves:  -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -Ofast   -OPT:Ofast   -OPT:treeheight=on   -LNO:blocking=off   -LNO:ignore_feedback=off   -LNO:fu=4   -LNO:loop_model_simd=on   -LNO:simd_rm_unity_remainder=on   -WOPT:aggstr=0   -HP:bdt=2m:heap=2m   -CG:cmp_peep=on   -march=bdver2   -mno-fma4 
416.gamess:  -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -Ofast   -LNO:fu=6   -LNO:blocking=0   -LNO:simd=2   -OPT:ro=3   -OPT:recip=on   -CG:local_sched_alg=1   -HP:bdt=2m:heap=2m   -WOPT:sib=on   -march=bdver1   -mno-fma4 
434.zeusmp:  -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -Ofast   -LNO:blocking=off   -LNO:interchange=off   -IPA:plimit=1500   -HP:bdt=2m:heap=2m   -march=bdver2   -mno-fma4 
437.leslie3d:  -Ofast   -CG:pre_minreg_level=2   -LNO:simd=0   -LNO:fusion=2   -HP:bdt=2m:heap=2m   -mso   -march=bdver1   -mno-fma4 
459.GemsFDTD:  -Ofast   -IPA:plimit=1500   -OPT:unroll_size=1024   -OPT:unroll_times_max=16   -LNO:fission=2   -CG:local_sched_alg=2   -HP   -march=bdver1   -mno-fma4 
465.tonto:  -Ofast   -OPT:alias=no_f90_pointer_alias   -LNO:blocking=off   -CG:load_exe=1   -CG:local_sched_alg=3   -IPA:plimit=525   -HP:bdt=2m:heap=2m   -march=bdver2   -WB,   -mno-fma4   -mno-tbm   -mno-xop 

Benchmarks using both Fortran and C:

435.gromacs:  -Ofast   -OPT:rsqrt=2   -HP:bdt=2m:heap=2m   -CG:local_sched_alg=2   -CG:load_exe=3   -GRA:unspill=on   -march=bdver2   -mno-fma4   -LNO:simd=3 
436.cactusADM:  -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -Ofast   -LNO:blocking=off   -LNO:prefetch=2   -LNO:pf2=0   -LNO:prefetch_ahead=4   -HP   -CG:locs_shallow_depth=1   -CG:load_exe=0   -CG:dsched=on   -WOPT:sib=on   -march=bdver2   -mno-fma4 
454.calculix:  basepeak = yes 
481.wrf:  -Ofast   -LNO:blocking=off   -LANG:copyinout=off   -IPA:callee_limit=5000   -GRA:prioritize_by_density=on   -HP   -WOPT:sib=on   -march=bdver1   -mno-fma4 

The flags file that was used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/x86-openflags-rate-revA-I.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/cpu2006/flags/x86-openflags-rate-revA-I.xml.