Ubuntu 21.04 EPYC

AMD EPYC 72F3 8-Core testing with a Supermicro H12SSL-i v1.01 (2.0 BIOS) and ASPEED on Ubuntu 21.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2104226-IB-UBUNTU21033
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
AMD EPYC 72F3
April 21 2021
  8 Hours, 8 Minutes
EPYC 72F3
April 22 2021
  8 Hours, 22 Minutes
Invert Behavior (Only Show Selected Data)
  8 Hours, 15 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

AMD EPYC 72F3

Processor: AMD EPYC 72F3 8-Core @ 3.70GHz (8 Cores / 16 Threads), Motherboard: Supermicro H12SSL-i v1.01 (2.0 BIOS), Chipset: AMD Starship/Matisse, Memory: 8 x 16 GB DDR4-3200MT/s 18ASF2G72PDZ-3G2E1, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe

OS: Ubuntu 21.04, Kernel: 5.11.0-16-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.7, Vulkan: 1.0.2, Compiler: GCC 11.0.1 20210413, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --disable-multilib --enable-checking=release
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119
Python Notes: Python 3.9.4
Security Notes: itlb_multihit: Not affected + 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

EPYC 72F3

Processor: AMD EPYC 72F3 8-Core @ 3.70GHz (8 Cores / 16 Threads), Motherboard: Supermicro H12SSL-i v1.01 (2.0 BIOS), Chipset: AMD Starship/Matisse, Memory: 8 x 16 GB DDR4-3200MT/s 18ASF2G72PDZ-3G2E1, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe

OS: Ubuntu 21.04, Kernel: 5.11.0-16-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.7, Vulkan: 1.0.2, Compiler: GCC 11.0.1 20210413, File-System: ext4, Screen Resolution: 1024x768

Ubuntu 21.04 EPYCProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionAMD EPYC 72F3EPYC 72F3AMD EPYC 72F3 8-Core @ 3.70GHz (8 Cores / 16 Threads)Supermicro H12SSL-i v1.01 (2.0 BIOS)AMD Starship/Matisse8 x 16 GB DDR4-3200MT/s 18ASF2G72PDZ-3G2E13841GB Micron_9300_MTFDHAL3T8TDPASPEEDVE2282 x Broadcom NetXtreme BCM5720 2-port PCIeUbuntu 21.045.11.0-16-generic (x86_64)GNOME Shell 3.38.4X Server 1.20.71.0.2GCC 11.0.1 20210413ext41920x10801024x768OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --disable-multilib --enable-checking=releaseProcessor Details- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119 Python Details- Python 3.9.4Security Details- itlb_multihit: Not affected + 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

AMD EPYC 72F3 vs. EPYC 72F3 ComparisonPhoronix Test SuiteBaseline+2.2%+2.2%+4.4%+4.4%+6.6%+6.6%5.1%3.6%2.6%2.4%2.4%2.2%S.F.P.R8.6%tConvolve MPI - GriddingR.C.a.P - CPU4.4%tConvolve OpenMP - Gridding3.7%CPUP.P.S100 - 50 - Read Write100 - 50 - Read Write - Average LatencyFayalite-FISTACES DGEMMASKAPLuxCoreRenderASKAPDeepSpeechHimeno BenchmarkPostgreSQL pgbenchPostgreSQL pgbenchCP2K Molecular DynamicsAMD EPYC 72F3EPYC 72F3

Ubuntu 21.04 EPYCaskap: tConvolve MPI - Griddingluxcorerender: Rainbow Colors and Prism - CPUaskap: tConvolve OpenMP - Griddingdeepspeech: CPUhimeno: Poisson Pressure Solverpgbench: 100 - 50 - Read Writepgbench: 100 - 50 - Read Write - Average Latencycp2k: Fayalite-FISTaskap: tConvolve MPI - Degriddingx265: Bosphorus 1080phelsing: 12 digitplaidml: No - Inference - VGG19 - CPUluxcorerender: DLSC - CPUopenfoam: Motorbike 30Mpgbench: 100 - 250 - Read Only - Average Latencyaskap: tConvolve OpenMP - Degriddingx265: Bosphorus 4Kpgbench: 100 - 250 - Read Onlyembree: Pathtracer ISPC - Asian Dragon Objaskap: tConvolve MT - Griddingembree: Pathtracer ISPC - Asian Dragonplaidml: No - Inference - ResNet 50 - CPUpgbench: 100 - 100 - Read Only - Average Latencytoktx: Zstd Compression 19ospray: NASA Streamlines - Path Tracerpgbench: 100 - 250 - Read Write - Average Latencypgbench: 100 - 250 - Read Writecloverleaf: Lagrangian-Eulerian Hydrodynamicssvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080pavifenc: 6pgbench: 100 - 100 - Read Onlyaom-av1: Speed 6 Two-Pass - Bosphorus 4Kluxcorerender: Danish Mood - CPUsvt-av1: Enc Mode 0 - 1080pliquid-dsp: 1 - 256 - 57luxcorerender: LuxCore Benchmark - CPUospray: NASA Streamlines - SciVispgbench: 100 - 50 - Read Onlysvt-av1: Enc Mode 8 - 1080paom-av1: Speed 9 Realtime - Bosphorus 4Kinfluxdb: 64 - 10000 - 2,5000,1 - 10000keydb: helsing: 14 digitencode-wavpack: WAV To WavPacklammps: Rhodopsin Proteincoremark: CoreMark Size 666 - Iterations Per Secondtensorflow-lite: Mobilenet Floatbuild-wasmer: Time To Compilelammps: 20k Atomsnumpy: pybench: Total For Average Test Timesospray: San Miguel - SciVisastcenc: Mediumpgbench: 100 - 50 - Read Only - Average Latencysimdjson: PartialTweetsbotan: AES-256 - Decryptembree: Pathtracer - Crownliquid-dsp: 2 - 256 - 57build-erlang: Time To Compilesvt-vp9: VMAF Optimized - Bosphorus 1080pbuild-nodejs: Time To Compilebotan: Blowfishtensorflow-lite: Inception V4svt-hevc: 1 - Bosphorus 1080pbotan: Blowfish - Decryptembree: Pathtracer ISPC - Crowntensorflow-lite: NASNet Mobileavifenc: 10aom-av1: Speed 8 Realtime - Bosphorus 4Ksvt-hevc: 10 - Bosphorus 1080paskap: tConvolve MT - Degriddingtensorflow-lite: SqueezeNetavifenc: 6, Losslesssimdjson: Kostyaphpbench: PHP Benchmark Suiteembree: Pathtracer - Asian Dragonplaidml: No - Inference - VGG16 - CPUtoktx: Zstd Compression 9svt-vp9: Visual Quality Optimized - Bosphorus 1080ptensorflow-lite: Inception ResNet V2tnn: CPU - MobileNet v2build-linux-kernel: Time To Compileembree: Pathtracer - Asian Dragon Objtoktx: UASTC 3 + Zstd Compression 19tensorflow-lite: Mobilenet Quanthmmer: Pfam Database Searchsimdjson: DistinctUserIDsvt-av1: Enc Mode 4 - 1080pbuild-godot: Time To Compileencode-mp3: WAV To MP3encode-opus: WAV To Opus Encodecaffe: AlexNet - CPU - 100securemark: SecureMark-TLSbotan: ChaCha20Poly1305rnnoise: toktx: UASTC 3botan: ChaCha20Poly1305 - Decryptliquid-dsp: 4 - 256 - 57pgbench: 100 - 100 - Read Writeencode-flac: WAV To FLACoidn: Memorialliquid-dsp: 16 - 256 - 57pgbench: 100 - 100 - Read Write - Average Latencyastcenc: Thoroughbotan: AES-256liquid-dsp: 8 - 256 - 57botan: KASUMIbotan: Twofish - Decryptbotan: Twofishsvt-hevc: 7 - Bosphorus 1080paom-av1: Speed 6 Realtime - Bosphorus 4Kbotan: CAST-256 - Decrypttnn: CPU - SqueezeNet v1.1caffe: GoogleNet - CPU - 100namd: ATPase Simulation - 327,506 Atomstoktx: UASTC 4 + Zstd Compression 19botan: KASUMI - Decryptastcenc: Exhaustivebotan: CAST-256influxdb: 4 - 10000 - 2,5000,1 - 10000openvkl: vklBenchmarkaom-av1: Speed 4 Two-Pass - Bosphorus 4Kaom-av1: Speed 0 Two-Pass - Bosphorus 4Kospray: Magnetic Reconnection - Path Tracerospray: Magnetic Reconnection - SciVisospray: XFrog Forest - Path Tracerospray: San Miguel - Path Tracerospray: XFrog Forest - SciVisluxcorerender: Orange Juice - CPUsimdjson: LargeRandmt-dgemm: Sustained Floating-Point RateAMD EPYC 72F3EPYC 72F37951.386.715290.3267.610874474.625633238152.1001143.5286349.1059.275.16811.281.8948.151.0355471.511.7824179011.98645588.4013.61419.750.41517.7464.2411.3622201130.03182.9211.5202411377.261.240.128687856671.4120.1423148535.34043.561673745.3510311.00543.04412.9856.907409274.96080112529554.1736.911440.9883014.565.16710.2164.316379.72612.1806137116667117.524174.09396.021440.17227170908.42438.47711.93521601253.00236.15255.904934.5019051149.0623.3972852313.701914.022.461137.812447280245.68089.15412.619616.60413694491.2544.964.549125.8256.6867.11937315282076839.41417.82611.174823.610271970000250496.9847.765931433333.99712.59816327.68253110000098.771370.218366.161121.9414.69146.652243.2231021721.95771310.58994.853100.1242146.6741424060.51453.850.15166.6710.531.511.182.812.791.113.5734958358.576.435101.6665.251724589.362834243972.0501118.6676465.4258.245.25711.091.8648.841.0215542.4511.6324487012.13265522.1413.77309.850.41117.9184.2011.4692180930.30181.3111.6192431937.201.250.129682620001.402023309935.09643.861662367.2506884.14546.63213.0616.868411546.62100812598554.4456.877443.1283414.635.19160.2154.336408.48212.1280136563333117.065173.44397.502438.57027268808.39436.94711.97641606713.01236.27255.084950.2619111549.2113.3873064813.662313.982.468137.442453380246.26389.36112.590616.64213725291.0524.974.540126.0706.6997.13237383282560838.02417.85411.191824.760271593333250156.9937.775938866674.00212.61256334.44053164666798.695369.938365.888121.8514.70146.694243.2791021941.95806310.53494.844100.1169146.6781424062.01453.850.15166.6710.531.511.182.812.791.113.291354OpenBenchmarking.org

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingAMD EPYC 72F3EPYC 72F32K4K6K8K10KSE +/- 0.00, N = 3SE +/- 64.79, N = 57951.388358.571. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMpix/sec Per Watt, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingEPYC 72F3132639526557.89
MinAvgMaxEPYC 72F347.6144.4273.9OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F342.050.157.8OpenBenchmarking.orgCelsius, Fewer Is BetterASKAP 1.0CPU Temperature Monitor1632486480

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: CPUAMD EPYC 72F3EPYC 72F3246810SE +/- 0.10, N = 3SE +/- 0.06, N = 156.716.43MIN: 6.39 / MAX: 6.92MIN: 5.68 / MAX: 6.74
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: CPUEPYC 72F30.01260.02520.03780.05040.0630.056
MinAvgMaxEPYC 72F347.7113.9188.1OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.5CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F342.552.461.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.5CPU Temperature Monitor20406080100

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - GriddingAMD EPYC 72F3EPYC 72F311002200330044005500SE +/- 34.80, N = 3SE +/- 51.82, N = 155290.325101.661. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

DeepSpeech

Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUAMD EPYC 72F3EPYC 72F31530456075SE +/- 0.55, N = 3SE +/- 0.69, N = 367.6165.25
MinAvgMaxEPYC 72F348.9124.8188.4OpenBenchmarking.orgWatts, Fewer Is BetterDeepSpeech 0.6CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F342.347.054.0OpenBenchmarking.orgCelsius, Fewer Is BetterDeepSpeech 0.6CPU Temperature Monitor1530456075

Himeno Benchmark

The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverAMD EPYC 72F3EPYC 72F310002000300040005000SE +/- 64.66, N = 15SE +/- 67.21, N = 154474.634589.361. (CC) gcc options: -O3 -mavx2
OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverEPYC 72F3102030405044.61
MinAvgMaxEPYC 72F348.1102.9154.7OpenBenchmarking.orgWatts, Fewer Is BetterHimeno Benchmark 3.0CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F340.344.656.0OpenBenchmarking.orgCelsius, Fewer Is BetterHimeno Benchmark 3.0CPU Temperature Monitor1632486480

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read WriteAMD EPYC 72F3EPYC 72F35K10K15K20K25KSE +/- 104.83, N = 3SE +/- 272.45, N = 323815243971. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average LatencyAMD EPYC 72F3EPYC 72F30.47250.9451.41751.892.3625SE +/- 0.009, N = 3SE +/- 0.023, N = 32.1002.0501. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
MinAvgMaxEPYC 72F348.2125.1302.6OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 13.0CPU Power Consumption Monitor80160240320400
MinAvgMaxEPYC 72F341.546.155.5OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0CPU Temperature Monitor1530456075

CP2K Molecular Dynamics

CP2K is an open-source molecular dynamics software package focused on quantum chemistry and solid-state physics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 8.1Input: Fayalite-FISTAMD EPYC 72F3EPYC 72F320040060080010001143.531118.67
MinAvgMaxEPYC 72F349.3157.0294.0OpenBenchmarking.orgWatts, Fewer Is BetterCP2K Molecular Dynamics 8.1CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F341.556.364.8OpenBenchmarking.orgCelsius, Fewer Is BetterCP2K Molecular Dynamics 8.1CPU Temperature Monitor20406080100

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingAMD EPYC 72F3EPYC 72F314002800420056007000SE +/- 50.79, N = 3SE +/- 62.67, N = 56349.106465.421. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pAMD EPYC 72F3EPYC 72F31326395265SE +/- 0.30, N = 3SE +/- 0.30, N = 559.2758.241. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterx265 3.4Video Input: Bosphorus 1080pEPYC 72F30.09920.19840.29760.39680.4960.441
MinAvgMaxEPYC 72F349.2131.9269.5OpenBenchmarking.orgWatts, Fewer Is Betterx265 3.4CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F341.850.761.5OpenBenchmarking.orgCelsius, Fewer Is Betterx265 3.4CPU Temperature Monitor20406080100

Helsing

Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 12 digitAMD EPYC 72F3EPYC 72F31.18282.36563.54844.73125.9145.1685.2571. (CC) gcc options: -O2 -pthread -lcrypto

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUAMD EPYC 72F3EPYC 72F33691215SE +/- 0.05, N = 3SE +/- 0.09, N = 311.2811.09
OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUEPYC 72F30.01760.03520.05280.07040.0880.078
MinAvgMaxEPYC 72F350.5143.1207.8OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLCPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F342.554.861.8OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLCPU Temperature Monitor20406080100

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: CPUAMD EPYC 72F3EPYC 72F30.42530.85061.27591.70122.1265SE +/- 0.01, N = 3SE +/- 0.01, N = 31.891.86MIN: 1.81 / MAX: 1.96MIN: 1.79 / MAX: 1.94
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: CPUEPYC 72F30.00320.00640.00960.01280.0160.014
MinAvgMaxEPYC 72F348.4132.9189.0OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.5CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F340.055.962.3OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.5CPU Temperature Monitor20406080100

OpenFOAM

OpenFOAM is the leading free, open source software for computational fluid dynamics (CFD). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 30MAMD EPYC 72F3EPYC 72F31122334455SE +/- 0.16, N = 3SE +/- 0.07, N = 348.1548.841. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lgenericPatchFields -ldynamicMesh -lmeshTools -lOpenFOAM -ldl -lm
MinAvgMaxEPYC 72F349.2163.3260.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 8CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F341.557.164.8OpenBenchmarking.orgCelsius, Fewer Is BetterOpenFOAM 8CPU Temperature Monitor20406080100

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average LatencyAMD EPYC 72F3EPYC 72F30.23290.46580.69870.93161.1645SE +/- 0.001, N = 3SE +/- 0.000, N = 31.0351.0211. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
MinAvgMaxEPYC 72F347.9112.0210.9OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 13.0CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F341.546.255.8OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0CPU Temperature Monitor1632486480

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingAMD EPYC 72F3EPYC 72F312002400360048006000SE +/- 37.73, N = 3SE +/- 35.96, N = 155471.505542.451. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second Per Watt, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingEPYC 72F3122436486052.62
MinAvgMaxEPYC 72F346.6105.3201.2OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F341.343.552.8OpenBenchmarking.orgCelsius, Fewer Is BetterASKAP 1.0CPU Temperature Monitor1530456075

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KAMD EPYC 72F3EPYC 72F33691215SE +/- 0.02, N = 3SE +/- 0.13, N = 711.7811.631. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterx265 3.4Video Input: Bosphorus 4KEPYC 72F30.01870.03740.05610.07480.09350.083
MinAvgMaxEPYC 72F349.3140.4286.7OpenBenchmarking.orgWatts, Fewer Is Betterx265 3.4CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F340.551.663.3OpenBenchmarking.orgCelsius, Fewer Is Betterx265 3.4CPU Temperature Monitor20406080100

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read OnlyAMD EPYC 72F3EPYC 72F350K100K150K200K250KSE +/- 207.21, N = 3SE +/- 102.95, N = 32417902448701. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian Dragon ObjAMD EPYC 72F3EPYC 72F33691215SE +/- 0.01, N = 3SE +/- 0.03, N = 311.9912.13MIN: 11.79 / MAX: 12.28MIN: 11.99 / MAX: 12.42
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian Dragon ObjEPYC 72F30.02180.04360.06540.08720.1090.097
MinAvgMaxEPYC 72F349.5125.1187.3OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.9.0CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F342.850.459.5OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 3.9.0CPU Temperature Monitor1632486480

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - GriddingAMD EPYC 72F3EPYC 72F312002400360048006000SE +/- 21.67, N = 3SE +/- 64.72, N = 35588.405522.141. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian DragonAMD EPYC 72F3EPYC 72F348121620SE +/- 0.02, N = 3SE +/- 0.07, N = 313.6113.77MIN: 13.41 / MAX: 13.8MIN: 13.57 / MAX: 14.09
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian DragonEPYC 72F30.02250.0450.06750.090.11250.1
MinAvgMaxEPYC 72F351.8137.1179.9OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.9.0CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F342.853.859.8OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 3.9.0CPU Temperature Monitor1632486480

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUAMD EPYC 72F3EPYC 72F33691215SE +/- 0.04, N = 3SE +/- 0.05, N = 39.759.85
OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUEPYC 72F30.01640.03280.04920.06560.0820.073
MinAvgMaxEPYC 72F350.4134.7210.6OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLCPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F343.048.258.0OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLCPU Temperature Monitor1632486480

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average LatencyAMD EPYC 72F3EPYC 72F30.09340.18680.28020.37360.467SE +/- 0.001, N = 3SE +/- 0.001, N = 30.4150.4111. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
MinAvgMaxEPYC 72F347.1115.5214.5OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 13.0CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F341.346.856.3OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0CPU Temperature Monitor1632486480

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 19AMD EPYC 72F3EPYC 72F348121620SE +/- 0.09, N = 3SE +/- 0.07, N = 317.7517.92
MinAvgMaxEPYC 72F348.396.6144.0OpenBenchmarking.orgWatts, Fewer Is BetterKTX-Software toktx 4.0CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F338.840.742.0OpenBenchmarking.orgCelsius, Fewer Is BetterKTX-Software toktx 4.0CPU Temperature Monitor1224364860

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path TracerAMD EPYC 72F3EPYC 72F30.9541.9082.8623.8164.77SE +/- 0.00, N = 3SE +/- 0.01, N = 34.244.20MIN: 4.13 / MAX: 4.29MIN: 3.97 / MAX: 4.26
OpenBenchmarking.orgFPS Per Watt, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path TracerEPYC 72F30.0070.0140.0210.0280.0350.031
MinAvgMaxEPYC 72F348.2137.3185.4OpenBenchmarking.orgWatts, Fewer Is BetterOSPray 1.8.5CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F343.056.062.5OpenBenchmarking.orgCelsius, Fewer Is BetterOSPray 1.8.5CPU Temperature Monitor20406080100

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyAMD EPYC 72F3EPYC 72F33691215SE +/- 0.02, N = 3SE +/- 0.04, N = 311.3611.471. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
MinAvgMaxEPYC 72F349.6122.1316.7OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 13.0CPU Power Consumption Monitor80160240320400
MinAvgMaxEPYC 72F341.345.854.8OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0CPU Temperature Monitor1530456075

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read WriteAMD EPYC 72F3EPYC 72F35K10K15K20K25KSE +/- 42.31, N = 3SE +/- 75.09, N = 322011218091. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version and benchmarked with the clover_bm.in input file (Problem 5). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsAMD EPYC 72F3EPYC 72F3714212835SE +/- 0.05, N = 3SE +/- 0.13, N = 330.0330.301. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
MinAvgMaxEPYC 72F347.8126.1172.7OpenBenchmarking.orgWatts, Fewer Is BetterCloverLeafCPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F334.547.959.5OpenBenchmarking.orgCelsius, Fewer Is BetterCloverLeafCPU Temperature Monitor1632486480

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pAMD EPYC 72F3EPYC 72F34080120160200SE +/- 0.27, N = 3SE +/- 0.27, N = 9182.92181.311. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pEPYC 72F30.38790.77581.16371.55161.93951.724
MinAvgMaxEPYC 72F349.8105.2173.9OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F340.045.058.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.3CPU Temperature Monitor1632486480

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6AMD EPYC 72F3EPYC 72F33691215SE +/- 0.02, N = 3SE +/- 0.03, N = 411.5211.621. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxEPYC 72F349.5115.9223.5OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.9.0CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F340.047.061.3OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.9.0CPU Temperature Monitor20406080100

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read OnlyAMD EPYC 72F3EPYC 72F350K100K150K200K250KSE +/- 281.80, N = 3SE +/- 571.75, N = 32411372431931. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KAMD EPYC 72F3EPYC 72F3246810SE +/- 0.03, N = 3SE +/- 0.00, N = 37.267.201. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KEPYC 72F30.01130.02260.03390.04520.05650.05
MinAvgMaxEPYC 72F348.6144.7269.8OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.0CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F343.054.563.5OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.0CPU Temperature Monitor20406080100

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: CPUAMD EPYC 72F3EPYC 72F30.28130.56260.84391.12521.4065SE +/- 0.02, N = 4SE +/- 0.02, N = 31.241.25MIN: 0.31 / MAX: 1.58MIN: 0.31 / MAX: 1.58
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: CPUEPYC 72F30.00230.00460.00690.00920.01150.01
MinAvgMaxEPYC 72F348.6130.8173.4OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.5CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F342.554.961.5OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.5CPU Temperature Monitor20406080100

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pAMD EPYC 72F3EPYC 72F30.0290.0580.0870.1160.145SE +/- 0.001, N = 3SE +/- 0.001, N = 30.1280.1291. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pEPYC 72F30.00020.00040.00060.00080.0010.001
MinAvgMaxEPYC 72F350.6126.5244.2OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 0.8CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F340.351.363.8OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8CPU Temperature Monitor20406080100

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 1 - Buffer Length: 256 - Filter Length: 57AMD EPYC 72F3EPYC 72F315M30M45M60M75MSE +/- 87563.94, N = 3SE +/- 573512.28, N = 368785667682620001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 2021.01.31Threads: 1 - Buffer Length: 256 - Filter Length: 57EPYC 72F3150K300K450K600K750K694569.55
MinAvgMaxEPYC 72F348.498.3149.0OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 2021.01.31CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F338.840.341.8OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 2021.01.31CPU Temperature Monitor1224364860

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: CPUAMD EPYC 72F3EPYC 72F30.31730.63460.95191.26921.5865SE +/- 0.01, N = 3SE +/- 0.00, N = 31.411.40MIN: 0.4 / MAX: 1.74MIN: 0.4 / MAX: 1.73
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: CPUEPYC 72F30.00250.0050.00750.010.01250.011
MinAvgMaxEPYC 72F347.9131.2196.2OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.5CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F343.055.863.3OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.5CPU Temperature Monitor20406080100

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVisAMD EPYC 72F3EPYC 72F3510152025SE +/- 0.14, N = 320.1420.00MIN: 19.23 / MAX: 20.83MIN: 19.23 / MAX: 20.83
OpenBenchmarking.orgFPS Per Watt, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVisEPYC 72F30.03890.07780.11670.15560.19450.173
MinAvgMaxEPYC 72F349.2115.3185.0OpenBenchmarking.orgWatts, Fewer Is BetterOSPray 1.8.5CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F343.850.761.3OpenBenchmarking.orgCelsius, Fewer Is BetterOSPray 1.8.5CPU Temperature Monitor20406080100

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read OnlyAMD EPYC 72F3EPYC 72F350K100K150K200K250KSE +/- 276.25, N = 3SE +/- 332.66, N = 32314852330991. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pAMD EPYC 72F3EPYC 72F3816243240SE +/- 0.06, N = 3SE +/- 0.04, N = 535.3435.101. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pEPYC 72F30.06640.13280.19920.26560.3320.295
MinAvgMaxEPYC 72F350.0118.8243.4OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 0.8CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F340.849.261.3OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8CPU Temperature Monitor20406080100

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KAMD EPYC 72F3EPYC 72F31020304050SE +/- 0.26, N = 3SE +/- 0.38, N = 1243.5643.861. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.0Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KEPYC 72F30.07580.15160.22740.30320.3790.337
MinAvgMaxEPYC 72F348.9130.0244.5OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.0CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F342.849.659.8OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.0CPU Temperature Monitor1632486480

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000AMD EPYC 72F3EPYC 72F3400K800K1200K1600K2000KSE +/- 1784.04, N = 3SE +/- 4165.96, N = 31673745.31662367.2
OpenBenchmarking.orgval/sec Per Watt, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000EPYC 72F33K6K9K12K15K12118.09
MinAvgMaxEPYC 72F348.7137.2276.1OpenBenchmarking.orgWatts, Fewer Is BetterInfluxDB 1.8.2CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F342.851.962.3OpenBenchmarking.orgCelsius, Fewer Is BetterInfluxDB 1.8.2CPU Temperature Monitor20406080100

KeyDB

A benchmark of KeyDB as a multi-threaded fork of the Redis server. The KeyDB benchmark is conducted using memtier-benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.0.16AMD EPYC 72F3EPYC 72F3110K220K330K440K550KSE +/- 258.74, N = 3SE +/- 1632.83, N = 3510311.00506884.141. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterKeyDB 6.0.16EPYC 72F380016002400320040003716.95
MinAvgMaxEPYC 72F349.7136.4249.1OpenBenchmarking.orgWatts, Fewer Is BetterKeyDB 6.0.16CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F340.550.756.3OpenBenchmarking.orgCelsius, Fewer Is BetterKeyDB 6.0.16CPU Temperature Monitor1632486480

Helsing

Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digitAMD EPYC 72F3EPYC 72F3120240360480600543.04546.631. (CC) gcc options: -O2 -pthread -lcrypto
MinAvgMaxEPYC 72F349.2151.2185.9OpenBenchmarking.orgWatts, Fewer Is BetterHelsing 1.0-betaCPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F339.360.263.0OpenBenchmarking.orgCelsius, Fewer Is BetterHelsing 1.0-betaCPU Temperature Monitor20406080100

WavPack Audio Encoding

This test times how long it takes to encode a sample WAV file to WavPack format with very high quality settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPackAMD EPYC 72F3EPYC 72F33691215SE +/- 0.00, N = 5SE +/- 0.00, N = 512.9913.061. (CXX) g++ options: -rdynamic
MinAvgMaxEPYC 72F348.293.5144.8OpenBenchmarking.orgWatts, Fewer Is BetterWavPack Audio Encoding 5.3CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F339.041.343.0OpenBenchmarking.orgCelsius, Fewer Is BetterWavPack Audio Encoding 5.3CPU Temperature Monitor1224364860

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin ProteinAMD EPYC 72F3EPYC 72F3246810SE +/- 0.002, N = 3SE +/- 0.013, N = 96.9076.8681. (CXX) g++ options: -O3 -pthread -lm
OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin ProteinEPYC 72F30.01370.02740.04110.05480.06850.061
MinAvgMaxEPYC 72F347.0112.4235.3OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F342.348.658.8OpenBenchmarking.orgCelsius, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020CPU Temperature Monitor1632486480

Coremark

This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondAMD EPYC 72F3EPYC 72F390K180K270K360K450KSE +/- 884.76, N = 3SE +/- 1142.43, N = 3409274.96411546.621. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec Per Watt, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondEPYC 72F380016002400320040003860.53
MinAvgMaxEPYC 72F348.0106.6150.1OpenBenchmarking.orgWatts, Fewer Is BetterCoremark 1.0CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F342.050.461.3OpenBenchmarking.orgCelsius, Fewer Is BetterCoremark 1.0CPU Temperature Monitor20406080100

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatAMD EPYC 72F3EPYC 72F330K60K90K120K150KSE +/- 40.37, N = 3SE +/- 102.61, N = 3125295125985
MinAvgMaxEPYC 72F349.6131.7165.1OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F340.556.662.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Temperature Monitor20406080100

Timed Wasmer Compilation

This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 1.0.2Time To CompileAMD EPYC 72F3EPYC 72F31224364860SE +/- 0.32, N = 3SE +/- 0.10, N = 354.1754.451. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc
MinAvgMaxEPYC 72F349.9142.3252.9OpenBenchmarking.orgWatts, Fewer Is BetterTimed Wasmer Compilation 1.0.2CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F341.855.963.3OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Wasmer Compilation 1.0.2CPU Temperature Monitor20406080100

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: 20k AtomsAMD EPYC 72F3EPYC 72F3246810SE +/- 0.014, N = 3SE +/- 0.016, N = 36.9116.8771. (CXX) g++ options: -O3 -pthread -lm
OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: 20k AtomsEPYC 72F30.00880.01760.02640.03520.0440.039
OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020CPU Power Consumption MonitorEPYC 72F350100150200250Min: 49.53 / Avg: 178.15 / Max: 265.61
OpenBenchmarking.orgCelsius, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020CPU Temperature MonitorEPYC 72F31326395265Min: 42.5 / Avg: 60.52 / Max: 64

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkAMD EPYC 72F3EPYC 72F3100200300400500SE +/- 0.77, N = 3SE +/- 0.98, N = 3440.98443.12
OpenBenchmarking.orgScore Per Watt, More Is BetterNumpy BenchmarkEPYC 72F30.9631.9262.8893.8524.8154.28
MinAvgMaxEPYC 72F350.9103.5172.6OpenBenchmarking.orgWatts, Fewer Is BetterNumpy BenchmarkCPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F340.345.958.0OpenBenchmarking.orgCelsius, Fewer Is BetterNumpy BenchmarkCPU Temperature Monitor1632486480

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesAMD EPYC 72F3EPYC 72F32004006008001000SE +/- 2.08, N = 3SE +/- 2.40, N = 3830834
MinAvgMaxEPYC 72F350.798.2146.3OpenBenchmarking.orgWatts, Fewer Is BetterPyBench 2018-02-16CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F340.342.345.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyBench 2018-02-16CPU Temperature Monitor1224364860

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisAMD EPYC 72F3EPYC 72F348121620SE +/- 0.07, N = 3SE +/- 0.07, N = 314.5614.63MIN: 14.08 / MAX: 15.63MIN: 14.08 / MAX: 15.63
OpenBenchmarking.orgFPS Per Watt, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisEPYC 72F30.02930.05860.08790.11720.14650.13
MinAvgMaxEPYC 72F349.0112.6197.5OpenBenchmarking.orgWatts, Fewer Is BetterOSPray 1.8.5CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F342.846.259.8OpenBenchmarking.orgCelsius, Fewer Is BetterOSPray 1.8.5CPU Temperature Monitor1632486480

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: MediumAMD EPYC 72F3EPYC 72F31.16812.33623.50434.67245.8405SE +/- 0.0069, N = 3SE +/- 0.0025, N = 75.16715.19161. (CXX) g++ options: -O3 -flto -pthread
MinAvgMaxEPYC 72F349.896.3255.5OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 2.4CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F340.343.059.3OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 2.4CPU Temperature Monitor1632486480

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average LatencyAMD EPYC 72F3EPYC 72F30.04860.09720.14580.19440.243SE +/- 0.000, N = 3SE +/- 0.000, N = 30.2160.2151. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
MinAvgMaxEPYC 72F347.2121.5310.9OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 13.0CPU Power Consumption Monitor80160240320400
MinAvgMaxEPYC 72F340.848.359.0OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0CPU Temperature Monitor1632486480

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: PartialTweetsAMD EPYC 72F3EPYC 72F30.97431.94862.92293.89724.8715SE +/- 0.01, N = 3SE +/- 0.00, N = 34.314.331. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s Per Watt, More Is Bettersimdjson 0.8.2Throughput Test: PartialTweetsEPYC 72F30.00950.0190.02850.0380.04750.042
MinAvgMaxEPYC 72F349.1102.6150.7OpenBenchmarking.orgWatts, Fewer Is Bettersimdjson 0.8.2CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F340.343.444.8OpenBenchmarking.orgCelsius, Fewer Is Bettersimdjson 0.8.2CPU Temperature Monitor1224364860

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256 - DecryptAMD EPYC 72F3EPYC 72F314002800420056007000SE +/- 5.41, N = 3SE +/- 16.31, N = 36379.736408.481. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s Per Watt, More Is BetterBotan 2.17.3Test: AES-256 - DecryptEPYC 72F3153045607566.15
MinAvgMaxEPYC 72F348.596.9145.8OpenBenchmarking.orgWatts, Fewer Is BetterBotan 2.17.3CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F340.343.344.5OpenBenchmarking.orgCelsius, Fewer Is BetterBotan 2.17.3CPU Temperature Monitor1224364860

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: CrownAMD EPYC 72F3EPYC 72F33691215SE +/- 0.05, N = 3SE +/- 0.02, N = 312.1812.13MIN: 12 / MAX: 12.47MIN: 11.99 / MAX: 12.37
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: CrownEPYC 72F30.01910.03820.05730.07640.09550.085
MinAvgMaxEPYC 72F350.6142.0268.9OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.9.0CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F343.054.561.8OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 3.9.0CPU Temperature Monitor20406080100

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 57AMD EPYC 72F3EPYC 72F330M60M90M120M150MSE +/- 61191.87, N = 3SE +/- 552941.63, N = 31371166671365633331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 57EPYC 72F3300K600K900K1200K1500K1252576.32
MinAvgMaxEPYC 72F348.4109.0165.0OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 2021.01.31CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F338.541.142.5OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 2021.01.31CPU Temperature Monitor1224364860

Timed Erlang/OTP Compilation

This test times how long it takes to compile Erlang/OTP. Erlang is a programming language and run-time for massively scalable soft real-time systems with high availability requirements. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Erlang/OTP Compilation 23.2Time To CompileAMD EPYC 72F3EPYC 72F3306090120150SE +/- 0.20, N = 3SE +/- 0.11, N = 3117.52117.07
MinAvgMaxEPYC 72F351.8130.7281.5OpenBenchmarking.orgWatts, Fewer Is BetterTimed Erlang/OTP Compilation 23.2CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F338.849.862.3OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Erlang/OTP Compilation 23.2CPU Temperature Monitor20406080100

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pAMD EPYC 72F3EPYC 72F34080120160200SE +/- 0.21, N = 3SE +/- 1.17, N = 9174.09173.441. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pEPYC 72F30.36830.73661.10491.47321.84151.637
MinAvgMaxEPYC 72F349.5105.9163.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F339.844.857.3OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.3CPU Temperature Monitor1632486480

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To CompileAMD EPYC 72F3EPYC 72F390180270360450SE +/- 0.20, N = 3SE +/- 0.31, N = 3396.02397.50
MinAvgMaxEPYC 72F348.4153.2207.2OpenBenchmarking.orgWatts, Fewer Is BetterTimed Node.js Compilation 15.11CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F343.357.565.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Node.js Compilation 15.11CPU Temperature Monitor20406080100

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: BlowfishAMD EPYC 72F3EPYC 72F3100200300400500SE +/- 0.16, N = 3SE +/- 0.84, N = 3440.17438.571. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4AMD EPYC 72F3EPYC 72F3600K1200K1800K2400K3000KSE +/- 342.20, N = 3SE +/- 212.21, N = 327170902726880
MinAvgMaxEPYC 72F350.1141.0171.2OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F341.858.662.3OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Temperature Monitor20406080100

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pAMD EPYC 72F3EPYC 72F3246810SE +/- 0.01, N = 3SE +/- 0.02, N = 38.428.391. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pEPYC 72F30.01370.02740.04110.05480.06850.061
MinAvgMaxEPYC 72F351.7136.9166.4OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F340.853.363.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-HEVC 1.5.0CPU Temperature Monitor20406080100

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish - DecryptAMD EPYC 72F3EPYC 72F390180270360450SE +/- 0.08, N = 3SE +/- 0.73, N = 3438.48436.951. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s Per Watt, More Is BetterBotan 2.17.3Test: Blowfish - DecryptEPYC 72F31.00172.00343.00514.00685.00854.452
MinAvgMaxEPYC 72F349.298.2146.9OpenBenchmarking.orgWatts, Fewer Is BetterBotan 2.17.3CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F339.841.443.3OpenBenchmarking.orgCelsius, Fewer Is BetterBotan 2.17.3CPU Temperature Monitor1224364860

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: CrownAMD EPYC 72F3EPYC 72F33691215SE +/- 0.03, N = 3SE +/- 0.04, N = 311.9411.98MIN: 11.76 / MAX: 12.19MIN: 11.46 / MAX: 12.26
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: CrownEPYC 72F30.0180.0360.0540.0720.090.08
MinAvgMaxEPYC 72F350.5150.3258.4OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.9.0CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F342.856.262.5OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 3.9.0CPU Temperature Monitor20406080100

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileAMD EPYC 72F3EPYC 72F330K60K90K120K150KSE +/- 38.01, N = 3SE +/- 103.00, N = 3160125160671
MinAvgMaxEPYC 72F349.4137.3177.4OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F341.058.663.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Temperature Monitor20406080100

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10AMD EPYC 72F3EPYC 72F30.67771.35542.03312.71083.3885SE +/- 0.005, N = 3SE +/- 0.006, N = 93.0023.0121. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxEPYC 72F347.994.8203.9OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.9.0CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F338.841.558.5OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.9.0CPU Temperature Monitor1632486480

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KAMD EPYC 72F3EPYC 72F3816243240SE +/- 0.28, N = 3SE +/- 0.07, N = 336.1536.271. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.0Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KEPYC 72F30.06140.12280.18420.24560.3070.273
MinAvgMaxEPYC 72F348.8132.8247.7OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.0CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F341.549.058.0OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.0CPU Temperature Monitor1632486480

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pAMD EPYC 72F3EPYC 72F360120180240300SE +/- 0.68, N = 3SE +/- 0.33, N = 10255.90255.081. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pEPYC 72F30.60531.21061.81592.42123.02652.69
MinAvgMaxEPYC 72F347.294.8231.3OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F341.043.456.3OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-HEVC 1.5.0CPU Temperature Monitor1632486480

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingAMD EPYC 72F3EPYC 72F311002200330044005500SE +/- 8.30, N = 3SE +/- 34.90, N = 34934.504950.261. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second Per Watt, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingEPYC 72F3102030405045.05
MinAvgMaxEPYC 72F348.3109.9179.5OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F340.345.056.8OpenBenchmarking.orgCelsius, Fewer Is BetterASKAP 1.0CPU Temperature Monitor1632486480

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetAMD EPYC 72F3EPYC 72F340K80K120K160K200KSE +/- 10.60, N = 3SE +/- 62.38, N = 3190511191115
MinAvgMaxEPYC 72F348.4132.9189.1OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F344.057.863.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Temperature Monitor20406080100

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6, LosslessAMD EPYC 72F3EPYC 72F31122334455SE +/- 0.06, N = 3SE +/- 0.10, N = 349.0649.211. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxEPYC 72F346.9140.2254.7OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.9.0CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F338.356.063.8OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.9.0CPU Temperature Monitor20406080100

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: KostyaAMD EPYC 72F3EPYC 72F30.76281.52562.28843.05123.814SE +/- 0.01, N = 3SE +/- 0.01, N = 33.393.381. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s Per Watt, More Is Bettersimdjson 0.8.2Throughput Test: KostyaEPYC 72F30.00630.01260.01890.02520.03150.028
MinAvgMaxEPYC 72F348.8119.3177.3OpenBenchmarking.orgWatts, Fewer Is Bettersimdjson 0.8.2CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F340.843.445.8OpenBenchmarking.orgCelsius, Fewer Is Bettersimdjson 0.8.2CPU Temperature Monitor1224364860

PHPBench

PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteAMD EPYC 72F3EPYC 72F3160K320K480K640K800KSE +/- 2636.91, N = 3SE +/- 4873.12, N = 3728523730648
OpenBenchmarking.orgScore Per Watt, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteEPYC 72F3160032004800640080007535.44
MinAvgMaxEPYC 72F347.797.0148.2OpenBenchmarking.orgWatts, Fewer Is BetterPHPBench 0.8.1CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F339.041.142.3OpenBenchmarking.orgCelsius, Fewer Is BetterPHPBench 0.8.1CPU Temperature Monitor1224364860

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian DragonAMD EPYC 72F3EPYC 72F348121620SE +/- 0.08, N = 3SE +/- 0.06, N = 313.7013.66MIN: 13.54 / MAX: 13.98MIN: 13.51 / MAX: 13.86
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian DragonEPYC 72F30.02250.0450.06750.090.11250.1
MinAvgMaxEPYC 72F349.0137.0183.6OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.9.0CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F343.053.661.3OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 3.9.0CPU Temperature Monitor20406080100

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUAMD EPYC 72F3EPYC 72F348121620SE +/- 0.14, N = 3SE +/- 0.16, N = 614.0213.98
OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUEPYC 72F30.02180.04360.06540.08720.1090.097
MinAvgMaxEPYC 72F350.1144.1215.3OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLCPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F339.353.259.3OpenBenchmarking.orgCelsius, Fewer Is BetterPlaidMLCPU Temperature Monitor1632486480

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 9AMD EPYC 72F3EPYC 72F30.55531.11061.66592.22122.7765SE +/- 0.002, N = 3SE +/- 0.002, N = 102.4612.468
MinAvgMaxEPYC 72F348.184.9141.3OpenBenchmarking.orgWatts, Fewer Is BetterKTX-Software toktx 4.0CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F339.040.642.5OpenBenchmarking.orgCelsius, Fewer Is BetterKTX-Software toktx 4.0CPU Temperature Monitor1224364860

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pAMD EPYC 72F3EPYC 72F3306090120150SE +/- 0.31, N = 3SE +/- 0.20, N = 8137.81137.441. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pEPYC 72F30.27290.54580.81871.09161.36451.213
MinAvgMaxEPYC 72F348.0113.3168.8OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F340.346.855.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.3CPU Temperature Monitor1530456075

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2AMD EPYC 72F3EPYC 72F3500K1000K1500K2000K2500KSE +/- 357.91, N = 3SE +/- 645.52, N = 324472802453380
MinAvgMaxEPYC 72F348.2137.9169.3OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F341.058.762.3OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Temperature Monitor20406080100

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2AMD EPYC 72F3EPYC 72F350100150200250SE +/- 0.07, N = 3SE +/- 0.10, N = 3245.68246.26MIN: 245.34 / MAX: 251.08MIN: 245.29 / MAX: 254.351. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
MinAvgMaxEPYC 72F349.7101.2166.1OpenBenchmarking.orgWatts, Fewer Is BetterTNN 0.2.3CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F341.343.445.0OpenBenchmarking.orgCelsius, Fewer Is BetterTNN 0.2.3CPU Temperature Monitor1224364860

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To CompileAMD EPYC 72F3EPYC 72F320406080100SE +/- 1.07, N = 3SE +/- 1.07, N = 389.1589.36
MinAvgMaxEPYC 72F350.2149.0246.5OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F342.356.264.3OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20CPU Temperature Monitor20406080100

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon ObjAMD EPYC 72F3EPYC 72F33691215SE +/- 0.01, N = 3SE +/- 0.02, N = 312.6212.59MIN: 12.55 / MAX: 12.76MIN: 12.52 / MAX: 12.74
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon ObjEPYC 72F30.0230.0460.0690.0920.1150.102
MinAvgMaxEPYC 72F348.7123.5184.9OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.9.0CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F343.050.560.0OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 3.9.0CPU Temperature Monitor1632486480

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3 + Zstd Compression 19AMD EPYC 72F3EPYC 72F348121620SE +/- 0.03, N = 3SE +/- 0.04, N = 416.6016.64
MinAvgMaxEPYC 72F348.7100.4178.3OpenBenchmarking.orgWatts, Fewer Is BetterKTX-Software toktx 4.0CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F338.845.058.8OpenBenchmarking.orgCelsius, Fewer Is BetterKTX-Software toktx 4.0CPU Temperature Monitor1632486480

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantAMD EPYC 72F3EPYC 72F330K60K90K120K150KSE +/- 4.73, N = 3SE +/- 79.39, N = 3136944137252
MinAvgMaxEPYC 72F349.9123.9149.8OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F341.056.362.3OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Temperature Monitor20406080100

Timed HMMer Search

This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database SearchAMD EPYC 72F3EPYC 72F320406080100SE +/- 0.01, N = 3SE +/- 0.05, N = 391.2591.051. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
MinAvgMaxEPYC 72F347.0109.6172.6OpenBenchmarking.orgWatts, Fewer Is BetterTimed HMMer Search 3.3.1CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F342.346.558.3OpenBenchmarking.orgCelsius, Fewer Is BetterTimed HMMer Search 3.3.1CPU Temperature Monitor1632486480

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: DistinctUserIDAMD EPYC 72F3EPYC 72F31.11832.23663.35494.47325.5915SE +/- 0.01, N = 3SE +/- 0.01, N = 34.964.971. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s Per Watt, More Is Bettersimdjson 0.8.2Throughput Test: DistinctUserIDEPYC 72F30.0110.0220.0330.0440.0550.049
MinAvgMaxEPYC 72F349.0102.0151.5OpenBenchmarking.orgWatts, Fewer Is Bettersimdjson 0.8.2CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F339.541.743.0OpenBenchmarking.orgCelsius, Fewer Is Bettersimdjson 0.8.2CPU Temperature Monitor1224364860

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pAMD EPYC 72F3EPYC 72F31.02352.0473.07054.0945.1175SE +/- 0.021, N = 3SE +/- 0.018, N = 34.5494.5401. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pEPYC 72F30.00810.01620.02430.03240.04050.036
MinAvgMaxEPYC 72F348.7126.0207.5OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 0.8CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F340.051.561.8OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8CPU Temperature Monitor20406080100

Timed Godot Game Engine Compilation

This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileAMD EPYC 72F3EPYC 72F3306090120150SE +/- 0.13, N = 3SE +/- 0.03, N = 3125.83126.07
MinAvgMaxEPYC 72F351.1146.6287.3OpenBenchmarking.orgWatts, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F340.554.864.3OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3CPU Temperature Monitor20406080100

LAME MP3 Encoding

LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3AMD EPYC 72F3EPYC 72F3246810SE +/- 0.007, N = 3SE +/- 0.009, N = 66.6866.6991. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lncurses -lm
MinAvgMaxEPYC 72F348.691.5148.0OpenBenchmarking.orgWatts, Fewer Is BetterLAME MP3 Encoding 3.100CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F339.842.955.3OpenBenchmarking.orgCelsius, Fewer Is BetterLAME MP3 Encoding 3.100CPU Temperature Monitor1530456075

Opus Codec Encoding

Opus is an open audio codec. Opus is a lossy audio compression format designed primarily for interactive real-time applications over the Internet. This test uses Opus-Tools and measures the time required to encode a WAV file to Opus. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus EncodeAMD EPYC 72F3EPYC 72F3246810SE +/- 0.004, N = 5SE +/- 0.014, N = 67.1197.1321. (CXX) g++ options: -fvisibility=hidden -logg -lm
MinAvgMaxEPYC 72F347.391.0145.2OpenBenchmarking.orgWatts, Fewer Is BetterOpus Codec Encoding 1.3.1CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F339.341.143.3OpenBenchmarking.orgCelsius, Fewer Is BetterOpus Codec Encoding 1.3.1CPU Temperature Monitor1224364860

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100AMD EPYC 72F3EPYC 72F38K16K24K32K40KSE +/- 62.17, N = 3SE +/- 64.71, N = 337315373831. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
MinAvgMaxEPYC 72F349.4163.8280.0OpenBenchmarking.orgWatts, Fewer Is BetterCaffe 2020-02-13CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F341.357.364.5OpenBenchmarking.orgCelsius, Fewer Is BetterCaffe 2020-02-13CPU Temperature Monitor20406080100

SecureMark

SecureMark is an objective, standardized benchmarking framework for measuring the efficiency of cryptographic processing solutions developed by EEMBC. SecureMark-TLS is benchmarking Transport Layer Security performance with a focus on IoT/edge computing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSAMD EPYC 72F3EPYC 72F360K120K180K240K300KSE +/- 801.00, N = 3SE +/- 1383.28, N = 32820762825601. (CC) gcc options: -pedantic -O3
OpenBenchmarking.orgmarks Per Watt, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSEPYC 72F360012001800240030002803.59
MinAvgMaxEPYC 72F349.6100.8146.2OpenBenchmarking.orgWatts, Fewer Is BetterSecureMark 1.0.4CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F339.841.843.5OpenBenchmarking.orgCelsius, Fewer Is BetterSecureMark 1.0.4CPU Temperature Monitor1224364860

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305AMD EPYC 72F3EPYC 72F32004006008001000SE +/- 0.53, N = 3SE +/- 0.87, N = 3839.41838.021. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

RNNoise

RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28AMD EPYC 72F3EPYC 72F348121620SE +/- 0.01, N = 3SE +/- 0.04, N = 317.8317.851. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
MinAvgMaxEPYC 72F350.294.1142.1OpenBenchmarking.orgWatts, Fewer Is BetterRNNoise 2020-06-28CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F340.542.443.8OpenBenchmarking.orgCelsius, Fewer Is BetterRNNoise 2020-06-28CPU Temperature Monitor1224364860

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3AMD EPYC 72F3EPYC 72F33691215SE +/- 0.00, N = 3SE +/- 0.00, N = 511.1711.19
MinAvgMaxEPYC 72F349.898.3183.5OpenBenchmarking.orgWatts, Fewer Is BetterKTX-Software toktx 4.0CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F341.347.660.5OpenBenchmarking.orgCelsius, Fewer Is BetterKTX-Software toktx 4.0CPU Temperature Monitor20406080100

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - DecryptAMD EPYC 72F3EPYC 72F32004006008001000SE +/- 0.04, N = 3SE +/- 0.26, N = 3823.61824.761. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s Per Watt, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - DecryptEPYC 72F32468108.317
MinAvgMaxEPYC 72F348.699.2145.0OpenBenchmarking.orgWatts, Fewer Is BetterBotan 2.17.3CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F339.845.456.3OpenBenchmarking.orgCelsius, Fewer Is BetterBotan 2.17.3CPU Temperature Monitor1632486480

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 57AMD EPYC 72F3EPYC 72F360M120M180M240M300MSE +/- 710093.89, N = 3SE +/- 1535625.10, N = 32719700002715933331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 57EPYC 72F3500K1000K1500K2000K2500K2259077.56
MinAvgMaxEPYC 72F348.5120.2188.4OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 2021.01.31CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F338.846.459.5OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 2021.01.31CPU Temperature Monitor1632486480

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read WriteAMD EPYC 72F3EPYC 72F35K10K15K20K25KSE +/- 314.10, N = 5SE +/- 423.48, N = 325049250151. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

FLAC Audio Encoding

This test times how long it takes to encode a sample WAV file to FLAC format five times. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACAMD EPYC 72F3EPYC 72F3246810SE +/- 0.006, N = 5SE +/- 0.005, N = 66.9846.9931. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
MinAvgMaxEPYC 72F347.592.5153.8OpenBenchmarking.orgWatts, Fewer Is BetterFLAC Audio Encoding 1.3.2CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F338.843.855.0OpenBenchmarking.orgCelsius, Fewer Is BetterFLAC Audio Encoding 1.3.2CPU Temperature Monitor1530456075

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.2.0Scene: MemorialAMD EPYC 72F3EPYC 72F3246810SE +/- 0.01, N = 3SE +/- 0.01, N = 37.767.77
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 1.2.0Scene: MemorialEPYC 72F30.01080.02160.03240.04320.0540.048
MinAvgMaxEPYC 72F352.0160.6252.1OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 1.2.0CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F344.356.963.8OpenBenchmarking.orgCelsius, Fewer Is BetterIntel Open Image Denoise 1.2.0CPU Temperature Monitor20406080100

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57AMD EPYC 72F3EPYC 72F3130M260M390M520M650MSE +/- 554416.61, N = 3SE +/- 355027.39, N = 35931433335938866671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57EPYC 72F31.1M2.2M3.3M4.4M5.5M5060872.73
MinAvgMaxEPYC 72F349.0117.3156.5OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 2021.01.31CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F340.353.063.0OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 2021.01.31CPU Temperature Monitor20406080100

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average LatencyAMD EPYC 72F3EPYC 72F30.90051.8012.70153.6024.5025SE +/- 0.051, N = 5SE +/- 0.067, N = 33.9974.0021. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
MinAvgMaxEPYC 72F349.0119.1316.4OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 13.0CPU Power Consumption Monitor80160240320400
MinAvgMaxEPYC 72F341.046.258.3OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0CPU Temperature Monitor1632486480

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: ThoroughAMD EPYC 72F3EPYC 72F33691215SE +/- 0.00, N = 3SE +/- 0.00, N = 412.6012.611. (CXX) g++ options: -O3 -flto -pthread
MinAvgMaxEPYC 72F347.5108.4158.7OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 2.4CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F339.347.060.3OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 2.4CPU Temperature Monitor1632486480

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256AMD EPYC 72F3EPYC 72F314002800420056007000SE +/- 0.21, N = 3SE +/- 1.43, N = 36327.686334.441. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 57AMD EPYC 72F3EPYC 72F3110M220M330M440M550MSE +/- 3074692.40, N = 3SE +/- 2041766.66, N = 35311000005316466671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 57EPYC 72F3700K1400K2100K2800K3500K3451252.35
MinAvgMaxEPYC 72F348.4154.0239.9OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 2021.01.31CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F339.355.461.0OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 2021.01.31CPU Temperature Monitor20406080100

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMIAMD EPYC 72F3EPYC 72F320406080100SE +/- 0.01, N = 3SE +/- 0.02, N = 398.7798.701. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish - DecryptAMD EPYC 72F3EPYC 72F380160240320400SE +/- 0.11, N = 3SE +/- 0.02, N = 3370.22369.941. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s Per Watt, More Is BetterBotan 2.17.3Test: Twofish - DecryptEPYC 72F30.84981.69962.54943.39924.2493.777
MinAvgMaxEPYC 72F351.498.0144.8OpenBenchmarking.orgWatts, Fewer Is BetterBotan 2.17.3CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F341.042.744.0OpenBenchmarking.orgCelsius, Fewer Is BetterBotan 2.17.3CPU Temperature Monitor1224364860

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: TwofishAMD EPYC 72F3EPYC 72F380160240320400SE +/- 0.14, N = 3SE +/- 0.07, N = 3366.16365.891. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pAMD EPYC 72F3EPYC 72F3306090120150SE +/- 0.27, N = 3SE +/- 0.19, N = 7121.94121.851. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pEPYC 72F30.26210.52420.78631.04841.31051.165
MinAvgMaxEPYC 72F349.4104.6181.0OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F340.845.358.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-HEVC 1.5.0CPU Temperature Monitor1632486480

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KAMD EPYC 72F3EPYC 72F348121620SE +/- 0.03, N = 3SE +/- 0.07, N = 314.6914.701. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KEPYC 72F30.02360.04720.07080.09440.1180.105
MinAvgMaxEPYC 72F347.3140.6275.5OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.0CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F341.853.260.5OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.0CPU Temperature Monitor20406080100

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256 - DecryptAMD EPYC 72F3EPYC 72F3306090120150SE +/- 0.10, N = 3SE +/- 0.08, N = 3146.65146.691. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s Per Watt, More Is BetterBotan 2.17.3Test: CAST-256 - DecryptEPYC 72F30.34130.68261.02391.36521.70651.517
MinAvgMaxEPYC 72F348.296.7144.5OpenBenchmarking.orgWatts, Fewer Is BetterBotan 2.17.3CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F340.042.644.0OpenBenchmarking.orgCelsius, Fewer Is BetterBotan 2.17.3CPU Temperature Monitor1224364860

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1AMD EPYC 72F3EPYC 72F350100150200250SE +/- 0.17, N = 3SE +/- 0.06, N = 3243.22243.28MIN: 242.89 / MAX: 243.69MIN: 242.94 / MAX: 243.921. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
MinAvgMaxEPYC 72F348.894.7143.3OpenBenchmarking.orgWatts, Fewer Is BetterTNN 0.2.3CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F340.342.244.0OpenBenchmarking.orgCelsius, Fewer Is BetterTNN 0.2.3CPU Temperature Monitor1224364860

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100AMD EPYC 72F3EPYC 72F320K40K60K80K100KSE +/- 153.26, N = 3SE +/- 262.46, N = 31021721021941. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
MinAvgMaxEPYC 72F349.0171.0276.1OpenBenchmarking.orgWatts, Fewer Is BetterCaffe 2020-02-13CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F341.559.764.5OpenBenchmarking.orgCelsius, Fewer Is BetterCaffe 2020-02-13CPU Temperature Monitor20406080100

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsAMD EPYC 72F3EPYC 72F30.44060.88121.32181.76242.203SE +/- 0.00064, N = 3SE +/- 0.00055, N = 31.957711.95806
MinAvgMaxEPYC 72F348.4142.8162.8OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 2.14CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F342.558.464.0OpenBenchmarking.orgCelsius, Fewer Is BetterNAMD 2.14CPU Temperature Monitor20406080100

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 4 + Zstd Compression 19AMD EPYC 72F3EPYC 72F370140210280350SE +/- 0.05, N = 3SE +/- 0.06, N = 3310.59310.53
MinAvgMaxEPYC 72F348.3135.4163.7OpenBenchmarking.orgWatts, Fewer Is BetterKTX-Software toktx 4.0CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F340.357.462.0OpenBenchmarking.orgCelsius, Fewer Is BetterKTX-Software toktx 4.0CPU Temperature Monitor20406080100

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI - DecryptAMD EPYC 72F3EPYC 72F320406080100SE +/- 0.03, N = 3SE +/- 0.00, N = 394.8594.841. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s Per Watt, More Is BetterBotan 2.17.3Test: KASUMI - DecryptEPYC 72F30.22030.44060.66090.88121.10150.979
MinAvgMaxEPYC 72F349.596.9145.2OpenBenchmarking.orgWatts, Fewer Is BetterBotan 2.17.3CPU Power Consumption Monitor4080120160200
MinAvgMaxEPYC 72F339.342.544.0OpenBenchmarking.orgCelsius, Fewer Is BetterBotan 2.17.3CPU Temperature Monitor1224364860

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: ExhaustiveAMD EPYC 72F3EPYC 72F320406080100SE +/- 0.03, N = 3SE +/- 0.05, N = 3100.12100.121. (CXX) g++ options: -O3 -flto -pthread
MinAvgMaxEPYC 72F349.1136.8171.8OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 2.4CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F340.356.663.5OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 2.4CPU Temperature Monitor20406080100

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256AMD EPYC 72F3EPYC 72F3306090120150SE +/- 0.06, N = 3SE +/- 0.09, N = 3146.67146.681. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000AMD EPYC 72F3EPYC 72F3300K600K900K1200K1500KSE +/- 3116.00, N = 3SE +/- 4799.90, N = 31424060.51424062.0
OpenBenchmarking.orgval/sec Per Watt, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000EPYC 72F32K4K6K8K10K10206.45
MinAvgMaxEPYC 72F350.2139.5273.5OpenBenchmarking.orgWatts, Fewer Is BetterInfluxDB 1.8.2CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F339.350.661.3OpenBenchmarking.orgCelsius, Fewer Is BetterInfluxDB 1.8.2CPU Temperature Monitor20406080100

Meta Performance Per Watts

OpenBenchmarking.orgPerformance Per Watts, More Is BetterMeta Performance Per WattsPerformance Per WattsEPYC 72F34080120160200178.37

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkAMD EPYC 72F3EPYC 72F3306090120150145145MIN: 1 / MAX: 560MIN: 1 / MAX: 563
OpenBenchmarking.orgItems / Sec Per Watt, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkEPYC 72F30.25110.50220.75331.00441.25551.116
MinAvgMaxEPYC 72F346.4129.9247.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenVKL 0.9CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F341.850.263.3OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVKL 0.9CPU Temperature Monitor20406080100

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KAMD EPYC 72F3EPYC 72F30.86631.73262.59893.46524.3315SE +/- 0.01, N = 3SE +/- 0.01, N = 33.853.851. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.0Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KEPYC 72F30.00610.01220.01830.02440.03050.027
MinAvgMaxEPYC 72F348.7142.2272.9OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.0CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F341.355.564.0OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.0CPU Temperature Monitor20406080100

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KAMD EPYC 72F3EPYC 72F30.03380.06760.10140.13520.169SE +/- 0.00, N = 3SE +/- 0.00, N = 30.150.151. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.0Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KEPYC 72F30.00020.00040.00060.00080.0010.001
MinAvgMaxEPYC 72F351.0135.3262.7OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.0CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F341.353.365.3OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.0CPU Temperature Monitor20406080100

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: Path TracerAMD EPYC 72F3EPYC 72F34080120160200SE +/- 0.00, N = 3SE +/- 0.00, N = 10166.67166.67MIN: 142.86 / MAX: 200MIN: 142.86 / MAX: 200
OpenBenchmarking.orgFPS Per Watt, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: Path TracerEPYC 72F30.36860.73721.10581.47441.8431.638
MinAvgMaxEPYC 72F347.4101.7236.5OpenBenchmarking.orgWatts, Fewer Is BetterOSPray 1.8.5CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F342.346.056.0OpenBenchmarking.orgCelsius, Fewer Is BetterOSPray 1.8.5CPU Temperature Monitor1632486480

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisAMD EPYC 72F3EPYC 72F33691215SE +/- 0.00, N = 3SE +/- 0.00, N = 310.5310.53MIN: 10.31 / MAX: 11.11MIN: 10 / MAX: 11.11
OpenBenchmarking.orgFPS Per Watt, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisEPYC 72F30.01910.03820.05730.07640.09550.085
MinAvgMaxEPYC 72F348.0123.3233.1OpenBenchmarking.orgWatts, Fewer Is BetterOSPray 1.8.5CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F341.852.059.3OpenBenchmarking.orgCelsius, Fewer Is BetterOSPray 1.8.5CPU Temperature Monitor1632486480

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path TracerAMD EPYC 72F3EPYC 72F30.33980.67961.01941.35921.699SE +/- 0.00, N = 3SE +/- 0.00, N = 31.511.51MIN: 1.49 / MAX: 1.53MIN: 1.47 / MAX: 1.53
OpenBenchmarking.orgFPS Per Watt, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path TracerEPYC 72F30.00230.00460.00690.00920.01150.01
MinAvgMaxEPYC 72F348.8149.0193.7OpenBenchmarking.orgWatts, Fewer Is BetterOSPray 1.8.5CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F342.558.764.0OpenBenchmarking.orgCelsius, Fewer Is BetterOSPray 1.8.5CPU Temperature Monitor20406080100

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerAMD EPYC 72F3EPYC 72F30.26550.5310.79651.0621.3275SE +/- 0.00, N = 3SE +/- 0.00, N = 31.181.18MIN: 1.16 / MAX: 1.19MIN: 1.16 / MAX: 1.2
OpenBenchmarking.orgFPS Per Watt, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerEPYC 72F30.0020.0040.0060.0080.010.009
MinAvgMaxEPYC 72F348.0136.6211.0OpenBenchmarking.orgWatts, Fewer Is BetterOSPray 1.8.5CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F343.054.361.0OpenBenchmarking.orgCelsius, Fewer Is BetterOSPray 1.8.5CPU Temperature Monitor20406080100

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisAMD EPYC 72F3EPYC 72F30.63231.26461.89692.52923.1615SE +/- 0.01, N = 3SE +/- 0.00, N = 32.812.81MIN: 2.73 / MAX: 2.85MIN: 2.7 / MAX: 2.85
OpenBenchmarking.orgFPS Per Watt, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisEPYC 72F30.00450.0090.01350.0180.02250.02
MinAvgMaxEPYC 72F347.2143.0189.9OpenBenchmarking.orgWatts, Fewer Is BetterOSPray 1.8.5CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F341.357.263.5OpenBenchmarking.orgCelsius, Fewer Is BetterOSPray 1.8.5CPU Temperature Monitor20406080100

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: CPUAMD EPYC 72F3EPYC 72F30.62781.25561.88342.51123.139SE +/- 0.01, N = 3SE +/- 0.01, N = 32.792.79MIN: 2.74 / MAX: 2.87MIN: 2.73 / MAX: 2.86
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: CPUEPYC 72F30.00470.00940.01410.01880.02350.021
MinAvgMaxEPYC 72F350.4130.3235.9OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.5CPU Power Consumption Monitor60120180240300
MinAvgMaxEPYC 72F342.354.762.5OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.5CPU Temperature Monitor20406080100

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: LargeRandomAMD EPYC 72F3EPYC 72F30.24980.49960.74940.99921.249SE +/- 0.00, N = 3SE +/- 0.00, N = 31.111.111. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s Per Watt, More Is Bettersimdjson 0.8.2Throughput Test: LargeRandomEPYC 72F30.00230.00460.00690.00920.01150.01
MinAvgMaxEPYC 72F348.4116.5174.8OpenBenchmarking.orgWatts, Fewer Is Bettersimdjson 0.8.2CPU Power Consumption Monitor50100150200250
MinAvgMaxEPYC 72F340.543.646.0OpenBenchmarking.orgCelsius, Fewer Is Bettersimdjson 0.8.2CPU Temperature Monitor1224364860

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System MonitoringEPYC 72F31326395265Min: 34.5 / Avg: 51.16 / Max: 65.25

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringEPYC 72F360120180240300Min: 45.74 / Avg: 131.51 / Max: 316.71

ACES DGEMM

MinAvgMaxEPYC 72F341.350.757.5OpenBenchmarking.orgCelsius, Fewer Is BetterACES DGEMM 1.0CPU Temperature Monitor1632486480

MinAvgMaxEPYC 72F348.9140.4264.4OpenBenchmarking.orgWatts, Fewer Is BetterACES DGEMM 1.0CPU Power Consumption Monitor70140210280350

OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 72F30.00520.01040.01560.02080.0260.023

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateAMD EPYC 72F3EPYC 72F30.8041.6082.4123.2164.02SE +/- 0.062739, N = 13SE +/- 0.021694, N = 33.5734953.2913541. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 72F30.00520.01040.01560.02080.0260.023
MinAvgMaxEPYC 72F348.9140.4264.4OpenBenchmarking.orgWatts, Fewer Is BetterACES DGEMM 1.0CPU Power Consumption Monitor70140210280350
MinAvgMaxEPYC 72F341.350.757.5OpenBenchmarking.orgCelsius, Fewer Is BetterACES DGEMM 1.0CPU Temperature Monitor1632486480

137 Results Shown

ASKAP
LuxCoreRender
ASKAP
DeepSpeech
Himeno Benchmark
PostgreSQL pgbench:
  100 - 50 - Read Write
  100 - 50 - Read Write - Average Latency
CP2K Molecular Dynamics
ASKAP
x265
Helsing
PlaidML
LuxCoreRender
OpenFOAM
PostgreSQL pgbench
ASKAP
x265
PostgreSQL pgbench
Embree
ASKAP
Embree
PlaidML
PostgreSQL pgbench
KTX-Software toktx
OSPray
PostgreSQL pgbench:
  100 - 250 - Read Write - Average Latency
  100 - 250 - Read Write
CloverLeaf
SVT-VP9
libavif avifenc
PostgreSQL pgbench
AOM AV1
LuxCoreRender
SVT-AV1
Liquid-DSP
LuxCoreRender
OSPray
PostgreSQL pgbench
SVT-AV1
AOM AV1
InfluxDB
KeyDB
Helsing
WavPack Audio Encoding
LAMMPS Molecular Dynamics Simulator
Coremark
TensorFlow Lite
Timed Wasmer Compilation
LAMMPS Molecular Dynamics Simulator
Numpy Benchmark
PyBench
OSPray
ASTC Encoder
PostgreSQL pgbench
simdjson
Botan
Embree
Liquid-DSP
Timed Erlang/OTP Compilation
SVT-VP9
Timed Node.js Compilation
Botan
TensorFlow Lite
SVT-HEVC
Botan
Embree
TensorFlow Lite
libavif avifenc
AOM AV1
SVT-HEVC
ASKAP
TensorFlow Lite
libavif avifenc
simdjson
PHPBench
Embree
PlaidML
KTX-Software toktx
SVT-VP9
TensorFlow Lite
TNN
Timed Linux Kernel Compilation
Embree
KTX-Software toktx
TensorFlow Lite
Timed HMMer Search
simdjson
SVT-AV1
Timed Godot Game Engine Compilation
LAME MP3 Encoding
Opus Codec Encoding
Caffe
SecureMark
Botan
RNNoise
KTX-Software toktx
Botan
Liquid-DSP
PostgreSQL pgbench
FLAC Audio Encoding
Intel Open Image Denoise
Liquid-DSP
PostgreSQL pgbench
ASTC Encoder
Botan
Liquid-DSP
Botan:
  KASUMI
  Twofish - Decrypt
  Twofish
SVT-HEVC
AOM AV1
Botan
TNN
Caffe
NAMD
KTX-Software toktx
Botan
ASTC Encoder
Botan
InfluxDB
Meta Performance Per Watts
OpenVKL
AOM AV1:
  Speed 4 Two-Pass - Bosphorus 4K
  Speed 0 Two-Pass - Bosphorus 4K
OSPray:
  Magnetic Reconnection - Path Tracer
  Magnetic Reconnection - SciVis
  XFrog Forest - Path Tracer
  San Miguel - Path Tracer
  XFrog Forest - SciVis
LuxCoreRender
simdjson
CPU Temperature Monitor:
  Phoronix Test Suite System Monitoring:
    Celsius
    Watts
  CPU Temp Monitor:
    Celsius
  CPU Power Consumption Monitor:
    Watts
  Sustained Floating-Point Rate:
    GFLOP/s Per Watt
ACES DGEMM

AMD EPYC 72F3

Processor: AMD EPYC 72F3 8-Core @ 3.70GHz (8 Cores / 16 Threads), Motherboard: Supermicro H12SSL-i v1.01 (2.0 BIOS), Chipset: AMD Starship/Matisse, Memory: 8 x 16 GB DDR4-3200MT/s 18ASF2G72PDZ-3G2E1, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe

OS: Ubuntu 21.04, Kernel: 5.11.0-16-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.7, Vulkan: 1.0.2, Compiler: GCC 11.0.1 20210413, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --disable-multilib --enable-checking=release
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119
Python Notes: Python 3.9.4
Security Notes: itlb_multihit: Not affected + 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 21 April 2021 12:58 by user root.

EPYC 72F3

Processor: AMD EPYC 72F3 8-Core @ 3.70GHz (8 Cores / 16 Threads), Motherboard: Supermicro H12SSL-i v1.01 (2.0 BIOS), Chipset: AMD Starship/Matisse, Memory: 8 x 16 GB DDR4-3200MT/s 18ASF2G72PDZ-3G2E1, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 2-port PCIe

OS: Ubuntu 21.04, Kernel: 5.11.0-16-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.7, Vulkan: 1.0.2, Compiler: GCC 11.0.1 20210413, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --disable-multilib --enable-checking=release
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119
Python Notes: Python 3.9.4
Security Notes: itlb_multihit: Not affected + 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 22 April 2021 05:18 by user root.