Threadripper 7000 EXPO

Benchmarks for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2311209-NE-UPPEREXPO30&grs&sro.

ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionTR 7970XTR 7980X EXPO DDR5-6400 DDR5-4800 DDR5-4800 EXPO DDR5-6400AMD Ryzen Threadripper 7970X 32-Cores @ 7.21GHz (32 Cores / 64 Threads)ASUS Pro WS TRX50-SAGE WIFI (0217 BIOS)AMD Device 14a4128GB1000GB Western Digital WDS100T1X0E-00AFY0AMD Radeon RX 7900 XT 20GB (2025/1249MHz)Realtek ALC1220ASUS MG28UAquantia Device 04c0 + Intel I226-LM + MEDIATEK MT7922 802.11ax PCIUbuntu 23.106.5.0-9-generic (x86_64)GNOME Shell 45.0X Server 1.21.1.7 + Wayland4.6 Mesa 23.2.1-1ubuntu3 (LLVM 15.0.7 DRM 3.54)GCC 13.2.0ext43840x2160AMD 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- TR 7970X: EXPO DDR5-6400: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105- TR 7970X: DDR5-4800: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105- TR 7980X: DDR5-4800: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105- TR 7980X: EXPO DDR5-6400: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105Java Details- OpenJDK Runtime Environment (build 17.0.9-ea+6-Ubuntu-1)Python Details- Python 3.11.6Security Details- 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

openvino: Vehicle Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUeasywave: e2Asean Grid + BengkuluSept2007 Source - 2400openvino: Machine Translation EN To DE FP16 - CPUnpb: SP.Bnpb: BT.Ceasywave: e2Asean Grid + BengkuluSept2007 Source - 1200specfem3d: Layered Halfspaceincompact3d: input.i3d 193 Cells Per Directionspecfem3d: Mount St. Helensopenfoam: drivaerFastback, Medium Mesh Size - Execution Timenpb: EP.Dopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenradioss: Chrysler Neon 1Mopenvino: Handwritten English Recognition FP16-INT8 - CPUcompress-7zip: Decompression Ratinghpcg: 160 160 160 - 60openvino: Face Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUquantlib: Multi-Threadedopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection Retail FP16 - CPUincompact3d: X3D-benchmarking input.i3dopenfoam: drivaerFastback, Small Mesh Size - Execution Timeospray-studio: 3 - 4K - 32 - Path Tracer - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUnpb: LU.Cospray-studio: 1 - 4K - 32 - Path Tracer - CPUhpcg: 144 144 144 - 60openvino: Vehicle Detection FP16 - CPUopenvkl: vklBenchmarkCPU ISPCdacapobench: Apache Tomcatopenvino: Handwritten English Recognition FP16 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Person Detection FP16 - CPUtensorflow: CPU - 256 - ResNet-50graph500: 26openvino: Person Detection FP32 - CPUwrf: conus 2.5kmtensorflow: CPU - 512 - ResNet-50specfem3d: Tomographic Modelnpb: CG.Copenvino: Age Gender Recognition Retail 0013 FP16 - CPUbuild-llvm: Ninjagraph500: 26openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUspecfem3d: Homogeneous Halfspacenpb: MG.Copenvino: Face Detection FP16 - CPUopenvino: Face Detection Retail FP16 - CPUnpb: FT.Copenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUbuild-linux-kernel: allmodconfigdacapobench: H2O In-Memory Platform For Machine Learningopenvino: Weld Porosity Detection FP16 - CPUcompress-7zip: Compression Ratingnpb: IS.Dopenvino: Weld Porosity Detection FP16-INT8 - CPUbuild-ffmpeg: Time To Compileopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUgraph500: 26pgbench: 1000 - 1000 - Read Onlypgbench: 1000 - 1000 - Read Only - Average Latencygraph500: 26build-godot: Time To Compilebuild-llvm: Unix Makefilessvt-av1: Preset 12 - Bosphorus 4Kdacapobench: Avrora AVR Simulation Frameworkbuild-linux-kernel: defconfigopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timesvt-av1: Preset 13 - Bosphorus 4Khadoop: Create - 500 - 100000dacapobench: Spring Bootbuild-gem5: Time To Compiledacapobench: Apache Xalan XSLTopenfoam: drivaerFastback, Small Mesh Size - Mesh Timeffmpeg: libx265 - Livedacapobench: Apache Lucene Search Enginedacapobench: H2 Database Enginesvt-av1: Preset 8 - Bosphorus 4Kdacapobench: Zxing 1D/2D Barcode Image Processingsvt-av1: Preset 4 - Bosphorus 4Kcockroach: KV, 60% Reads - 128ffmpeg: libx265 - Uploadffmpeg: libx265 - Video On Demanddacapobench: GraphChiffmpeg: libx265 - Platformcockroach: KV, 50% Reads - 128dacapobench: Apache Lucene Search Indexffmpeg: libx264 - Livecockroach: KV, 95% Reads - 128dacapobench: Batik SVG Toolkitdacapobench: Jythonffmpeg: libx264 - Platformstargate: 192000 - 512dacapobench: Eclipseffmpeg: libx264 - Video On Demanddacapobench: BioJava Biological Data Frameworkstargate: 96000 - 1024dacapobench: FOP Print Formatterdacapobench: Apache Kafkastargate: 192000 - 1024ffmpeg: libx264 - Uploadstargate: 96000 - 512dacapobench: jMonkeyEngineopenvino: Road Segmentation ADAS FP16 - CPUgpaw: Carbon Nanotubetensorflow: CPU - 64 - ResNet-50pgbench: 1000 - 1000 - Read Write - Average Latencypgbench: 1000 - 1000 - Read Writegromacs: MPI CPU - water_GMX50_baredacapobench: PMD Source Code Analyzerdacapobench: Tradebeansdacapobench: Tradesoapspecfem3d: Water-layered Halfspacerelion: Basic - CPUnpb: SP.Cnpb: EP.Chpcg: 104 104 104 - 60TR 7970XTR 7980X EXPO DDR5-6400 DDR5-4800 DDR5-4800 EXPO DDR5-640014.56131.86129.8332.4998.75770.7771577.4681296.2835.08650.85048736844.305792516.0666871211470.70685413.492736.771205.29589.551062.4332552010.0867549.045017.48157096.0225.923055.569189.682557.7425.406514.461206.1495065.70084786635972.82133092.137400910.66261096.861159181926.5616.42123.3463.45183307000121.2426532.71862.8014.41044038225479.4662301.84184.37024301300083072.5717.52529188564616.38627.822.4570966.580.423.48296.032245112.503464953228.186.3715.4295.22325.675.8330.100.354411400015675980.638557889000100.328221.032260.947459532.540119.34268260.563582761976162.13569221.327906171.0712701704120.3975296.972129956.535.6571.96231672.00119714.42625298.76172355.3992386266.653.339721748066.3048275.68212243850853.67314117.245.2257536811493.4291.82969.1727.460364265.0189814828319649.147323686640.93928213.625183.9612.148211.3792.0492.0324.31120.74259.8457780.19101621.1142.14236.90814867627.674578313.887247306881.012315491.412639.491308.29385.751081.7232771217.252449.445082.50158877.5267.083040.169340.302584.6525.596645.78726.26165860.96763887464944.70111137.297434017.25181404.761117182824.4516.9173.7184.93218034000173.6918836.29185.9713.83578865721204.9362776.15177.45928062900083614.7317.60471264849967.68622.552.4054860.650.413.42301.669266612.363074392559.456.2915.5775.25322.936.0529.560.352711100015096800.662545439000105.260223.091241.594550533.411118.97576244.322554912046165.36271019.502787153.5513981885115.2265446.739126941.033.8567.73247067.83116189.72780286.53167038.41018395265.353.281438760965.3948485.62813243951433.65542417.255.1989456828657.0268.50481.0131.232320965.41110267305425636.264507523488.81839258.445278.4617.716120.68175.36172.5536.0755.63884.2494646.75127875.1622.00025.41136154422.45447868.286745005758.553479716.414565.502081.67342.271825.8555763382.808463.53264789.5379.445095.6815377.304273.3742.3210853.67813.29134139.779228532141549.30151736.05454821543.891769119230.7220.62185.6892.60276064000182.3819008.12992.989.72738125425996.7590969.47126.723348825000119023.4512.39337059152028.26753.192.9454712.960.524.15230.000320914.964012052509.847.5512.0256.27385.656.9935.030.3765842800018725900.53467468500087.547181.867213.574483428.717120.60038219.685507172258147.17378521.782386161.7813051872122.4095777.240127545.335.9971.77235171.89114604.82680293.38173398.6997391666.023.314182755466.2447735.68676743450873.69279517.265.1852796810886.0053.14681.4931.507319337.30512976724364922.647956793437.10745192.147793.4017.733133.33263.04262.5666.3853.731123.07118412.00164973.4320.89742.96968381037.32831709.0606604151124.39428890.294281.681670.68524.421696.5652242577.017849.16244787.3259.674762.5314226.243959.1938.5910021.441177.6042953.083667552811259.98182248.2447200957.531679116238.2725.36121.7261.30193327000121.4928320.63562.1910.18148495331277.6789142.74157.706256254000116415.1412.70548268667959.47824.953.1872124.200.544.49232.528279616.153606663255.388.1512.1446.70414.417.4637.700.3862457600017990880.55665152300085.436189.753229.182479228.105141.35081228.017518072210145.65574921.979705164.6912571815126.0375647.267121451.836.2172.40232172.32112710.32755294.86167662.31018392266.493.319479753166.5048195.69396543450853.68546317.395.2214036810481.8877.28561.0744.584224355.25611566342356130.797727236612.33359193.797380.179.91018OpenBenchmarking.org

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUDDR5-4800EXPO DDR5-6400816243240SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.17, N = 8SE +/- 0.08, N = 311.3714.5620.6833.331. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Detection FP32 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUDDR5-4800EXPO DDR5-640060120180240300SE +/- 0.48, N = 3SE +/- 0.54, N = 3SE +/- 1.19, N = 15SE +/- 0.21, N = 392.04131.86175.36263.041. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Detection FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUDDR5-4800EXPO DDR5-640060120180240300SE +/- 0.25, N = 3SE +/- 1.39, N = 14SE +/- 2.21, N = 15SE +/- 0.13, N = 392.03129.83172.55262.561. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUDDR5-4800EXPO DDR5-64001530456075SE +/- 0.08, N = 3SE +/- 0.49, N = 15SE +/- 0.36, N = 3SE +/- 0.64, N = 1324.3132.4936.0766.381. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

easyWave

Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400DDR5-4800EXPO DDR5-6400306090120150SE +/- 0.17, N = 3SE +/- 0.50, N = 3SE +/- 0.26, N = 3SE +/- 0.17, N = 3120.7498.7655.6453.731. (CXX) g++ options: -O3 -fopenmp

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUDDR5-4800EXPO DDR5-6400306090120150SE +/- 0.02, N = 3SE +/- 0.37, N = 15SE +/- 0.24, N = 3SE +/- 0.10, N = 359.8470.7784.24123.071. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

NAS Parallel Benchmarks

Test / Class: SP.B

TR 7970XTR 7980XOpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BDDR5-4800EXPO DDR5-640030K60K90K120K150KSE +/- 64.93, N = 3SE +/- 396.91, N = 3SE +/- 789.17, N = 3SE +/- 1263.27, N = 357780.1971577.4694646.75118412.001. (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

NAS Parallel Benchmarks

Test / Class: BT.C

TR 7970XTR 7980XOpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CDDR5-4800EXPO DDR5-640040K80K120K160K200KSE +/- 101.88, N = 3SE +/- 939.16, N = 15SE +/- 67.32, N = 3SE +/- 1397.90, N = 3101621.1181296.28127875.16164973.431. (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

easyWave

Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200DDR5-4800EXPO DDR5-64001020304050SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 342.1435.0922.0020.901. (CXX) g++ options: -O3 -fopenmp

SPECFEM3D

Model: Layered Halfspace

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Layered HalfspaceDDR5-4800EXPO DDR5-64001122334455SE +/- 0.35, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.31, N = 336.9150.8525.4142.971. (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

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionDDR5-4800EXPO DDR5-64001020304050SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.13, N = 3SE +/- 0.15, N = 327.6744.3122.4537.331. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

SPECFEM3D

Model: Mount St. Helens

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Mount St. HelensDDR5-4800EXPO DDR5-640048121620SE +/- 0.011025154, N = 3SE +/- 0.120342848, N = 3SE +/- 0.042295263, N = 3SE +/- 0.095852702, N = 313.88724730616.0666871218.2867450059.0606604151. (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

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Execution Time

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution TimeDDR5-4800EXPO DDR5-640030060090012001500881.011470.71758.551124.391. (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

NAS Parallel Benchmarks

Test / Class: EP.D

TR 7970XTR 7980XOpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DDDR5-4800EXPO DDR5-64002K4K6K8K10KSE +/- 21.65, N = 3SE +/- 39.36, N = 15SE +/- 28.06, N = 3SE +/- 69.83, N = 155491.415413.499716.418890.291. (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

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUDDR5-4800EXPO DDR5-640010002000300040005000SE +/- 18.24, N = 3SE +/- 10.19, N = 3SE +/- 5.16, N = 3SE +/- 34.35, N = 92639.492736.774565.504281.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUDDR5-4800EXPO DDR5-6400400800120016002000SE +/- 15.22, N = 4SE +/- 12.43, N = 15SE +/- 2.79, N = 3SE +/- 15.77, N = 61308.291205.292081.671670.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenRadioss

Model: Chrysler Neon 1M

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1MDDR5-4800EXPO DDR5-6400130260390520650SE +/- 0.52, N = 3SE +/- 0.87, N = 3SE +/- 1.60, N = 3SE +/- 0.06, N = 3385.75589.55342.27524.42

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-6400400800120016002000SE +/- 5.40, N = 3SE +/- 2.55, N = 3SE +/- 4.17, N = 3SE +/- 3.81, N = 31081.721062.431825.851696.561. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

7-Zip Compression

Test: Decompression Rating

TR 7970XTR 7980XOpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingDDR5-4800EXPO DDR5-6400120K240K360K480K600KSE +/- 561.34, N = 3SE +/- 308.82, N = 3SE +/- 897.83, N = 3SE +/- 1072.57, N = 33277123255205576335224251. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

High Performance Conjugate Gradient

X Y Z: 160 160 160 - RT: 60

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 160 160 160 - RT: 60DDR5-4800EXPO DDR5-640048121620SE +/- 0.00, N = 3SE +/- 0.10, N = 617.2510.091. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-640020406080100SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 349.4449.0482.8077.011. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-64002K4K6K8K10KSE +/- 2.38, N = 3SE +/- 2.13, N = 3SE +/- 5.47, N = 3SE +/- 2.54, N = 35082.505017.488463.537849.161. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

QuantLib

Configuration: Multi-Threaded

TR 7970XTR 7980XOpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedDDR5-4800EXPO DDR5-640060K120K180K240K300KSE +/- 356.95, N = 3SE +/- 653.46, N = 3SE +/- 805.61, N = 3SE +/- 899.24, N = 3158877.5157096.0264789.5244787.31. (CXX) g++ options: -O3 -march=native -fPIE -pie

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUDDR5-4800EXPO DDR5-640080160240320400SE +/- 0.10, N = 3SE +/- 1.28, N = 15SE +/- 1.03, N = 3SE +/- 0.22, N = 3267.08225.92379.44259.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-640011002200330044005500SE +/- 5.62, N = 3SE +/- 12.77, N = 3SE +/- 0.93, N = 3SE +/- 6.20, N = 33040.163055.565095.684762.531. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-64003K6K9K12K15KSE +/- 1.38, N = 3SE +/- 9.32, N = 3SE +/- 8.15, N = 3SE +/- 4.57, N = 39340.309189.6815377.3014226.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUDDR5-4800EXPO DDR5-64009001800270036004500SE +/- 2.62, N = 3SE +/- 0.70, N = 3SE +/- 2.32, N = 3SE +/- 0.40, N = 32584.652557.744273.373959.191. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUDDR5-4800EXPO DDR5-64001020304050SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 325.5925.4042.3238.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUDDR5-4800EXPO DDR5-64002K4K6K8K10KSE +/- 12.71, N = 3SE +/- 4.79, N = 3SE +/- 8.32, N = 3SE +/- 5.37, N = 36645.786514.4610853.6710021.441. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Xcompact3d Incompact3d

Input: X3D-benchmarking input.i3d

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dDDR5-4800EXPO DDR5-640030060090012001500SE +/- 0.32, N = 3SE +/- 8.58, N = 3SE +/- 13.28, N = 9SE +/- 4.98, N = 3726.261206.15813.291177.601. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

OpenFOAM

Input: drivaerFastback, Small Mesh Size - Execution Time

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution TimeDDR5-4800EXPO DDR5-6400153045607560.9765.7039.7853.081. (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

OSPRay Studio

Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUDDR5-4800EXPO DDR5-640020K40K60K80K100KSE +/- 156.54, N = 3SE +/- 120.96, N = 3SE +/- 75.07, N = 3SE +/- 43.32, N = 387464866355321455281

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-640030060090012001500SE +/- 0.01, N = 3SE +/- 7.71, N = 3SE +/- 11.53, N = 3SE +/- 7.57, N = 15944.70972.821549.301259.981. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

NAS Parallel Benchmarks

Test / Class: LU.C

TR 7970XTR 7980XOpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CDDR5-4800EXPO DDR5-640040K80K120K160K200KSE +/- 230.34, N = 3SE +/- 112.44, N = 3SE +/- 423.29, N = 3SE +/- 694.34, N = 3111137.29133092.13151736.05182248.241. (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

OSPRay Studio

Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUDDR5-4800EXPO DDR5-640016K32K48K64K80KSE +/- 231.14, N = 3SE +/- 108.78, N = 3SE +/- 68.39, N = 3SE +/- 45.04, N = 374340740094548247200

High Performance Conjugate Gradient

X Y Z: 144 144 144 - RT: 60

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 144 144 144 - RT: 60DDR5-4800EXPO DDR5-640048121620SE +/- 0.01, N = 3SE +/- 0.07, N = 317.2510.661. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUDDR5-4800EXPO DDR5-640030060090012001500SE +/- 2.84, N = 3SE +/- 2.13, N = 3SE +/- 13.18, N = 8SE +/- 2.29, N = 31404.761096.861543.89957.531. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVKL

Benchmark: vklBenchmarkCPU ISPC

TR 7970XTR 7980XOpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 2.0.0Benchmark: vklBenchmarkCPU ISPCDDR5-4800EXPO DDR5-6400400800120016002000SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 4.48, N = 3SE +/- 18.50, N = 31117115917691679

DaCapo Benchmark

Java Test: Apache Tomcat

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache TomcatDDR5-4800EXPO DDR5-6400400800120016002000SE +/- 1.15, N = 3SE +/- 5.03, N = 3SE +/- 14.62, N = 3SE +/- 8.09, N = 31828181911921162

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUDDR5-4800EXPO DDR5-6400918273645SE +/- 0.28, N = 4SE +/- 0.25, N = 15SE +/- 0.04, N = 3SE +/- 0.37, N = 624.4526.5630.7238.271. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-6400612182430SE +/- 0.00, N = 3SE +/- 0.13, N = 3SE +/- 0.15, N = 3SE +/- 0.14, N = 1516.9016.4220.6225.361. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Detection FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUDDR5-4800EXPO DDR5-64004080120160200SE +/- 0.49, N = 3SE +/- 1.51, N = 14SE +/- 2.64, N = 15SE +/- 0.07, N = 3173.71123.34185.68121.721. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

TensorFlow

Device: CPU - Batch Size: 256 - Model: ResNet-50

TR 7970XTR 7980XOpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: ResNet-50DDR5-4800EXPO DDR5-640020406080100SE +/- 0.02, N = 3SE +/- 0.17, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 384.9363.4592.6061.30

Graph500

Scale: 26

TR 7970XTR 7980XOpenBenchmarking.orgsssp median_TEPS, More Is BetterGraph500 3.0Scale: 26DDR5-4800EXPO DDR5-640060M120M180M240M300M2180340001833070002760640001933270001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

OpenVINO

Model: Person Detection FP32 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUDDR5-4800EXPO DDR5-64004080120160200SE +/- 0.92, N = 3SE +/- 0.50, N = 3SE +/- 1.34, N = 15SE +/- 0.09, N = 3173.69121.24182.38121.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

WRF

Input: conus 2.5km

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterWRF 4.2.2Input: conus 2.5kmDDR5-4800EXPO DDR5-64006K12K18K24K30K18836.2926532.7219008.1328320.641. (F9X) gfortran options: -O2 -ftree-vectorize -funroll-loops -ffree-form -fconvert=big-endian -frecord-marker=4 -fallow-invalid-boz -lesmf_time -lwrfio_nf -lnetcdff -lnetcdf -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

TensorFlow

Device: CPU - Batch Size: 512 - Model: ResNet-50

TR 7970XTR 7980XOpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: ResNet-50DDR5-4800EXPO DDR5-640020406080100SE +/- 0.07, N = 3SE +/- 0.28, N = 3SE +/- 0.61, N = 3SE +/- 0.00, N = 385.9762.8092.9862.19

SPECFEM3D

Model: Tomographic Model

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Tomographic ModelDDR5-4800EXPO DDR5-640048121620SE +/- 0.082041385, N = 3SE +/- 0.111802640, N = 3SE +/- 0.080434443, N = 3SE +/- 0.090087134, N = 313.83578865714.4104403829.72738125410.1814849531. (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

NAS Parallel Benchmarks

Test / Class: CG.C

TR 7970XTR 7980XOpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CDDR5-4800EXPO DDR5-64007K14K21K28K35KSE +/- 55.75, N = 3SE +/- 362.71, N = 3SE +/- 67.11, N = 3SE +/- 345.04, N = 321204.9325479.4625996.7531277.671. (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

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUDDR5-4800EXPO DDR5-640020K40K60K80K100KSE +/- 79.44, N = 3SE +/- 22.17, N = 3SE +/- 121.72, N = 3SE +/- 132.34, N = 362776.1562301.8490969.4789142.741. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Timed LLVM Compilation

Build System: Ninja

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaDDR5-4800EXPO DDR5-64004080120160200SE +/- 0.84, N = 3SE +/- 0.26, N = 3SE +/- 0.17, N = 3SE +/- 0.30, N = 3177.46184.37126.72157.71

Graph500

Scale: 26

TR 7970XTR 7980XOpenBenchmarking.orgsssp max_TEPS, More Is BetterGraph500 3.0Scale: 26DDR5-4800EXPO DDR5-640070M140M210M280M350M2806290002430130003488250002562540001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-640030K60K90K120K150KSE +/- 121.39, N = 3SE +/- 73.01, N = 3SE +/- 64.14, N = 3SE +/- 270.04, N = 383614.7383072.57119023.45116415.141. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

SPECFEM3D

Model: Homogeneous Halfspace

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Homogeneous HalfspaceDDR5-4800EXPO DDR5-640048121620SE +/- 0.11, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 15SE +/- 0.13, N = 617.6017.5312.3912.711. (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

NAS Parallel Benchmarks

Test / Class: MG.C

TR 7970XTR 7980XOpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CDDR5-4800EXPO DDR5-640015K30K45K60K75KSE +/- 133.55, N = 3SE +/- 743.70, N = 3SE +/- 452.06, N = 3SE +/- 196.76, N = 349967.6864616.3852028.2667959.471. (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

OpenVINO

Model: Face Detection FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUDDR5-4800EXPO DDR5-64002004006008001000SE +/- 0.87, N = 3SE +/- 0.53, N = 3SE +/- 0.12, N = 3SE +/- 0.39, N = 3622.55627.82753.19824.951. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUDDR5-4800EXPO DDR5-64000.71551.4312.14652.8623.5775SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.402.452.943.181. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

NAS Parallel Benchmarks

Test / Class: FT.C

TR 7970XTR 7980XOpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CDDR5-4800EXPO DDR5-640015K30K45K60K75KSE +/- 30.91, N = 3SE +/- 124.26, N = 3SE +/- 11.32, N = 3SE +/- 111.54, N = 354860.6570966.5854712.9672124.201. (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

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUDDR5-4800EXPO DDR5-64000.12150.2430.36450.4860.6075SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.410.420.520.541. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-64001.01032.02063.03094.04125.0515SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.423.484.154.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Timed Linux Kernel Compilation

Build: allmodconfig

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfigDDR5-4800EXPO DDR5-640070140210280350SE +/- 0.40, N = 3SE +/- 1.05, N = 3SE +/- 0.35, N = 3SE +/- 1.53, N = 3301.67296.03230.00232.53

DaCapo Benchmark

Java Test: H2O In-Memory Platform For Machine Learning

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: H2O In-Memory Platform For Machine LearningDDR5-4800EXPO DDR5-64007001400210028003500SE +/- 33.41, N = 3SE +/- 28.24, N = 3SE +/- 2.19, N = 3SE +/- 2.03, N = 32666245132092796

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUDDR5-4800EXPO DDR5-640048121620SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 312.3612.5014.9616.151. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

7-Zip Compression

Test: Compression Rating

TR 7970XTR 7980XOpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingDDR5-4800EXPO DDR5-640090K180K270K360K450KSE +/- 663.67, N = 3SE +/- 455.41, N = 3SE +/- 558.57, N = 3SE +/- 3624.16, N = 33074393464954012053606661. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

NAS Parallel Benchmarks

Test / Class: IS.D

TR 7970XTR 7980XOpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DDDR5-4800EXPO DDR5-64007001400210028003500SE +/- 8.35, N = 3SE +/- 8.96, N = 3SE +/- 17.57, N = 3SE +/- 11.72, N = 32559.453228.182509.843255.381. (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

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-6400246810SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 36.296.377.558.151. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Timed FFmpeg Compilation

Time To Compile

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 6.1Time To CompileDDR5-4800EXPO DDR5-640048121620SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 315.5815.4312.0312.14

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-6400246810SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 35.255.226.276.701. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-640090180270360450SE +/- 0.25, N = 3SE +/- 0.27, N = 3SE +/- 0.22, N = 3SE +/- 0.21, N = 3322.93325.67385.65414.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUDDR5-4800EXPO DDR5-6400246810SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 96.055.836.997.461. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-6400918273645SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 329.5630.1035.0337.701. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUDDR5-4800EXPO DDR5-64000.08550.1710.25650.3420.4275SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.300.300.370.381. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Graph500

Scale: 26

TR 7970XTR 7980XOpenBenchmarking.orgbfs median_TEPS, More Is BetterGraph500 3.0Scale: 26DDR5-4800EXPO DDR5-6400140M280M420M560M700M5271110005441140006584280006245760001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

PostgreSQL

Scaling Factor: 1000 - Clients: 1000 - Mode: Read Only

TR 7970XTR 7980XOpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read OnlyDDR5-4800EXPO DDR5-6400400K800K1200K1600K2000KSE +/- 1883.80, N = 3SE +/- 1538.86, N = 3SE +/- 16351.50, N = 3SE +/- 3511.06, N = 315096801567598187259017990881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL

Scaling Factor: 1000 - Clients: 1000 - Mode: Read Only - Average Latency

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read Only - Average LatencyDDR5-4800EXPO DDR5-64000.1490.2980.4470.5960.745SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.005, N = 3SE +/- 0.001, N = 30.6620.6380.5340.5561. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Graph500

Scale: 26

TR 7970XTR 7980XOpenBenchmarking.orgbfs max_TEPS, More Is BetterGraph500 3.0Scale: 26DDR5-4800EXPO DDR5-6400140M280M420M560M700M5454390005578890006746850006515230001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

Timed Godot Game Engine Compilation

Time To Compile

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To CompileDDR5-4800EXPO DDR5-640020406080100SE +/- 0.13, N = 3SE +/- 0.16, N = 3SE +/- 0.23, N = 3SE +/- 0.45, N = 3105.26100.3387.5585.44

Timed LLVM Compilation

Build System: Unix Makefiles

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix MakefilesDDR5-4800EXPO DDR5-640050100150200250SE +/- 1.35, N = 3SE +/- 2.99, N = 3SE +/- 0.16, N = 3SE +/- 0.91, N = 3223.09221.03181.87189.75

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 4K

TR 7970XTR 7980XOpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 12 - Input: Bosphorus 4KDDR5-4800EXPO DDR5-640060120180240300SE +/- 0.56, N = 3SE +/- 0.59, N = 3SE +/- 2.27, N = 4SE +/- 2.95, N = 3241.59260.95213.57229.181. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

DaCapo Benchmark

Java Test: Avrora AVR Simulation Framework

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Avrora AVR Simulation FrameworkDDR5-4800EXPO DDR5-640012002400360048006000SE +/- 36.90, N = 3SE +/- 40.06, N = 8SE +/- 5.93, N = 3SE +/- 6.66, N = 35505459548344792

Timed Linux Kernel Compilation

Build: defconfig

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigDDR5-4800EXPO DDR5-6400816243240SE +/- 0.45, N = 3SE +/- 0.43, N = 3SE +/- 0.33, N = 4SE +/- 0.33, N = 433.4132.5428.7228.11

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Mesh Time

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh TimeDDR5-4800EXPO DDR5-6400306090120150118.98119.34120.60141.351. (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

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

TR 7970XTR 7980XOpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 13 - Input: Bosphorus 4KDDR5-4800EXPO DDR5-640060120180240300SE +/- 0.64, N = 3SE +/- 0.61, N = 3SE +/- 1.79, N = 3SE +/- 3.18, N = 3244.32260.56219.69228.021. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Apache Hadoop

Operation: Create - Threads: 500 - Files: 100000

TR 7970XTR 7980XOpenBenchmarking.orgOps per sec, More Is BetterApache Hadoop 3.3.6Operation: Create - Threads: 500 - Files: 100000DDR5-4800EXPO DDR5-640012K24K36K48K60KSE +/- 438.19, N = 3SE +/- 199.33, N = 3SE +/- 630.85, N = 3SE +/- 260.74, N = 355491582765071751807

DaCapo Benchmark

Java Test: Spring Boot

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Spring BootDDR5-4800EXPO DDR5-64005001000150020002500SE +/- 22.38, N = 5SE +/- 24.32, N = 4SE +/- 12.02, N = 3SE +/- 21.15, N = 32046197622582210

Timed Gem5 Compilation

Time To Compile

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 23.0.1Time To CompileDDR5-4800EXPO DDR5-64004080120160200SE +/- 1.72, N = 5SE +/- 1.35, N = 9SE +/- 1.30, N = 3SE +/- 1.16, N = 3165.36162.14147.17145.66

DaCapo Benchmark

Java Test: Apache Xalan XSLT

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Xalan XSLTDDR5-4800EXPO DDR5-64002004006008001000SE +/- 5.70, N = 3SE +/- 5.78, N = 3SE +/- 4.93, N = 3SE +/- 7.69, N = 3710692785749

OpenFOAM

Input: drivaerFastback, Small Mesh Size - Mesh Time

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Mesh TimeDDR5-4800EXPO DDR5-640051015202519.5021.3321.7821.981. (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

FFmpeg

Encoder: libx265 - Scenario: Live

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: LiveDDR5-4800EXPO DDR5-64004080120160200SE +/- 0.44, N = 3SE +/- 0.47, N = 3SE +/- 0.72, N = 3SE +/- 0.23, N = 3153.55171.07161.78164.691. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

DaCapo Benchmark

Java Test: Apache Lucene Search Engine

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search EngineDDR5-4800EXPO DDR5-640030060090012001500SE +/- 10.81, N = 3SE +/- 7.23, N = 3SE +/- 10.91, N = 3SE +/- 15.46, N = 41398127013051257

DaCapo Benchmark

Java Test: H2 Database Engine

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: H2 Database EngineDDR5-4800EXPO DDR5-6400400800120016002000SE +/- 5.21, N = 3SE +/- 11.10, N = 3SE +/- 10.49, N = 3SE +/- 0.58, N = 31885170418721815

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

TR 7970XTR 7980XOpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 8 - Input: Bosphorus 4KDDR5-4800EXPO DDR5-6400306090120150SE +/- 0.26, N = 3SE +/- 0.27, N = 3SE +/- 1.27, N = 5SE +/- 1.09, N = 7115.23120.40122.41126.041. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

DaCapo Benchmark

Java Test: Zxing 1D/2D Barcode Image Processing

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Zxing 1D/2D Barcode Image ProcessingDDR5-4800EXPO DDR5-6400120240360480600SE +/- 4.18, N = 3SE +/- 4.04, N = 3SE +/- 0.88, N = 3SE +/- 5.49, N = 3544529577564

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

TR 7970XTR 7980XOpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 4 - Input: Bosphorus 4KDDR5-4800EXPO DDR5-6400246810SE +/- 0.013, N = 3SE +/- 0.011, N = 3SE +/- 0.009, N = 3SE +/- 0.022, N = 36.7396.9727.2407.2671. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

CockroachDB

Workload: KV, 60% Reads - Concurrency: 128

TR 7970XTR 7980XOpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 60% Reads - Concurrency: 128DDR5-4800EXPO DDR5-640030K60K90K120K150KSE +/- 710.74, N = 3SE +/- 266.16, N = 3SE +/- 770.96, N = 3SE +/- 1100.91, N = 3126941.0129956.5127545.3121451.8

FFmpeg

Encoder: libx265 - Scenario: Upload

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: UploadDDR5-4800EXPO DDR5-6400816243240SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 333.8535.6535.9936.211. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

FFmpeg

Encoder: libx265 - Scenario: Video On Demand

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Video On DemandDDR5-4800EXPO DDR5-64001632486480SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 367.7371.9671.7772.401. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

DaCapo Benchmark

Java Test: GraphChi

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: GraphChiDDR5-4800EXPO DDR5-64005001000150020002500SE +/- 20.83, N = 3SE +/- 26.31, N = 3SE +/- 25.44, N = 3SE +/- 17.67, N = 32470231623512321

FFmpeg

Encoder: libx265 - Scenario: Platform

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: PlatformDDR5-4800EXPO DDR5-64001632486480SE +/- 0.06, N = 3SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 367.8372.0071.8972.321. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

CockroachDB

Workload: KV, 50% Reads - Concurrency: 128

TR 7970XTR 7980XOpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 50% Reads - Concurrency: 128DDR5-4800EXPO DDR5-640030K60K90K120K150KSE +/- 784.94, N = 3SE +/- 378.23, N = 3SE +/- 276.17, N = 3SE +/- 1315.96, N = 3116189.7119714.4114604.8112710.3

DaCapo Benchmark

Java Test: Apache Lucene Search Index

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search IndexDDR5-4800EXPO DDR5-64006001200180024003000SE +/- 17.67, N = 15SE +/- 26.30, N = 3SE +/- 14.52, N = 3SE +/- 21.77, N = 152780262526802755

FFmpeg

Encoder: libx264 - Scenario: Live

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx264 - Scenario: LiveDDR5-4800EXPO DDR5-640070140210280350SE +/- 0.68, N = 3SE +/- 0.96, N = 3SE +/- 0.91, N = 3SE +/- 0.95, N = 3286.53298.76293.38294.861. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

CockroachDB

Workload: KV, 95% Reads - Concurrency: 128

TR 7970XTR 7980XOpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 95% Reads - Concurrency: 128DDR5-4800EXPO DDR5-640040K80K120K160K200KSE +/- 547.20, N = 3SE +/- 1329.68, N = 3SE +/- 1922.22, N = 5SE +/- 1665.32, N = 15167038.4172355.3173398.6167662.3

DaCapo Benchmark

Java Test: Batik SVG Toolkit

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Batik SVG ToolkitDDR5-4800EXPO DDR5-64002004006008001000SE +/- 6.52, N = 15SE +/- 7.88, N = 15SE +/- 2.40, N = 3SE +/- 7.36, N = 310189929971018

DaCapo Benchmark

Java Test: Jython

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: JythonDDR5-4800EXPO DDR5-64008001600240032004000SE +/- 26.47, N = 13SE +/- 45.12, N = 4SE +/- 26.21, N = 3SE +/- 12.72, N = 33952386239163922

FFmpeg

Encoder: libx264 - Scenario: Platform

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx264 - Scenario: PlatformDDR5-4800EXPO DDR5-64001530456075SE +/- 0.03, N = 3SE +/- 0.22, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 365.3566.6566.0266.491. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Stargate Digital Audio Workstation

Sample Rate: 192000 - Buffer Size: 512

TR 7970XTR 7980XOpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 192000 - Buffer Size: 512DDR5-4800EXPO DDR5-64000.75141.50282.25423.00563.757SE +/- 0.036589, N = 3SE +/- 0.005974, N = 3SE +/- 0.002084, N = 3SE +/- 0.006840, N = 33.2814383.3397213.3141823.3194791. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

DaCapo Benchmark

Java Test: Eclipse

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: EclipseDDR5-4800EXPO DDR5-640016003200480064008000SE +/- 66.35, N = 3SE +/- 19.97, N = 3SE +/- 81.07, N = 3SE +/- 42.88, N = 37609748075547531

FFmpeg

Encoder: libx264 - Scenario: Video On Demand

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx264 - Scenario: Video On DemandDDR5-4800EXPO DDR5-64001530456075SE +/- 0.09, N = 3SE +/- 0.21, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 365.3966.3066.2466.501. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

DaCapo Benchmark

Java Test: BioJava Biological Data Framework

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: BioJava Biological Data FrameworkDDR5-4800EXPO DDR5-640010002000300040005000SE +/- 25.56, N = 3SE +/- 33.08, N = 15SE +/- 68.83, N = 3SE +/- 51.13, N = 34848482747734819

Stargate Digital Audio Workstation

Sample Rate: 96000 - Buffer Size: 1024

TR 7970XTR 7980XOpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 96000 - Buffer Size: 1024DDR5-4800EXPO DDR5-64001.28112.56223.84335.12446.4055SE +/- 0.057914, N = 3SE +/- 0.014858, N = 3SE +/- 0.014835, N = 3SE +/- 0.015459, N = 35.6281325.6821225.6867675.6939651. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

DaCapo Benchmark

Java Test: FOP Print Formatter

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: FOP Print FormatterDDR5-4800EXPO DDR5-6400100200300400500SE +/- 6.17, N = 3SE +/- 1.20, N = 3SE +/- 5.07, N = 4SE +/- 3.84, N = 3439438434434

DaCapo Benchmark

Java Test: Apache Kafka

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache KafkaDDR5-4800EXPO DDR5-640011002200330044005500SE +/- 27.18, N = 3SE +/- 2.85, N = 3SE +/- 2.08, N = 3SE +/- 2.40, N = 35143508550875085

Stargate Digital Audio Workstation

Sample Rate: 192000 - Buffer Size: 1024

TR 7970XTR 7980XOpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 192000 - Buffer Size: 1024DDR5-4800EXPO DDR5-64000.83091.66182.49273.32364.1545SE +/- 0.019812, N = 3SE +/- 0.028152, N = 3SE +/- 0.027413, N = 3SE +/- 0.020858, N = 33.6554243.6731413.6927953.6854631. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

FFmpeg

Encoder: libx264 - Scenario: Upload

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx264 - Scenario: UploadDDR5-4800EXPO DDR5-640048121620SE +/- 0.13, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 317.2517.2417.2617.391. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Stargate Digital Audio Workstation

Sample Rate: 96000 - Buffer Size: 512

TR 7970XTR 7980XOpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 96000 - Buffer Size: 512DDR5-4800EXPO DDR5-64001.17582.35163.52744.70325.879SE +/- 0.016332, N = 3SE +/- 0.019461, N = 3SE +/- 0.024670, N = 3SE +/- 0.009527, N = 35.1989455.2257535.1852795.2214031. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

DaCapo Benchmark

Java Test: jMonkeyEngine

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: jMonkeyEngineDDR5-4800EXPO DDR5-640015003000450060007500SE +/- 2.19, N = 3SE +/- 1.45, N = 3SE +/- 1.86, N = 3SE +/- 0.88, N = 36828681168106810

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUDDR5-4800EXPO DDR5-64002004006008001000SE +/- 2.08, N = 3SE +/- 8.40, N = 15SE +/- 8.77, N = 3SE +/- 5.20, N = 13657.02493.42886.00481.881. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

GPAW

Input: Carbon Nanotube

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 23.6Input: Carbon NanotubeDDR5-4800EXPO DDR5-640020406080100SE +/- 0.18, N = 3SE +/- 2.03, N = 15SE +/- 0.36, N = 3SE +/- 0.59, N = 368.5091.8353.1577.291. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi

TensorFlow

Device: CPU - Batch Size: 64 - Model: ResNet-50

TR 7970XTR 7980XOpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50DDR5-4800EXPO DDR5-640020406080100SE +/- 0.03, N = 3SE +/- 2.43, N = 15SE +/- 0.08, N = 3SE +/- 2.39, N = 1481.0169.1781.4961.07

PostgreSQL

Scaling Factor: 1000 - Clients: 1000 - Mode: Read Write - Average Latency

TR 7970XTR 7980XOpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read Write - Average LatencyDDR5-4800EXPO DDR5-64001020304050SE +/- 0.55, N = 9SE +/- 0.30, N = 3SE +/- 0.76, N = 12SE +/- 0.50, N = 331.2327.4631.5144.581. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL

Scaling Factor: 1000 - Clients: 1000 - Mode: Read Write

TR 7970XTR 7980XOpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read WriteDDR5-4800EXPO DDR5-64008K16K24K32K40KSE +/- 549.71, N = 9SE +/- 400.71, N = 3SE +/- 732.17, N = 12SE +/- 253.13, N = 3320963642631933224351. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

TR 7970XTR 7980XOpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareDDR5-4800EXPO DDR5-6400246810SE +/- 0.007, N = 3SE +/- 0.113, N = 15SE +/- 0.004, N = 3SE +/- 0.001, N = 35.4115.0187.3055.2561. (CXX) g++ options: -O3

DaCapo Benchmark

Java Test: PMD Source Code Analyzer

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: PMD Source Code AnalyzerDDR5-4800EXPO DDR5-640030060090012001500SE +/- 7.69, N = 3SE +/- 3.53, N = 3SE +/- 13.08, N = 3SE +/- 19.86, N = 15102698112971156

DaCapo Benchmark

Java Test: Tradebeans

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: TradebeansDDR5-4800EXPO DDR5-640016003200480064008000SE +/- 137.67, N = 15SE +/- 69.43, N = 3SE +/- 92.52, N = 15SE +/- 118.84, N = 157305482867246342

DaCapo Benchmark

Java Test: Tradesoap

TR 7970XTR 7980XOpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: TradesoapDDR5-4800EXPO DDR5-64009001800270036004500SE +/- 71.80, N = 15SE +/- 23.87, N = 15SE +/- 39.27, N = 4SE +/- 28.48, N = 154256319636493561

SPECFEM3D

Model: Water-layered Halfspace

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Water-layered HalfspaceDDR5-4800EXPO DDR5-64001122334455SE +/- 0.35, N = 3SE +/- 0.36, N = 13SE +/- 0.14, N = 3SE +/- 0.70, N = 1536.2649.1522.6530.801. (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

RELION

Test: Basic - Device: CPU

TR 7970XTR 7980XOpenBenchmarking.orgSeconds, Fewer Is BetterRELION 4.0.1Test: Basic - Device: CPUDDR5-4800EXPO DDR5-6400140280420560700SE +/- 9.34, N = 9SE +/- 13.42, N = 9SE +/- 12.25, N = 9SE +/- 11.95, N = 6488.82640.94437.11612.331. (CXX) g++ options: -fopenmp -std=c++11 -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -ljpeg -lmpi_cxx -lmpi

NAS Parallel Benchmarks

Test / Class: SP.C

TR 7970XTR 7980XOpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CDDR5-4800EXPO DDR5-640013K26K39K52K65KSE +/- 130.63, N = 3SE +/- 1269.11, N = 15SE +/- 18.62, N = 3SE +/- 36.42, N = 339258.4428213.6245192.1459193.791. (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

NAS Parallel Benchmarks

Test / Class: EP.C

TR 7970XTR 7980XOpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CDDR5-4800EXPO DDR5-64002K4K6K8K10KSE +/- 57.31, N = 3SE +/- 82.99, N = 14SE +/- 138.57, N = 15SE +/- 201.32, N = 155278.465183.967793.407380.171. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.5

High Performance Conjugate Gradient

X Y Z: 104 104 104 - RT: 60

TR 7970XTR 7980XOpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 104 104 104 - RT: 60DDR5-4800EXPO DDR5-640048121620SE +/- 0.00400, N = 3SE +/- 0.55655, N = 9SE +/- 0.00061, N = 3SE +/- 0.00362, N = 317.7161012.1482017.733109.910181. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

Phoronix Test Suite v10.8.4