Dual Xeon vs. Dual EPYC Linux Benchmarks

Tests for a future article.

HTML result view exported from: https://openbenchmarking.org/result/1810136-SK-XEONEPYC228&sro&grs.

Dual Xeon vs. Dual EPYC Linux BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelCompilerFile-SystemScreen ResolutionDual EPYC 76012 x Xeon Gold 61382 x AMD EPYC 7601 32-Core @ 2.62GHz (64 Cores / 128 Threads)Dell 02MJ3T (1.2.5 BIOS)AMD Family 17h516096MB120GB SSDSCKJB120G7RMatrox Matrox G200eW3VE228Broadcom and subsidiaries BCM57416 NetXtreme-E Dual-Media 10G RDMAUbuntu 18.104.18.0-8-generic (x86_64)GCC 8.2.0ext41600x12002 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads)TYAN S7106 (V1.01 BIOS)Intel Sky Lake-E DMI3 Registers96256MB256GB Samsung SSD 850 + Samsung SSD 970 EVO 250GBASPEED ASPEED FamilyIntel I210 Gigabit Connection1920x1080OpenBenchmarking.orgEnvironment Details- CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler 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-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v Python Details- Python 2.7.15+ + Python 3.6.7rc1Security Details- Dual EPYC 7601: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp- 2 x Xeon Gold 6138: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable Processor Details- 2 x Xeon Gold 6138: Scaling Governor: intel_pstate powersave

Dual Xeon vs. Dual EPYC Linux Benchmarksmbw: Memory Copy - 4096 MiBm-queens: Time To Solvejohn-the-ripper: Traditional DESm-queens: Time To Solvedacapobench: H2povray: Trace Timestockfish: Total Timeasmfish: 1024 Hash Memory, 26 Depthsysbench: CPUnamd: ATPase Simulation - 327,506 Atomsjohn-the-ripper: Blowfishtinymembench: Standard Memcpyprimesieve: 1e12 Prime Number Generationblender: BMW27 - CPU-Onlyopm-git: Flow MPI Norne - 32v-ray: CPUopm-git: Flow MPI Extra - 16blender: Barbershop - CPU-Onlyopm-git: Flow MPI Norne - 16opm-git: Flow MPI Extra - 32openssl: RSA 4096-bit Performancebuild-llvm: Time To Compileopm-git: Flow MPI Extra - 8ramspeed: Average - Integeropm-git: Flow MPI Norne - 8octave-benchmark: compress-7zip: Compress Speed Testcompress-rar: Linux Source Tree Archiving To RARapache-siege: 250aircrack-ng: pgbench: Buffer Test - Normal Load - Read Writepgbench: Buffer Test - Normal Load - Read Onlymysqlslap: 32tachyon: Total Timebuild-linux-kernel: Time To Compileebizzy: stream: Addstream: CopyDual EPYC 76012 x Xeon Gold 61381228613.6725843900019.00562012.75102477345120566996891070.447497022380656.3557.8072.2025.4029431261.9321992331513343182611421.521563101091673981961503550226410351.4627.271717436161714145076466928.1114924666729.38851718.996882163781433933608250.649644918357538.8177.9189.2131.2836037673.1825878381763742927712323.19146340116127715809092692.0935.33996830113967132874OpenBenchmarking.org

Stockfish

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613895.8378.6442.5Dual EPYC 7601156.8507.3543.7OpenBenchmarking.orgWatts, Fewer Is BetterStockfish 9System Power Consumption Monitor140280420560700

NAMD

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138101.2374.3423.1Dual EPYC 7601245.0506.2569.4OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 2.13b1System Power Consumption Monitor140280420560700

asmFish

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613897.6370.3415.0Dual EPYC 7601307.4519.6535.2OpenBenchmarking.orgWatts, Fewer Is BetterasmFish 2017-09-19System Power Consumption Monitor140280420560700

POV-Ray

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138101.7315.9389.6Dual EPYC 7601306.8457.0549.2OpenBenchmarking.orgWatts, Fewer Is BetterPOV-Ray 3.7.0.7System Power Consumption Monitor140280420560700

Chaos Group V-RAY

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138101.4318.8431.6Dual EPYC 7601204.6447.1540.1OpenBenchmarking.orgWatts, Fewer Is BetterChaos Group V-RAY 1.1.0System Power Consumption Monitor140280420560700

Timed LLVM Compilation

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138105.7322.1426.6Dual EPYC 7601150.1394.4559.9OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 6.0.1System Power Consumption Monitor140280420560700

Timed Linux Kernel Compilation

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138105.3269.0401.2Dual EPYC 7601151.6349.3553.9OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 4.18System Power Consumption Monitor140280420560700

Primesieve

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613898.8277.4361.2Dual EPYC 7601150.2298.6498.1OpenBenchmarking.orgWatts, Fewer Is BetterPrimesieve 7.1System Power Consumption Monitor130260390520650

ebizzy

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613898.1318.6380.7Dual EPYC 7601149.9440.8493.8OpenBenchmarking.orgWatts, Fewer Is Betterebizzy 0.3System Power Consumption Monitor130260390520650

7-Zip Compression

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138100.0322.8415.2Dual EPYC 7601207.2384.2499.2OpenBenchmarking.orgWatts, Fewer Is Better7-Zip Compression 16.02System Power Consumption Monitor130260390520650

Blender

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138111.4360.0403.5Dual EPYC 7601207.6477.5531.0OpenBenchmarking.orgWatts, Fewer Is BetterBlender 2.79aSystem Power Consumption Monitor130260390520650

PostgreSQL pgbench

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613894.4274.6396.0Dual EPYC 7601147.4215.2436.9OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 10.3System Power Consumption Monitor110220330440550

John The Ripper

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613898.0316.5370.6Dual EPYC 7601153.5346.3426.0OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 1.8.0-jumbo-1System Power Consumption Monitor110220330440550

m-queens

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613898.1343.8384.4Dual EPYC 7601146.0360.7423.4OpenBenchmarking.orgWatts, Fewer Is Betterm-queens 1.1System Power Consumption Monitor110220330440550

Open Porous Media Git

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613898.2379.3418.0Dual EPYC 7601153.5368.9384.1OpenBenchmarking.orgWatts, Fewer Is BetterOpen Porous Media GitSystem Power Consumption Monitor110220330440550

OpenSSL

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138102.1352.0417.1Dual EPYC 7601148.5367.3432.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 1.1.1System Power Consumption Monitor110220330440550

m-queens

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138107.7319.1365.2Dual EPYC 7601154.8381.9441.5OpenBenchmarking.orgWatts, Fewer Is Betterm-queens 1.2System Power Consumption Monitor120240360480600

Open Porous Media Git

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138106.6379.3423.4Dual EPYC 7601153.6370.8384.9OpenBenchmarking.orgWatts, Fewer Is BetterOpen Porous Media GitSystem Power Consumption Monitor110220330440550

GNU Octave Benchmark

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613899.4268.9379.0Dual EPYC 7601167.1274.0380.1OpenBenchmarking.orgWatts, Fewer Is BetterGNU Octave Benchmark 4.4.1System Power Consumption Monitor100200300400500

Open Porous Media Git

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138113.6384.8419.3Dual EPYC 7601154.6402.2422.3OpenBenchmarking.orgWatts, Fewer Is BetterOpen Porous Media GitSystem Power Consumption Monitor110220330440550

Blender

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138148.4353.7392.2Dual EPYC 7601293.6482.7546.1OpenBenchmarking.orgWatts, Fewer Is BetterBlender 2.79aSystem Power Consumption Monitor140280420560700

Open Porous Media Git

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613897.6307.0359.1Dual EPYC 7601223.5306.8315.2OpenBenchmarking.orgWatts, Fewer Is BetterOpen Porous Media GitSystem Power Consumption Monitor100200300400500

Open Porous Media Git

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613895.0302.0346.7Dual EPYC 7601151.7298.7306.0OpenBenchmarking.orgWatts, Fewer Is BetterOpen Porous Media GitSystem Power Consumption Monitor100200300400500

Open Porous Media Git

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138113.4369.9407.5Dual EPYC 7601182.3349.5361.8OpenBenchmarking.orgWatts, Fewer Is BetterOpen Porous Media GitSystem Power Consumption Monitor110220330440550

John The Ripper

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138282.3353.7376.9Dual EPYC 7601147.1405.2508.1OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 1.8.0-jumbo-1System Power Consumption Monitor130260390520650

MariaDB

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613897.2143.3195.5Dual EPYC 7601152.2259.2279.0OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 10.3.8System Power Consumption Monitor70140210280350

PostgreSQL pgbench

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138100.6176.5199.9Dual EPYC 7601148.7196.3287.4OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 10.3System Power Consumption Monitor70140210280350

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS Per Watt, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Write2 x Xeon Gold 6138Dual EPYC 7601163248648072.3425.65

Apache Siege

System Power Consumption Monitor

MinAvgMaxDual EPYC 7601150.2397.7412.0OpenBenchmarking.orgWatts, Fewer Is BetterApache Siege 2.4.29System Power Consumption Monitor110220330440550

Stream

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138146.2298.8371.1Dual EPYC 7601147.2333.9399.0OpenBenchmarking.orgWatts, Fewer Is BetterStream 2013-01-17System Power Consumption Monitor110220330440550

MBW

Test: Memory Copy - Array Size: 4096 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 4096 MiB2 x Xeon Gold 6138Dual EPYC 76013K6K9K12K15KSE +/- 3.83, N = 3SE +/- 85.94, N = 34669122861. (CC) gcc options: -O3 -march=native

DaCapo Benchmark

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613896.5162.9230.8Dual EPYC 7601204.4224.0248.8OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 9.12-MR1System Power Consumption Monitor60120180240300

RAR Compression

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613897.4177.8200.5Dual EPYC 7601196.5233.6247.5OpenBenchmarking.orgWatts, Fewer Is BetterRAR Compression 5.6.1System Power Consumption Monitor60120180240300

MBW

Test: Memory Copy - Array Size: 4096 MiB

OpenBenchmarking.orgMiB/s Per Watt, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 4096 MiB2 x Xeon Gold 6138Dual EPYC 7601132639526524.0159.57

RAMspeed SMP

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613894.1189.5214.4Dual EPYC 7601218.4226.7228.4OpenBenchmarking.orgWatts, Fewer Is BetterRAMspeed SMP 3.5.0System Power Consumption Monitor60120180240300

Tinymembench

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 613899.6189.7200.9Dual EPYC 7601148.3204.1212.6OpenBenchmarking.orgWatts, Fewer Is BetterTinymembench 2018-05-28System Power Consumption Monitor60120180240300

MariaDB

Clients: 32

OpenBenchmarking.orgQueries Per Second Per Watt, More Is BetterMariaDB 10.3.8Clients: 322 x Xeon Gold 6138Dual EPYC 76010.89781.79562.69343.59124.4891.883.99

m-queens

Time To Solve

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To Solve2 x Xeon Gold 6138Dual EPYC 7601714212835SE +/- 0.05, N = 3SE +/- 0.01, N = 328.1113.671. (CXX) g++ options: -fopenmp -O3 -march=native -O2

John The Ripper

Test: Traditional DES

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0-jumbo-1Test: Traditional DES2 x Xeon Gold 6138Dual EPYC 760160M120M180M240M300MSE +/- 2318740.77, N = 3SE +/- 1826124.04, N = 31492466672584390001. (CC) gcc options: -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt -lbz2

Sysbench

Test: CPU

OpenBenchmarking.orgEvents Per Second Per Watt, More Is BetterSysbench 2018-07-28Test: CPU2 x Xeon Gold 6138Dual EPYC 760170140210280350176.90300.83

Sysbench

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138242.5343.8381.7Dual EPYC 7601226.9296.2319.6OpenBenchmarking.orgWatts, Fewer Is BetterSysbench 2018-07-28System Power Consumption Monitor100200300400500

m-queens

Time To Solve

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.1Time To Solve2 x Xeon Gold 6138Dual EPYC 7601714212835SE +/- 0.06, N = 3SE +/- 0.11, N = 329.3819.001. (CXX) g++ options: -fopenmp -O3 -march=native -O2

DaCapo Benchmark

Java Test: H2

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H22 x Xeon Gold 6138Dual EPYC 76012K4K6K8K10KSE +/- 10.12, N = 4SE +/- 155.01, N = 485175620

John The Ripper

Test: Traditional DES

OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 1.8.0-jumbo-1Test: Traditional DES2 x Xeon Gold 6138Dual EPYC 7601140K280K420K560K700K421920.39637839.75

POV-Ray

Trace Time

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace Time2 x Xeon Gold 6138Dual EPYC 7601510152025SE +/- 0.05, N = 3SE +/- 0.07, N = 318.9912.751. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSDL -lXpm -lSM -lICE -lX11 -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total Time2 x Xeon Gold 6138Dual EPYC 760120M40M60M80M100MSE +/- 615118.06, N = 3SE +/- 495197.34, N = 3688216371024773451. (CXX) g++ options: -m64 -lpthread -O3 -march=native -fno-exceptions -std=c++11 -pedantic -msse -msse3 -mpopcnt -flto

asmFish

1024 Hash Memory, 26 Depth

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2017-09-191024 Hash Memory, 26 Depth2 x Xeon Gold 6138Dual EPYC 760130M60M90M120M150MSE +/- 897247.72, N = 3SE +/- 645460.31, N = 381433933120566996

Sysbench

Test: CPU

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: CPU2 x Xeon Gold 6138Dual EPYC 760120K40K60K80K100KSE +/- 127.33, N = 3SE +/- 263.79, N = 360825891071. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=native -rdynamic -ldl -laio -lm

MBW

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138145.8194.5202.5Dual EPYC 7601148.7206.2212.3OpenBenchmarking.orgWatts, Fewer Is BetterMBW 2018-09-08System Power Consumption Monitor60120180240300

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13b1ATPase Simulation - 327,506 Atoms2 x Xeon Gold 6138Dual EPYC 76010.14620.29240.43860.58480.731SE +/- 0.00262, N = 3SE +/- 0.00087, N = 30.649640.44749

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0-jumbo-1Test: Blowfish2 x Xeon Gold 6138Dual EPYC 760115K30K45K60K75KSE +/- 346.62, N = 3SE +/- 746.57, N = 349183702231. (CC) gcc options: -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt -lbz2

Tinymembench

Standard Memcpy

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memcpy2 x Xeon Gold 6138Dual EPYC 76012K4K6K8K10KSE +/- 8.34, N = 3SE +/- 7.86, N = 3575380651. (CC) gcc options: -O2 -O3 -march=native -lm

Primesieve

1e12 Prime Number Generation

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.11e12 Prime Number Generation2 x Xeon Gold 6138Dual EPYC 7601246810SE +/- 0.04, N = 3SE +/- 0.03, N = 38.816.351. (CXX) g++ options: -O3 -march=native -lpthread

Tachyon

System Power Consumption Monitor

MinAvgMax2 x Xeon Gold 6138111.9132.6153.3Dual EPYC 7601147.4147.4147.4OpenBenchmarking.orgWatts, Fewer Is BetterTachyon 0.98.9System Power Consumption Monitor4080120160200

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: BMW27 - Compute: CPU-Only2 x Xeon Gold 6138Dual EPYC 76012040608010077.9157.80

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 1.8.0-jumbo-1Test: Blowfish2 x Xeon Gold 6138Dual EPYC 76014080120160200155.38202.81

ebizzy

OpenBenchmarking.orgRecords/s Per Watt, More Is Betterebizzy 0.32 x Xeon Gold 6138Dual EPYC 760180016002400320040003128.953896.18

Open Porous Media Git

OPM Benchmark: Flow MPI Norne - Threads: 32

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 322 x Xeon Gold 6138Dual EPYC 760120406080100SE +/- 1.65, N = 3SE +/- 0.55, N = 389.2172.201. 2 x Xeon Gold 6138: Build Time Fri Oct 12 18:12:17 EDT 2018;2. Dual EPYC 7601: Build Time Fri Oct 12 08:04:54 EDT 2018;

Open Porous Media Git

OPM Benchmark: Flow MPI Norne - Threads: 32 - Solver Time

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 32 - Solver Time2 x Xeon Gold 6138Dual EPYC 760120406080100SE +/- 1.65, N = 3SE +/- 0.54, N = 386.8670.341. 2 x Xeon Gold 6138: Build Time Fri Oct 12 18:12:17 EDT 2018;2. Dual EPYC 7601: Build Time Fri Oct 12 08:04:54 EDT 2018;

Chaos Group V-RAY

Mode: CPU

OpenBenchmarking.orgSeconds, Fewer Is BetterChaos Group V-RAY 1.1.0Mode: CPU2 x Xeon Gold 6138Dual EPYC 7601714212835SE +/- 0.13, N = 3SE +/- 0.32, N = 331.2825.40

Tinymembench

Standard Memset

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memset2 x Xeon Gold 6138Dual EPYC 76012K4K6K8K10KSE +/- 35.85, N = 3SE +/- 150.46, N = 39231113511. (CC) gcc options: -O2 -O3 -march=native -lm

Open Porous Media Git

OPM Benchmark: Flow MPI Extra - Threads: 16 - Solver Time

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Extra - Threads: 16 - Solver Time2 x Xeon Gold 6138Dual EPYC 760180160240320400SE +/- 0.69, N = 3SE +/- 0.66, N = 33532881. 2 x Xeon Gold 6138: Build Time Fri Oct 12 18:12:17 EDT 2018;2. Dual EPYC 7601: Build Time Fri Oct 12 08:04:54 EDT 2018;

Open Porous Media Git

OPM Benchmark: Flow MPI Extra - Threads: 16

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Extra - Threads: 162 x Xeon Gold 6138Dual EPYC 760180160240320400SE +/- 0.71, N = 3SE +/- 0.65, N = 33602941. 2 x Xeon Gold 6138: Build Time Fri Oct 12 18:12:17 EDT 2018;2. Dual EPYC 7601: Build Time Fri Oct 12 08:04:54 EDT 2018;

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Barbershop - Compute: CPU-Only2 x Xeon Gold 6138Dual EPYC 760180160240320400376312

Open Porous Media Git

OPM Benchmark: Flow MPI Norne - Threads: 16

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 162 x Xeon Gold 6138Dual EPYC 76011632486480SE +/- 0.40, N = 3SE +/- 1.40, N = 373.1861.931. 2 x Xeon Gold 6138: Build Time Fri Oct 12 18:12:17 EDT 2018;2. Dual EPYC 7601: Build Time Fri Oct 12 08:04:54 EDT 2018;

Open Porous Media Git

OPM Benchmark: Flow MPI Norne - Threads: 16 - Solver Time

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 16 - Solver Time2 x Xeon Gold 6138Dual EPYC 76011632486480SE +/- 0.38, N = 3SE +/- 1.39, N = 371.2260.381. 2 x Xeon Gold 6138: Build Time Fri Oct 12 18:12:17 EDT 2018;2. Dual EPYC 7601: Build Time Fri Oct 12 08:04:54 EDT 2018;

Open Porous Media Git

OPM Benchmark: Flow MPI Extra - Threads: 32 - Solver Time

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Extra - Threads: 32 - Solver Time2 x Xeon Gold 6138Dual EPYC 760150100150200250SE +/- 2.19, N = 3SE +/- 0.91, N = 32512131. 2 x Xeon Gold 6138: Build Time Fri Oct 12 18:12:17 EDT 2018;2. Dual EPYC 7601: Build Time Fri Oct 12 08:04:54 EDT 2018;

Open Porous Media Git

OPM Benchmark: Flow MPI Extra - Threads: 32

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Extra - Threads: 322 x Xeon Gold 6138Dual EPYC 760160120180240300SE +/- 2.17, N = 3SE +/- 0.91, N = 32582191. 2 x Xeon Gold 6138: Build Time Fri Oct 12 18:12:17 EDT 2018;2. Dual EPYC 7601: Build Time Fri Oct 12 08:04:54 EDT 2018;

OpenSSL

RSA 4096-bit Performance

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performance2 x Xeon Gold 6138Dual EPYC 76012K4K6K8K10KSE +/- 52.87, N = 3SE +/- 13.53, N = 3783892331. (CC) gcc options: -pthread -m64 -O3 -march=native -lssl -lcrypto -ldl

Timed LLVM Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To Compile2 x Xeon Gold 6138Dual EPYC 76014080120160200176151

Tinymembench

Standard Memset

OpenBenchmarking.orgMB/s Per Watt, More Is BetterTinymembench 2018-05-28Standard Memset2 x Xeon Gold 6138Dual EPYC 7601122436486048.6755.61

OpenSSL

RSA 4096-bit Performance

OpenBenchmarking.orgSigns Per Second Per Watt, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performance2 x Xeon Gold 6138Dual EPYC 760161218243022.2725.14

Open Porous Media Git

OPM Benchmark: Flow MPI Extra - Threads: 8

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Extra - Threads: 82 x Xeon Gold 6138Dual EPYC 760180160240320400SE +/- 1.33, N = 3SE +/- 1.06, N = 33743341. 2 x Xeon Gold 6138: Build Time Fri Oct 12 18:12:17 EDT 2018;2. Dual EPYC 7601: Build Time Fri Oct 12 08:04:54 EDT 2018;

Open Porous Media Git

OPM Benchmark: Flow MPI Extra - Threads: 8 - Solver Time

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Extra - Threads: 8 - Solver Time2 x Xeon Gold 6138Dual EPYC 760180160240320400SE +/- 1.32, N = 3SE +/- 1.06, N = 33673281. 2 x Xeon Gold 6138: Build Time Fri Oct 12 18:12:17 EDT 2018;2. Dual EPYC 7601: Build Time Fri Oct 12 08:04:54 EDT 2018;

7-Zip Compression

Compress Speed Test

OpenBenchmarking.orgMIPS Per Watt, More Is Better7-Zip Compression 16.02Compress Speed Test2 x Xeon Gold 6138Dual EPYC 7601100200300400500453.40406.85

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterStockfish 9Total Time2 x Xeon Gold 6138Dual EPYC 760140K80K120K160K200K181793.69202014.26

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS Per Watt, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Only2 x Xeon Gold 6138Dual EPYC 760150010001500200025002115.532334.42

RAMspeed SMP

Type: Average - Benchmark: Integer

OpenBenchmarking.orgMB/s Per Watt, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Integer2 x Xeon Gold 6138Dual EPYC 7601306090120150154.50140.37

RAMspeed SMP

Type: Average - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Integer2 x Xeon Gold 6138Dual EPYC 76017K14K21K28K35K29277318261. (CC) gcc options: -O3 -march=native

Open Porous Media Git

OPM Benchmark: Flow MPI Norne - Threads: 8 - Solver Time

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 8 - Solver Time2 x Xeon Gold 6138Dual EPYC 7601306090120150SE +/- 0.24, N = 3SE +/- 1.71, N = 31211121. 2 x Xeon Gold 6138: Build Time Fri Oct 12 18:12:17 EDT 2018;2. Dual EPYC 7601: Build Time Fri Oct 12 08:04:54 EDT 2018;

Aircrack-ng

System Power Consumption Monitor

MinAvgMaxDual EPYC 7601437.9465.5472.7OpenBenchmarking.orgWatts, Fewer Is BetterAircrack-ng 1.3System Power Consumption Monitor120240360480600

Open Porous Media Git

OPM Benchmark: Flow MPI Norne - Threads: 8

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 82 x Xeon Gold 6138Dual EPYC 7601306090120150SE +/- 0.24, N = 3SE +/- 1.71, N = 31231141. 2 x Xeon Gold 6138: Build Time Fri Oct 12 18:12:17 EDT 2018;2. Dual EPYC 7601: Build Time Fri Oct 12 08:04:54 EDT 2018;

GNU Octave Benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 4.4.12 x Xeon Gold 6138Dual EPYC 7601612182430SE +/- 0.61, N = 3SE +/- 0.59, N = 323.1921.52

7-Zip Compression

Compress Speed Test

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed Test2 x Xeon Gold 6138Dual EPYC 760130K60K90K120K150KSE +/- 1426.52, N = 3SE +/- 4241.04, N = 31463401563101. (CXX) g++ options: -pipe -lpthread

RAR Compression

Linux Source Tree Archiving To RAR

OpenBenchmarking.orgSeconds, Fewer Is BetterRAR Compression 5.6.1Linux Source Tree Archiving To RAR2 x Xeon Gold 6138Dual EPYC 7601306090120150SE +/- 1.08, N = 3SE +/- 1.44, N = 3116109

asmFish

1024 Hash Memory, 26 Depth

OpenBenchmarking.orgNodes/second Per Watt, More Is BetterasmFish 2017-09-191024 Hash Memory, 26 Depth2 x Xeon Gold 6138Dual EPYC 760150K100K150K200K250K219925.44232034.75

Stream

Type: Copy

OpenBenchmarking.orgMB/s Per Watt, More Is BetterStream 2013-01-17Type: Copy2 x Xeon Gold 6138Dual EPYC 7601100200300400500444.72434.45

Stream

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterStream 2013-01-17System Power Consumption Monitor2 x Xeon Gold 613820406080100102.8

Apache Siege

Concurrent Users: 250

OpenBenchmarking.orgTransactions Per Second Per Watt, More Is BetterApache Siege 2.4.29Concurrent Users: 250Dual EPYC 7601102030405042.09

Aircrack-ng

OpenBenchmarking.orgk/s Per Watt, More Is BetterAircrack-ng 1.3Dual EPYC 76014080120160200176.08

Apache Siege

Concurrent Users: 250

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 250Dual EPYC 76014K8K12K16K20KSE +/- 157.03, N = 3167391. (CC) gcc options: -O3 -march=native -lpthread -ldl -lssl -lcrypto

Aircrack-ng

OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.3Dual EPYC 760120K40K60K80K100KSE +/- 38.60, N = 3819611. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -march=native -lpthread -lcrypto -lz -ldl -lm -pthread

System Power Consumption Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System Monitoring2 x Xeon Gold 6138Dual EPYC 7601100200300400500Min: 94.1 / Avg: 251.75 / Max: 442.5Min: 145.4 / Avg: 276.23 / Max: 569.4

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 Write2 x Xeon Gold 6138Dual EPYC 76013K6K9K12K15KSE +/- 1042.55, N = 3SE +/- 106.70, N = 31277150351. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

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 Only2 x Xeon Gold 6138Dual EPYC 7601120K240K360K480K600KSE +/- 3252.30, N = 3SE +/- 20638.79, N = 35809095022641. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

MariaDB

Clients: 32

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 322 x Xeon Gold 6138Dual EPYC 76012004006008001000SE +/- 66.88, N = 3SE +/- 7.82, N = 326910351. (CXX) g++ options: -O3 -march=native -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

Tachyon

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.98.9Total Time2 x Xeon Gold 6138Dual EPYC 76010.47030.94061.41091.88122.3515SE +/- 0.03, N = 3SE +/- 0.05, N = 32.091.461. (CC) gcc options: -m32 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.18Time To Compile2 x Xeon Gold 6138Dual EPYC 7601816243240SE +/- 1.66, N = 3SE +/- 1.20, N = 335.3327.27

ebizzy

OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.32 x Xeon Gold 6138Dual EPYC 7601400K800K1200K1600K2000KSE +/- 57749.43, N = 3SE +/- 35972.43, N = 399683017174361. (CC) gcc options: -pthread -lpthread -O3 -march=native

Stream

Type: Add

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Add2 x Xeon Gold 6138Dual EPYC 760130K60K90K120K150KSE +/- 170.04, N = 5SE +/- 4347.84, N = 51139671617141. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Copy

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Copy2 x Xeon Gold 6138Dual EPYC 760130K60K90K120K150KSE +/- 1486.39, N = 5SE +/- 5104.77, N = 51328741450761. (CC) gcc options: -O3 -march=native -fopenmp

Phoronix Test Suite v10.8.4