Linux 5.4 AMD EPYC Benchmarks

Tests for a future article.

HTML result view exported from: https://openbenchmarking.org/result/1909252-AS-ROME54LIN47&grs&sor.

ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionEPYC 7642EPYC 7642 2PEPYC 7742EPYC 7742 2P Linux 5.2.16 Linux 5.3 Linux 5.4 Git Linux 5.2.16 Linux 5.3 Linux 5.4 Git Linux 5.2.16 Linux 5.3 Linux 5.4 Git Linux 5.2.16 Linux 5.3 Linux 5.4 GitAMD EPYC 7642 48-Core @ 2.30GHz (48 Cores / 96 Threads)AMD DAYTONA_X (RDY1001C BIOS)AMD Device 1480258048MB280GB INTEL SSDPE21D280GA + 256GB Micron_1100_MTFDllvmpipe 252GBVE2282 x Mellanox MT27710Ubuntu 19.045.2.16-050216-generic (x86_64)GNOME Shell 3.32.2X Server 1.20.4modesetting 1.20.43.3 Mesa 19.0.8 (LLVM 8.0 128 bits)GCC 8.3.0ext41920x10805.3.0-050300-generic (x86_64)5.3.0-999-generic (x86_64) 201909182 x AMD EPYC 7642 48-Core @ 2.30GHz (96 Cores / 192 Threads)516096MB280GB INTEL SSDPE21D280GA + 280GB INTEL SSDPED1D280GA + 256GB Micron_1100_MTFDllvmpipe 504GB5.2.16-050216-generic (x86_64)5.3.0-050300-generic (x86_64)5.3.0-999-generic (x86_64) 20190918AMD EPYC 7742 64-Core @ 2.25GHz (64 Cores / 128 Threads)258048MB280GB INTEL SSDPE21D280GA + 256GB Micron_1100_MTFDllvmpipe 252GB5.2.16-050216-generic (x86_64)5.3.0-050300-generic (x86_64)5.3.0-999-generic (x86_64) 201909182 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads)516096MB280GB INTEL SSDPE21D280GA + 280GB INTEL SSDPED1D280GA + 256GB Micron_1100_MTFDllvmpipe 504GB5.2.16-050216-generic (x86_64)5.3.0-050300-generic (x86_64)5.3.0-999-generic (x86_64) 20190918OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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 Processor Details- Scaling Governor: acpi-cpufreq ondemandPython Details- Python 2.7.16 + Python 3.7.3Security Details- l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

blender: Classroom - CPU-Onlynamd: ATPase Simulation - 327,506 Atomsblender: Pabellon Barcelona - CPU-Onlystress-ng: System V Message Passingblender: BMW27 - CPU-Onlytungsten: Hairblender: Fishy Cat - CPU-Onlybuild-llvm: Time To Compileblender: Barbershop - CPU-Onlyapache-siege: 250apache-siege: 200neatbench: CPUtungsten: Water CausticEPYC 7642EPYC 7642 2PEPYC 7742EPYC 7742 2P Linux 5.2.16 Linux 5.3 Linux 5.4 Git Linux 5.2.16 Linux 5.3 Linux 5.4 Git Linux 5.2.16 Linux 5.3 Linux 5.4 Git Linux 5.2.16 Linux 5.3 Linux 5.4 Git112.530.54538148.4924163049.6046.598.5070.37116.83191.8831692.3930835.7133.7722.74112.650.54608149.7625887258.8846.598.4470.11113.03192.0535100.0635369.7433.7722.79114.410.54471148.6725836413.9146.908.4670.25114.36192.6534459.5833938.6233.5322.7358.890.3080987.1220596976.6029.855.6849.7286.00150.5732135.3731162.7931.0323.6359.150.3085887.9321470910.4229.795.7149.4086.06151.1634856.8533773.5730.6723.8858.030.3102786.2229920770.5429.645.6048.7384.80150.0338224.3134564.3331.9023.2686.880.42842118.4926456794.8237.736.9359.56101.06169.8035789.0732821.8733.0021.7385.860.42881116.9528985535.5737.316.9059.70101.19169.1137576.4836630.6333.6321.7886.860.42826117.3227691221.8037.736.9359.39101.32168.6639127.8538029.7233.6021.7546.890.2606675.0128396036.4526.955.4445.1280.62144.3633124.6531972.5629.7322.7446.510.2595373.9330059502.9226.865.3744.7278.54143.5634441.3732836.7130.3322.7346.830.2657874.6237457745.5226.785.3144.5880.35143.0936288.0034520.4930.8322.48OpenBenchmarking.org

Blender

Blend File: Classroom - Compute: CPU-Only

EPYC 7742 2PEPYC 7642 2PEPYC 7742EPYC 7642OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Classroom - Compute: CPU-OnlyLinux 5.3Linux 5.4 GitLinux 5.2.16306090120150SE +/- 0.24, N = 3SE +/- 0.21, N = 3SE +/- 0.32, N = 3SE +/- 0.33, N = 3SE +/- 0.32, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.21, N = 3SE +/- 0.08, N = 3SE +/- 0.33, N = 3SE +/- 0.72, N = 3SE +/- 0.47, N = 346.5146.8346.8958.0358.8959.1585.8686.8686.88112.53112.65114.41

NAMD

ATPase Simulation - 327,506 Atoms

EPYC 7742 2PEPYC 7642 2PEPYC 7742EPYC 7642OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13b1ATPase Simulation - 327,506 AtomsLinux 5.3Linux 5.2.16Linux 5.4 Git0.12290.24580.36870.49160.6145SE +/- 0.00337, N = 4SE +/- 0.00318, N = 5SE +/- 0.00143, N = 3SE +/- 0.00116, N = 6SE +/- 0.00354, N = 3SE +/- 0.00231, N = 3SE +/- 0.00028, N = 15SE +/- 0.00024, N = 12SE +/- 0.00020, N = 15SE +/- 0.00137, N = 3SE +/- 0.00128, N = 3SE +/- 0.00069, N = 30.259530.260660.265780.308090.308580.310270.428260.428420.428810.544710.545380.54608

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

EPYC 7742 2PEPYC 7642 2PEPYC 7742EPYC 7642OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Pabellon Barcelona - Compute: CPU-OnlyLinux 5.3Linux 5.4 GitLinux 5.2.16306090120150SE +/- 0.22, N = 3SE +/- 0.28, N = 3SE +/- 0.20, N = 3SE +/- 0.28, N = 3SE +/- 0.12, N = 3SE +/- 0.63, N = 3SE +/- 0.52, N = 3SE +/- 0.23, N = 3SE +/- 0.16, N = 3SE +/- 0.23, N = 3SE +/- 0.30, N = 3SE +/- 0.31, N = 373.9374.6275.0186.2287.1287.93116.95117.32118.49148.49148.67149.76

Stress-NG

Test: System V Message Passing

EPYC 7742 2PEPYC 7642 2PEPYC 7742EPYC 7642OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: System V Message PassingLinux 5.4 GitLinux 5.3Linux 5.2.168M16M24M32M40MSE +/- 225804.68, N = 3SE +/- 184929.64, N = 3SE +/- 286340.79, N = 15SE +/- 363932.36, N = 13SE +/- 201067.95, N = 15SE +/- 139164.45, N = 3SE +/- 392105.15, N = 3SE +/- 358948.83, N = 3SE +/- 334188.10, N = 3SE +/- 318150.61, N = 3SE +/- 67547.36, N = 3SE +/- 291216.27, N = 337457745.5230059502.9228396036.4529920770.5421470910.4220596976.6028985535.5727691221.8026456794.8225887258.8825836413.9124163049.601. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Blender

Blend File: BMW27 - Compute: CPU-Only

EPYC 7742 2PEPYC 7642 2PEPYC 7742EPYC 7642OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: BMW27 - Compute: CPU-OnlyLinux 5.4 GitLinux 5.3Linux 5.2.161122334455SE +/- 0.04, N = 3SE +/- 0.20, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.18, N = 3SE +/- 0.15, N = 3SE +/- 0.13, N = 3SE +/- 0.19, N = 326.7826.8626.9529.6429.7929.8537.3137.7337.7346.5946.5946.90

Tungsten Renderer

Scene: Hair

EPYC 7742 2PEPYC 7642 2PEPYC 7742EPYC 7642OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: HairLinux 5.4 GitLinux 5.3Linux 5.2.16246810SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 4SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 35.315.375.445.605.685.716.906.936.938.448.468.501. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl

Blender

Blend File: Fishy Cat - Compute: CPU-Only

EPYC 7742 2PEPYC 7642 2PEPYC 7742EPYC 7642OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Fishy Cat - Compute: CPU-OnlyLinux 5.4 GitLinux 5.3Linux 5.2.161632486480SE +/- 0.07, N = 3SE +/- 0.53, N = 3SE +/- 0.20, N = 3SE +/- 0.19, N = 3SE +/- 0.16, N = 3SE +/- 0.13, N = 3SE +/- 0.14, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.25, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 344.5844.7245.1248.7349.4049.7259.3959.5659.7070.1170.2570.37

Timed LLVM Compilation

Time To Compile

EPYC 7742 2PEPYC 7642 2PEPYC 7742EPYC 7642OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To CompileLinux 5.3Linux 5.4 GitLinux 5.2.1630609012015078.5480.3580.6284.8086.0086.06101.06101.19101.32113.03114.36116.83

Blender

Blend File: Barbershop - Compute: CPU-Only

EPYC 7742 2PEPYC 7642 2PEPYC 7742EPYC 7642OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Barbershop - Compute: CPU-OnlyLinux 5.4 GitLinux 5.3Linux 5.2.164080120160200SE +/- 0.64, N = 3SE +/- 0.94, N = 3SE +/- 0.33, N = 3SE +/- 0.69, N = 3SE +/- 1.40, N = 3SE +/- 0.83, N = 3SE +/- 0.21, N = 3SE +/- 0.15, N = 3SE +/- 0.04, N = 3SE +/- 0.23, N = 3SE +/- 0.25, N = 3SE +/- 0.30, N = 3143.09143.56144.36150.03150.57151.16168.66169.11169.80191.88192.05192.65

Apache Siege

Concurrent Users: 250

EPYC 7742EPYC 7642 2PEPYC 7742 2PEPYC 7642OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 250Linux 5.4 GitLinux 5.3Linux 5.2.168K16K24K32K40KSE +/- 52.52, N = 3SE +/- 158.52, N = 3SE +/- 46.73, N = 3SE +/- 337.29, N = 11SE +/- 517.39, N = 3SE +/- 71.80, N = 3SE +/- 520.89, N = 3SE +/- 465.30, N = 3SE +/- 302.98, N = 15SE +/- 121.27, N = 3SE +/- 100.62, N = 3SE +/- 206.44, N = 339127.8537576.4835789.0738224.3134856.8532135.3736288.0034441.3733124.6535100.0634459.5831692.391. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

Apache Siege

Concurrent Users: 200

EPYC 7742EPYC 7642EPYC 7642 2PEPYC 7742 2POpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 200Linux 5.4 GitLinux 5.3Linux 5.2.168K16K24K32K40KSE +/- 418.92, N = 3SE +/- 363.93, N = 3SE +/- 32.16, N = 3SE +/- 441.28, N = 3SE +/- 28.40, N = 3SE +/- 30.90, N = 3SE +/- 46.56, N = 3SE +/- 142.06, N = 3SE +/- 81.80, N = 3SE +/- 322.20, N = 3SE +/- 286.21, N = 3SE +/- 500.52, N = 338029.7236630.6332821.8735369.7433938.6230835.7134564.3333773.5731162.7934520.4932836.7131972.561. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

NeatBench

Acceleration: CPU

EPYC 7642EPYC 7742EPYC 7642 2PEPYC 7742 2POpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: CPULinux 5.3Linux 5.2.16Linux 5.4 Git816243240SE +/- 0.38, N = 3SE +/- 0.23, N = 3SE +/- 0.23, N = 3SE +/- 0.24, N = 3SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 333.7733.7733.5333.6333.6033.0031.9031.0330.6730.8330.3329.73

Tungsten Renderer

Scene: Water Caustic

EPYC 7742EPYC 7742 2PEPYC 7642EPYC 7642 2POpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Water CausticLinux 5.2.16Linux 5.4 GitLinux 5.3612182430SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.22, N = 9SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.27, N = 3SE +/- 0.33, N = 421.7321.7521.7822.4822.7322.7422.7322.7422.7923.2623.6323.881. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl

Phoronix Test Suite v10.8.5