AMD Threadripper 2990WX vs. EPYC 7551 vs. Opteron 6276 4P HTA On

AMD EPYC 7551 32-Core versus AMD Threadripper 2990WX versus AMD Opteron 6276 64-Core 4P with HyperTransport Assist enabled.

HTML result view exported from: https://openbenchmarking.org/result/1809290-RA-1808109RA03&rdt&grs.

AMD Threadripper 2990WX vs. EPYC 7551 vs. Opteron 6276 4P HTA OnProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist OnAMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (32 Cores / 64 Threads)ASUS ROG ZENITH EXTREME (0064 BIOS)AMD Family 17h32768MB280GB INTEL SSDPE21D280GA + Samsung SSD 970 EVO 500GBAMD Radeon RX Vega 8192MBRealtek ALC1220DELL P2415QIntel I211 Gigabit Connection + Qualcomm Atheros QCA6174 802.11ac WirelessUbuntu 18.044.18.0-999-generic (x86_64) 20180808GNOME Shell 3.28.2X Server 1.19.6modesetting 1.19.64.5 Mesa 18.0.5 (LLVM 6.0.0)GCC 7.3.0ext43840x2160AMD EPYC 7551 32-Core @ 2.00GHz (32 Cores / 64 Threads)GIGABYTE MZ31-AR0-00 v01010101 (F07 BIOS)28672MB280GB INTEL SSDPE21D280GA + 2 x Samsung SSD 960 EVO 500GBllvmpipe 28032MBASUS PB278Realtek RTL8111/8168/84113.3 Mesa 18.0.5 (LLVM 6.0 128 bits)1920x10804 x AMD Opteron 6276 @ 2.30GHz (32 Cores / 64 Threads)Dell 0272WF (3.2.2 BIOS)AMD RD890S/SR5650 + SB7x0/SB8x0/SB9x0129024MB62GB Ultra + 479GB PERC H700Matrox MGA G200eW WPCM450Broadcom Limited NetXtreme II BCM5709 Gigabit4.15.0-34-generic (x86_64)1280x1024OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-as=/usr/bin/x86_64-linux-gnu-as --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-ld=/usr/bin/x86_64-linux-gnu-ld --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v Disk Details- Threadripper 2990WX: NONE / errors=remount-ro,relatime,rw- EPYC 7551: NONE / errors=remount-ro,relatime,rw- AMD Opteron 6276 4P HT Assist On: CFQ / acl,active_logs=6,background_gc=on,extent_cache,flush_merge,inline_data,inline_dentry,inline_xattr,lazytime,mode=adaptive,no_heap,relatime,rw,user_xattrProcessor Details- Scaling Governor: acpi-cpufreq ondemandPython Details- Threadripper 2990WX: Python 2.7.15rc1 + Python 3.6.5- EPYC 7551: Python 2.7.15rc1 + Python 3.6.5- AMD Opteron 6276 4P HT Assist On: Python 2.7.15rc1 + Python 3.6.6Security Details- Threadripper 2990WX: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp Protection- EPYC 7551: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp Protection- AMD Opteron 6276 4P HT Assist On: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp

AMD Threadripper 2990WX vs. EPYC 7551 vs. Opteron 6276 4P HTA Onpgbench: Buffer Test - Normal Load - Read Writeparboil: OpenMP MRI Griddingstress-ng: System V Message Passingnpb: FT.Ascikit-learn: redis: LPUSHnpb: EP.Cebizzy: redis: LPOPredis: GETredis: SADDblender: Classroom - CPU-Onlyredis: SETblender: BMW27 - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlyparboil: OpenMP CUTCPpovray: Trace Timenumpy: build-gcc: Time To Compilestress-ng: Socket Activityblender: Fishy Cat - CPU-Onlyrodinia: OpenMP CFD Solvernpb: BT.Arodinia: OpenMP LavaMDblender: Barbershop - CPU-Onlystress-ng: Cryptopgbench: Buffer Test - Normal Load - Read Onlyparboil: OpenMP LBMpgbench: Mostly RAM - Normal Load - Read Onlybuild-linux-kernel: Time To Compilestress-ng: CPU Stressnpb: LU.Astress-ng: Semaphoresblogbench: Readramspeed: Scale - Integernpb: LU.Cramspeed: Copy - Integerramspeed: Average - Integerapache-siege: 100apache-siege: 250apache-siege: 200stress-ng: Context Switchingpgbench: Mostly RAM - Normal Load - Read Writerodinia: OpenMP Streamclusterparboil: OpenMP Stencilnpb: SP.Astream: Addstream: Triadstream: Scalestream: Copyblogbench: WriteThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On4250727011750862220026.36147908521801415799258855724161941993378155170961579.492072.2216.996728366651192931119.51313625.20416748643016193.1326285532.4010137508431556715818775205663050128096.5828642.6715675.941748118079228763322860231.3222.4725713597436100322605201621137374493599841969186336.271065068157411608311075729161443014707312111240913105.472792.7822.6493938208891745014513.07233134.54532559940436370.2725582939.86722749098147621982082323763.973336329316.1629112.2515556.721716017101144931752509122.3616.331986437234501643643620101860256251608346967376671.455538758185434141014725965601803965382705761184.634734.9836.86145747871407896423720.29150750.11811401123765952.3243411754.12609032710100826367816930761711254054707596103231.5015.9483665549651066077310224712367OpenBenchmarking.org

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read WriteThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On9K18K27K36K45KSE +/- 163.31, N = 3SE +/- 123.83, N = 3SE +/- 29.86, N = 3425073744956251. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Parboil

Test: OpenMP MRI Gridding

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI GriddingThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On30060090012001500SE +/- 1.45, N = 3SE +/- 2.02, N = 3SE +/- 7.56, N = 327035916081. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp

Stress-NG

Test: System V Message Passing

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: System V Message PassingThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On3M6M9M12M15MSE +/- 59458.33, N = 3SE +/- 58422.58, N = 3SE +/- 68870.08, N = 31175086298419693469673-laio-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

NAS Parallel Benchmarks

Test / Class: FT.A

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: FT.AThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On5001000150020002500SE +/- 1.75, N = 3SE +/- 4.26, N = 3SE +/- 0.75, N = 3220018637661. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 2.1.1

Scikit-Learn

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.17.1Threadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On1632486480SE +/- 0.43, N = 3SE +/- 0.38, N = 3SE +/- 0.89, N = 326.3636.2771.45

Redis

Test: LPUSH

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPUSHThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On300K600K900K1200K1500KSE +/- 19641.34, N = 3SE +/- 16036.47, N = 3SE +/- 4164.60, N = 3147908510650685538751. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

NAS Parallel Benchmarks

Test / Class: EP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: EP.CThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On5001000150020002500SE +/- 12.49, N = 3SE +/- 25.81, N = 4SE +/- 0.35, N = 3218015748181. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 2.1.1

ebizzy

OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.3Threadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On300K600K900K1200K1500KSE +/- 22521.51, N = 3SE +/- 23117.36, N = 3SE +/- 3516.96, N = 3141579911608315434141. (CC) gcc options: -pthread -lpthread -O3 -march=native

Redis

Test: LPOP

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPOPThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On600K1200K1800K2400K3000KSE +/- 12382.26, N = 3SE +/- 6344.22, N = 3SE +/- 16215.18, N = 32588557107572910147251. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: GETThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On500K1000K1500K2000K2500KSE +/- 29666.21, N = 3SE +/- 23159.71, N = 3SE +/- 4359.25, N = 3241619416144309656011. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Redis

Test: SADD

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SADDThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On400K800K1200K1600K2000KSE +/- 4767.05, N = 3SE +/- 10264.23, N = 3SE +/- 6512.90, N = 3199337814707318039651. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Classroom - Compute: CPU-OnlyThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On80160240320400155211382

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SETThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On400K800K1200K1600K2000KSE +/- 13499.30, N = 3SE +/- 11616.66, N = 3SE +/- 8680.62, N = 3170961512409137057611. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: BMW27 - Compute: CPU-OnlyThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On408012016020079.49105.47184.63

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Pabellon Barcelona - Compute: CPU-OnlyThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On100200300400500207279473

Parboil

Test: OpenMP CUTCP

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On1.12052.2413.36154.4825.6025SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 32.222.784.981. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp

POV-Ray

Trace Time

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On816243240SE +/- 0.02, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 316.9922.6436.86-lSDL -lXpm-lSDL -lXpm1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

Numpy Benchmark

OpenBenchmarking.orgNanoseconds, Fewer Is BetterNumpy BenchmarkThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On3M6M9M12M15M6728366939382014574787

Timed GCC Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 7.2Time To CompileThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On30060090012001500SE +/- 3.17, N = 3SE +/- 0.78, N = 3SE +/- 10.11, N = 36518891407

Stress-NG

Test: Socket Activity

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Socket ActivityThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On4K8K12K16K20KSE +/- 76.24, N = 3SE +/- 305.51, N = 3SE +/- 98.22, N = 319293174508964-laio-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Fishy Cat - Compute: CPU-OnlyThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On50100150200250111145237

Rodinia

Test: OpenMP CFD Solver

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD SolverThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On510152025SE +/- 0.06, N = 3SE +/- 0.14, N = 3SE +/- 0.25, N = 39.5113.0720.291. (CXX) g++ options: -O2 -lOpenCL

NAS Parallel Benchmarks

Test / Class: BT.A

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: BT.AThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On7001400210028003500SE +/- 5.11, N = 3SE +/- 4.74, N = 3SE +/- 5.11, N = 33136233115071. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 2.1.1

Rodinia

Test: OpenMP LavaMD

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMDThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On1122334455SE +/- 0.03, N = 3SE +/- 0.24, N = 3SE +/- 0.04, N = 325.2034.5450.111. (CXX) g++ options: -O2 -lOpenCL

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Barbershop - Compute: CPU-OnlyThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On2004006008001000416532811

Stress-NG

Test: Crypto

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: CryptoThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On16003200480064008000SE +/- 1.58, N = 3SE +/- 4.62, N = 3SE +/- 22.12, N = 3748655994011-laio-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read OnlyThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On90K180K270K360K450KSE +/- 6254.09, N = 3SE +/- 103.66, N = 3SE +/- 3605.86, N = 44301614043632376591. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Parboil

Test: OpenMP LBM

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP LBMThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On20406080100SE +/- 1.42, N = 6SE +/- 1.05, N = 6SE +/- 0.80, N = 1293.1370.2752.321. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp

PostgreSQL pgbench

Scaling: Mostly RAM - Test: Normal Load - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Mostly RAM - Test: Normal Load - Mode: Read OnlyThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On90K180K270K360K450KSE +/- 115.23, N = 3SE +/- 1639.04, N = 3SE +/- 1343.91, N = 32628552558294341171. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.13Time To CompileThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On1224364860SE +/- 0.51, N = 6SE +/- 0.61, N = 6SE +/- 0.57, N = 1232.4039.8654.12

Stress-NG

Test: CPU Stress

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: CPU StressThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On2K4K6K8K10KSE +/- 61.19, N = 3SE +/- 71.78, N = 3SE +/- 28.15, N = 31013772276090-laio-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

NAS Parallel Benchmarks

Test / Class: LU.A

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: LU.AThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On11K22K33K44K55KSE +/- 368.79, N = 3SE +/- 727.42, N = 5SE +/- 431.94, N = 75084349098327101. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 2.1.1

Stress-NG

Test: Semaphores

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: SemaphoresThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On300K600K900K1200K1500KSE +/- 7392.64, N = 3SE +/- 7844.48, N = 3SE +/- 14819.55, N = 12155671514762191008263-laio-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

BlogBench

Test: Read

OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.0Test: ReadThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On200K400K600K800K1000KSE +/- 9403.45, N = 3SE +/- 6874.16, N = 3SE +/- 790.68, N = 38187758208236781691. (CC) gcc options: -O2 -pthread

RAMspeed SMP

Type: Scale - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: IntegerThreadripper 2990WXEPYC 75515K10K15K20K25K20566.0023763.971. (CC) gcc options: -O3 -march=native

NAS Parallel Benchmarks

Test / Class: LU.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: LU.CThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On7K14K21K28K35KSE +/- 85.98, N = 3SE +/- 56.16, N = 3SE +/- 176.12, N = 33050133363307611. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 2.1.1

RAMspeed SMP

Type: Copy - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: IntegerThreadripper 2990WXEPYC 75516K12K18K24K30K28096.5829316.161. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Average - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: IntegerThreadripper 2990WXEPYC 75516K12K18K24K30K28642.6729112.251. (CC) gcc options: -O3 -march=native

Apache Siege

Concurrent Users: 100

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 100Threadripper 2990WXEPYC 75513K6K9K12K15KSE +/- 50.31, N = 3SE +/- 67.52, N = 315675.9415556.721. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

Apache Siege

Concurrent Users: 250

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 250Threadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On4K8K12K16K20KSE +/- 304.65, N = 6SE +/- 302.36, N = 6SE +/- 231.72, N = 9174811716071121. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

Apache Siege

Concurrent Users: 200

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 200Threadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On4K8K12K16K20KSE +/- 107.03, N = 3SE +/- 394.82, N = 6SE +/- 201.44, N = 7180791710154051. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

Stress-NG

Test: Context Switching

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Context SwitchingThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On5M10M15M20M25MSE +/- 742879.18, N = 6SE +/- 521162.13, N = 6SE +/- 72872.20, N = 1222876332144931754707596-laio-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

PostgreSQL pgbench

Scaling: Mostly RAM - Test: Normal Load - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Mostly RAM - Test: Normal Load - Mode: Read WriteThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On6K12K18K24K30KSE +/- 109.73, N = 3SE +/- 119.66, N = 3SE +/- 64.44, N = 3286022509110321. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Rodinia

Test: OpenMP Streamcluster

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP StreamclusterThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On714212835SE +/- 0.69, N = 6SE +/- 1.51, N = 6SE +/- 0.48, N = 531.3222.3631.501. (CXX) g++ options: -O2 -lOpenCL

Parboil

Test: OpenMP Stencil

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP StencilThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On510152025SE +/- 0.26, N = 3SE +/- 0.84, N = 6SE +/- 1.14, N = 922.4716.3315.941. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp

NAS Parallel Benchmarks

Test / Class: SP.A

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: SP.AThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On6001200180024003000SE +/- 27.59, N = 3SE +/- 57.52, N = 6SE +/- 2.23, N = 3257119868361. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 2.1.1

Stream

Type: Add

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: AddThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On14K28K42K56K70KSE +/- 595.37, N = 5SE +/- 1791.35, N = 5SE +/- 426.46, N = 53597443723655491. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Triad

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: TriadThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On14K28K42K56K70KSE +/- 590.06, N = 5SE +/- 2345.71, N = 5SE +/- 460.38, N = 53610045016651061. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Scale

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: ScaleThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On13K26K39K52K65KSE +/- 658.63, N = 5SE +/- 3771.59, N = 5SE +/- 202.69, N = 53226043643607731. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Copy

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: CopyThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On20K40K60K80K100KSE +/- 452.18, N = 5SE +/- 2075.79, N = 10SE +/- 479.84, N = 552016620101022471. (CC) gcc options: -O3 -march=native -fopenmp

BlogBench

Test: Write

OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.0Test: WriteThreadripper 2990WXEPYC 7551AMD Opteron 6276 4P HT Assist On5K10K15K20K25KSE +/- 126.17, N = 3SE +/- 269.39, N = 3SE +/- 1340.58, N = 32113718602123671. (CC) gcc options: -O2 -pthread

Phoronix Test Suite v10.8.4