AMD Ryzen 9 7950X vs. Threadripper 7970X + 7980X On Linux

Benchmarks by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2311203-NE-DUPLICATE64
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

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

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
Performance Per
Dollar
Date
Run
  Test
  Duration
Ryzen 9 7950X
October 17 2023
  9 Hours, 11 Minutes
Ryzen 9 7950X3D
October 21 2023
  9 Hours, 12 Minutes
Threadripper 7970X
November 09 2023
  12 Hours, 43 Minutes
Threadripper 7980X
November 08 2023
  12 Hours, 24 Minutes
Invert Behavior (Only Show Selected Data)
  10 Hours, 52 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):

Ryzen 9 7950X

Processor: AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 7900 XTX 24GB (2304/1249MHz), Audio: AMD Navi 31 HDMI/DP, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Ubuntu 23.10, Kernel: 6.5.0-9-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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 Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203
Java Notes: OpenJDK Runtime Environment (build 17.0.9-ea+6-Ubuntu-1)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Ryzen 9 7950X3D

Changed Processor to AMD Ryzen 9 7950X3D 16-Core @ 5.76GHz (16 Cores / 32 Threads).

Threadripper 7970X

Processor: AMD Ryzen Threadripper 7970X 32-Cores @ 7.21GHz (32 Cores / 64 Threads), Motherboard: ASUS Pro WS TRX50-SAGE WIFI (0217 BIOS), Chipset: AMD Device 14a4, Memory: 128GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 7900 XTX 24GB (2304/1249MHz), Audio: Realtek ALC1220, Network: Aquantia Device 04c0 + Intel I226-LM + MEDIATEK MT7922 802.11ax PCI

OS: Ubuntu 23.10, Kernel: 6.5.0-9-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7 + Wayland, OpenGL: 4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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 Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Threadripper 7980X

Changed Processor to AMD Ryzen Threadripper 7980X 64-Cores @ 8.21GHz (64 Cores / 128 Threads).

AMD Ryzen 9 7950X vs. Threadripper 7970X + 7980X On LinuxProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionRyzen 9 7950XRyzen 9 7950X3DThreadripper 7970XThreadripper 7980XAMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads)ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS)AMD Device 14d832GB1000GB Western Digital WDS100T1X0E-00AFY0AMD Radeon RX 7900 XTX 24GB (2304/1249MHz)AMD Navi 31 HDMI/DPIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 23.106.5.0-9-generic (x86_64)GNOME Shell 45.0X Server + Wayland4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54)GCC 13.2.0ext43840x2160AMD Ryzen 9 7950X3D 16-Core @ 5.76GHz (16 Cores / 32 Threads)AMD Ryzen Threadripper 7970X 32-Cores @ 7.21GHz (32 Cores / 64 Threads)ASUS Pro WS TRX50-SAGE WIFI (0217 BIOS)AMD Device 14a4128GBRealtek ALC1220Aquantia Device 04c0 + Intel I226-LM + MEDIATEK MT7922 802.11ax PCIX Server 1.21.1.7 + WaylandAMD Ryzen Threadripper 7980X 64-Cores @ 8.21GHz (64 Cores / 128 Threads)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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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- Ryzen 9 7950X: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- Ryzen 9 7950X3D: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- Threadripper 7970X: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105- Threadripper 7980X: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105Java Details- Ryzen 9 7950X, Ryzen 9 7950X3D: OpenJDK Runtime Environment (build 17.0.9-ea+6-Ubuntu-1)Python Details- Python 3.11.6Security Details- Ryzen 9 7950X: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - Ryzen 9 7950X3D: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - Threadripper 7970X: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - Threadripper 7980X: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Ryzen 9 7950XRyzen 9 7950X3DThreadripper 7970XThreadripper 7980XLogarithmic Result OverviewPhoronix Test SuiteeasyWaveSPECFEM3DStockfishGROMACSOpenSSLminiBUDEASTC EncoderIndigoBenchEmbreeNAMDBlenderChaos Group V-RAY7-Zip CompressionIntel Open Image DenoiseasmFishJohn The RipperNAS Parallel BenchmarksOpenVKLXmrigOSPRayLuxCoreRenderMemcachedY-CruncherSVT-VP9OpenFOAMTimed Linux Kernel CompilationTimed LLVM CompilationPostgreSQLTimed Godot Game Engine CompilationTimed Node.js CompilationRodiniaoneDNNDarktableSVT-HEVCuvg266TensorFlowKvazaarnginxHigh Performance Conjugate GradientSVT-AV1Timed Mesa CompilationOpenRadiosslibavif avifencNatronLiquid-DSPGIMPNode.js V8 Web Tooling BenchmarkVVenCx265NgspicePyBenchRawTherapeePyPerformance

Ryzen 9 7950XRyzen 9 7950X3DThreadripper 7970XThreadripper 7980XLogarithmic Per Watt Result OverviewPhoronix Test SuiteNode.js V8 Web Tooling BenchmarkHigh Performance Conjugate GradientTensorFlowVVenCx265EmbreeNatronSVT-AV1ASTC EncoderminiBUDEStockfishLiquid-DSPGROMACSKvazaarIndigoBenchnginxChaos Group V-RAYOpenSSLXmriguvg266Intel Open Image DenoiseOSPRaySVT-VP9NAS Parallel Benchmarks7-Zip CompressionasmFishMemcachedJohn The RipperOpenVKLSVT-HEVCLuxCoreRenderP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

AMD Ryzen 9 7950X vs. Threadripper 7970X + 7980X On Linuxopenvkl: vklBenchmarkCPU ISPChpcg: 104 104 104 - 60openfoam: drivaerFastback, Medium Mesh Size - Execution Timeopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timebuild-linux-kernel: allmodconfigopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUtensorflow: CPU - 64 - ResNet-50build-nodejs: Time To Compilebuild-llvm: Ninjarodinia: OpenMP HotSpot3Dstockfish: Total Timeopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUnginx: 1000openssl: SHA256openssl: ChaCha20-Poly1305openssl: AES-256-GCMopenssl: AES-128-GCMopenssl: ChaCha20openssl: SHA512ospray: particle_volume/pathtracer/real_timeospray: particle_volume/scivis/real_timeopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUpgbench: 100 - 1000 - Read Only - Average Latencypgbench: 100 - 1000 - Read Onlypgbench: 100 - 1000 - Read Write - Average Latencypgbench: 100 - 1000 - Read Writeopenradioss: Bird Strike on Windshieldasmfish: 1024 Hash Memory, 26 Depthbuild-godot: Time To Compilenpb: SP.Cospray: particle_volume/ao/real_timenginx: 500openradioss: Bumper Beamonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Training - f32 - CPUngspice: C2670tensorflow: CPU - 16 - ResNet-50onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUnpb: BT.Cv-ray: CPUngspice: C7552minibude: OpenMP - BM2minibude: OpenMP - BM2vvenc: Bosphorus 4K - Fastavifenc: 2node-web-tooling: memcached: 1:100specfem3d: Mount St. Helensmemcached: 1:10luxcorerender: Orange Juice - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUluxcorerender: Danish Mood - CPUrodinia: OpenMP LavaMDluxcorerender: LuxCore Benchmark - CPUindigobench: CPU - Bedroomeasywave: e2Asean Grid + BengkuluSept2007 Source - 1200indigobench: CPU - Supercarxmrig: Wownero - 1Mluxcorerender: DLSC - CPUopenradioss: Rubber O-Ring Seal Installationopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUspecfem3d: Layered Halfspaceopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUjohn-the-ripper: MD5john-the-ripper: HMAC-SHA512openssl: RSA4096openssl: RSA4096ospray: gravity_spheres_volume/dim_512/scivis/real_timeospray: gravity_spheres_volume/dim_512/ao/real_timespecfem3d: Tomographic Modelospray: gravity_spheres_volume/dim_512/pathtracer/real_timegromacs: MPI CPU - water_GMX50_barexmrig: Monero - 1Mblender: Fishy Cat - CPU-Onlyquantlib: Multi-Threadedopenradioss: Cell Phone Drop Testrodinia: OpenMP Leukocyterawtherapee: Total Benchmark Timeopenfoam: drivaerFastback, Small Mesh Size - Execution Timeopenfoam: drivaerFastback, Small Mesh Size - Mesh Timespecfem3d: Homogeneous Halfspacenpb: LU.Cbuild-linux-kernel: defconfigblender: BMW27 - CPU-Onlyvvenc: Bosphorus 4K - Fasternamd: ATPase Simulation - 327,506 Atomsonednn: IP Shapes 1D - f32 - CPUuvg266: Bosphorus 4K - Mediumjohn-the-ripper: WPA PSKjohn-the-ripper: bcryptjohn-the-ripper: Blowfishliquid-dsp: 32 - 256 - 512pyperformance: crypto_pyaesoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlynatron: Spaceshipsvt-vp9: VMAF Optimized - Bosphorus 4Kpyperformance: regex_compilecompress-7zip: Decompression Ratingcompress-7zip: Compression Ratingastcenc: Exhaustivekvazaar: Bosphorus 4K - Mediumy-cruncher: 500Mpyperformance: json_loadsrodinia: OpenMP Streamclusterbuild-mesa: Time To Compilepybench: Total For Average Test Timesquantlib: Single-Threadedsvt-av1: Preset 8 - Bosphorus 4Kembree: Pathtracer ISPC - Crownembree: Pathtracer ISPC - Asian Dragonx265: Bosphorus 4Kgimp: unsharp-maskluxcorerender: Rainbow Colors and Prism - CPUgimp: resizeastcenc: Thoroughsvt-hevc: 7 - Bosphorus 4Kgimp: auto-levelsminibude: OpenMP - BM1minibude: OpenMP - BM1npb: FT.Cuvg266: Bosphorus 4K - Very Fastuvg266: Bosphorus 4K - Ultra Fastnpb: CG.Cuvg266: Bosphorus 4K - Super Fastkvazaar: Bosphorus 4K - Very Fastgimp: rotateonednn: IP Shapes 3D - f32 - CPUrodinia: OpenMP CFD Solverkvazaar: Bosphorus 4K - Super Fastnpb: SP.Bkvazaar: Bosphorus 4K - Ultra Fastsvt-vp9: PSNR/SSIM Optimized - Bosphorus 4Ksvt-vp9: Visual Quality Optimized - Bosphorus 4Kavifenc: 6, Losslessnpb: MG.Castcenc: Mediumsvt-av1: Preset 13 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Ksvt-hevc: 10 - Bosphorus 4Kdarktable: Boat - CPU-onlynpb: EP.Cavifenc: 6darktable: Server Room - CPU-onlydarktable: Masskrug - CPU-onlydarktable: Server Rack - CPU-onlyRyzen 9 7950XRyzen 9 7950X3DThreadripper 7970XThreadripper 7980X6518.278062111.7058189.67417498.95644.40239.907297.44858.14475582217149910.01367005446139733106547022847754777026581751425313685790201011729598013216.5507.905030.736135778620.08549790145.9881537562156.11614050.217.91289163953.5587.381138.131138.8974.36142.93577.885577.31950174.373267165.75553.2911332.2858.40034.68820.943578222.6631.3788654273949525.198.254.5481.3545.035.553110.10912.23420641.15.2962.4976.9389347724617333203175333392731.615012.97.799228.0974927.0807414939.330472.58514326.862.9452.8649.53439.557163.7654523.86695535.27280913455883.1645.97950.3616.2370.782031.7348316.83174697477184749842609666740.80.916.2111.8962.51819291791361.839623.099.06910.49.00821.63553586.15733.917934.908335.6714.36919.8013.96017.6387103.6911.86353.3381333.43527769.0146.1058.3711354.7850.3850.4310.5983.230118.96266.1820740.0185.61120.72109.445.69923869.53141.0108185.885185.206169.182.8233057.303.2591.6531.8570.1726428.358451851.6529182.11381509.97344.10234.698289.27351.00871134158152792.56340130926379219313636721603004889024992575533312913956945710793072713209.4937.472070.777128774120.25349382141.9078129599152.94816652.497.48372160477.8691.861216.291212.8676.46743.03617.091621.70253674.903112763.98051.4441286.0957.90636.21120.623428673.6032.1082227623728181.417.864.3685.5564.755.35074.16211.75719594.75.0165.6274.3553364894138333190113667374201.913643.27.422097.7048227.2370449568.850122.67016167.866.2547.5453.97541.699128.8792124.11827234.62374882660336.2347.08053.2715.3320.822711.9447915.38164458451224494540651000041.40.876.1115.5063.61746261850151.693721.098.80910.77.56621.49458081.67833.675337.372234.6115.31318.9814.38016.075299.4412.79751.4311285.78327783.6242.0753.2312316.7946.0145.8311.1452.493859.39260.3927340.7677.65123.52108.885.83524667.53129.2166181.938182.184171.703.0652935.383.4121.6781.9140.175115912.13241410.5792106.11701297.66434.44468.64122.84131.8768.90148.437183.16858.477144329854128.80124.1768.68233.4716.37976.17220591.926444568889017535897636340780018710747424513629324634327204020703493623227.20313.93225.792756.600.419238817516.82959424108.40136573860100.73534600.0913.8649241556.6377.90732.764730.92282.65071.22421.647421.82892396.095620371.86794.5522363.7979.00329.12017.886045286.4013.6142554976151877.1413.14624.8825.49324.6949.177.5048.5068.039.75835.29021.36037197.78.9051.053.479212.020.383081.6629.821072.280.4262357.6823.491361.635.163095.8714.321115.202.446530.7612.472563.326.365020.307997000247720333700571.826660.013.705914.219816.42025.90529160.436.41155457.127.9430.27138.36853.44510921.102787133061.2932.76428.8316.5460.441931.1102724.48309645840138402254845000042.71.648.3224.9166.03242563444343.284831.494.42711.14.78416.1885794296.9119.58059.574668.869538.8917.45931.8014.52431.5851176.5813.96095.7872394.66270557.0660.9971.9326421.3466.3865.8711.6511.128087.87084.4672927.7396.65240.15205.494.82565635.18247.9571259.588260.800273.751.9495249.282.4591.1861.2100.09616569.983951091.5397118.15892236.27166.37481.79258.85123.6257.92132.590158.38956.813239566649260.55122.66121.42263.2025.471254.53223524.7710352383108028442086213364522813303374700577978740133667253033735793170249.55622.01477.544239.590.262381103317.27957889108.6221012286285.57759125.6022.0820226562.3075.74654.461654.25681.31047.00434.150432.42375669.528750871.489154.9393873.4839.39426.58117.578310152.628.9566547456829197.9518.71809.8139.33415.1276.8910.6232.44611.1515.40121.03133.96845190.913.4655.254.4914224.400.38116361.8223.45587079237.761694.010.5489281.4937.731693.656.744738.2832.69976.193.1810021.4916.173954.448.167834.68124010003040036671186776.940456.322.177922.996410.07861821625.90108.07042793.923.71243365.023.2027.59841.03037.50657822.66426412.483888523143837.9728.34018.5116.8540.288481.1635428.2049696113960113963253671666743.22.358.3231.1266.35284274611835.225735.514.802114.14215.2925654348.9126.20793.5298103.964238.1318.48533.7616.38649.7960214.6814.427158.1873954.67571652.9370.5373.9016008.3272.5279.6311.8181.065345.57395.52118372.2899.72234.87221.644.53867758.76378.2202226.114228.228214.301.7177568.142.2041.4071.0990.077OpenBenchmarking.org

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 2.0.0Benchmark: vklBenchmarkCPU ISPCThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D400800120016002000SE +/- 20.34, N = 4SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 316561159651642MIN: 143 / MAX: 22326MIN: 90 / MAX: 14895MIN: 50 / MAX: 9084MIN: 48 / MAX: 8633
OpenBenchmarking.orgItems / Sec Per Watt, More Is BetterOpenVKL 2.0.0Benchmark: vklBenchmarkCPU ISPCRyzen 9 7950X3DThreadripper 7980XThreadripper 7970XRyzen 9 7950X1.242.483.724.966.25.5115.0523.7763.599
OpenBenchmarking.orgWatts, Fewer Is BetterOpenVKL 2.0.0CPU Power Consumption MonitorRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X60120180240300Min: 20.81 / Avg: 116.5 / Max: 135.24Min: 10.97 / Avg: 180.89 / Max: 231.3Min: 69.19 / Avg: 306.95 / Max: 357.58Min: 76.56 / Avg: 327.79 / Max: 355.99

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 104 104 104 - RT: 60Threadripper 7970XThreadripper 7980XRyzen 9 7950X3DRyzen 9 7950X3691215SE +/- 0.75174, N = 12SE +/- 0.08251, N = 9SE +/- 0.00341, N = 3SE +/- 0.00296, N = 312.132409.983958.358458.278061. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 104 104 104 - RT: 60Ryzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X0.02210.04420.06630.08840.11050.0980.0690.0510.029
MinAvgMaxRyzen 9 7950X3D20.585.2108.5Ryzen 9 7950X21.1120.7157.4Threadripper 7970X66.9239.5293.4Threadripper 7980X67.8346.7356.2OpenBenchmarking.orgWatts, Fewer Is BetterHigh Performance Conjugate Gradient 3.1CPU Power Consumption Monitor100200300400500

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution TimeThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X50010001500200025001091.541410.581851.652111.711. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption MonitorRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X60120180240300Min: 21.13 / Avg: 98 / Max: 132.98Min: 20.58 / Avg: 141.11 / Max: 211.76Min: 70.17 / Avg: 273.1 / Max: 349.71Min: 80.64 / Avg: 348.1 / Max: 353.64

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh TimeThreadripper 7970XThreadripper 7980XRyzen 9 7950X3DRyzen 9 7950X4080120160200106.12118.16182.11189.671. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfigThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D110220330440550SE +/- 1.66, N = 3SE +/- 1.44, N = 3SE +/- 0.26, N = 3SE +/- 0.40, N = 3236.27297.66498.96509.97
OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.1CPU Power Consumption MonitorRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X60120180240300Min: 19.74 / Avg: 139.86 / Max: 148.11Min: 20.46 / Avg: 207.17 / Max: 226.59Min: 65.88 / Avg: 321.92 / Max: 349.94Min: 84.25 / Avg: 324.01 / Max: 350.82

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.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUThreadripper 7970XThreadripper 7980X1530456075SE +/- 0.79, N = 15SE +/- 0.53, N = 1534.4466.37MIN: 11.22 / MAX: 81.54MIN: 15.97 / MAX: 225.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X69.4315.6352.4Threadripper 7980X86.6332.4358.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUThreadripper 7980XThreadripper 7970X100200300400500SE +/- 4.23, N = 15SE +/- 14.96, N = 15481.79468.641. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUThreadripper 7970XThreadripper 7980X60120180240300SE +/- 3.22, N = 15SE +/- 2.43, N = 14122.84258.85MIN: 32.52 / MAX: 219.63MIN: 66.38 / MAX: 680.981. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X68.4301.2352.6Threadripper 7980X84.6331.2358.1OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUThreadripper 7970XThreadripper 7980X306090120150SE +/- 4.76, N = 15SE +/- 1.31, N = 14131.87123.621. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50Threadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D1530456075SE +/- 1.42, N = 15SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 368.9057.9244.4044.10
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50Ryzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X0.10040.20080.30120.40160.5020.4460.2670.2430.173
MinAvgMaxRyzen 9 7950X3D19.498.9109.2Ryzen 9 7950X20.6166.6184.9Threadripper 7970X68.2284.1338.2Threadripper 7980X81.1335.7357.1OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.12CPU Power Consumption Monitor100200300400500

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 19.8.1Time To CompileThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X50100150200250SE +/- 1.24, N = 7SE +/- 1.99, N = 3SE +/- 0.11, N = 3SE +/- 0.28, N = 3132.59148.44234.70239.91
MinAvgMaxRyzen 9 7950X3D18.6123.5148.3Ryzen 9 7950X22.1181.2225.6Threadripper 7970X66.7292.2349.7Threadripper 7980X84.1299.1353.1OpenBenchmarking.orgWatts, Fewer Is BetterTimed Node.js Compilation 19.8.1CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X60120180240300SE +/- 0.22, N = 3SE +/- 1.67, N = 3SE +/- 0.39, N = 3SE +/- 0.23, N = 3158.39183.17289.27297.45
MinAvgMaxRyzen 9 7950X3D20.7128.4146.1Ryzen 9 7950X21.5187.9224.8Threadripper 7970X68.1304.7349.8Threadripper 7980X82.5308.6350.9OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0CPU Power Consumption Monitor100200300400500

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DRyzen 9 7950X3DThreadripper 7980XRyzen 9 7950XThreadripper 7970X1326395265SE +/- 0.61, N = 3SE +/- 0.52, N = 15SE +/- 0.70, N = 15SE +/- 0.71, N = 1551.0156.8158.1458.481. (CXX) g++ options: -O2 -lOpenCL
MinAvgMaxRyzen 9 7950X3D19.160.998.9Ryzen 9 7950X20.969.6152.7Threadripper 7970X65.9136.3248.4Threadripper 7980X47.5192.4352.1OpenBenchmarking.orgWatts, Fewer Is BetterRodinia 3.1CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 15Total TimeThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D50M100M150M200M250MSE +/- 3126793.94, N = 15SE +/- 1804570.74, N = 15SE +/- 1075255.64, N = 3SE +/- 664531.63, N = 1523956664914432985475582217711341581. (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
OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterStockfish 15Total TimeThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X160K320K480K640K800K725403.25527557.06448716.48369949.09
MinAvgMaxRyzen 9 7950X3D16.5134.8149.8Ryzen 9 7950X21.0204.3231.6Threadripper 7970X68.2321.7355.6Threadripper 7980X85.9330.3355.9OpenBenchmarking.orgWatts, Fewer Is BetterStockfish 15CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUThreadripper 7970XThreadripper 7980X60120180240300SE +/- 0.76, N = 15SE +/- 0.08, N = 3128.80260.55MIN: 34.25 / MAX: 201.2MIN: 86.15 / MAX: 591.331. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X69.6298.5336.0Threadripper 7980X82.0330.7358.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUThreadripper 7970XThreadripper 7980X306090120150SE +/- 0.79, N = 15SE +/- 0.03, N = 3124.17122.661. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUThreadripper 7970XThreadripper 7980X306090120150SE +/- 0.98, N = 15SE +/- 0.14, N = 368.68121.42MIN: 30.77 / MAX: 103.63MIN: 52.39 / MAX: 186.061. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X69.7327.5355.6Threadripper 7980X82.4331.1353.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUThreadripper 7980XThreadripper 7970X60120180240300SE +/- 0.31, N = 3SE +/- 3.82, N = 15263.20233.471. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUThreadripper 7970XThreadripper 7980X612182430SE +/- 0.03, N = 3SE +/- 0.17, N = 1516.3725.47MIN: 8.96 / MAX: 42.28MIN: 11.02 / MAX: 56.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X69.5330.2352.5Threadripper 7980X83.8331.8356.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUThreadripper 7980XThreadripper 7970X30060090012001500SE +/- 8.86, N = 15SE +/- 1.92, N = 31254.53976.171. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 1000Threadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X50K100K150K200K250KSE +/- 765.31, N = 3SE +/- 1552.94, N = 15SE +/- 60.37, N = 3SE +/- 296.00, N = 3223524.77220591.92152792.56149910.011. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.23.2Connections: 1000Ryzen 9 7950X3DRyzen 9 7950XThreadripper 7980XThreadripper 7970X300600900120015001183.84734.03673.99657.19
MinAvgMaxRyzen 9 7950X3D18.4129.1138.6Ryzen 9 7950X17.9204.2224.9Threadripper 7980X80.2331.6352.1Threadripper 7970X71.3335.7352.4OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA256Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D20000M40000M60000M80000M100000MSE +/- 27013882.16, N = 3SE +/- 205735347.19, N = 3SE +/- 60605198.80, N = 3SE +/- 21912048.82, N = 3103523831080644456888903670054461334013092637-lssl -lcrypto-lssl -lcrypto1. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: SHA256Threadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X60M120M180M240M300M301175412.84250863697.52190597097.75177847480.38
MinAvgMaxRyzen 9 7950X3D17.5135.6146.9Ryzen 9 7950X21.4206.4226.4Threadripper 7970X68.6338.1355.6Threadripper 7980X82.4343.7355.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly1305Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D60000M120000M180000M240000M300000MSE +/- 62044501.02, N = 3SE +/- 17191319.99, N = 3SE +/- 9715065.66, N = 3SE +/- 8455160.78, N = 32844208621331753589763639733106547092193136367-lssl -lcrypto-lssl -lcrypto1. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly1305Threadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X200M400M600M800M1000M828095189.79698769112.04512087265.67481821806.42
MinAvgMaxRyzen 9 7950X3D18.6131.9149.5Ryzen 9 7950X19.3202.0228.8Threadripper 7970X69.3342.4355.6Threadripper 7980X84.2343.5355.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-256-GCMThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D140000M280000M420000M560000M700000MSE +/- 367853216.68, N = 3SE +/- 123690634.42, N = 3SE +/- 128224666.36, N = 3SE +/- 80429325.94, N = 3645228133033407800187107228477547770216030048890-lssl -lcrypto-lssl -lcrypto1. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: AES-256-GCMThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X400M800M1200M1600M2000M1875627358.701589344830.081197240741.871079764258.51
MinAvgMaxRyzen 9 7950X3D20.0135.9150.0Ryzen 9 7950X19.0211.6225.2Threadripper 7970X69.1340.6355.6Threadripper 7980X87.2344.0355.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-128-GCMThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D160000M320000M480000M640000M800000MSE +/- 1140268222.55, N = 3SE +/- 191897159.27, N = 3SE +/- 336387713.32, N = 3SE +/- 342110135.08, N = 3747005779787474245136293265817514253249925755333-lssl -lcrypto-lssl -lcrypto1. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: AES-128-GCMThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X500M1000M1500M2000M2500M2168275073.831833541357.821393300045.461249483542.71
MinAvgMaxRyzen 9 7950X3D18.3136.3150.8Ryzen 9 7950X21.2212.7226.5Threadripper 7970X70.9340.4355.6Threadripper 7980X78.6344.5355.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D90000M180000M270000M360000M450000MSE +/- 39784116.46, N = 3SE +/- 73173783.96, N = 3SE +/- 14829006.68, N = 3SE +/- 237067533.55, N = 3401336672530246343272040136857902010129139569457-lssl -lcrypto-lssl -lcrypto1. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: ChaCha20Threadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X200M400M600M800M1000M1166093314.63972263650.16718654798.54677847924.91
MinAvgMaxRyzen 9 7950X3D19.7132.8153.0Ryzen 9 7950X16.7201.9228.9Threadripper 7970X67.0342.8355.6Threadripper 7980X87.0344.2355.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA512Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D7000M14000M21000M28000M35000MSE +/- 119147968.13, N = 3SE +/- 13496149.59, N = 3SE +/- 3317494.71, N = 3SE +/- 2200828.53, N = 333735793170207034936231172959801310793072713-lssl -lcrypto-lssl -lcrypto1. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: SHA512Threadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X20M40M60M80M100M98086300.2481648795.0263726304.8658367002.21
MinAvgMaxRyzen 9 7950X3D17.2132.2142.2Ryzen 9 7950X21.6201.0226.5Threadripper 7970X69.8324.9349.6Threadripper 7980X83.9343.9355.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/pathtracer/real_timeThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D50100150200250SE +/- 0.08, N = 3SE +/- 0.48, N = 3SE +/- 0.24, N = 3SE +/- 0.11, N = 3249.56227.20216.55209.49
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: particle_volume/pathtracer/real_timeRyzen 9 7950X3DRyzen 9 7950XThreadripper 7980XThreadripper 7970X0.43310.86621.29931.73242.16551.9251.2070.8020.770
MinAvgMaxRyzen 9 7950X3D17.0108.8129.0Ryzen 9 7950X21.4179.4225.2Threadripper 7970X68.9294.9355.5Threadripper 7980X84.8311.2355.6OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/scivis/real_timeThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D510152025SE +/- 0.00793, N = 3SE +/- 0.00280, N = 3SE +/- 0.00426, N = 3SE +/- 0.00616, N = 322.0147013.932207.905037.47207
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: particle_volume/scivis/real_timeThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.01640.03280.04920.06560.0820.0730.0690.0490.046
MinAvgMaxRyzen 9 7950X3D18.0107.6125.6Ryzen 9 7950X23.0172.7205.4Threadripper 7970X70.4282.2349.8Threadripper 7980X82.0302.9353.8OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUThreadripper 7970XThreadripper 7980X246810SE +/- 0.01, N = 3SE +/- 0.05, N = 115.797.54MIN: 3.63 / MAX: 32.73MIN: 4.5 / MAX: 34.11. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X70.9330.5349.7Threadripper 7980X81.5331.1355.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUThreadripper 7980XThreadripper 7970X9001800270036004500SE +/- 30.95, N = 11SE +/- 3.14, N = 34239.592756.601. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -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.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average LatencyThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D0.17480.34960.52440.69920.874SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 3SE +/- 0.008, N = 30.2620.4190.7360.7771. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
MinAvgMaxRyzen 9 7950X3D16.0120.5140.7Ryzen 9 7950X18.5185.2216.7Threadripper 7970X66.9310.8355.6Threadripper 7980X82.2315.9355.6OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 16CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read OnlyThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D800K1600K2400K3200K4000KSE +/- 10625.39, N = 3SE +/- 7962.80, N = 3SE +/- 7265.40, N = 3SE +/- 12946.22, N = 338110332388175135778612877411. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average LatencyThreadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D510152025SE +/- 0.07, N = 3SE +/- 0.19, N = 3SE +/- 0.02, N = 3SE +/- 0.16, N = 316.8317.2820.0920.251. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
MinAvgMaxRyzen 9 7950X3D19.4111.3132.0Ryzen 9 7950X21.3171.2201.7Threadripper 7970X66.9293.1343.6Threadripper 7980X84.9307.9349.0OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 16CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read WriteThreadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D13K26K39K52K65KSE +/- 235.48, N = 3SE +/- 645.57, N = 3SE +/- 55.66, N = 3SE +/- 383.17, N = 3594245788949790493821. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bird Strike on WindshieldThreadripper 7970XThreadripper 7980XRyzen 9 7950X3DRyzen 9 7950X306090120150SE +/- 0.06, N = 3SE +/- 0.21, N = 3SE +/- 0.51, N = 3SE +/- 0.66, N = 3108.40108.62141.90145.98
MinAvgMaxRyzen 9 7950X3D19.8124.2133.4Ryzen 9 7950X21.4188.3201.0Threadripper 7970X68.6324.5349.7Threadripper 7980X69.4335.3351.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor100200300400500

asmFish

This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D50M100M150M200M250MSE +/- 1054748.56, N = 3SE +/- 920278.06, N = 3SE +/- 783795.42, N = 6SE +/- 924259.84, N = 42101228621365738608153756278129599
OpenBenchmarking.orgNodes/second Per Watt, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X130K260K390K520K650K621207.66588881.94415427.59403699.75
MinAvgMaxRyzen 9 7950X3D20.3132.7143.2Ryzen 9 7950X18.5202.0218.1Threadripper 7970X71.1328.8349.7Threadripper 7980X81.6338.2355.9OpenBenchmarking.orgWatts, Fewer Is BetterasmFish 2018-07-23CPU Power Consumption Monitor100200300400500

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 4.0Time To CompileThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X306090120150SE +/- 0.36, N = 3SE +/- 0.17, N = 3SE +/- 0.10, N = 3SE +/- 0.14, N = 385.58100.74152.95156.12
MinAvgMaxRyzen 9 7950X3D18.3123.9147.1Ryzen 9 7950X21.1181.7228.7Threadripper 7980X83.9262.9351.4Threadripper 7970X67.3271.1351.0OpenBenchmarking.orgWatts, Fewer Is BetterTimed Godot Game Engine Compilation 4.0CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X13K26K39K52K65KSE +/- 45.03, N = 3SE +/- 1728.07, N = 15SE +/- 21.10, N = 3SE +/- 20.72, N = 359125.6034600.0916652.4914050.211. (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 4.1.5
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X4080120160200191.25181.18150.11107.94
MinAvgMaxRyzen 9 7950X3D18.691.996.8Ryzen 9 7950X19.5130.2139.1Threadripper 7970X68.3230.5273.3Threadripper 7980X61.2309.1350.0OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/ao/real_timeThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D510152025SE +/- 0.01466, N = 3SE +/- 0.05557, N = 3SE +/- 0.00250, N = 3SE +/- 0.00448, N = 322.0820013.864907.912897.48372
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: particle_volume/ao/real_timeThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.01490.02980.04470.05960.07450.0660.0630.0420.041
MinAvgMaxRyzen 9 7950X3D19.8119.3124.0Ryzen 9 7950X22.0192.6205.3Threadripper 7970X64.8329.1350.1Threadripper 7980X85.0335.2353.7OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor100200300400500

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500Threadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D50K100K150K200K250KSE +/- 770.12, N = 3SE +/- 842.03, N = 3SE +/- 253.11, N = 3SE +/- 222.18, N = 3241556.63226562.30163953.55160477.861. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.23.2Connections: 500Ryzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X300600900120015001232.72768.97732.81683.69
MinAvgMaxRyzen 9 7950X3D19.8130.2139.4Ryzen 9 7950X18.2213.2236.0Threadripper 7970X68.2329.6351.0Threadripper 7980X82.3331.4352.2OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2CPU Power Consumption Monitor100200300400500

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bumper BeamThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D20406080100SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.23, N = 3SE +/- 0.21, N = 375.7477.9087.3891.86
MinAvgMaxRyzen 9 7950X3D17.8131.6139.7Ryzen 9 7950X19.7198.4214.9Threadripper 7970X70.7318.9349.7Threadripper 7980X70.3331.4351.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor100200300400500

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D30060090012001500SE +/- 0.97, N = 3SE +/- 0.55, N = 3SE +/- 0.83, N = 3SE +/- 1.03, N = 3654.46732.761138.131216.29MIN: 645.13MIN: 725.63MIN: 1131.56MIN: 1204.311. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
MinAvgMaxRyzen 9 7950X3D19.5111.6134.7Ryzen 9 7950X20.2202.7234.5Threadripper 7970X70.9318.0355.6Threadripper 7980X82.7323.2355.9OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.3CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D30060090012001500SE +/- 0.21, N = 3SE +/- 2.17, N = 3SE +/- 1.10, N = 3SE +/- 1.02, N = 3654.26730.921138.891212.86MIN: 645.77MIN: 721.72MIN: 1132.02MIN: 1200.841. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
MinAvgMaxRyzen 9 7950X3D19.4112.2134.0Ryzen 9 7950X20.4204.5235.4Threadripper 7970X69.9318.3355.6Threadripper 7980X83.0322.6355.6OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.3CPU Power Consumption Monitor100200300400500

Ngspice

Ngspice is an open-source SPICE circuit simulator. Ngspice was originally based on the Berkeley SPICE electronic circuit simulator. Ngspice supports basic threading using OpenMP. This test profile is making use of the ISCAS 85 benchmark circuits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C2670Ryzen 9 7950XRyzen 9 7950X3DThreadripper 7980XThreadripper 7970X20406080100SE +/- 0.29, N = 3SE +/- 0.38, N = 3SE +/- 0.67, N = 3SE +/- 0.62, N = 374.3676.4781.3182.651. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE
MinAvgMaxRyzen 9 7950X3D19.841.254.6Ryzen 9 7950X21.159.262.6Threadripper 7970X65.9117.2120.4Threadripper 7980X81.6163.4169.6OpenBenchmarking.orgWatts, Fewer Is BetterNgspice 34CPU Power Consumption Monitor50100150200250

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.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50Threadripper 7970XThreadripper 7980XRyzen 9 7950X3DRyzen 9 7950X1632486480SE +/- 0.10, N = 3SE +/- 0.95, N = 15SE +/- 0.00, N = 3SE +/- 0.03, N = 371.2247.0043.0342.93
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50Ryzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X0.10420.20840.31260.41680.5210.4630.2690.2620.150
MinAvgMaxRyzen 9 7950X3D20.492.9104.7Ryzen 9 7950X21.0159.6184.2Threadripper 7970X70.3271.7336.8Threadripper 7980X82.7312.7356.2OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.12CPU Power Consumption Monitor100200300400500

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUThreadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D130260390520650SE +/- 1.23, N = 3SE +/- 1.41, N = 3SE +/- 0.09, N = 3SE +/- 1.75, N = 3421.65434.15577.89617.09MIN: 415.12MIN: 425.83MIN: 573.39MIN: 609.011. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
MinAvgMaxRyzen 9 7950X3D18.7112.2133.3Ryzen 9 7950X19.1204.5233.0Threadripper 7970X69.6292.3355.6Threadripper 7980X83.1324.7355.6OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.3CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUThreadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D130260390520650SE +/- 0.20, N = 3SE +/- 0.74, N = 3SE +/- 0.40, N = 3SE +/- 0.28, N = 3421.83432.42577.32621.70MIN: 416.63MIN: 423.73MIN: 572.36MIN: 615.451. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
MinAvgMaxRyzen 9 7950X3D16.8111.8134.4Ryzen 9 7950X20.0205.1234.3Threadripper 7970X69.3292.5355.6Threadripper 7980X82.0324.4350.1OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.3CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CThreadripper 7970XThreadripper 7980XRyzen 9 7950X3DRyzen 9 7950X20K40K60K80K100KSE +/- 2505.89, N = 15SE +/- 16.80, N = 3SE +/- 137.17, N = 3SE +/- 4.68, N = 392396.0975669.5253674.9050174.371. (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 4.1.5
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950XThreadripper 7980X120240360480600547.64373.12347.80235.15
MinAvgMaxRyzen 9 7950X3D18.298.0106.1Ryzen 9 7950X21.1144.3157.4Threadripper 7970X67.7247.6308.3Threadripper 7980X59.3321.8352.8OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor100200300400500

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5.02Mode: CPUThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D20K40K60K80K100KSE +/- 292.46, N = 3SE +/- 165.51, N = 3SE +/- 125.41, N = 3SE +/- 66.67, N = 387508562033267131127
OpenBenchmarking.orgvsamples Per Watt, More Is BetterChaos Group V-RAY 5.02Mode: CPUThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X60120180240300284.07243.27187.55165.78
MinAvgMaxRyzen 9 7950X3D17.7128.0152.8Ryzen 9 7950X21.3197.1236.0Threadripper 7970X65.4299.7355.6Threadripper 7980X79.5308.1356.0OpenBenchmarking.orgWatts, Fewer Is BetterChaos Group V-RAY 5.02CPU Power Consumption Monitor100200300400500

Ngspice

Ngspice is an open-source SPICE circuit simulator. Ngspice was originally based on the Berkeley SPICE electronic circuit simulator. Ngspice supports basic threading using OpenMP. This test profile is making use of the ISCAS 85 benchmark circuits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C7552Ryzen 9 7950X3DRyzen 9 7950XThreadripper 7980XThreadripper 7970X1632486480SE +/- 0.58, N = 3SE +/- 0.05, N = 3SE +/- 0.34, N = 3SE +/- 0.98, N = 363.9865.7671.4971.871. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE
MinAvgMaxRyzen 9 7950X3D19.041.149.7Ryzen 9 7950X11.056.262.8Threadripper 7970X57.0113.8120.7Threadripper 7980X78.0160.6172.4OpenBenchmarking.orgWatts, Fewer Is BetterNgspice 34CPU Power Consumption Monitor50100150200250

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.

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D306090120150SE +/- 0.53, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3154.9494.5553.2951.441. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgBillion Interactions/s Per Watt, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2Threadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.10910.21820.32730.43640.54550.4850.3710.2880.264
MinAvgMaxRyzen 9 7950X3D17.6138.7144.4Ryzen 9 7950X15.9202.2218.8Threadripper 7980X72.7319.3349.9Threadripper 7970X69.6328.2355.6OpenBenchmarking.orgWatts, Fewer Is BetterminiBUDE 20210901CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D8001600240032004000SE +/- 13.28, N = 3SE +/- 2.51, N = 3SE +/- 0.65, N = 3SE +/- 0.17, N = 33873.482363.801332.291286.101. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FastThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D3691215SE +/- 0.003, N = 3SE +/- 0.059, N = 3SE +/- 0.065, N = 3SE +/- 0.059, N = 39.3949.0038.4007.9061. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FastRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X0.01780.03560.05340.07120.0890.0790.0530.0390.037
MinAvgMaxRyzen 9 7950X3D20.1100.2135.1Ryzen 9 7950X20.2157.4220.3Threadripper 7970X68.7228.9325.5Threadripper 7980X81.9256.3339.2OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.9CPU Power Consumption Monitor80160240320400

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 1.0Encoder Speed: 2Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D816243240SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.29, N = 1526.5829.1234.6936.211. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxRyzen 9 7950X3D17.688.7145.8Ryzen 9 7950X20.6126.3228.4Threadripper 7970X68.6181.7349.7Threadripper 7980X83.1202.9349.7OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 1.0CPU Power Consumption Monitor100200300400500

Node.js V8 Web Tooling Benchmark

Running the V8 project's Web-Tooling-Benchmark under Node.js. The Web-Tooling-Benchmark stresses JavaScript-related workloads common to web developers like Babel and TypeScript and Babylon. This test profile can test the system's JavaScript performance with Node.js. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkRyzen 9 7950XRyzen 9 7950X3DThreadripper 7970XThreadripper 7980X510152025SE +/- 0.13, N = 3SE +/- 0.13, N = 3SE +/- 0.17, N = 6SE +/- 0.06, N = 320.9420.6217.8817.57
OpenBenchmarking.orgruns/s Per Watt, More Is BetterNode.js V8 Web Tooling BenchmarkRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X0.10530.21060.31590.42120.52650.4680.3380.1470.105
MinAvgMaxRyzen 9 7950X3D18.444.153.5Ryzen 9 7950X21.262.074.4Threadripper 7970X68.2121.7134.6Threadripper 7980X80.3167.0182.3OpenBenchmarking.orgWatts, Fewer Is BetterNode.js V8 Web Tooling BenchmarkCPU Power Consumption Monitor50100150200250

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D2M4M6M8M10MSE +/- 79970.94, N = 3SE +/- 11545.55, N = 3SE +/- 3554.46, N = 3SE +/- 4644.17, N = 38310152.626045286.403578222.663428673.601. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100Ryzen 9 7950X3DThreadripper 7980XRyzen 9 7950XThreadripper 7970X6K12K18K24K30K28981.7926993.8219702.9719586.25
MinAvgMaxRyzen 9 7950X3D18.9118.3137.4Ryzen 9 7950X20.5181.6214.6Threadripper 7980X79.8307.9355.6Threadripper 7970X68.2308.6355.6OpenBenchmarking.orgWatts, Fewer Is BetterMemcached 1.6.19CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Mount St. HelensThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D714212835SE +/- 0.173431256, N = 12SE +/- 0.120393028, N = 4SE +/- 0.426973136, N = 3SE +/- 0.298848759, N = 158.95665474513.61425549731.37886542732.1082227621. (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
MinAvgMaxRyzen 9 7950X3D17.0112.6131.1Ryzen 9 7950X20.6176.3207.7Threadripper 7980X84.7263.2349.7Threadripper 7970X70.2274.5349.7OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.0CPU Power Consumption Monitor100200300400500

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D1.5M3M4.5M6M7.5MSE +/- 24794.28, N = 3SE +/- 24760.91, N = 3SE +/- 6583.36, N = 3SE +/- 16424.21, N = 36829197.956151877.143949525.193728181.411. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10Ryzen 9 7950X3DThreadripper 7980XRyzen 9 7950XThreadripper 7970X7K14K21K28K35K31715.2121887.7621623.6419881.34
MinAvgMaxRyzen 9 7950X3D18.9117.6139.0Ryzen 9 7950X19.8182.6215.6Threadripper 7970X40.1309.4355.6Threadripper 7980X83.0312.0355.9OpenBenchmarking.orgWatts, Fewer Is BetterMemcached 1.6.19CPU Power Consumption Monitor100200300400500

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 2.6Scene: Orange Juice - Acceleration: CPUThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D510152025SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 318.7113.148.257.86MIN: 16.51 / MAX: 24.21MIN: 11.45 / MAX: 15.06MIN: 7.34 / MAX: 8.72MIN: 7.02 / MAX: 8.29
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPURyzen 9 7950X3DThreadripper 7980XThreadripper 7970XRyzen 9 7950X0.01310.02620.03930.05240.06550.0580.0570.0410.040
MinAvgMaxRyzen 9 7950X3D18.8134.7148.2Ryzen 9 7950X20.9205.5229.8Threadripper 7970X68.7323.8351.0Threadripper 7980X75.6328.3355.6OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUThreadripper 7970XThreadripper 7980X2004006008001000SE +/- 0.89, N = 3SE +/- 2.60, N = 3624.88809.81MIN: 584.3 / MAX: 646.5MIN: 690.2 / MAX: 841.11. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X68.5327.4352.4Threadripper 7980X83.1328.0355.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUThreadripper 7980XThreadripper 7970X918273645SE +/- 0.13, N = 3SE +/- 0.04, N = 339.3325.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUThreadripper 7970XThreadripper 7980X90180270360450SE +/- 0.24, N = 3SE +/- 0.08, N = 3324.69415.12MIN: 161.92 / MAX: 347.84MIN: 198.03 / MAX: 438.311. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X69.5326.3352.4Threadripper 7980X84.8328.8349.7OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUThreadripper 7980XThreadripper 7970X20406080100SE +/- 0.03, N = 3SE +/- 0.03, N = 376.8949.171. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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 2.6Scene: Danish Mood - Acceleration: CPUThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D3691215SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 310.627.504.544.36MIN: 5.7 / MAX: 11.93MIN: 4.1 / MAX: 8.31MIN: 1.92 / MAX: 5.15MIN: 1.82 / MAX: 4.95
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: CPUThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.00740.01480.02220.02960.0370.0330.0330.0230.022
MinAvgMaxRyzen 9 7950X3D19.8132.7147.3Ryzen 9 7950X19.4202.1222.4Threadripper 7970X70.1323.9350.9Threadripper 7980X59.2326.6349.8OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor100200300400500

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D20406080100SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 332.4548.5181.3585.561. (CXX) g++ options: -O2 -lOpenCL
MinAvgMaxRyzen 9 7950X3D18.6138.2150.7Ryzen 9 7950X17.0201.6223.4Threadripper 7980X70.4299.5349.6Threadripper 7970X71.5301.2349.6OpenBenchmarking.orgWatts, Fewer Is BetterRodinia 3.1CPU Power Consumption Monitor100200300400500

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 2.6Scene: LuxCore Benchmark - Acceleration: CPUThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D3691215SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 311.158.035.034.75MIN: 5.98 / MAX: 12.6MIN: 3.89 / MAX: 9.02MIN: 2.25 / MAX: 5.66MIN: 2.04 / MAX: 5.37
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: CPURyzen 9 7950X3DThreadripper 7980XThreadripper 7970XRyzen 9 7950X0.00790.01580.02370.03160.03950.0350.0340.0250.024
MinAvgMaxRyzen 9 7950X3D20.0135.7149.8Ryzen 9 7950X20.6205.6226.5Threadripper 7970X65.3321.7349.7Threadripper 7980X73.3325.8352.4OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor100200300400500

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D48121620SE +/- 0.030, N = 3SE +/- 0.011, N = 3SE +/- 0.016, N = 3SE +/- 0.012, N = 315.4019.7585.5535.350
OpenBenchmarking.orgM samples/s Per Watt, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.01060.02120.03180.04240.0530.0470.0390.0300.026
MinAvgMaxRyzen 9 7950X3D20.3137.7149.1Ryzen 9 7950X20.8209.7232.3Threadripper 7970X72.0327.6355.6Threadripper 7980X82.9329.2355.6OpenBenchmarking.orgWatts, Fewer Is BetterIndigoBench 4.4CPU Power Consumption Monitor100200300400500

easyWave

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200Threadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X20406080100SE +/- 0.16, N = 3SE +/- 0.13, N = 3SE +/- 0.19, N = 3SE +/- 0.05, N = 321.0335.2974.16110.111. (CXX) g++ options: -O3 -fopenmp
MinAvgMaxRyzen 9 7950X3D16.778.595.1Ryzen 9 7950X20.3108.4148.8Threadripper 7970X67.3202.4235.6Threadripper 7980X68.6229.7278.0OpenBenchmarking.orgWatts, Fewer Is BettereasyWave r34CPU Power Consumption Monitor70140210280350

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D816243240SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 333.9721.3612.2311.76
OpenBenchmarking.orgM samples/s Per Watt, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.02320.04640.06960.09280.1160.1030.0870.0650.059
MinAvgMaxRyzen 9 7950X3D19.9135.3147.1Ryzen 9 7950X21.9208.1230.1Threadripper 7970X72.0326.9354.8Threadripper 7980X84.5329.8355.6OpenBenchmarking.orgWatts, Fewer Is BetterIndigoBench 4.4CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.18.1Variant: Wownero - Hash Count: 1MThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D10K20K30K40K50KSE +/- 1219.23, N = 15SE +/- 128.43, N = 3SE +/- 14.10, N = 3SE +/- 8.50, N = 345190.937197.720641.119594.71. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.18.1Variant: Wownero - Hash Count: 1MRyzen 9 7950X3DThreadripper 7980XThreadripper 7970XRyzen 9 7950X306090120150150.91146.43119.0897.00
MinAvgMaxRyzen 9 7950X3D16.0129.8140.9Ryzen 9 7950X19.1212.8235.8Threadripper 7980X62.0308.6349.9Threadripper 7970X70.0312.4349.6OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.18.1CPU Power Consumption Monitor100200300400500

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 2.6Scene: DLSC - Acceleration: CPUThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D3691215SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 313.468.905.295.01MIN: 13.15 / MAX: 15.27MIN: 8.64 / MAX: 10.12MIN: 5.17 / MAX: 5.62MIN: 4.88 / MAX: 5.31
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.00920.01840.02760.03680.0460.0410.0370.0270.025
MinAvgMaxRyzen 9 7950X3D20.5137.1149.9Ryzen 9 7950X21.8208.9231.0Threadripper 7970X67.7326.2353.7Threadripper 7980X65.1331.7355.7OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor100200300400500

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Rubber O-Ring Seal InstallationThreadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D1530456075SE +/- 0.11, N = 3SE +/- 0.16, N = 3SE +/- 0.24, N = 3SE +/- 0.40, N = 351.0555.2562.4965.62
MinAvgMaxRyzen 9 7950X3D18.8128.9139.5Ryzen 9 7950X19.2200.8225.5Threadripper 7970X70.8316.1350.2Threadripper 7980X71.3323.1349.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUThreadripper 7970XThreadripper 7980X1.01032.02063.03094.04125.0515SE +/- 0.00, N = 3SE +/- 0.00, N = 33.474.49MIN: 2.2 / MAX: 24.47MIN: 2.65 / MAX: 27.481. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X67.9331.7355.6Threadripper 7980X84.4332.0355.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUThreadripper 7980XThreadripper 7970X3K6K9K12K15KSE +/- 7.00, N = 3SE +/- 12.28, N = 314224.409212.021. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUThreadripper 7970XThreadripper 7980X0.08550.1710.25650.3420.4275SE +/- 0.00, N = 3SE +/- 0.00, N = 30.300.38MIN: 0.17 / MAX: 26.96MIN: 0.17 / MAX: 25.51. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7980X83.3330.7355.6Threadripper 7970X70.2331.2352.5OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUThreadripper 7980XThreadripper 7970X20K40K60K80K100KSE +/- 113.36, N = 3SE +/- 51.46, N = 3116361.8283081.661. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Layered HalfspaceThreadripper 7980XRyzen 9 7950X3DRyzen 9 7950X20406080100SE +/- 0.07, N = 3SE +/- 0.37, N = 3SE +/- 0.49, N = 323.4674.3676.941. (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
MinAvgMaxRyzen 9 7950X3D17.2120.8133.2Ryzen 9 7950X20.5186.3206.0Threadripper 7980X80.1302.2349.7OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.0CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUThreadripper 7970XThreadripper 7980X918273645SE +/- 0.01, N = 3SE +/- 0.17, N = 329.8237.76MIN: 19.09 / MAX: 55.59MIN: 22.01 / MAX: 60.71. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X70.0329.5354.8Threadripper 7980X84.1331.9355.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUThreadripper 7980XThreadripper 7970X400800120016002000SE +/- 7.59, N = 3SE +/- 0.30, N = 31694.011072.281. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUThreadripper 7970XThreadripper 7980X0.12150.2430.36450.4860.6075SE +/- 0.00, N = 3SE +/- 0.00, N = 30.420.54MIN: 0.23 / MAX: 22.06MIN: 0.23 / MAX: 28.011. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X70.3331.1353.8Threadripper 7980X81.5331.8352.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUThreadripper 7980XThreadripper 7970X20K40K60K80K100KSE +/- 95.03, N = 3SE +/- 61.51, N = 389281.4962357.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUThreadripper 7970XThreadripper 7980X918273645SE +/- 0.29, N = 3SE +/- 0.05, N = 323.4937.73MIN: 14.87 / MAX: 49.92MIN: 17.58 / MAX: 73.451. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X68.6330.7355.9Threadripper 7980X84.6332.2352.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUThreadripper 7980XThreadripper 7970X400800120016002000SE +/- 2.01, N = 3SE +/- 16.82, N = 31693.651361.631. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUThreadripper 7970XThreadripper 7980X246810SE +/- 0.02, N = 3SE +/- 0.01, N = 35.166.74MIN: 3.13 / MAX: 31.95MIN: 3.79 / MAX: 28.451. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X65.6331.4355.6Threadripper 7980X80.9331.6355.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUThreadripper 7980XThreadripper 7970X10002000300040005000SE +/- 3.26, N = 3SE +/- 12.16, N = 34738.283095.871. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUThreadripper 7970XThreadripper 7980X816243240SE +/- 0.17, N = 3SE +/- 0.17, N = 314.3232.69MIN: 4.24 / MAX: 45.38MIN: 8.61 / MAX: 79.61. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X69.1326.4355.1Threadripper 7980X84.2332.0356.7OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUThreadripper 7970XThreadripper 7980X2004006008001000SE +/- 13.58, N = 3SE +/- 4.99, N = 31115.20976.191. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUThreadripper 7970XThreadripper 7980X0.71551.4312.14652.8623.5775SE +/- 0.01, N = 3SE +/- 0.00, N = 32.443.18MIN: 1.52 / MAX: 24.26MIN: 1.95 / MAX: 24.981. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X66.4330.5355.6Threadripper 7980X83.7331.8352.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUThreadripper 7980XThreadripper 7970X2K4K6K8K10KSE +/- 13.88, N = 3SE +/- 11.85, N = 310021.496530.761. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUThreadripper 7970XThreadripper 7980X48121620SE +/- 0.01, N = 3SE +/- 0.01, N = 312.4716.17MIN: 6.5 / MAX: 30.63MIN: 7.78 / MAX: 40.111. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X72.7330.7355.9Threadripper 7980X84.1331.8351.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUThreadripper 7980XThreadripper 7970X8001600240032004000SE +/- 1.95, N = 3SE +/- 0.98, N = 33954.442563.321. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUThreadripper 7970XThreadripper 7980X246810SE +/- 0.00, N = 3SE +/- 0.01, N = 36.368.16MIN: 3.41 / MAX: 25.97MIN: 4.34 / MAX: 30.181. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxThreadripper 7970X70.7332.0355.6Threadripper 7980X83.6332.7355.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUThreadripper 7980XThreadripper 7970X2K4K6K8K10KSE +/- 8.70, N = 3SE +/- 2.30, N = 37834.685020.301. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

John The Ripper

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

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D3M6M9M12M15MSE +/- 28827.07, N = 3SE +/- 24027.76, N = 3SE +/- 5607.53, N = 3SE +/- 2962.73, N = 312401000799700046173334138333-lgmp-lgmp1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: MD5Threadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X8K16K24K32K40K37264.5633699.9124178.7621601.93
MinAvgMaxRyzen 9 7950X3D20.0122.8134.2Ryzen 9 7950X22.2213.7229.4Threadripper 7970X69.5330.7349.7Threadripper 7980X65.1332.8349.8OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: HMAC-SHA512Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D70M140M210M280M350MSE +/- 941055.49, N = 3SE +/- 624105.85, N = 3SE +/- 81486.88, N = 3SE +/- 177246.85, N = 3304003667247720333203175333190113667-lgmp-lgmp1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: HMAC-SHA512Ryzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X400K800K1200K1600K2000K2031904.061313119.481010258.62915423.23
MinAvgMaxRyzen 9 7950X3D21.393.6120.4Ryzen 9 7950X21.4154.7203.0Threadripper 7970X67.6245.2340.9Threadripper 7980X37.8332.1349.8OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D300K600K900K1200K1500KSE +/- 195.97, N = 3SE +/- 722.53, N = 3SE +/- 397.14, N = 3SE +/- 56.25, N = 31186776.9700571.8392731.6374201.9-lssl -lcrypto-lssl -lcrypto1. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgverify/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: RSA4096Threadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X80016002400320040003561.303103.632217.292105.85
MinAvgMaxRyzen 9 7950X3D20.8120.6133.4Ryzen 9 7950X19.3186.5212.1Threadripper 7970X71.4316.0349.6Threadripper 7980X77.7333.2355.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D9K18K27K36K45KSE +/- 66.09, N = 3SE +/- 13.54, N = 3SE +/- 16.41, N = 3SE +/- 14.69, N = 340456.326660.015012.913643.2-lssl -lcrypto-lssl -lcrypto1. (CC) gcc options: -pthread -m64 -O3 -ldl

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.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D510152025SE +/- 0.02515, N = 3SE +/- 0.02596, N = 3SE +/- 0.01071, N = 3SE +/- 0.02215, N = 322.1779013.705907.799227.42209
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.01580.03160.04740.06320.0790.0700.0650.0440.042
MinAvgMaxRyzen 9 7950X3D20.0114.4128.5Ryzen 9 7950X22.6186.9214.3Threadripper 7970X71.3310.9355.5Threadripper 7980X43.1315.9356.0OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/ao/real_timeThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D612182430SE +/- 0.06490, N = 3SE +/- 0.02226, N = 3SE +/- 0.02263, N = 3SE +/- 0.01121, N = 322.9964014.219808.097497.70482
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/ao/real_timeThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.01640.03280.04920.06560.0820.0730.0670.0460.044
MinAvgMaxRyzen 9 7950X3D19.7115.6129.3Ryzen 9 7950X21.2186.0214.1Threadripper 7970X72.4311.7355.7Threadripper 7980X82.4316.0354.5OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Tomographic ModelThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D612182430SE +/- 0.10, N = 4SE +/- 0.20, N = 11SE +/- 0.29, N = 510.0827.0827.241. (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
MinAvgMaxRyzen 9 7950X3D19.9115.7135.1Ryzen 9 7950X20.3181.5216.2Threadripper 7980X79.0265.3350.1OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.0CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D612182430SE +/- 0.05289, N = 3SE +/- 0.00059, N = 3SE +/- 0.01892, N = 3SE +/- 0.00706, N = 325.9010016.420209.330478.85012
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.01850.0370.05550.0740.09250.0820.0750.0530.050
MinAvgMaxRyzen 9 7950X3D18.8117.4131.9Ryzen 9 7950X19.9188.2215.7Threadripper 7970X67.1308.8355.5Threadripper 7980X83.1316.1355.9OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor100200300400500

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X246810SE +/- 0.021, N = 3SE +/- 0.006, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 38.0705.9052.6702.5851. (CXX) g++ options: -O3
OpenBenchmarking.orgNs Per Day Per Watt, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.00590.01180.01770.02360.02950.0260.0220.0190.014
MinAvgMaxRyzen 9 7950X3D18.2121.7137.5Ryzen 9 7950X21.2180.0217.3Threadripper 7970X70.3311.2350.0Threadripper 7980X81.5313.0350.1OpenBenchmarking.orgWatts, Fewer Is BetterGROMACS 2023CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.18.1Variant: Monero - Hash Count: 1MThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X9K18K27K36K45KSE +/- 562.87, N = 3SE +/- 286.12, N = 3SE +/- 21.30, N = 3SE +/- 89.86, N = 342793.929160.416167.814326.81. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.18.1Variant: Monero - Hash Count: 1MThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X306090120150139.05128.5391.9671.78
MinAvgMaxRyzen 9 7950X3D18.2125.8136.2Ryzen 9 7950X21.4199.6213.3Threadripper 7980X56.5307.8349.8Threadripper 7970X67.8317.1352.4OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.18.1CPU Power Consumption Monitor100200300400500

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Fishy Cat - Compute: CPU-OnlyThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D1530456075SE +/- 0.04, N = 3SE +/- 0.14, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 323.7136.4162.9466.25
MinAvgMaxRyzen 9 7950X3D18.3140.4152.6Ryzen 9 7950X21.3212.9233.2Threadripper 7980X87.1302.8349.6Threadripper 7970X69.1314.2353.1OpenBenchmarking.orgWatts, Fewer Is BetterBlender 3.6CPU Power Consumption Monitor100200300400500

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedThreadripper 7980XThreadripper 7970X50K100K150K200K250KSE +/- 390.24, N = 3SE +/- 206.88, N = 3243365.0155457.11. (CXX) g++ options: -O3 -march=native -fPIE -pie
OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedThreadripper 7980XThreadripper 7970X160320480640800750.62524.89
MinAvgMaxThreadripper 7970X70.0296.2349.6Threadripper 7980X82.8324.2355.6OpenBenchmarking.orgWatts, Fewer Is BetterQuantLib 1.32CPU Power Consumption Monitor100200300400500

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Cell Phone Drop TestThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X1224364860SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.54, N = 4SE +/- 0.30, N = 323.2027.9447.5452.86
MinAvgMaxRyzen 9 7950X3D18.6117.4134.0Ryzen 9 7950X18.0173.6197.4Threadripper 7980X84.1282.6349.7Threadripper 7970X69.4286.8349.7OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor100200300400500

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D1224364860SE +/- 0.25, N = 3SE +/- 0.09, N = 3SE +/- 0.29, N = 3SE +/- 0.67, N = 427.6030.2749.5353.981. (CXX) g++ options: -O2 -lOpenCL
MinAvgMaxRyzen 9 7950X3D18.792.6111.8Ryzen 9 7950X19.9150.7170.2Threadripper 7970X69.2246.2281.4Threadripper 7980X59.1283.7334.3OpenBenchmarking.orgWatts, Fewer Is BetterRodinia 3.1CPU Power Consumption Monitor80160240320400

RawTherapee

RawTherapee is a cross-platform, open-source multi-threaded RAW image processing program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeThreadripper 7970XRyzen 9 7950XThreadripper 7980XRyzen 9 7950X3D1020304050SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 338.3739.5641.0341.701. RawTherapee, version 5.9, command line.
MinAvgMaxRyzen 9 7950X3D19.463.580.6Ryzen 9 7950X22.996.3131.8Threadripper 7970X67.6146.1180.4Threadripper 7980X80.7193.6235.2OpenBenchmarking.orgWatts, Fewer Is BetterRawTherapeeCPU Power Consumption Monitor60120180240300

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution TimeThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X408012016020037.5153.45128.88163.771. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
MinAvgMaxRyzen 9 7950X3D21.2113.3131.8Ryzen 9 7950X19.9157.0204.7Threadripper 7980X81.5319.8350.4Threadripper 7970X70.7324.8349.8OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Mesh TimeThreadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D61218243021.1022.6623.8724.121. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Homogeneous HalfspaceThreadripper 7980XRyzen 9 7950X3DRyzen 9 7950X816243240SE +/- 0.14, N = 4SE +/- 0.35, N = 5SE +/- 0.34, N = 312.4834.6235.271. (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
MinAvgMaxRyzen 9 7950X3D18.6118.6134.4Ryzen 9 7950X20.5184.2212.4Threadripper 7980X63.4278.0354.8OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.0CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X30K60K90K120K150KSE +/- 8713.22, N = 12SE +/- 118.50, N = 4SE +/- 94.41, N = 3SE +/- 40.81, N = 3143837.97133061.2960336.2355883.161. (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 4.1.5
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CRyzen 9 7950X3DThreadripper 7970XThreadripper 7980XRyzen 9 7950X140280420560700662.52522.38494.83425.52
MinAvgMaxRyzen 9 7950X3D19.691.1101.6Ryzen 9 7950X19.7131.3150.2Threadripper 7970X66.1254.7316.2Threadripper 7980X66.6290.7352.4OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D1122334455SE +/- 0.39, N = 3SE +/- 0.42, N = 3SE +/- 0.34, N = 3SE +/- 0.40, N = 328.3432.7645.9847.08
MinAvgMaxRyzen 9 7950X3D19.5108.9148.6Ryzen 9 7950X20.4160.1228.6Threadripper 7970X68.5223.8349.7Threadripper 7980X84.0232.4350.0OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.1CPU Power Consumption Monitor100200300400500

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: BMW27 - Compute: CPU-OnlyThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D1224364860SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 318.5128.8350.3653.27
MinAvgMaxRyzen 9 7950X3D18.0138.9152.0Ryzen 9 7950X19.1211.4234.2Threadripper 7980X79.2295.8349.6Threadripper 7970X70.4309.9349.6OpenBenchmarking.orgWatts, Fewer Is BetterBlender 3.6CPU Power Consumption Monitor100200300400500

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FasterThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D48121620SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 316.8516.5516.2415.331. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FasterRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X0.03690.07380.11070.14760.18450.1640.1080.0730.066
MinAvgMaxRyzen 9 7950X3D19.593.4120.0Ryzen 9 7950X19.6150.5200.4Threadripper 7970X70.3226.1302.6Threadripper 7980X73.0255.4321.9OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.9CPU Power Consumption Monitor80160240320400

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 AtomsThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D0.18510.37020.55530.74040.9255SE +/- 0.00020, N = 3SE +/- 0.00034, N = 3SE +/- 0.00052, N = 3SE +/- 0.00222, N = 30.288480.441930.782030.82271
MinAvgMaxRyzen 9 7950X3D17.9136.3153.4Ryzen 9 7950X19.0206.7235.8Threadripper 7970X70.7304.2355.7Threadripper 7980X80.0313.9349.7OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 2.14CPU Power Consumption Monitor100200300400500

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUThreadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D0.43760.87521.31281.75042.188SE +/- 0.00575, N = 4SE +/- 0.04339, N = 15SE +/- 0.00372, N = 4SE +/- 0.00565, N = 41.110271.163541.734831.94479MIN: 0.97MIN: 0.86MIN: 1.52MIN: 1.731. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
MinAvgMaxRyzen 9 7950X3D16.882.6121.1Ryzen 9 7950X19.6156.8220.7Threadripper 7970X65.6247.2349.7Threadripper 7980X84.3294.8355.6OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.3CPU Power Consumption Monitor100200300400500

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D714212835SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 328.2024.4816.8315.38
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumRyzen 9 7950X3DThreadripper 7980XRyzen 9 7950XThreadripper 7970X0.02790.05580.08370.11160.13950.1240.0930.0850.083
MinAvgMaxRyzen 9 7950X3D19.3123.7138.1Ryzen 9 7950X19.9198.0222.9Threadripper 7970X69.6296.0341.5Threadripper 7980X56.4302.7348.8OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor100200300400500

John The Ripper

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

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D110K220K330K440K550KSE +/- 1248.32, N = 3SE +/- 504.05, N = 3SE +/- 310.64, N = 3SE +/- 108.67, N = 3496961309645174697164458-lgmp-lgmp1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X300600900120015001563.871397.54979.60913.66
MinAvgMaxRyzen 9 7950X3D19.5117.7132.1Ryzen 9 7950X21.9191.2218.9Threadripper 7970X68.6316.1349.7Threadripper 7980X71.6317.8349.7OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D30K60K90K120K150KSE +/- 456.52, N = 3SE +/- 154.01, N = 3SE +/- 31.63, N = 3SE +/- 32.05, N = 3139601840134771845122-lgmp-lgmp1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: bcryptThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X100200300400500439.59410.14283.56273.16
MinAvgMaxRyzen 9 7950X3D19.8108.1123.4Ryzen 9 7950X20.1171.0200.9Threadripper 7970X69.5295.9349.7Threadripper 7980X74.9317.6349.7OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D30K60K90K120K150KSE +/- 403.13, N = 3SE +/- 133.58, N = 3SE +/- 3.84, N = 3SE +/- 20.99, N = 3139632840224749844945-lgmp-lgmp1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X90180270360450437.74415.93283.96277.84

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 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 512Threadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D120M240M360M480M600MSE +/- 1585097.26, N = 3SE +/- 2608833.29, N = 3SE +/- 387742.76, N = 3SE +/- 242693.22, N = 35484500005367166674260966674065100001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 512Ryzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X700K1400K2100K2800K3500K3176695.472160622.961757868.431700167.60
MinAvgMaxRyzen 9 7950X3D19.1128.0147.5Ryzen 9 7950X20.2197.2227.1Threadripper 7970X67.1312.0349.7Threadripper 7980X80.9315.7349.7OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor100200300400500

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesRyzen 9 7950XRyzen 9 7950X3DThreadripper 7970XThreadripper 7980X1020304050SE +/- 0.06, N = 3SE +/- 0.25, N = 3SE +/- 0.32, N = 3SE +/- 0.03, N = 340.841.442.743.2
MinAvgMaxRyzen 9 7950X3D19.943.651.8Ryzen 9 7950X21.353.960.0Threadripper 7970X68.8113.6120.6Threadripper 7980X78.5156.2169.6OpenBenchmarking.orgWatts, Fewer Is BetterPyPerformance 1.0.0CPU Power Consumption Monitor50100150200250

Intel Open Image Denoise

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D0.52881.05761.58642.11522.644SE +/- 0.01, N = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.351.640.910.87
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.00180.00360.00540.00720.0090.0080.0080.0060.005
MinAvgMaxRyzen 9 7950X3D19.0112.1125.4Ryzen 9 7950X21.0175.6204.1Threadripper 7980X52.9281.3355.6Threadripper 7970X65.6291.3349.3OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 2.1CPU Power Consumption Monitor100200300400500

Natron

Natron is an open-source, cross-platform compositing software for visual effects (VFX) and motion graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterNatron 2.4.3Input: SpaceshipThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D246810SE +/- 0.03, N = 4SE +/- 0.06, N = 11SE +/- 0.06, N = 3SE +/- 0.03, N = 38.38.36.26.1
OpenBenchmarking.orgFPS Per Watt, More Is BetterNatron 2.4.3Input: SpaceshipRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X0.01580.03160.04740.06320.0790.0700.0460.0400.034
MinAvgMaxRyzen 9 7950X3D16.386.7135.1Ryzen 9 7950X22.3136.3214.5Threadripper 7970X66.8206.2349.9Threadripper 7980X83.2243.7354.2OpenBenchmarking.orgWatts, Fewer Is BetterNatron 2.4.3CPU Power Consumption Monitor100200300400500

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 4KThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X50100150200250SE +/- 0.93, N = 7SE +/- 6.10, N = 15SE +/- 1.02, N = 15SE +/- 0.69, N = 15231.12224.91115.50111.891. (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 4KRyzen 9 7950X3DThreadripper 7970XThreadripper 7980XRyzen 9 7950X0.37460.74921.12381.49841.8731.6651.4231.3391.039
MinAvgMaxRyzen 9 7950X3D19.369.4118.1Ryzen 9 7950X18.4107.7192.4Threadripper 7970X67.8158.1347.8Threadripper 7980X51.2172.6336.5OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor100200300400500

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileRyzen 9 7950XRyzen 9 7950X3DThreadripper 7970XThreadripper 7980X1530456075SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.69, N = 3SE +/- 0.18, N = 362.563.666.066.3
MinAvgMaxRyzen 9 7950X3D19.442.648.5Ryzen 9 7950X17.243.159.8Threadripper 7970X68.7112.5120.4Threadripper 7980X79.7155.6169.4OpenBenchmarking.orgWatts, Fewer Is BetterPyPerformance 1.0.0CPU Power Consumption Monitor50100150200250

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.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D110K220K330K440K550KSE +/- 1800.65, N = 3SE +/- 240.20, N = 4SE +/- 296.67, N = 3SE +/- 604.03, N = 35284273242561819291746261. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS Per Watt, More Is Better7-Zip Compression 22.01Test: Decompression RatingThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X4008001200160020001772.061672.871161.921149.02
MinAvgMaxRyzen 9 7950X3D20.3104.4137.6Ryzen 9 7950X20.9158.3213.2Threadripper 7970X68.1279.1349.6Threadripper 7980X84.5298.2352.2OpenBenchmarking.orgWatts, Fewer Is Better7-Zip Compression 22.01CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X100K200K300K400K500KSE +/- 4999.82, N = 3SE +/- 3696.50, N = 4SE +/- 289.40, N = 3SE +/- 53.43, N = 34611833444341850151791361. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

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.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ExhaustiveThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D1.17582.35163.52744.70325.879SE +/- 0.0156, N = 4SE +/- 0.0081, N = 3SE +/- 0.0008, N = 3SE +/- 0.0008, N = 35.22573.28481.83961.69371. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.0Preset: ExhaustiveThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.00470.00940.01410.01880.02350.0210.0140.0120.010
MinAvgMaxRyzen 9 7950X3D17.5118.2141.8Ryzen 9 7950X18.9191.7231.1Threadripper 7980X79.1252.2349.6Threadripper 7970X68.5267.2349.6OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.0CPU Power Consumption Monitor100200300400500

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D816243240SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 335.5131.4923.0921.091. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumRyzen 9 7950X3DThreadripper 7980XRyzen 9 7950XThreadripper 7970X0.04140.08280.12420.16560.2070.1840.1250.1250.113
MinAvgMaxRyzen 9 7950X3D18.5114.5133.0Ryzen 9 7950X20.9184.6215.1Threadripper 7970X69.2277.7327.1Threadripper 7980X81.0284.6341.0OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor80160240320400

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark capable of computing Pi to trillions of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.7.10.9513Pi Digits To Calculate: 500MThreadripper 7970XThreadripper 7980XRyzen 9 7950X3DRyzen 9 7950X3691215SE +/- 0.003, N = 7SE +/- 0.074, N = 15SE +/- 0.004, N = 5SE +/- 0.007, N = 54.4274.8028.8099.069
MinAvgMaxRyzen 9 7950X3D17.179.0127.3Ryzen 9 7950X20.5132.8220.4Threadripper 7970X69.0192.7342.6Threadripper 7980X83.2216.4350.9OpenBenchmarking.orgWatts, Fewer Is BetterY-Cruncher 0.7.10.9513CPU Power Consumption Monitor100200300400500

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsRyzen 9 7950XRyzen 9 7950X3DThreadripper 7980XThreadripper 7970X3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 310.410.711.011.1
MinAvgMaxRyzen 9 7950X3D19.042.046.7Ryzen 9 7950X18.152.461.3Threadripper 7970X67.9111.1120.4Threadripper 7980X82.6153.8171.4OpenBenchmarking.orgWatts, Fewer Is BetterPyPerformance 1.0.0CPU Power Consumption Monitor50100150200250

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X3691215SE +/- 0.006, N = 8SE +/- 0.079, N = 15SE +/- 0.103, N = 15SE +/- 0.027, N = 54.1424.7847.5669.0081. (CXX) g++ options: -O2 -lOpenCL
MinAvgMaxRyzen 9 7950X3D17.374.3111.9Ryzen 9 7950X20.4103.5150.7Threadripper 7970X67.1168.2286.5Threadripper 7980X46.8201.5349.7OpenBenchmarking.orgWatts, Fewer Is BetterRodinia 3.1CPU Power Consumption Monitor100200300400500

Timed Mesa Compilation

This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To CompileThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X510152025SE +/- 0.05, N = 4SE +/- 0.12, N = 4SE +/- 0.01, N = 3SE +/- 0.06, N = 315.2916.1921.4921.64
MinAvgMaxRyzen 9 7950X3D17.3102.0145.9Ryzen 9 7950X21.0149.5227.0Threadripper 7970X69.8206.7349.7Threadripper 7980X81.3216.0350.0OpenBenchmarking.orgWatts, Fewer Is BetterTimed Mesa Compilation 21.0CPU Power Consumption Monitor100200300400500

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 TimesRyzen 9 7950XThreadripper 7980XThreadripper 7970XRyzen 9 7950X3D130260390520650SE +/- 3.97, N = 4SE +/- 4.97, N = 4SE +/- 2.95, N = 4SE +/- 5.25, N = 7535565579580
MinAvgMaxRyzen 9 7950X3D19.036.141.3Ryzen 9 7950X18.447.757.8Threadripper 7970X67.0108.2120.8Threadripper 7980X82.2146.6168.5OpenBenchmarking.orgWatts, Fewer Is BetterPyBench 2018-02-16CPU Power Consumption Monitor50100150200250

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Single-ThreadedThreadripper 7980XThreadripper 7970X9001800270036004500SE +/- 6.66, N = 3SE +/- 11.48, N = 34348.94296.91. (CXX) g++ options: -O3 -march=native -fPIE -pie
OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterQuantLib 1.32Configuration: Single-ThreadedThreadripper 7970XThreadripper 7980X91827364538.8328.39
MinAvgMaxThreadripper 7970X67.7110.7119.8Threadripper 7980X83.9153.2171.1OpenBenchmarking.orgWatts, Fewer Is BetterQuantLib 1.32CPU Power Consumption Monitor50100150200250

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 8 - Input: Bosphorus 4KThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D306090120150SE +/- 0.97, N = 15SE +/- 0.73, N = 6SE +/- 0.41, N = 6SE +/- 0.39, N = 6126.21119.5886.1681.681. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 8 - Input: Bosphorus 4KRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X0.22970.45940.68910.91881.14851.0210.6580.6540.619
MinAvgMaxRyzen 9 7950X3D20.080.0123.6Ryzen 9 7950X18.1130.9217.0Threadripper 7970X70.9182.7325.5Threadripper 7980X54.8203.8341.4OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.7CPU Power Consumption Monitor80160240320400

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: CrownThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D20406080100SE +/- 0.21, N = 6SE +/- 0.16, N = 4SE +/- 0.07, N = 3SE +/- 0.03, N = 393.5359.5733.9233.68MIN: 91.58 / MAX: 96.69MIN: 58.56 / MAX: 61.24MIN: 33.44 / MAX: 35.08MIN: 33.34 / MAX: 34.54
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: CrownThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.08120.16240.24360.32480.4060.3610.2760.2130.174
MinAvgMaxRyzen 9 7950X3D19.0122.2143.3Ryzen 9 7950X20.9195.3234.4Threadripper 7980X76.0259.0349.7Threadripper 7970X67.8279.3349.7OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian DragonThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X20406080100SE +/- 0.24, N = 6SE +/- 0.07, N = 5SE +/- 0.05, N = 3SE +/- 0.01, N = 3103.9668.8737.3734.91MIN: 88.88 / MAX: 106.23MIN: 68.28 / MAX: 70.14MIN: 37.01 / MAX: 38.06MIN: 34.6 / MAX: 35.91
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian DragonThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.09270.18540.27810.37080.46350.4120.3310.2550.199
MinAvgMaxRyzen 9 7950X3D19.4112.8135.4Ryzen 9 7950X21.1175.4208.8Threadripper 7980X76.4252.3349.8Threadripper 7970X68.0269.8349.7OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3CPU Power Consumption Monitor100200300400500

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 4KThreadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D918273645SE +/- 0.14, N = 4SE +/- 0.09, N = 4SE +/- 0.13, N = 3SE +/- 0.06, N = 338.8938.1335.6734.611. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterx265 3.4Video Input: Bosphorus 4KRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X0.08750.1750.26250.350.43750.3890.2450.1930.169
MinAvgMaxRyzen 9 7950X3D18.488.9110.7Ryzen 9 7950X23.4145.9187.6Threadripper 7970X69.9201.9266.0Threadripper 7980X74.1225.9284.3OpenBenchmarking.orgWatts, Fewer Is Betterx265 3.4CPU Power Consumption Monitor70140210280350

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: unsharp-maskRyzen 9 7950XRyzen 9 7950X3DThreadripper 7970XThreadripper 7980X510152025SE +/- 0.02, N = 4SE +/- 0.05, N = 4SE +/- 0.08, N = 3SE +/- 0.14, N = 314.3715.3117.4618.49
MinAvgMaxRyzen 9 7950X3D16.849.062.2Threadripper 7970X66.5125.8148.7Threadripper 7980X80.3170.8208.5OpenBenchmarking.orgWatts, Fewer Is BetterGIMP 2.10.34CPU Power Consumption Monitor60120180240300

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 2.6Scene: Rainbow Colors and Prism - Acceleration: CPUThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D816243240SE +/- 1.02, N = 15SE +/- 0.15, N = 6SE +/- 0.07, N = 5SE +/- 0.15, N = 533.7631.8019.8018.98MIN: 24.06 / MAX: 37.38MIN: 27.87 / MAX: 33.03MIN: 17.6 / MAX: 20.28MIN: 16.87 / MAX: 19.59
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: CPURyzen 9 7950X3DThreadripper 7980XRyzen 9 7950XThreadripper 7970X0.04430.08860.13290.17720.22150.1970.1420.1360.135
MinAvgMaxRyzen 9 7950X3D18.796.2138.5Ryzen 9 7950X20.6146.0214.7Threadripper 7970X72.4235.1349.4Threadripper 7980X57.4237.4349.9OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor100200300400500

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: resizeRyzen 9 7950XRyzen 9 7950X3DThreadripper 7970XThreadripper 7980X48121620SE +/- 0.15, N = 4SE +/- 0.08, N = 4SE +/- 0.16, N = 4SE +/- 0.08, N = 313.9614.3814.5216.39
MinAvgMaxRyzen 9 7950X3D19.149.570.4Threadripper 7970X67.3121.9156.5Threadripper 7980X78.9175.2251.6OpenBenchmarking.orgWatts, Fewer Is BetterGIMP 2.10.34CPU Power Consumption Monitor60120180240300

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.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ThoroughThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D1122334455SE +/- 0.09, N = 6SE +/- 0.06, N = 5SE +/- 0.01, N = 4SE +/- 0.00, N = 349.8031.5917.6416.081. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.0Preset: ThoroughThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.0520.1040.1560.2080.260.2310.1520.1380.107
MinAvgMaxRyzen 9 7950X3D19.7106.0140.1Ryzen 9 7950X19.7165.3229.9Threadripper 7980X79.6215.6349.2Threadripper 7970X67.6228.6349.2OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.0CPU Power Consumption Monitor100200300400500

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 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 4KThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D50100150200250SE +/- 7.34, N = 15SE +/- 3.47, N = 15SE +/- 0.53, N = 6SE +/- 0.56, N = 6214.68176.58103.6999.441. (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 4KRyzen 9 7950X3DThreadripper 7980XThreadripper 7970XRyzen 9 7950X0.2590.5180.7771.0361.2951.1511.1460.9510.769
MinAvgMaxRyzen 9 7950X3D17.186.4139.3Ryzen 9 7950X20.1134.8234.3Threadripper 7970X66.8185.6355.1Threadripper 7980X60.1187.3355.3OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor100200300400500

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: auto-levelsRyzen 9 7950XRyzen 9 7950X3DThreadripper 7970XThreadripper 7980X48121620SE +/- 0.03, N = 4SE +/- 0.05, N = 4SE +/- 0.08, N = 4SE +/- 0.04, N = 411.8612.8013.9614.43
MinAvgMaxRyzen 9 7950X3D17.545.057.6Threadripper 7970X44.1117.5138.7Threadripper 7980X81.9159.2189.8OpenBenchmarking.orgWatts, Fewer Is BetterGIMP 2.10.34CPU Power Consumption Monitor50100150200250

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.

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D306090120150SE +/- 0.27, N = 7SE +/- 0.18, N = 6SE +/- 0.01, N = 4SE +/- 0.01, N = 4158.1995.7953.3451.431. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgBillion Interactions/s Per Watt, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1Threadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.15320.30640.45960.61280.7660.6810.4350.3700.310
MinAvgMaxRyzen 9 7950X3D16.8118.2143.9Ryzen 9 7950X20.1172.2215.8Threadripper 7980X63.3232.1349.6Threadripper 7970X68.4258.9349.7OpenBenchmarking.orgWatts, Fewer Is BetterminiBUDE 20210901CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D8001600240032004000SE +/- 6.64, N = 7SE +/- 4.40, N = 6SE +/- 0.37, N = 4SE +/- 0.15, N = 43954.682394.661333.441285.781. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X15K30K45K60K75KSE +/- 254.39, N = 6SE +/- 123.06, N = 6SE +/- 17.99, N = 4SE +/- 7.92, N = 471652.9370557.0627783.6227769.011. (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 4.1.5
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CThreadripper 7970XRyzen 9 7950X3DThreadripper 7980XRyzen 9 7950X80160240320400357.01339.83306.92229.48
MinAvgMaxRyzen 9 7950X3D17.681.8105.1Ryzen 9 7950X18.9121.0158.1Threadripper 7970X70.1197.6309.4Threadripper 7980X58.8233.5350.1OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor100200300400500

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D1632486480SE +/- 0.14, N = 5SE +/- 0.05, N = 5SE +/- 0.05, N = 4SE +/- 0.04, N = 470.5360.9946.1042.07
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastRyzen 9 7950X3DRyzen 9 7950XThreadripper 7980XThreadripper 7970X0.08980.17960.26940.35920.4490.3990.2700.2680.238
MinAvgMaxRyzen 9 7950X3D19.6105.4133.7Ryzen 9 7950X21.6170.8222.7Threadripper 7970X69.8256.4341.8Threadripper 7980X70.4263.0349.8OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D1632486480SE +/- 0.09, N = 6SE +/- 0.06, N = 5SE +/- 0.09, N = 5SE +/- 0.07, N = 573.9071.9358.3753.23
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X0.11990.23980.35970.47960.59950.5330.3600.3030.287
MinAvgMaxRyzen 9 7950X3D16.899.8130.1Ryzen 9 7950X20.7162.1224.6Threadripper 7970X70.8237.4327.1Threadripper 7980X44.9257.7349.7OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CThreadripper 7970XThreadripper 7980XRyzen 9 7950X3DRyzen 9 7950X6K12K18K24K30KSE +/- 188.56, N = 7SE +/- 76.67, N = 5SE +/- 43.31, N = 4SE +/- 82.86, N = 426421.3416008.3212316.7911354.781. (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 4.1.5
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950XThreadripper 7980X306090120150148.34130.5296.8660.25
MinAvgMaxRyzen 9 7950X3D19.583.0107.2Ryzen 9 7950X19.5117.2149.4Threadripper 7970X65.9202.4316.9Threadripper 7980X80.8265.7350.1OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor100200300400500

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D1632486480SE +/- 0.17, N = 6SE +/- 0.09, N = 5SE +/- 0.05, N = 4SE +/- 0.02, N = 472.5266.3850.3846.01
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastRyzen 9 7950X3DRyzen 9 7950XThreadripper 7980XThreadripper 7970X0.09770.19540.29310.39080.48850.4340.2950.2770.264
MinAvgMaxRyzen 9 7950X3D17.5106.0136.3Ryzen 9 7950X21.1170.6226.1Threadripper 7970X67.1251.6342.2Threadripper 7980X80.5262.0349.7OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor100200300400500

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D20406080100SE +/- 0.26, N = 6SE +/- 0.14, N = 5SE +/- 0.05, N = 4SE +/- 0.02, N = 479.6365.8750.4345.831. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastRyzen 9 7950X3DRyzen 9 7950XThreadripper 7980XThreadripper 7970X0.10980.21960.32940.43920.5490.4880.3270.3120.271
MinAvgMaxRyzen 9 7950X3D18.493.9120.7Ryzen 9 7950X21.1154.0205.8Threadripper 7970X71.4242.8329.4Threadripper 7980X70.1254.9352.0OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor100200300400500

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.34Test: rotateRyzen 9 7950XRyzen 9 7950X3DThreadripper 7970XThreadripper 7980X3691215SE +/- 0.01, N = 5SE +/- 0.02, N = 4SE +/- 0.01, N = 4SE +/- 0.02, N = 410.6011.1511.6511.82
MinAvgMaxRyzen 9 7950X3D19.043.253.5Threadripper 7970X68.1107.9132.3Threadripper 7980X81.6147.0179.9OpenBenchmarking.orgWatts, Fewer Is BetterGIMP 2.10.34CPU Power Consumption Monitor50100150200250

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X0.72681.45362.18042.90723.634SE +/- 0.00175, N = 5SE +/- 0.00112, N = 5SE +/- 0.00764, N = 5SE +/- 0.00303, N = 51.065341.128082.493853.23011MIN: 0.93MIN: 1.05MIN: 2.42MIN: 3.171. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
MinAvgMaxRyzen 9 7950X3D17.168.398.3Ryzen 9 7950X18.9103.4165.3Threadripper 7970X70.5190.6260.4Threadripper 7980X80.9268.5355.6OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.3CPU Power Consumption Monitor100200300400500

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D3691215SE +/- 0.014, N = 7SE +/- 0.010, N = 6SE +/- 0.026, N = 5SE +/- 0.023, N = 55.5737.8708.9629.3921. (CXX) g++ options: -O2 -lOpenCL
MinAvgMaxRyzen 9 7950X3D17.080.2119.6Ryzen 9 7950X21.4117.7180.2Threadripper 7970X68.2180.6275.0Threadripper 7980X52.0209.1349.7OpenBenchmarking.orgWatts, Fewer Is BetterRodinia 3.1CPU Power Consumption Monitor100200300400500

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super FastThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D20406080100SE +/- 0.86, N = 6SE +/- 0.08, N = 6SE +/- 0.07, N = 5SE +/- 0.05, N = 595.5284.4666.1860.391. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super FastRyzen 9 7950X3DRyzen 9 7950XThreadripper 7980XThreadripper 7970X0.14670.29340.44010.58680.73350.6520.4360.3910.364
MinAvgMaxRyzen 9 7950X3D18.492.6125.1Ryzen 9 7950X21.2151.6215.2Threadripper 7970X67.3232.0333.3Threadripper 7980X56.8244.1349.8OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X30K60K90K120K150KSE +/- 938.91, N = 8SE +/- 387.71, N = 7SE +/- 80.81, N = 4SE +/- 41.35, N = 3118372.2872927.7327340.7620740.011. (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 4.1.5
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X130260390520650590.51397.08325.61173.96
MinAvgMaxRyzen 9 7950X3D18.384.0107.7Ryzen 9 7950X22.7119.2144.4Threadripper 7970X70.0183.7288.9Threadripper 7980X72.3200.5349.7OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor100200300400500

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra FastThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D20406080100SE +/- 0.35, N = 7SE +/- 0.23, N = 7SE +/- 0.05, N = 6SE +/- 0.06, N = 699.7296.6585.6177.651. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra FastRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X0.20950.4190.62850.8381.04750.9310.6190.4650.420
MinAvgMaxRyzen 9 7950X3D19.983.4119.0Ryzen 9 7950X19.2138.4212.7Threadripper 7970X67.9207.8308.7Threadripper 7980X76.2237.5345.4OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor100200300400500

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 4KThreadripper 7970XThreadripper 7980XRyzen 9 7950X3DRyzen 9 7950X50100150200250SE +/- 0.32, N = 8SE +/- 1.19, N = 7SE +/- 0.26, N = 7SE +/- 0.08, N = 7240.15234.87123.52120.721. (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 4KRyzen 9 7950X3DThreadripper 7970XThreadripper 7980XRyzen 9 7950X0.40480.80961.21441.61922.0241.7991.5321.3581.142
MinAvgMaxRyzen 9 7950X3D18.068.7119.9Ryzen 9 7950X19.0105.7196.2Threadripper 7970X66.1156.8349.1Threadripper 7980X73.7172.9337.5OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 4KThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D50100150200250SE +/- 1.62, N = 7SE +/- 0.35, N = 7SE +/- 0.10, N = 6SE +/- 0.11, N = 6221.64205.49109.44108.881. (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 4KRyzen 9 7950X3DThreadripper 7970XThreadripper 7980XRyzen 9 7950X0.31860.63720.95581.27441.5931.4161.2201.2160.886
MinAvgMaxRyzen 9 7950X3D17.676.9129.6Ryzen 9 7950X20.3123.5217.0Threadripper 7970X68.2168.4354.9Threadripper 7980X61.0182.3353.5OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor100200300400500

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 1.0Encoder Speed: 6, LosslessThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D1.31292.62583.93875.25166.5645SE +/- 0.016, N = 8SE +/- 0.008, N = 8SE +/- 0.020, N = 7SE +/- 0.016, N = 74.5384.8255.6995.8351. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxRyzen 9 7950X3D18.067.2144.0Ryzen 9 7950X20.393.3233.7Threadripper 7970X67.9139.7351.6Threadripper 7980X76.9159.8348.8OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 1.0CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CThreadripper 7980XThreadripper 7970XRyzen 9 7950X3DRyzen 9 7950X15K30K45K60K75KSE +/- 379.64, N = 9SE +/- 169.74, N = 9SE +/- 9.50, N = 6SE +/- 10.07, N = 667758.7665635.1824667.5323869.531. (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 4.1.5
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CThreadripper 7970XRyzen 9 7950X3DThreadripper 7980XRyzen 9 7950X100200300400500462.02395.90354.40268.44
MinAvgMaxRyzen 9 7950X3D19.362.387.7Ryzen 9 7950X17.388.9128.0Threadripper 7970X66.3142.1254.9Threadripper 7980X65.7191.2350.2OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor100200300400500

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.orgMT/s, More Is BetterASTC Encoder 4.0Preset: MediumThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D80160240320400SE +/- 0.18, N = 9SE +/- 0.11, N = 8SE +/- 0.05, N = 7SE +/- 0.06, N = 7378.22247.96141.01129.221. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.0Preset: MediumThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X0.53511.07021.60532.14042.67552.3781.7841.6461.320
MinAvgMaxRyzen 9 7950X3D18.672.4140.6Ryzen 9 7950X16.5106.8231.1Threadripper 7970X67.1150.6346.3Threadripper 7980X82.8159.1348.5OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.0CPU Power Consumption Monitor100200300400500

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 13 - Input: Bosphorus 4KThreadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D60120180240300SE +/- 0.78, N = 8SE +/- 1.61, N = 8SE +/- 0.40, N = 8SE +/- 0.27, N = 8259.59226.11185.89181.941. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 13 - Input: Bosphorus 4KRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X0.69751.3952.09252.793.48753.1002.0561.8971.361
MinAvgMaxRyzen 9 7950X3D17.358.7112.6Ryzen 9 7950X20.890.4197.6Threadripper 7970X67.6136.8297.6Threadripper 7980X63.9166.2308.1OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.7CPU Power Consumption Monitor80160240320400

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 12 - Input: Bosphorus 4KThreadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D60120180240300SE +/- 0.59, N = 8SE +/- 1.67, N = 8SE +/- 0.34, N = 8SE +/- 0.24, N = 8260.80228.23185.21182.181. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 12 - Input: Bosphorus 4KRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X0.70471.40942.11412.81883.52353.1322.0521.9061.394
MinAvgMaxRyzen 9 7950X3D17.758.2112.1Ryzen 9 7950X15.990.2194.6Threadripper 7970X69.2136.8298.5Threadripper 7980X63.0163.7306.2OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.7CPU Power Consumption Monitor80160240320400

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 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 4KThreadripper 7970XThreadripper 7980XRyzen 9 7950X3DRyzen 9 7950X60120180240300SE +/- 1.67, N = 9SE +/- 1.49, N = 8SE +/- 0.27, N = 8SE +/- 0.14, N = 8273.75214.30171.70169.181. (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 4KRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950XThreadripper 7980X0.57471.14941.72412.29882.87352.5541.8051.6731.241
MinAvgMaxRyzen 9 7950X3D19.967.2128.5Ryzen 9 7950X19.2101.1210.3Threadripper 7970X67.9151.7335.1Threadripper 7980X64.7172.7311.9OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor80160240320400

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.4.2Test: Boat - Acceleration: CPU-onlyThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D0.68961.37922.06882.75843.448SE +/- 0.017, N = 15SE +/- 0.007, N = 10SE +/- 0.005, N = 9SE +/- 0.003, N = 81.7171.9492.8233.065
MinAvgMaxRyzen 9 7950X3D19.656.8130.4Threadripper 7970X67.1127.9320.3Threadripper 7980X79.3144.3301.5OpenBenchmarking.orgWatts, Fewer Is BetterDarktable 4.4.2CPU Power Consumption Monitor80160240320400

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D16003200480064008000SE +/- 114.31, N = 15SE +/- 44.79, N = 15SE +/- 23.43, N = 10SE +/- 20.05, N = 97568.145249.283057.302935.381. (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 4.1.5
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CThreadripper 7980XRyzen 9 7950X3DThreadripper 7970XRyzen 9 7950X112233445549.9943.7735.0931.35
MinAvgMaxRyzen 9 7950X3D19.167.1136.5Ryzen 9 7950X12.797.5212.3Threadripper 7970X67.1149.6349.9Threadripper 7980X63.1151.4349.7OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor100200300400500

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 1.0Encoder Speed: 6Threadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D0.76771.53542.30313.07083.8385SE +/- 0.006, N = 10SE +/- 0.006, N = 10SE +/- 0.007, N = 9SE +/- 0.013, N = 92.2042.4593.2593.4121. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxRyzen 9 7950X3D15.963.1145.1Ryzen 9 7950X19.988.1230.0Threadripper 7970X67.4133.6349.5Threadripper 7980X79.0147.2336.2OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 1.0CPU Power Consumption Monitor100200300400500

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.4.2Test: Server Room - Acceleration: CPU-onlyThreadripper 7970XThreadripper 7980XRyzen 9 7950XRyzen 9 7950X3D0.37760.75521.13281.51041.888SE +/- 0.003, N = 10SE +/- 0.005, N = 10SE +/- 0.003, N = 10SE +/- 0.002, N = 101.1861.4071.6531.678
MinAvgMaxRyzen 9 7950X3D17.744.2110.8Threadripper 7970X66.5105.6226.6Threadripper 7980X79.2141.1291.7OpenBenchmarking.orgWatts, Fewer Is BetterDarktable 4.4.2CPU Power Consumption Monitor70140210280350

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.4.2Test: Masskrug - Acceleration: CPU-onlyThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D0.43070.86141.29211.72282.1535SE +/- 0.003, N = 11SE +/- 0.001, N = 11SE +/- 0.002, N = 10SE +/- 0.003, N = 101.0991.2101.8571.914
MinAvgMaxRyzen 9 7950X3D17.946.7106.4Threadripper 7970X67.9108.4212.2Threadripper 7980X78.1128.4249.5OpenBenchmarking.orgWatts, Fewer Is BetterDarktable 4.4.2CPU Power Consumption Monitor60120180240300

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.4.2Test: Server Rack - Acceleration: CPU-onlyThreadripper 7980XThreadripper 7970XRyzen 9 7950XRyzen 9 7950X3D0.03940.07880.11820.15760.197SE +/- 0.001, N = 13SE +/- 0.000, N = 13SE +/- 0.001, N = 15SE +/- 0.000, N = 130.0770.0960.1720.175
MinAvgMaxRyzen 9 7950X3D17.728.861.8Threadripper 7970X67.682.3129.6Threadripper 7980X80.7105.3173.2OpenBenchmarking.orgWatts, Fewer Is BetterDarktable 4.4.2CPU Power Consumption Monitor50100150200250

Meta Performance Per Watts

OpenBenchmarking.orgPerformance Per Watts, More Is BetterMeta Performance Per WattsPerformance Per WattsThreadripper 7980XThreadripper 7970X120024003600480060005592.644373.29

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringRyzen 9 7950X3DRyzen 9 7950XThreadripper 7970XThreadripper 7980X60120180240300Min: 15.29 / Avg: 94.49 / Max: 153.39Min: 9.58 / Avg: 146.31 / Max: 235.98Min: 35.97 / Avg: 281.29 / Max: 357.58Min: 37.84 / Avg: 294.72 / Max: 358.44

178 Results Shown

OpenVKL
High Performance Conjugate Gradient
OpenFOAM:
  drivaerFastback, Medium Mesh Size - Execution Time
  drivaerFastback, Medium Mesh Size - Mesh Time
Timed Linux Kernel Compilation
OpenVINO:
  Road Segmentation ADAS FP16 - CPU:
    ms
    FPS
  Person Detection FP16 - CPU:
    ms
    FPS
TensorFlow
Timed Node.js Compilation
Timed LLVM Compilation
Rodinia
Stockfish
OpenVINO:
  Person Detection FP32 - CPU:
    ms
    FPS
  Machine Translation EN To DE FP16 - CPU:
    ms
    FPS
  Road Segmentation ADAS FP16-INT8 - CPU:
    ms
    FPS
nginx
OpenSSL:
  SHA256
  ChaCha20-Poly1305
  AES-256-GCM
  AES-128-GCM
  ChaCha20
  SHA512
OSPRay:
  particle_volume/pathtracer/real_time
  particle_volume/scivis/real_time
OpenVINO:
  Person Vehicle Bike Detection FP16 - CPU:
    ms
    FPS
PostgreSQL:
  100 - 1000 - Read Only - Average Latency
  100 - 1000 - Read Only
  100 - 1000 - Read Write - Average Latency
  100 - 1000 - Read Write
OpenRadioss
asmFish
Timed Godot Game Engine Compilation
NAS Parallel Benchmarks
OSPRay
nginx
OpenRadioss
oneDNN:
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Recurrent Neural Network Training - f32 - CPU
Ngspice
TensorFlow
oneDNN:
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - f32 - CPU
NAS Parallel Benchmarks
Chaos Group V-RAY
Ngspice
miniBUDE:
  OpenMP - BM2:
    Billion Interactions/s
    GFInst/s
VVenC
libavif avifenc
Node.js V8 Web Tooling Benchmark
Memcached
SPECFEM3D
Memcached
LuxCoreRender
OpenVINO:
  Face Detection FP16 - CPU:
    ms
    FPS
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
LuxCoreRender
Rodinia
LuxCoreRender
IndigoBench
easyWave
IndigoBench
Xmrig
LuxCoreRender
OpenRadioss
OpenVINO:
  Face Detection Retail FP16-INT8 - CPU:
    ms
    FPS
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    ms
    FPS
SPECFEM3D
OpenVINO:
  Handwritten English Recognition FP16-INT8 - CPU:
    ms
    FPS
  Age Gender Recognition Retail 0013 FP16 - CPU:
    ms
    FPS
  Handwritten English Recognition FP16 - CPU:
    ms
    FPS
  Vehicle Detection FP16-INT8 - CPU:
    ms
    FPS
  Vehicle Detection FP16 - CPU:
    ms
    FPS
  Face Detection Retail FP16 - CPU:
    ms
    FPS
  Weld Porosity Detection FP16 - CPU:
    ms
    FPS
  Weld Porosity Detection FP16-INT8 - CPU:
    ms
    FPS
John The Ripper:
  MD5
  HMAC-SHA512
OpenSSL:
  RSA4096:
    verify/s
    sign/s
OSPRay:
  gravity_spheres_volume/dim_512/scivis/real_time
  gravity_spheres_volume/dim_512/ao/real_time
SPECFEM3D
OSPRay
GROMACS
Xmrig
Blender
QuantLib
OpenRadioss
Rodinia
RawTherapee
OpenFOAM:
  drivaerFastback, Small Mesh Size - Execution Time
  drivaerFastback, Small Mesh Size - Mesh Time
SPECFEM3D
NAS Parallel Benchmarks
Timed Linux Kernel Compilation
Blender
VVenC
NAMD
oneDNN
uvg266
John The Ripper:
  WPA PSK
  bcrypt
  Blowfish
Liquid-DSP
PyPerformance
Intel Open Image Denoise
Natron
SVT-VP9
PyPerformance
7-Zip Compression:
  Decompression Rating
  Compression Rating
ASTC Encoder
Kvazaar
Y-Cruncher
PyPerformance
Rodinia
Timed Mesa Compilation
PyBench
QuantLib
SVT-AV1
Embree:
  Pathtracer ISPC - Crown
  Pathtracer ISPC - Asian Dragon
x265
GIMP
LuxCoreRender
GIMP
ASTC Encoder
SVT-HEVC
GIMP
miniBUDE:
  OpenMP - BM1:
    Billion Interactions/s
    GFInst/s
NAS Parallel Benchmarks
uvg266:
  Bosphorus 4K - Very Fast
  Bosphorus 4K - Ultra Fast
NAS Parallel Benchmarks
uvg266
Kvazaar
GIMP
oneDNN
Rodinia
Kvazaar
NAS Parallel Benchmarks
Kvazaar
SVT-VP9:
  PSNR/SSIM Optimized - Bosphorus 4K
  Visual Quality Optimized - Bosphorus 4K
libavif avifenc
NAS Parallel Benchmarks
ASTC Encoder
SVT-AV1:
  Preset 13 - Bosphorus 4K
  Preset 12 - Bosphorus 4K
SVT-HEVC
Darktable
NAS Parallel Benchmarks
libavif avifenc
Darktable:
  Server Room - CPU-only
  Masskrug - CPU-only
  Server Rack - CPU-only
Meta Performance Per Watts:
  Performance Per Watts
  Phoronix Test Suite System Monitoring

Ryzen 9 7950X

Processor: AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 7900 XTX 24GB (2304/1249MHz), Audio: AMD Navi 31 HDMI/DP, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Ubuntu 23.10, Kernel: 6.5.0-9-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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 Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203
Java Notes: OpenJDK Runtime Environment (build 17.0.9-ea+6-Ubuntu-1)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 17 October 2023 21:04 by user pts.

Ryzen 9 7950X3D

Processor: AMD Ryzen 9 7950X3D 16-Core @ 5.76GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 7900 XTX 24GB (2304/1249MHz), Audio: AMD Navi 31 HDMI/DP, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Ubuntu 23.10, Kernel: 6.5.0-9-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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 Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203
Java Notes: OpenJDK Runtime Environment (build 17.0.9-ea+6-Ubuntu-1)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 21 October 2023 10:00 by user pts.

Threadripper 7970X

Processor: AMD Ryzen Threadripper 7970X 32-Cores @ 7.21GHz (32 Cores / 64 Threads), Motherboard: ASUS Pro WS TRX50-SAGE WIFI (0217 BIOS), Chipset: AMD Device 14a4, Memory: 128GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 7900 XTX 24GB (2304/1249MHz), Audio: Realtek ALC1220, Network: Aquantia Device 04c0 + Intel I226-LM + MEDIATEK MT7922 802.11ax PCI

OS: Ubuntu 23.10, Kernel: 6.5.0-9-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7 + Wayland, OpenGL: 4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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 Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 9 November 2023 00:42 by user phoronix.

Threadripper 7980X

Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 8.21GHz (64 Cores / 128 Threads), Motherboard: ASUS Pro WS TRX50-SAGE WIFI (0217 BIOS), Chipset: AMD Device 14a4, Memory: 128GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 7900 XTX 24GB (2304/1249MHz), Audio: Realtek ALC1220, Network: Aquantia Device 04c0 + Intel I226-LM + MEDIATEK MT7922 802.11ax PCI

OS: Ubuntu 23.10, Kernel: 6.5.0-9-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7 + Wayland, OpenGL: 4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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 Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 8 November 2023 03:04 by user phoronix.