AMD EPYC 9754 Bergamo SMT On/Off Comparison

Benchmarks by Michael Larabel for a future article (post 19th) looking at SMT on/off comparison toggled via BIOS. SMT comparison testing of AMD EPYC 9754 128-Core CPUs on Titanite with Ubuntu 22.04 LTS.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2307190-NE-BERGAMOSM27
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 Comparison
Transpose Comparison

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
EPYC 9754 1P: SMT On
July 14 2023
  16 Hours, 51 Minutes
EPYC 9754 1P: SMT Off
July 13 2023
  15 Hours, 43 Minutes
EPYC 9754 2P: SMT On
July 11 2023
  14 Hours, 12 Minutes
EPYC 9754 2P: SMT Off
July 12 2023
  13 Hours, 40 Minutes
Invert Behavior (Only Show Selected Data)
  15 Hours, 6 Minutes

Only show results where is faster than
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):


ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionEPYC 9754 1PEPYC 9754 2P SMT On SMT Off SMT On SMT OffAMD EPYC 9754 128-Core @ 2.25GHz (128 Cores / 256 Threads)AMD Titanite_4G (RTI1007B BIOS)AMD Device 14a4768GB2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007ASPEEDBroadcom NetXtreme BCM5720 PCIeUbuntu 22.045.19.0-41-generic (x86_64)GNOME Shell 42.5X Server 1.21.1.41.3.224GCC 11.3.0ext41024x768AMD EPYC 9754 128-Core @ 2.25GHz (128 Cores)2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads)1520GB2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores)OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa0010bPython Details- Python 3.10.6Security Details- EPYC 9754 1P: SMT On: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9754 1P: SMT Off: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9754 2P: SMT On: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9754 2P: SMT Off: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

compress-7zip: Compression Ratingcompress-7zip: Decompression Ratingaircrack-ng: appleseed: Emilyappleseed: Disney Materialappleseed: Material Testerastcenc: Fastastcenc: Thoroughastcenc: Exhaustiveblender: BMW27 - CPU-Onlyblender: Classroom - CPU-Onlyblender: Fishy Cat - CPU-Onlyblender: Barbershop - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlycloverleaf: Lagrangian-Eulerian Hydrodynamicscp2k: H2O-DFT-LSembree: Pathtracer ISPC - Crownembree: Pathtracer ISPC - Asian Dragongraph500: 26graph500: 26graph500: 26graph500: 26heffte: c2c - FFTW - float - 512heffte: r2c - FFTW - float - 512heffte: c2c - FFTW - double - 512heffte: r2c - FFTW - double - 512helsing: 14 digitoidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyoidn: RTLightmap.hdr.4096x4096 - CPU-Onlyjohn-the-ripper: bcryptjohn-the-ripper: WPA PSKjohn-the-ripper: Blowfishjohn-the-ripper: MD5libxsmm: 128libxsmm: 256liquid-dsp: 256 - 256 - 512liquid-dsp: 512 - 256 - 512luxcorerender: DLSC - CPUluxcorerender: Orange Juice - CPUluxcorerender: LuxCore Benchmark - CPUluxcorerender: Rainbow Colors and Prism - CPUmysqlslap: 2048mysqlslap: 4096minibude: OpenMP - BM1minibude: OpenMP - BM1minibude: OpenMP - BM2minibude: OpenMP - BM2minife: Smallnamd: ATPase Simulation - 327,506 Atomsnpb: BT.Cnpb: CG.Cnpb: EP.Dnpb: FT.Cnpb: IS.Dnpb: LU.Cnpb: MG.Cnpb: SP.Bnpb: SP.Cnekrs: Kershawnekrs: TurboPipe Periodicdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamopenssl: SHA256openssl: SHA512openssl: RSA4096openssl: RSA4096openssl: ChaCha20openssl: AES-128-GCMopenssl: AES-256-GCMopenssl: ChaCha20-Poly1305openvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvkl: vklBenchmark ISPCospray: particle_volume/ao/real_timeospray: particle_volume/scivis/real_timeospray: gravity_spheres_volume/dim_512/ao/real_timeospray: gravity_spheres_volume/dim_512/scivis/real_timeospray-studio: 1 - 4K - 1 - Path Tracerospray-studio: 2 - 4K - 1 - Path Tracerospray-studio: 3 - 4K - 1 - Path Tracerospray-studio: 1 - 4K - 16 - Path Tracerospray-studio: 1 - 4K - 32 - Path Tracerospray-studio: 2 - 4K - 16 - Path Tracerospray-studio: 2 - 4K - 32 - Path Tracerospray-studio: 3 - 4K - 16 - Path Tracerospray-studio: 3 - 4K - 32 - Path Tracerpgbench: 1000 - 800 - Read Onlypgbench: 1000 - 800 - Read Only - Average Latencyprimesieve: 1e12primesieve: 1e13specfem3d: Mount St. Helensspecfem3d: Layered Halfspacespecfem3d: Tomographic Modelspecfem3d: Homogeneous Halfspacespecfem3d: Water-layered Halfspacesrsran: PUSCH Processor Benchmark, Throughput Totalstockfish: Total Timetensorflow: CPU - 256 - AlexNettensorflow: CPU - 512 - AlexNettensorflow: CPU - 256 - GoogLeNettensorflow: CPU - 256 - ResNet-50tensorflow: CPU - 512 - GoogLeNettensorflow: CPU - 512 - ResNet-50build-gem5: Time To Compilebuild-godot: Time To Compilebuild-linux-kernel: defconfigbuild-linux-kernel: allmodconfigbuild-llvm: Ninjabuild-llvm: Unix Makefilesbuild-nodejs: Time To Compiletoybrot: TBBtoybrot: OpenMPxmrig: Monero - 1Mxmrig: Wownero - 1MEPYC 9754 1PEPYC 9754 2P SMT On SMT Off SMT On SMT Off726271791787171120.354122.58770944.30492166.6761311190.754975.08318.174312.7731.1216.49116.5439.2712.005012.26125.5813157.6504857890000880249000333445000445912000128.124245.54234.845166.341850.4733.623.621.74216064810375216115203126672713.43331.71696766667178370000016.3424.4712.1820.887806555944.062237.7635972.643238.90551784.10.20702292243.6145686.8813264.79140791.525300.29279662.55128129.56149355.54131909.915808636667253840692373.3807859.86531376.214246.4318240.8667267.7088417.1186152.9895968.626765.9747624.4789102.2265126.9310499.5866316.0466201.625873.2077859.8771636336255535300587933054195.11890935.36593468579871169673735557101253776621046241583732060.771049.3126.612377.7926.572378.071464.2943.73117.88541.295311.4812.076067.7810.53582.08110.0011794.3210.846148.8910.40120515.110.8385400.881.21139630.850730.816532.675031.924586187310321375927538139632788516484329728555690.9521.94421.2866.21637984915.9649316887.4806747069.40434850017.1944927798389.03650343491422.081628.80504.09118.45416.03122.77161.648105.79726.225227.517125.364211.079113.7043591408124409.474803.6592741510470149056.953123.29839638.492263167.9005971278.646668.30727.314715.1538.4420.47147.2250.019.274957.68685.2893107.3608893624000928320000363750000493535000128.597248.55735.404967.990757.9563.573.571.72163220676218163263167516672696.53813.41313933333141470000013.2720.988.8814.377836955867.108234.6845903.205236.12851741.00.20595298801.4448672.2414274.53147448.725315.15289518.14136942.13161475.24133415.425734266667258608333396.9697644.97681780.442135.5549246.3732259.2779504.3578125.44671275.770749.5111812.102377.8148134.5717468.7809404.2338156.056397.0913645.00191114145572805180433363756647.31799293.0550700307433115283892806399703462188339278268998762.18513.2328.741105.9628.831102.822784.6711.49119.01268.826744.664.745837.625.47545.1358.7111710.5910.915118.296.24113162.290.7071673.851.30110723.733323.721025.717825.51211127114613581800435926182693653921666433718777220.9171.79621.1325.03003158015.0281219294.9372655066.09275029913.41945450120430.92727229401375.331526.81525.39121.47429.16123.88148.484102.58822.984177.758119.576213.907116.1225590624251218.963182.29258201353957164.567164610.1137134.885315.93057.1216.289.8769.0321.7521.652143.513210.0714255.986415711000001724030000672541000960471000221.765433.601109.645207.19727.2804.764.782.354078601524533409850348793334976.76112.62544400000333016666718.6134.459.8619.025805456328.069253.1237888.085315.52462774.20.10646491231.8367554.7423705.40211432.899849.01591505.17249109.09236490.76224243.28139.6590902.85932627.314248.6206556.9411229.1624797.6248159.88611868.331068.36381190.7168107.1835242.9589521.3108602.2602211.4848139.8821902.7792327926038513106049655203108490.53782091.8131754995402723398907001072019317070327909817360110121.03526.9840.671559.9540.901552.155810.4111.03235.65270.9313214.204.8311299.325.641159.9955.1222954.4411.009889.616.46168372.890.62133931.531.08172049.132849.231153.829552.73184824955827698156197817157319253184558278780.9741.50811.1203.9066750959.9974475703.7827417984.7278301489.77838143717891.45823869241225.411770.91329.22124.98538.52172.36152.586100.79020.344145.929107.721199.36593.2712014332186533.7142082.7771462913091128050.219159.90661440.570691265.885808693.3961127.208814.40998.4520.2411.7285.5427.4715.152363.579146.2051178.3046181516000020788800007701800001075900000223.584430.265112.413210.93350.0544.354.312.093170461301500320885302216674505.56373.02542633333261093333314.4525.116.9713.5159157910976.682439.06710989.938439.59753798.60.13969536518.7466822.9725983.74224178.108635.30658754.21268721.05246272.79231041.57182.4453676.81282730.498045.8765590.8789212.68211058.6776118.12852409.803551.81031541.951281.1994290.7562426.7362770.1392162.0191182.5974676.4342222269428867102232233590113251.43598946.3110045339457023075245354571998234148863784489570523121.08526.4641.051545.2340.201579.146242.6810.26235.37271.2413141.514.8611373.955.611174.9954.4222955.6411.109878.886.47142135.580.67118225.551.13153041.656741.553144.710444.28896316457631004620133102322054512127242387859681.0181.16011.1522.6301225997.4707729302.7092054283.4518301696.21806925736573.84470231431581.661908.76452.99146.74634.13189.40148.376100.24018.474118.09999.215198.75093.9522976367185946.0100754.3OpenBenchmarking.org

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingSMT OffSMT On200K400K600K800K1000KSE +/- 4792.89, N = 3SE +/- 1345.49, N = 3SE +/- 4721.80, N = 3SE +/- 5539.49, N = 35927417262717714629258201. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingSMT OffSMT On300K600K900K1200K1500KSE +/- 429.17, N = 3SE +/- 1608.29, N = 3SE +/- 1897.81, N = 3SE +/- 5499.45, N = 351047079178791309113539571. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Aircrack-ng

Aircrack-ng is a tool for assessing WiFi/WLAN network security. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.7SMT OffSMT On40K80K120K160K200KSE +/- 1020.90, N = 3SE +/- 101.44, N = 3SE +/- 1109.71, N = 3149056.95171120.35128050.221. (CXX) g++ options: -std=gnu++17 -O3 -fvisibility=hidden -fcommon -rdynamic -lnl-3 -lnl-genl-3 -lpcre -lpthread -lz -lssl -lcrypto -lhwloc -ldl -lm -pthread

EPYC 9754 2P: SMT On: The test run did not produce a result.

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: EmilySMT OffSMT On4080120160200123.30122.59159.91164.57

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Disney MaterialSMT OffSMT On102030405038.4944.3040.57

Scene: Disney Material

EPYC 9754 2P: SMT On: The test run did not produce a result.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Material TesterSMT OffSMT On60120180240300167.90166.68265.89

Scene: Material Tester

EPYC 9754 2P: SMT On: The test run did not produce a result.

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.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: FastSMT OffSMT On30060090012001500SE +/- 1.20, N = 7SE +/- 1.79, N = 6SE +/- 1.25, N = 5SE +/- 1.29, N = 51278.651190.75693.40610.111. (CXX) g++ options: -O3 -flto -pthread

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ThoroughSMT OffSMT On306090120150SE +/- 0.01, N = 6SE +/- 0.02, N = 6SE +/- 0.05, N = 6SE +/- 0.22, N = 668.3175.08127.21134.891. (CXX) g++ options: -O3 -flto -pthread

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ExhaustiveSMT OffSMT On48121620SE +/- 0.0028, N = 5SE +/- 0.0006, N = 5SE +/- 0.0257, N = 6SE +/- 0.0081, N = 67.31478.174314.409915.93051. (CXX) g++ options: -O3 -flto -pthread

Blender

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: BMW27 - Compute: CPU-OnlySMT OffSMT On48121620SE +/- 0.05, N = 4SE +/- 0.02, N = 4SE +/- 0.05, N = 5SE +/- 0.02, N = 615.1512.778.457.12

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Classroom - Compute: CPU-OnlySMT OffSMT On918273645SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 338.4431.1220.2416.28

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Fishy Cat - Compute: CPU-OnlySMT OffSMT On510152025SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 4SE +/- 0.02, N = 520.4716.4911.729.87

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Barbershop - Compute: CPU-OnlySMT OffSMT On306090120150SE +/- 0.17, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.19, N = 3147.22116.5485.5469.03

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Pabellon Barcelona - Compute: CPU-OnlySMT OffSMT On1122334455SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 350.0139.2727.4721.75

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.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsSMT OffSMT On510152025SE +/- 0.09, N = 5SE +/- 0.11, N = 4SE +/- 0.04, N = 4SE +/- 0.27, N = 49.2712.0015.1521.651. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

CP2K Molecular Dynamics

CP2K is an open-source molecular dynamics software package focused on quantum chemistry and solid-state physics. More details on the CP2K benchmark test cases and details can be found @ https://www.cp2k.org/performance Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 2023.1Input: H2O-DFT-LSSMT OffSMT On110022003300440055004957.695012.262363.582143.511. (F9X) gfortran options: -fopenmp -mtune=native -O3 -funroll-loops -fbacktrace -ffree-form -fimplicit-none -std=f2008 -lcp2kstart -lcp2kmc -lcp2kswarm -lcp2kmotion -lcp2kthermostat -lcp2kemd -lcp2ktmc -lcp2kmain -lcp2kdbt -lcp2ktas -lcp2kdbm -lcp2kgrid -lcp2kgridcpu -lcp2kgridref -lcp2kgridcommon -ldbcsrarnoldi -ldbcsrx -lcp2kshg_int -lcp2keri_mme -lcp2kminimax -lcp2khfxbase -lcp2ksubsys -lcp2kxc -lcp2kao -lcp2kpw_env -lcp2kinput -lcp2kpw -lcp2kgpu -lcp2kfft -lcp2kfpga -lcp2kfm -lcp2kcommon -lcp2koffload -lcp2kmpiwrap -lcp2kbase -ldbcsr -lsirius -lspla -lspfft -lsymspg -lvdwxc -lhdf5 -lhdf5_hl -lz -lgsl -lelpa_openmp -lcosma -lcosta -lscalapack -lxsmmf -lxsmm -ldl -lpthread -lxcf03 -lxc -lint2 -lfftw3_mpi -lfftw3 -lfftw3_omp -lmpi_cxx -lmpi -lopenblas -lvori -lstdc++ -lmpi_usempif08 -lmpi_mpifh -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm

CPU Power Consumption Monitor

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringSMT OffSMT On140280420560700Min: 10.61 / Avg: 238.75 / Max: 362.1Min: 10.52 / Avg: 248.93 / Max: 397.25Min: 97.83 / Avg: 446.01 / Max: 702.85Min: 21.61 / Avg: 460.57 / Max: 792.38

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer ISPC - Model: CrownSMT OffSMT On50100150200250SE +/- 0.05, N = 6SE +/- 0.13, N = 7SE +/- 0.13, N = 7SE +/- 0.16, N = 985.29125.58146.21210.07

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer ISPC - Model: Asian DragonSMT OffSMT On60120180240300SE +/- 0.09, N = 6SE +/- 0.09, N = 8SE +/- 0.26, N = 8SE +/- 0.48, N = 9107.36157.65178.30255.99

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgbfs median_TEPS, More Is BetterGraph500 3.0Scale: 26SMT OffSMT On400M800M1200M1600M2000M893624000857890000181516000015711000001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgbfs max_TEPS, More Is BetterGraph500 3.0Scale: 26SMT OffSMT On400M800M1200M1600M2000M928320000880249000207888000017240300001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgsssp median_TEPS, More Is BetterGraph500 3.0Scale: 26SMT OffSMT On160M320M480M640M800M3637500003334450007701800006725410001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgsssp max_TEPS, More Is BetterGraph500 3.0Scale: 26SMT OffSMT On200M400M600M800M1000M49353500044591200010759000009604710001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

HeFFTe - Highly Efficient FFT for Exascale

HeFFTe is the Highly Efficient FFT for Exascale software developed as part of the Exascale Computing Project. This test profile uses HeFFTe's built-in speed benchmarks under a variety of configuration options and currently catering to CPU/processor testing. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: float - X Y Z: 512SMT OffSMT On50100150200250SE +/- 0.01, N = 4SE +/- 0.15, N = 4SE +/- 1.28, N = 5SE +/- 1.37, N = 5128.60128.12223.58221.771. (CXX) g++ options: -O3

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: float - X Y Z: 512SMT OffSMT On90180270360450SE +/- 0.09, N = 5SE +/- 0.52, N = 5SE +/- 0.77, N = 6SE +/- 0.86, N = 7248.56245.54430.27433.601. (CXX) g++ options: -O3

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: double - X Y Z: 512SMT OffSMT On306090120150SE +/- 2.10, N = 15SE +/- 2.09, N = 15SE +/- 1.48, N = 3SE +/- 0.77, N = 335.4034.85112.41109.651. (CXX) g++ options: -O3

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: double - X Y Z: 512SMT OffSMT On50100150200250SE +/- 3.41, N = 15SE +/- 3.14, N = 15SE +/- 1.62, N = 5SE +/- 0.28, N = 567.9966.34210.93207.201. (CXX) g++ options: -O3

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.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digitSMT OffSMT On1326395265SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.31, N = 3SE +/- 0.37, N = 357.9650.4750.0527.281. (CC) gcc options: -O2 -pthread

Intel Open Image Denoise

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

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.0Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-OnlySMT OffSMT On1.0712.1423.2134.2845.355SE +/- 0.02, N = 7SE +/- 0.00, N = 7SE +/- 0.03, N = 7SE +/- 0.01, N = 73.573.624.354.76

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.0Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlySMT OffSMT On1.07552.1513.22654.3025.3775SE +/- 0.02, N = 15SE +/- 0.00, N = 7SE +/- 0.03, N = 15SE +/- 0.01, N = 73.573.624.314.78

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.0Run: RTLightmap.hdr.4096x4096 - Device: CPU-OnlySMT OffSMT On0.52881.05761.58642.11522.644SE +/- 0.01, N = 4SE +/- 0.00, N = 4SE +/- 0.02, N = 5SE +/- 0.00, N = 51.721.742.092.35

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptSMT OffSMT On90K180K270K360K450KSE +/- 33.22, N = 3SE +/- 92.54, N = 3SE +/- 1964.45, N = 3SE +/- 2298.36, N = 31632202160643170464078601. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKSMT OffSMT On300K600K900K1200K1500KSE +/- 6933.79, N = 3SE +/- 505.98, N = 3SE +/- 15887.63, N = 4SE +/- 18163.51, N = 15676218810375130150015245331. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishSMT OffSMT On90K180K270K360K450KSE +/- 12.67, N = 3SE +/- 117.40, N = 3SE +/- 1247.49, N = 3SE +/- 3726.56, N = 31632632161153208854098501. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5SMT OffSMT On7M14M21M28M35MSE +/- 35950.58, N = 3SE +/- 52818.35, N = 3SE +/- 140717.61, N = 3SE +/- 83819.91, N = 3167516672031266730221667348793331. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

libxsmm

Libxsmm is an open-source library for specialized dense and sparse matrix operations and deep learning primitives. Libxsmm supports making use of Intel AMX, AVX-512, and other modern CPU instruction set capabilities. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 128SMT OffSMT On11002200330044005500SE +/- 19.26, N = 3SE +/- 0.99, N = 3SE +/- 114.55, N = 9SE +/- 62.14, N = 42696.52713.44505.54976.71. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 256SMT OffSMT On14002800420056007000SE +/- 16.75, N = 3SE +/- 2.32, N = 3SE +/- 66.66, N = 9SE +/- 1.43, N = 33813.43331.76373.06112.61. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

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.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 512SMT OffSMT On500M1000M1500M2000M2500MSE +/- 592546.29, N = 3SE +/- 470224.53, N = 3SE +/- 1068228.02, N = 3SE +/- 1877054.43, N = 313139333331696766667254263333325444000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 512 - Buffer Length: 256 - Filter Length: 512SMT OffSMT On700M1400M2100M2800M3500MSE +/- 2946183.97, N = 3SE +/- 1814754.35, N = 3SE +/- 3555434.03, N = 3SE +/- 569600.25, N = 314147000001783700000261093333333301666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUSMT OffSMT On510152025SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 3SE +/- 0.20, N = 413.2716.3414.4518.61

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUSMT OffSMT On816243240SE +/- 0.03, N = 3SE +/- 0.30, N = 15SE +/- 0.60, N = 15SE +/- 1.35, N = 1520.9824.4725.1134.45

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: CPUSMT OffSMT On3691215SE +/- 0.08, N = 8SE +/- 0.09, N = 15SE +/- 0.11, N = 12SE +/- 0.11, N = 158.8812.186.979.86

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: CPUSMT OffSMT On510152025SE +/- 0.04, N = 4SE +/- 0.03, N = 5SE +/- 0.35, N = 15SE +/- 0.03, N = 514.3720.8813.5119.02

MariaDB

This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.0.1Clients: 2048SMT OffSMT On2004006008001000SE +/- 1.06, N = 3SE +/- 1.81, N = 3SE +/- 0.73, N = 3SE +/- 8.04, N = 37837805915801. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -lpthread -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.0.1Clients: 4096SMT OffSMT On150300450600750SE +/- 3.99, N = 3SE +/- 8.08, N = 3SE +/- 1.48, N = 3SE +/- 5.45, N = 66956555795451. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -lpthread -ldl

miniBUDE

MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1SMT OffSMT On2K4K6K8K10KSE +/- 2.53, N = 9SE +/- 1.30, N = 9SE +/- 180.32, N = 15SE +/- 5.35, N = 95867.115944.0610976.686328.071. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1SMT OffSMT On100200300400500SE +/- 0.10, N = 9SE +/- 0.05, N = 9SE +/- 7.21, N = 15SE +/- 0.21, N = 9234.68237.76439.07253.121. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2SMT OffSMT On2K4K6K8K10KSE +/- 6.13, N = 3SE +/- 0.21, N = 3SE +/- 150.60, N = 12SE +/- 10.75, N = 45903.215972.6410989.947888.091. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2SMT OffSMT On100200300400500SE +/- 0.25, N = 3SE +/- 0.01, N = 3SE +/- 6.02, N = 12SE +/- 0.43, N = 4236.13238.91439.60315.521. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

miniFE

MiniFE Finite Element is an application for unstructured implicit finite element codes. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallSMT OffSMT On13K26K39K52K65KSE +/- 25.22, N = 5SE +/- 52.11, N = 5SE +/- 478.13, N = 5SE +/- 411.42, N = 551741.051784.153798.662774.21. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi

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.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsSMT OffSMT On0.04660.09320.13980.18640.233SE +/- 0.00018, N = 4SE +/- 0.00095, N = 4SE +/- 0.00135, N = 5SE +/- 0.00040, N = 30.205950.207020.139690.10646

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CSMT OffSMT On110K220K330K440K550KSE +/- 269.21, N = 5SE +/- 396.74, N = 5SE +/- 3792.90, N = 12SE +/- 4903.75, N = 15298801.44292243.61536518.74491231.831. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CSMT OffSMT On14K28K42K56K70KSE +/- 285.31, N = 8SE +/- 441.00, N = 15SE +/- 568.39, N = 8SE +/- 348.18, N = 848672.2445686.8866822.9767554.741. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DSMT OffSMT On6K12K18K24K30KSE +/- 54.02, N = 5SE +/- 214.86, N = 15SE +/- 940.02, N = 12SE +/- 413.32, N = 1514274.5313264.7925983.7423705.401. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CSMT OffSMT On50K100K150K200K250KSE +/- 93.32, N = 8SE +/- 1029.98, N = 8SE +/- 2978.54, N = 13SE +/- 1757.80, N = 9147448.72140791.52224178.10211432.891. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DSMT OffSMT On2K4K6K8K10KSE +/- 29.88, N = 6SE +/- 27.01, N = 6SE +/- 105.10, N = 15SE +/- 104.60, N = 155315.155300.298635.309849.011. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CSMT OffSMT On140K280K420K560K700KSE +/- 1485.96, N = 6SE +/- 2132.06, N = 6SE +/- 4916.03, N = 15SE +/- 7199.59, N = 15289518.14279662.55658754.21591505.171. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CSMT OffSMT On60K120K180K240K300KSE +/- 104.98, N = 10SE +/- 296.36, N = 10SE +/- 599.41, N = 10SE +/- 1284.96, N = 11136942.13128129.56268721.05249109.091. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BSMT OffSMT On50K100K150K200K250KSE +/- 885.17, N = 9SE +/- 1110.64, N = 9SE +/- 8884.57, N = 15SE +/- 732.52, N = 9161475.24149355.54246272.79236490.761. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CSMT OffSMT On50K100K150K200K250KSE +/- 228.86, N = 4SE +/- 290.95, N = 4SE +/- 1880.70, N = 6SE +/- 1293.24, N = 6133415.42131909.91231041.57224243.281. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

nekRS

nekRS is an open-source Navier Stokes solver based on the spectral element method. NekRS supports both CPU and GPU/accelerator support though this test profile is currently configured for CPU execution. NekRS is part of Nek5000 of the Mathematics and Computer Science MCS at Argonne National Laboratory. This nekRS benchmark is primarily relevant to large core count HPC servers and otherwise may be very time consuming on smaller systems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgflops/rank, More Is BetternekRS 23.0Input: KershawSMT OffSMT On1200M2400M3600M4800M6000MSE +/- 37190783.06, N = 3SE +/- 8226739.60, N = 3573426666758086366671. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi

Input: Kershaw

EPYC 9754 2P: SMT On: The test quit with a non-zero exit status. E: mpirun noticed that process rank 0 with PID 0 on node phoronix-QuantaGrid-D54Q-2U exited on signal 11 (Segmentation fault).

EPYC 9754 2P: SMT Off: The test quit with a non-zero exit status. E: mpirun noticed that process rank 0 with PID 0 on node phoronix-QuantaGrid-D54Q-2U exited on signal 11 (Segmentation fault).

OpenBenchmarking.orgflops/rank, More Is BetternekRS 23.0Input: TurboPipe PeriodicSMT OffSMT On600M1200M1800M2400M3000MSE +/- 87729075.59, N = 15SE +/- 62315945.32, N = 13258608333325384069231. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi

Input: TurboPipe Periodic

EPYC 9754 2P: SMT On: The test quit with a non-zero exit status. E: mpirun noticed that process rank 0 with PID 0 on node phoronix-QuantaGrid-D54Q-2U exited on signal 11 (Segmentation fault).

EPYC 9754 2P: SMT Off: The test quit with a non-zero exit status. E: mpirun noticed that process rank 0 with PID 0 on node phoronix-QuantaGrid-D54Q-2U exited on signal 11 (Segmentation fault).

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamSMT OffSMT On4080120160200SE +/- 0.09, N = 3SE +/- 0.25, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 396.9773.38182.45139.66

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamSMT OffSMT On2004006008001000SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.02, N = 3SE +/- 0.27, N = 3644.98859.87676.81902.86

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-StreamSMT OffSMT On6001200180024003000SE +/- 3.84, N = 3SE +/- 1.21, N = 3SE +/- 33.47, N = 15SE +/- 6.95, N = 31780.441376.212730.502627.31

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-StreamSMT OffSMT On1122334455SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.57, N = 15SE +/- 0.13, N = 335.5546.4345.8848.62

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamSMT OffSMT On130260390520650SE +/- 8.20, N = 15SE +/- 7.96, N = 15SE +/- 11.89, N = 15SE +/- 6.10, N = 15246.37240.87590.88556.94

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamSMT OffSMT On60120180240300SE +/- 6.30, N = 15SE +/- 6.66, N = 15SE +/- 3.96, N = 15SE +/- 2.29, N = 15259.28267.71212.68229.16

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamSMT OffSMT On2004006008001000SE +/- 5.07, N = 15SE +/- 0.46, N = 3SE +/- 0.90, N = 3SE +/- 0.32, N = 3504.36417.121058.68797.62

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamSMT OffSMT On4080120160200SE +/- 1.18, N = 15SE +/- 0.16, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3125.45152.99118.13159.89

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamSMT OffSMT On5001000150020002500SE +/- 5.02, N = 3SE +/- 0.74, N = 3SE +/- 1.63, N = 3SE +/- 1.60, N = 31275.77968.632409.801868.33

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamSMT OffSMT On1530456075SE +/- 0.20, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 349.5165.9751.8168.36

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamSMT OffSMT On30060090012001500SE +/- 3.93, N = 3SE +/- 0.29, N = 3SE +/- 1.38, N = 3SE +/- 1.02, N = 3812.10624.481541.951190.72

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamSMT OffSMT On20406080100SE +/- 0.37, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 377.81102.2381.20107.18

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamSMT OffSMT On60120180240300SE +/- 2.61, N = 15SE +/- 0.15, N = 3SE +/- 2.51, N = 3SE +/- 0.12, N = 3134.57126.93290.76242.96

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamSMT OffSMT On110220330440550SE +/- 8.17, N = 15SE +/- 0.68, N = 3SE +/- 3.79, N = 3SE +/- 0.26, N = 3468.78499.59426.74521.31

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamSMT OffSMT On170340510680850SE +/- 2.15, N = 3SE +/- 1.02, N = 3SE +/- 0.92, N = 3SE +/- 0.72, N = 3404.23316.05770.14602.26

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamSMT OffSMT On50100150200250SE +/- 0.81, N = 3SE +/- 0.54, N = 3SE +/- 0.09, N = 3SE +/- 0.18, N = 3156.06201.63162.02211.48

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamSMT OffSMT On4080120160200SE +/- 0.06, N = 3SE +/- 0.25, N = 3SE +/- 0.18, N = 3SE +/- 0.08, N = 397.0973.21182.60139.88

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamSMT OffSMT On2004006008001000SE +/- 0.12, N = 3SE +/- 0.49, N = 3SE +/- 0.21, N = 3SE +/- 0.45, N = 3645.00859.88676.43902.78

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA256SMT OffSMT On70000M140000M210000M280000M350000MSE +/- 15184699.42, N = 3SE +/- 161352968.33, N = 3SE +/- 224959781.68, N = 3SE +/- 207719324.78, N = 31114145572801636336255532222694288673279260385131. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA512SMT OffSMT On20000M40000M60000M80000M100000MSE +/- 19506083.54, N = 3SE +/- 4276543.39, N = 3SE +/- 660141733.06, N = 3SE +/- 22577791.79, N = 351804333637530058793301022322335901060496552031. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096SMT OffSMT On20K40K60K80K100KSE +/- 1.80, N = 3SE +/- 16.66, N = 3SE +/- 3.85, N = 3SE +/- 3.93, N = 356647.354195.1113251.4108490.51. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096SMT OffSMT On800K1600K2400K3200K4000KSE +/- 1031.37, N = 3SE +/- 405.88, N = 3SE +/- 1067.40, N = 3SE +/- 163.02, N = 31799293.01890935.33598946.33782091.81. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20SMT OffSMT On300000M600000M900000M1200000M1500000MSE +/- 70893114.79, N = 3SE +/- 23916253.09, N = 3SE +/- 107897909.37, N = 3SE +/- 46014499.85, N = 3550700307433659346857987110045339457013175499540271. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-128-GCMSMT OffSMT On500000M1000000M1500000M2000000M2500000MSE +/- 772883363.35, N = 3SE +/- 404585301.69, N = 3SE +/- 4718005576.14, N = 3SE +/- 4494053056.14, N = 311528389280631169673735557230752453545723398907001071. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-256-GCMSMT OffSMT On400000M800000M1200000M1600000M2000000MSE +/- 917614258.55, N = 3SE +/- 2018584981.53, N = 3SE +/- 2904032106.06, N = 3SE +/- 676471418.80, N = 39970346218831012537766210199823414886320193170703271. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly1305SMT OffSMT On200000M400000M600000M800000M1000000MSE +/- 86138373.27, N = 3SE +/- 15599558.91, N = 3SE +/- 39882779.79, N = 3SE +/- 267574958.87, N = 33927826899874624158373207844895705239098173601101. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPUSMT OffSMT On306090120150SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 362.1860.77121.08121.031. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPUSMT OffSMT On2004006008001000SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.28, N = 3SE +/- 0.18, N = 3513.231049.31526.46526.981. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUSMT OffSMT On918273645SE +/- 0.23, N = 9SE +/- 0.20, N = 12SE +/- 0.29, N = 3SE +/- 0.14, N = 328.7426.6141.0540.671. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUSMT OffSMT On5001000150020002500SE +/- 8.36, N = 9SE +/- 16.41, N = 12SE +/- 10.43, N = 3SE +/- 4.07, N = 31105.962377.791545.231559.951. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUSMT OffSMT On918273645SE +/- 0.29, N = 5SE +/- 0.15, N = 15SE +/- 0.14, N = 3SE +/- 0.22, N = 328.8326.5740.2040.901. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUSMT OffSMT On5001000150020002500SE +/- 10.77, N = 5SE +/- 12.47, N = 15SE +/- 4.61, N = 3SE +/- 8.82, N = 31102.822378.071579.141552.151. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUSMT OffSMT On13002600390052006500SE +/- 25.69, N = 13SE +/- 21.50, N = 14SE +/- 87.31, N = 13SE +/- 93.68, N = 152784.671464.296242.685810.411. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUSMT OffSMT On1020304050SE +/- 0.10, N = 13SE +/- 0.55, N = 14SE +/- 0.12, N = 13SE +/- 0.15, N = 1511.4943.7310.2611.031. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUSMT OffSMT On50100150200250SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3119.01117.88235.37235.651. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUSMT OffSMT On120240360480600SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3268.82541.29271.24270.931. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUSMT OffSMT On3K6K9K12K15KSE +/- 3.11, N = 3SE +/- 103.73, N = 15SE +/- 2.74, N = 3SE +/- 7.09, N = 36744.665311.4813141.5113214.201. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUSMT OffSMT On3691215SE +/- 0.00, N = 3SE +/- 0.20, N = 15SE +/- 0.00, N = 3SE +/- 0.00, N = 34.7412.074.864.831. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUSMT OffSMT On2K4K6K8K10KSE +/- 11.25, N = 3SE +/- 0.58, N = 3SE +/- 2.58, N = 3SE +/- 9.34, N = 35837.626067.7811373.9511299.321. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUSMT OffSMT On3691215SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 35.4710.535.615.641. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUSMT OffSMT On30060090012001500SE +/- 4.46, N = 15SE +/- 6.51, N = 15SE +/- 4.51, N = 3SE +/- 7.44, N = 3545.13582.081174.991159.991. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUSMT OffSMT On20406080100SE +/- 0.45, N = 15SE +/- 1.12, N = 15SE +/- 0.21, N = 3SE +/- 0.35, N = 358.71110.0054.4255.121. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUSMT OffSMT On5K10K15K20K25KSE +/- 13.11, N = 3SE +/- 2.13, N = 3SE +/- 15.58, N = 3SE +/- 16.03, N = 311710.5911794.3222955.6422954.441. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUSMT OffSMT On3691215SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 310.9110.8411.1011.001. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUSMT OffSMT On2K4K6K8K10KSE +/- 5.00, N = 3SE +/- 48.86, N = 15SE +/- 10.15, N = 3SE +/- 11.31, N = 35118.296148.899878.889889.611. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUSMT OffSMT On3691215SE +/- 0.01, N = 3SE +/- 0.08, N = 15SE +/- 0.01, N = 3SE +/- 0.01, N = 36.2410.406.476.461. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUSMT OffSMT On40K80K120K160K200KSE +/- 202.90, N = 3SE +/- 390.62, N = 3SE +/- 158.47, N = 3SE +/- 676.62, N = 3113162.29120515.11142135.58168372.891. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUSMT OffSMT On0.18680.37360.56040.74720.934SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.700.830.670.621. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUSMT OffSMT On30K60K90K120K150KSE +/- 126.57, N = 3SE +/- 192.97, N = 3SE +/- 420.06, N = 3SE +/- 602.14, N = 371673.8585400.88118225.55133931.531. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUSMT OffSMT On0.29250.5850.87751.171.4625SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.301.211.131.081. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

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.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.3.1Benchmark: vklBenchmark ISPCSMT OffSMT On400800120016002000SE +/- 0.33, N = 3SE +/- 1.86, N = 3SE +/- 1.33, N = 3SE +/- 6.06, N = 31107139615301720

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity 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.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/ao/real_timeSMT OffSMT On1122334455SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 323.7330.8541.6649.13

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/scivis/real_timeSMT OffSMT On1122334455SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 323.7230.8241.5549.23

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/ao/real_timeSMT OffSMT On1224364860SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 325.7232.6844.7153.83

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeSMT OffSMT On1224364860SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 325.5131.9244.2952.73

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity 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.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerSMT OffSMT On2004006008001000SE +/- 1.20, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 2.85, N = 311278616314821. (CXX) g++ options: -O3 -lm -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerSMT OffSMT On2004006008001000SE +/- 1.53, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 1.45, N = 311468736454951. (CXX) g++ options: -O3 -lm -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerSMT OffSMT On30060090012001500SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3135810327635821. (CXX) g++ options: -O3 -lm -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerSMT OffSMT On4K8K12K16K20KSE +/- 18.26, N = 3SE +/- 5.78, N = 3SE +/- 14.52, N = 3SE +/- 7.80, N = 318004137591004676981. (CXX) g++ options: -O3 -lm -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerSMT OffSMT On8K16K24K32K40KSE +/- 29.21, N = 3SE +/- 10.48, N = 3SE +/- 38.84, N = 3SE +/- 64.83, N = 3359262753820133156191. (CXX) g++ options: -O3 -lm -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerSMT OffSMT On4K8K12K16K20KSE +/- 11.93, N = 3SE +/- 6.12, N = 3SE +/- 5.29, N = 3SE +/- 19.63, N = 318269139631023278171. (CXX) g++ options: -O3 -lm -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerSMT OffSMT On8K16K24K32K40KSE +/- 53.62, N = 3SE +/- 21.53, N = 3SE +/- 96.56, N = 3SE +/- 41.40, N = 3365392788520545157311. (CXX) g++ options: -O3 -lm -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerSMT OffSMT On5K10K15K20K25KSE +/- 15.65, N = 3SE +/- 11.89, N = 3SE +/- 8.65, N = 3SE +/- 27.17, N = 321666164841212792531. (CXX) g++ options: -O3 -lm -ldl

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerSMT OffSMT On9K18K27K36K45KSE +/- 76.61, N = 3SE +/- 17.58, N = 3SE +/- 17.91, N = 3SE +/- 34.44, N = 3433713297224238184551. (CXX) g++ options: -O3 -lm -ldl

PostgreSQL

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

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 800 - Mode: Read OnlySMT OffSMT On200K400K600K800K1000KSE +/- 21185.07, N = 12SE +/- 45813.37, N = 9SE +/- 4149.87, N = 3SE +/- 23693.25, N = 128777228555697859688278781. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 800 - Mode: Read Only - Average LatencySMT OffSMT On0.22910.45820.68730.91641.1455SE +/- 0.020, N = 12SE +/- 0.040, N = 9SE +/- 0.006, N = 3SE +/- 0.025, N = 120.9170.9521.0180.9741. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 8.0Length: 1e12SMT OffSMT On0.43740.87481.31221.74962.187SE +/- 0.003, N = 11SE +/- 0.006, N = 11SE +/- 0.003, N = 12SE +/- 0.010, N = 141.7961.9441.1601.5081. (CXX) g++ options: -O3

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 8.0Length: 1e13SMT OffSMT On510152025SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 5SE +/- 0.01, N = 521.1321.2911.1511.121. (CXX) g++ options: -O3

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Mount St. HelensSMT OffSMT On246810SE +/- 0.069356320, N = 12SE +/- 0.034771470, N = 5SE +/- 0.013893024, N = 5SE +/- 0.014293172, N = 55.0300315806.2163798492.6301225993.9066750951. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Layered HalfspaceSMT OffSMT On48121620SE +/- 0.159428812, N = 3SE +/- 0.034780206, N = 3SE +/- 0.056354216, N = 4SE +/- 0.066481426, N = 1515.02812192915.9649316887.4707729309.9974475701. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Tomographic ModelSMT OffSMT On246810SE +/- 0.048140615, N = 15SE +/- 0.080164897, N = 5SE +/- 0.014728964, N = 6SE +/- 0.086611165, N = 154.9372655067.4806747062.7092054283.7827417981. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Homogeneous HalfspaceSMT OffSMT On3691215SE +/- 0.044108994, N = 15SE +/- 0.048294894, N = 4SE +/- 0.065109589, N = 12SE +/- 0.120152278, N = 156.0927502999.4043485003.4518301694.7278301481. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Water-layered HalfspaceSMT OffSMT On48121620SE +/- 0.021567327, N = 3SE +/- 0.142353904, N = 3SE +/- 0.062799204, N = 15SE +/- 0.063515594, N = 413.41945450117.1944927796.2180692579.7783814371. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

srsRAN Project

srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.5Test: PUSCH Processor Benchmark, Throughput TotalSMT OffSMT On8K16K24K32K40KSE +/- 54.33, N = 3SE +/- 50.60, N = 3SE +/- 211.99, N = 3SE +/- 831.80, N = 1520430.98389.036573.817891.41. (CXX) g++ options: -march=native -mfma -O3 -fno-trapping-math -fno-math-errno -lgtest

Stockfish

This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 15Total TimeSMT OffSMT On120M240M360M480M600MSE +/- 5762415.88, N = 15SE +/- 7021012.10, N = 12SE +/- 6859221.31, N = 12SE +/- 9265130.36, N = 152727229403650343494470231435823869241. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: AlexNetSMT OffSMT On30060090012001500SE +/- 8.29, N = 3SE +/- 3.81, N = 3SE +/- 11.49, N = 15SE +/- 14.23, N = 151375.331422.081581.661225.41

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: AlexNetSMT OffSMT On400800120016002000SE +/- 3.13, N = 3SE +/- 1.79, N = 3SE +/- 18.22, N = 3SE +/- 15.22, N = 151526.811628.801908.761770.91

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: GoogLeNetSMT OffSMT On110220330440550SE +/- 0.35, N = 3SE +/- 3.39, N = 3SE +/- 5.52, N = 4SE +/- 1.69, N = 3525.39504.09452.99329.22

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: ResNet-50SMT OffSMT On306090120150SE +/- 1.45, N = 12SE +/- 1.07, N = 12SE +/- 0.68, N = 3SE +/- 1.70, N = 3121.47118.45146.74124.98

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: GoogLeNetSMT OffSMT On140280420560700SE +/- 5.79, N = 12SE +/- 4.74, N = 12SE +/- 6.73, N = 3SE +/- 4.51, N = 15429.16416.03634.13538.52

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: ResNet-50SMT OffSMT On4080120160200SE +/- 1.35, N = 3SE +/- 0.90, N = 3SE +/- 0.13, N = 3SE +/- 0.59, N = 3123.88122.77189.40172.36

Timed Gem5 Compilation

This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 21.2Time To CompileSMT OffSMT On4080120160200SE +/- 0.50, N = 3SE +/- 0.32, N = 3SE +/- 1.24, N = 3SE +/- 1.29, N = 3148.48161.65148.38152.59

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.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To CompileSMT OffSMT On20406080100SE +/- 0.17, N = 3SE +/- 0.14, N = 3SE +/- 0.30, N = 3SE +/- 1.01, N = 3102.59105.80100.24100.79

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 or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigSMT OffSMT On612182430SE +/- 0.21, N = 7SE +/- 0.23, N = 7SE +/- 0.12, N = 13SE +/- 0.14, N = 1322.9826.2318.4720.34

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfigSMT OffSMT On50100150200250SE +/- 0.48, N = 3SE +/- 1.35, N = 3SE +/- 0.55, N = 3SE +/- 0.51, N = 3177.76227.52118.10145.93

Timed LLVM Compilation

This test times how long it takes to compile/build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaSMT OffSMT On306090120150SE +/- 0.18, N = 3SE +/- 0.29, N = 3SE +/- 0.70, N = 3SE +/- 0.91, N = 3119.58125.3699.22107.72

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix MakefilesSMT OffSMT On50100150200250SE +/- 0.70, N = 3SE +/- 0.15, N = 3SE +/- 0.11, N = 3SE +/- 0.14, N = 3213.91211.08198.75199.37

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.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 19.8.1Time To CompileSMT OffSMT On306090120150SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3116.12113.7093.9593.27

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: TBBSMT OffSMT On12002400360048006000SE +/- 43.30, N = 15SE +/- 21.75, N = 9SE +/- 31.80, N = 15SE +/- 23.04, N = 1555903591297620141. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: OpenMPSMT OffSMT On13002600390052006500SE +/- 0.20, N = 7SE +/- 17.08, N = 8SE +/- 53.03, N = 15SE +/- 23.29, N = 1262424081367133211. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgH/s, More Is BetterXmrig 6.18.1Variant: Monero - Hash Count: 1MSMT OffSMT On20K40K60K80K100KSE +/- 513.99, N = 3SE +/- 587.76, N = 15SE +/- 83.35, N = 4SE +/- 871.70, N = 451218.924409.485946.086533.71. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

EPYC 9754 1PEPYC 9754 2POpenBenchmarking.orgH/s, More Is BetterXmrig 6.18.1Variant: Wownero - Hash Count: 1MSMT OffSMT On30K60K90K120K150KSE +/- 13.77, N = 4SE +/- 513.11, N = 15SE +/- 741.13, N = 4SE +/- 677.82, N = 563182.274803.6100754.3142082.71. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

154 Results Shown

7-Zip Compression:
  Compression Rating
  Decompression Rating
Aircrack-ng
Appleseed:
  Emily
  Disney Material
  Material Tester
ASTC Encoder:
  Fast
  Thorough
  Exhaustive
Blender:
  BMW27 - CPU-Only
  Classroom - CPU-Only
  Fishy Cat - CPU-Only
  Barbershop - CPU-Only
  Pabellon Barcelona - CPU-Only
CloverLeaf
CP2K Molecular Dynamics
CPU Power Consumption Monitor
Embree:
  Pathtracer ISPC - Crown
  Pathtracer ISPC - Asian Dragon
Graph500:
  26:
    bfs median_TEPS
    bfs max_TEPS
    sssp median_TEPS
    sssp max_TEPS
HeFFTe - Highly Efficient FFT for Exascale:
  c2c - FFTW - float - 512
  r2c - FFTW - float - 512
  c2c - FFTW - double - 512
  r2c - FFTW - double - 512
Helsing
Intel Open Image Denoise:
  RT.hdr_alb_nrm.3840x2160 - CPU-Only
  RT.ldr_alb_nrm.3840x2160 - CPU-Only
  RTLightmap.hdr.4096x4096 - CPU-Only
John The Ripper:
  bcrypt
  WPA PSK
  Blowfish
  MD5
libxsmm:
  128
  256
Liquid-DSP:
  256 - 256 - 512
  512 - 256 - 512
LuxCoreRender:
  DLSC - CPU
  Orange Juice - CPU
  LuxCore Benchmark - CPU
  Rainbow Colors and Prism - CPU
MariaDB:
  2048
  4096
miniBUDE:
  OpenMP - BM1:
    GFInst/s
    Billion Interactions/s
  OpenMP - BM2:
    GFInst/s
    Billion Interactions/s
miniFE
NAMD
NAS Parallel Benchmarks:
  BT.C
  CG.C
  EP.D
  FT.C
  IS.D
  LU.C
  MG.C
  SP.B
  SP.C
nekRS:
  Kershaw
  TurboPipe Periodic
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
OpenSSL:
  SHA256
  SHA512
  RSA4096
  RSA4096
  ChaCha20
  AES-128-GCM
  AES-256-GCM
  ChaCha20-Poly1305
OpenVINO:
  Face Detection FP16 - CPU:
    FPS
    ms
  Person Detection FP16 - CPU:
    FPS
    ms
  Person Detection FP32 - CPU:
    FPS
    ms
  Vehicle Detection FP16 - CPU:
    FPS
    ms
  Face Detection FP16-INT8 - CPU:
    FPS
    ms
  Vehicle Detection FP16-INT8 - CPU:
    FPS
    ms
  Weld Porosity Detection FP16 - CPU:
    FPS
    ms
  Machine Translation EN To DE FP16 - CPU:
    FPS
    ms
  Weld Porosity Detection FP16-INT8 - CPU:
    FPS
    ms
  Person Vehicle Bike Detection FP16 - CPU:
    FPS
    ms
  Age Gender Recognition Retail 0013 FP16 - CPU:
    FPS
    ms
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    FPS
    ms
OpenVKL
OSPRay:
  particle_volume/ao/real_time
  particle_volume/scivis/real_time
  gravity_spheres_volume/dim_512/ao/real_time
  gravity_spheres_volume/dim_512/scivis/real_time
OSPRay Studio:
  1 - 4K - 1 - Path Tracer
  2 - 4K - 1 - Path Tracer
  3 - 4K - 1 - Path Tracer
  1 - 4K - 16 - Path Tracer
  1 - 4K - 32 - Path Tracer
  2 - 4K - 16 - Path Tracer
  2 - 4K - 32 - Path Tracer
  3 - 4K - 16 - Path Tracer
  3 - 4K - 32 - Path Tracer
PostgreSQL:
  1000 - 800 - Read Only
  1000 - 800 - Read Only - Average Latency
Primesieve:
  1e12
  1e13
SPECFEM3D:
  Mount St. Helens
  Layered Halfspace
  Tomographic Model
  Homogeneous Halfspace
  Water-layered Halfspace
srsRAN Project
Stockfish
TensorFlow:
  CPU - 256 - AlexNet
  CPU - 512 - AlexNet
  CPU - 256 - GoogLeNet
  CPU - 256 - ResNet-50
  CPU - 512 - GoogLeNet
  CPU - 512 - ResNet-50
Timed Gem5 Compilation
Timed Godot Game Engine Compilation
Timed Linux Kernel Compilation:
  defconfig
  allmodconfig
Timed LLVM Compilation:
  Ninja
  Unix Makefiles
Timed Node.js Compilation
toyBrot Fractal Generator:
  TBB
  OpenMP
Xmrig:
  Monero - 1M
  Wownero - 1M