GPTshop.ai NVIDIA GH200 Linux Benchmarks

Benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2402184-NE-GH200THRE73&sro.

GPTshop.ai NVIDIA GH200 Linux BenchmarksProcessorMotherboardMemoryDiskGraphicsNetworkChipsetAudioMonitorOSKernelCompilerFile-SystemScreen ResolutionDesktopDisplay ServerDisplay DriverOpenGLOpenCLGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WXARMv8 Neoverse-V2 @ 3.39GHz (72 Cores)Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS)1 x 480GB DRAM-6400MT/s960GB SAMSUNG MZ1L2960HCJR-00A07 + 1920GB SAMSUNG MZTL21T9ASPEED2 x Mellanox MT2910 + 2 x QLogic FastLinQ QL41000 10/25/40/50GbEUbuntu 23.106.5.0-15-generic (aarch64)GCC 13.2.0ext41920x1200AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads)HP Z6 G5 A Workstation 8B24 (U65 Ver. 01.01.04 BIOS)AMD Device 14a48 x 16GB DRAM-5200MT/s Hynix HMCG78AGBRA190N2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1NVIDIA RTX A4000 16GBNVIDIA GA104 HD AudioASUS VP28URealtek RTL8111/8168/84116.5.0-17-generic (x86_64)GNOME Shell 45.2X Server 1.21.1.7NVIDIA 535.154.054.6.0OpenCL 3.0 CUDA 12.2.1483840x2160OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- GPTshop.ai GH200: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --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-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v - HP Z6 G5 A - Threadripper PRO 7995WX: --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- GPTshop.ai GH200: Scaling Governor: cppc_cpufreq performance (Boost: Disabled)- HP Z6 G5 A - Threadripper PRO 7995WX: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105Python Details- Python 3.11.6Security Details- GPTshop.ai GH200: 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: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected - HP Z6 G5 A - Threadripper PRO 7995WX: 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 OpenCL Details- HP Z6 G5 A - Threadripper PRO 7995WX: GPU Compute Cores: 6144

GPTshop.ai NVIDIA GH200 Linux Benchmarkshpcg: 144 144 144 - 60npb: BT.Cnpb: CG.Cnpb: FT.Cnpb: IS.Dnpb: LU.Cnpb: MG.Cnpb: SP.Cminibude: OpenMP - BM2minibude: OpenMP - BM2rodinia: OpenMP LavaMDamg: libxsmm: 128libxsmm: 256nwchem: C240 Buckyballincompact3d: X3D-benchmarking input.i3dincompact3d: input.i3d 193 Cells Per Directionlulesh: xmrig: Monero - 1Mxmrig: Wownero - 1Mjohn-the-ripper: bcryptjohn-the-ripper: WPA PSKjohn-the-ripper: Blowfishjohn-the-ripper: MD5graphics-magick: Sharpengraphics-magick: Enhancedsvt-av1: Preset 4 - Bosphorus 4Ksvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 4Kmt-dgemm: Sustained Floating-Point Ratecoremark: CoreMark Size 666 - Iterations Per Secondcompress-7zip: Compression Ratingcompress-7zip: Decompression Ratingstockfish: Total Timeasmfish: 1024 Hash Memory, 26 Depthbuild-godot: Time To Compilebuild-linux-kernel: defconfigbuild-linux-kernel: allmodconfigbuild-llvm: Ninjabuild-nodejs: Time To Compileprimesieve: 1e13rays1bench: Large Sceneonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUhelsing: 14 digittachyon: Total Timecpuminer-opt: Deepcoincpuminer-opt: Blake-2 Scpuminer-opt: Myriad-Groestlcpuminer-opt: Triple SHA-256, Onecoinliquid-dsp: 128 - 256 - 512liquid-dsp: 240 - 256 - 512askap: tConvolve MPI - Degriddingaskap: tConvolve MPI - Griddingastcenc: Mediumastcenc: Thoroughastcenc: Exhaustivegraph500: 26graph500: 26graph500: 26graph500: 26gromacs: MPI CPU - water_GMX50_bareduckdb: IMDBduckdb: TPC-H Parquetpgbench: 100 - 1000 - Read Writepgbench: 100 - 1000 - Read Write - Average Latencyrawtherapee: Total Benchmark Timestress-ng: CPU Stressstress-ng: Matrix Mathstress-ng: Vector Mathstress-ng: AVX-512 VNNIstress-ng: Floating Pointstress-ng: Matrix 3D Mathstress-ng: Memory Copyingstress-ng: Wide Vector Mathstress-ng: Fused Multiply-Addstress-ng: Vector Floating Pointbuild-gem5: Time To Compileopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX41.694149381.6824046.2548109.281748.5539739.6258334.5321268.701193.12447.72530.30819979291111403.5254.4900319.8117205323185.17717253.021924.16881770310698111900667136317610.82613.90831.46831.49617.9367782263279.939802345295389055153826682150936379139.09966.894282.286195.982173.87735.49067.61222986666723774666712407.69652.19124979000013156500002990270004670120005.19492.081148.7595497518.23046.71830484.77512759.08359058.524173580.1320137.3517483.0227182.722002466.67139525267.41103967.93180.6227.46134.0619.0652.5119.1652.20124.478.021.01993.52184.365.4144.5822.449.94100.62285.003.5026.5337.703.24308.4223.7842.0576.4413.0726.6837.484.33231.18781.771.274.16240.51595.731.67213489.5450606.21100501.034351.68251214.2394796.9588821.774472.175178.88726.81416699396672039.82582.51601.1383.98571810.760549223830.86756612.271115.41727236128301728191469266782413807.016119.984206.132202.28343.4568853998440.41402454716565899128565135924830468686.96230.978261.438122.388109.23223.288582.320.3589021.2583555.90216.052933632560763449404013931306966667153046666740906.543543.9443.458962.63936.619663470200064771100031793100039999400010.314104.275120.7641612462.03257.892212486.91430429.52619071.099099613.6530460.619100.7427883.512721964.70206576021.93219092.94156.37448.01993.05340.49140.80341.45140.453237.4014.8194.94503.9111647.894.111712.7228.005727.478.374793.8020.0116968.105.642039.2423.52555.2186.389585.3410.005467.678.762541.5137.7583726.280.902141.6344.96107003.120.65OpenBenchmarking.org

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: 60GPTshop.ai GH2001020304050SE +/- 0.29, N = 341.691. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

NAS Parallel Benchmarks

Test / Class: BT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX50K100K150K200K250KSE +/- 150.57, N = 3SE +/- 492.77, N = 349381.68213489.541. (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: CG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX11K22K33K44K55KSE +/- 54.20, N = 3SE +/- 557.33, N = 324046.2550606.211. (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

NAS Parallel Benchmarks

Test / Class: FT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX20K40K60K80K100KSE +/- 82.39, N = 3SE +/- 62.59, N = 348109.28100501.031. (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: IS.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX9001800270036004500SE +/- 1.10, N = 3SE +/- 18.52, N = 31748.554351.681. (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: LU.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX50K100K150K200K250KSE +/- 430.26, N = 3SE +/- 1429.28, N = 339739.62251214.231. (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: MG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX20K40K60K80K100KSE +/- 39.48, N = 3SE +/- 555.59, N = 358334.5394796.951. (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: SP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX20K40K60K80K100KSE +/- 249.16, N = 4SE +/- 97.08, N = 321268.7088821.771. (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

miniBUDE

Implementation: OpenMP - Input Deck: BM2

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2GPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX10002000300040005000SE +/- 2.95, N = 3SE +/- 5.10, N = 31193.124472.18-mcpu=native-march=native1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -lm

miniBUDE

Implementation: OpenMP - Input Deck: BM2

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2GPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX4080120160200SE +/- 0.12, N = 3SE +/- 0.20, N = 347.73178.89-mcpu=native-march=native1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -lm

Rodinia

Test: OpenMP LavaMD

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX714212835SE +/- 0.08, N = 3SE +/- 0.05, N = 330.3126.811. (CXX) g++ options: -O2 -lOpenCL

Algebraic Multi-Grid Benchmark

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2GPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX400M800M1200M1600M2000MSE +/- 16287263.84, N = 9SE +/- 2196017.33, N = 3199792911116699396671. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi

libxsmm

M N K: 128

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 128HP Z6 G5 A - Threadripper PRO 7995WX400800120016002000SE +/- 4.04, N = 32039.81. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

libxsmm

M N K: 256

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 256HP Z6 G5 A - Threadripper PRO 7995WX6001200180024003000SE +/- 1.59, N = 32582.51. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

NWChem

Input: C240 Buckyball

OpenBenchmarking.orgSeconds, Fewer Is BetterNWChem 7.0.2Input: C240 BuckyballGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX300600900120015001403.51601.1-m641. (F9X) gfortran options: -lnwctask -lccsd -lmcscf -lselci -lmp2 -lmoints -lstepper -ldriver -loptim -lnwdft -lgradients -lcphf -lesp -lddscf -ldangchang -lguess -lhessian -lvib -lnwcutil -lrimp2 -lproperty -lsolvation -lnwints -lprepar -lnwmd -lnwpw -lofpw -lpaw -lpspw -lband -lnwpwlib -lcafe -lspace -lanalyze -lqhop -lpfft -ldplot -ldrdy -lvscf -lqmmm -lqmd -letrans -ltce -lbq -lmm -lcons -lperfm -ldntmc -lccca -ldimqm -lga -larmci -lpeigs -l64to32 -lopenblas -lpthread -lrt -llapack -lnwcblas -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lcomex -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2

Xcompact3d Incompact3d

Input: X3D-benchmarking input.i3d

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX80160240320400SE +/- 0.50, N = 3SE +/- 0.96, N = 3254.49383.991. (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

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX3691215SE +/- 0.02630858, N = 3SE +/- 0.08460429, N = 39.8117205310.760549201. (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

LULESH

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3GPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX5K10K15K20K25KSE +/- 15.38, N = 3SE +/- 128.12, N = 323185.1823830.871. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

Xmrig

Variant: Monero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.18.1Variant: Monero - Hash Count: 1MGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX12K24K36K48K60KSE +/- 9.66, N = 3SE +/- 161.30, N = 317253.056612.2-maes1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Xmrig

Variant: Wownero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.18.1Variant: Wownero - Hash Count: 1MGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX15K30K45K60K75KSE +/- 16.77, N = 3SE +/- 250.10, N = 321924.171115.4-maes1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

John The Ripper

Test: bcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX40K80K120K160K200KSE +/- 7.67, N = 3SE +/- 69.15, N = 368817172723-lgmp -lbz2-m641. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

John The Ripper

Test: WPA PSK

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX130K260K390K520K650KSE +/- 28.67, N = 3SE +/- 2936.87, N = 370310612830-m641. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX40K80K120K160K200KSE +/- 24.83, N = 3SE +/- 163.99, N = 369811172819-lgmp -lbz2-m641. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

John The Ripper

Test: MD5

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5GPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX3M6M9M12M15MSE +/- 12251.98, N = 3SE +/- 110105.00, N = 3190066714692667-m641. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

GraphicsMagick

Operation: Sharpen

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: SharpenGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX30060090012001500SE +/- 10.90, N = 3SE +/- 1.76, N = 31363824-ljbig -lwebp -lwebpmux -ltiff -lfreetype -lSM -lICE -lbz2 -lzstd1. (CC) gcc options: -fopenmp -O2 -ljpeg -lXext -lX11 -llzma -lz -lm -lpthread

GraphicsMagick

Operation: Enhanced

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: EnhancedGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX400800120016002000SE +/- 0.33, N = 3SE +/- 6.64, N = 317611380-ljbig -lwebp -lwebpmux -ltiff -lfreetype -lSM -lICE -lbz2 -lzstd1. (CC) gcc options: -fopenmp -O2 -ljpeg -lXext -lX11 -llzma -lz -lm -lpthread

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 4 - Input: Bosphorus 4KGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX246810SE +/- 0.002, N = 3SE +/- 0.053, N = 30.8267.016-mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq1. (CXX) g++ options: -march=native

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 8 - Input: Bosphorus 4KGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX306090120150SE +/- 0.03, N = 3SE +/- 0.98, N = 1213.91119.98-mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq1. (CXX) g++ options: -march=native

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 12 - Input: Bosphorus 4KGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX50100150200250SE +/- 0.00, N = 3SE +/- 1.23, N = 331.47206.13-mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq1. (CXX) g++ options: -march=native

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 13 - Input: Bosphorus 4KGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX4080120160200SE +/- 0.00, N = 3SE +/- 2.01, N = 331.50202.28-mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq1. (CXX) g++ options: -march=native

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX1020304050SE +/- 0.27, N = 12SE +/- 0.25, N = 317.9443.461. (CC) gcc options: -O3 -march=native -fopenmp

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX900K1800K2700K3600K4500KSE +/- 9376.30, N = 3SE +/- 5264.15, N = 32263279.943998440.411. (CC) gcc options: -O2 -lrt" -lrt

7-Zip Compression

Test: Compression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX120K240K360K480K600KSE +/- 220.18, N = 3SE +/- 2297.47, N = 33452955471651. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

7-Zip Compression

Test: Decompression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX140K280K420K560K700KSE +/- 229.99, N = 3SE +/- 3067.65, N = 33890556589911. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 15Total TimeGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX60M120M180M240M300MSE +/- 3694553.52, N = 12SE +/- 3424910.11, N = 3153826682285651359-m64 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi21. (CXX) g++ options: -lgcov -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -flto -flto=jobserver

asmFish

1024 Hash Memory, 26 Depth

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX50M100M150M200M250MSE +/- 653999.42, N = 3SE +/- 3281525.65, N = 3150936379248304686

Timed Godot Game Engine Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To CompileGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX306090120150SE +/- 1.36, N = 3SE +/- 0.83, N = 3139.1086.96

Timed Linux Kernel Compilation

Build: defconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX1530456075SE +/- 0.40, N = 3SE +/- 0.30, N = 366.8930.98

Timed Linux Kernel Compilation

Build: allmodconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfigGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX60120180240300SE +/- 1.16, N = 3SE +/- 0.89, N = 3282.29261.44

Timed LLVM Compilation

Build System: Ninja

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX4080120160200SE +/- 0.44, N = 3SE +/- 0.30, N = 3195.98122.39

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 19.8.1Time To CompileGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX4080120160200SE +/- 0.05, N = 3SE +/- 0.62, N = 3173.88109.23

Primesieve

Length: 1e13

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 8.0Length: 1e13GPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX816243240SE +/- 0.33, N = 3SE +/- 0.20, N = 335.4923.291. (CXX) g++ options: -O3

rays1bench

Large Scene

OpenBenchmarking.orgmrays/s, More Is Betterrays1bench 2020-01-09Large SceneHP Z6 G5 A - Threadripper PRO 7995WX130260390520650SE +/- 2.65, N = 3582.32

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUHP Z6 G5 A - Threadripper PRO 7995WX0.08080.16160.24240.32320.404SE +/- 0.001912, N = 30.358902MIN: 0.321. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUHP Z6 G5 A - Threadripper PRO 7995WX0.28310.56620.84931.13241.4155SE +/- 0.01004, N = 31.25835MIN: 1.011. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Helsing

Digit Range: 14 digit

OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digitGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX1530456075SE +/- 0.52, N = 10SE +/- 0.11, N = 367.6155.901. (CC) gcc options: -O2 -pthread

Tachyon

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99.2Total TimeHP Z6 G5 A - Threadripper PRO 7995WX48121620SE +/- 0.03, N = 316.051. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

Cpuminer-Opt

Algorithm: Deepcoin

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: DeepcoinHP Z6 G5 A - Threadripper PRO 7995WX7K14K21K28K35KSE +/- 357.43, N = 5336321. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Cpuminer-Opt

Algorithm: Blake-2 S

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: Blake-2 SHP Z6 G5 A - Threadripper PRO 7995WX120K240K360K480K600KSE +/- 1705.31, N = 35607631. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Cpuminer-Opt

Algorithm: Myriad-Groestl

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: Myriad-GroestlHP Z6 G5 A - Threadripper PRO 7995WX10K20K30K40K50KSE +/- 64.29, N = 3449401. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Cpuminer-Opt

Algorithm: Triple SHA-256, Onecoin

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: Triple SHA-256, OnecoinHP Z6 G5 A - Threadripper PRO 7995WX90K180K270K360K450KSE +/- 2385.23, N = 34013931. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Liquid-DSP

Threads: 128 - Buffer Length: 256 - Filter Length: 512

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 512GPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX300M600M900M1200M1500MSE +/- 271804.67, N = 3SE +/- 6716728.70, N = 322986666713069666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 240 - Buffer Length: 256 - Filter Length: 512

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 240 - Buffer Length: 256 - Filter Length: 512GPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX300M600M900M1200M1500MSE +/- 501741.41, N = 3SE +/- 7410877.89, N = 323774666715304666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

ASKAP

Test: tConvolve MPI - Degridding

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX9K18K27K36K45KSE +/- 21.70, N = 3SE +/- 524.43, N = 312407.640906.51. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

ASKAP

Test: tConvolve MPI - Gridding

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX9K18K27K36K45KSE +/- 13.17, N = 3SE +/- 527.54, N = 39652.1943543.901. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

ASTC Encoder

Preset: Medium

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: MediumHP Z6 G5 A - Threadripper PRO 7995WX100200300400500SE +/- 1.12, N = 3443.461. (CXX) g++ options: -O3 -flto -pthread

ASTC Encoder

Preset: Thorough

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ThoroughHP Z6 G5 A - Threadripper PRO 7995WX1428425670SE +/- 0.18, N = 362.641. (CXX) g++ options: -O3 -flto -pthread

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ExhaustiveHP Z6 G5 A - Threadripper PRO 7995WX246810SE +/- 0.0214, N = 36.61961. (CXX) g++ options: -O3 -flto -pthread

Graph500

Scale: 26

OpenBenchmarking.orgbfs median_TEPS, More Is BetterGraph500 3.0Scale: 26GPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX300M600M900M1200M1500M12497900006347020001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

Graph500

Scale: 26

OpenBenchmarking.orgbfs max_TEPS, More Is BetterGraph500 3.0Scale: 26GPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX300M600M900M1200M1500M13156500006477110001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

Graph500

Scale: 26

OpenBenchmarking.orgsssp median_TEPS, More Is BetterGraph500 3.0Scale: 26GPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX70M140M210M280M350M2990270003179310001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

Graph500

Scale: 26

OpenBenchmarking.orgsssp max_TEPS, More Is BetterGraph500 3.0Scale: 26GPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX100M200M300M400M500M4670120003999940001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX3691215SE +/- 0.002, N = 3SE +/- 0.389, N = 95.19410.3141. (CXX) g++ options: -O3

DuckDB

Benchmark: IMDB

OpenBenchmarking.orgSeconds, Fewer Is BetterDuckDB 0.9.1Benchmark: IMDBGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX20406080100SE +/- 0.70, N = 3SE +/- 0.12, N = 392.08104.281. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl

DuckDB

Benchmark: TPC-H Parquet

OpenBenchmarking.orgSeconds, Fewer Is BetterDuckDB 0.9.1Benchmark: TPC-H ParquetGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX306090120150SE +/- 1.06, N = 3SE +/- 0.09, N = 3148.76120.761. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl

PostgreSQL

Scaling Factor: 100 - Clients: 1000 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read WriteGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX12K24K36K48K60KSE +/- 783.91, N = 11SE +/- 176.81, N = 354975161241. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL

Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average LatencyGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX1428425670SE +/- 0.28, N = 11SE +/- 0.68, N = 318.2362.031. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

RawTherapee

Total Benchmark Time

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX1326395265SE +/- 0.24, N = 3SE +/- 0.31, N = 346.7257.891. RawTherapee, version 5.9, command line.

Stress-NG

Test: CPU Stress

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: CPU StressGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX50K100K150K200K250KSE +/- 24.74, N = 3SE +/- 1093.61, N = 330484.77212486.911. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Matrix Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Matrix MathGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX110K220K330K440K550KSE +/- 3363.22, N = 3SE +/- 1114.33, N = 3512759.08430429.521. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Vector Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector MathGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX130K260K390K520K650KSE +/- 38.26, N = 3SE +/- 183.75, N = 3359058.52619071.091. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: AVX-512 VNNI

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: AVX-512 VNNIGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX2M4M6M8M10MSE +/- 21528.43, N = 3SE +/- 4488.69, N = 34173580.139099613.651. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Floating Point

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Floating PointGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX7K14K21K28K35KSE +/- 4.82, N = 3SE +/- 30.90, N = 320137.3530460.611. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Matrix 3D Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Matrix 3D MathGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX4K8K12K16K20KSE +/- 12.40, N = 3SE +/- 2.39, N = 317483.029100.741. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Memory Copying

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Memory CopyingGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX6K12K18K24K30KSE +/- 78.88, N = 3SE +/- 21.26, N = 327182.7227883.511. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Wide Vector Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Wide Vector MathGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX600K1200K1800K2400K3000KSE +/- 16548.38, N = 15SE +/- 3634.23, N = 32002466.672721964.701. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Fused Multiply-Add

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Fused Multiply-AddGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX40M80M120M160M200MSE +/- 1701013.93, N = 3SE +/- 157257.42, N = 3139525267.41206576021.931. (CXX) g++ options: -O2 -std=gnu99 -lc

Stress-NG

Test: Vector Floating Point

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Floating PointGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX50K100K150K200K250KSE +/- 87.06, N = 3SE +/- 135.17, N = 3103967.93219092.941. (CXX) g++ options: -O2 -std=gnu99 -lc

Timed Gem5 Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 23.0.1Time To CompileGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX4080120160200SE +/- 2.14, N = 3SE +/- 1.07, N = 3180.62156.37

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX1122334455SE +/- 0.05, N = 3SE +/- 0.07, N = 37.4648.011. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX2004006008001000SE +/- 0.82, N = 3SE +/- 0.98, N = 3134.06993.05MIN: 482.47 / MAX: 1144.591. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX70140210280350SE +/- 0.19, N = 15SE +/- 0.25, N = 319.06340.491. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX306090120150SE +/- 0.52, N = 15SE +/- 0.12, N = 352.51140.80MIN: 45.64 / MAX: 88.61MIN: 52.25 / MAX: 220.241. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX70140210280350SE +/- 0.22, N = 4SE +/- 0.34, N = 319.16341.451. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX306090120150SE +/- 0.59, N = 4SE +/- 0.13, N = 352.20140.45MIN: 46.86 / MAX: 83.61MIN: 52.13 / MAX: 230.351. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX7001400210028003500SE +/- 0.97, N = 3SE +/- 4.78, N = 3124.473237.401. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX48121620SE +/- 0.06, N = 3SE +/- 0.02, N = 38.0214.81MIN: 6.08 / MAX: 18.7MIN: 6.08 / MAX: 45.261. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX20406080100SE +/- 0.00, N = 3SE +/- 0.05, N = 31.0194.941. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX2004006008001000SE +/- 4.42, N = 3SE +/- 0.20, N = 3993.52503.91MIN: 966.61 / MAX: 1035.71MIN: 253.56 / MAX: 608.111. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX2K4K6K8K10KSE +/- 0.31, N = 3SE +/- 20.00, N = 3184.3611647.891. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX1.21732.43463.65194.86926.0865SE +/- 0.01, N = 3SE +/- 0.01, N = 35.414.11MIN: 3.66 / MAX: 12.71MIN: 2.29 / MAX: 22.11. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX400800120016002000SE +/- 0.39, N = 15SE +/- 1.75, N = 344.581712.721. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX714212835SE +/- 0.19, N = 15SE +/- 0.03, N = 322.4428.00MIN: 18.38 / MAX: 33.33MIN: 18.2 / MAX: 67.591. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX12002400360048006000SE +/- 0.08, N = 3SE +/- 16.25, N = 39.945727.471. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX20406080100SE +/- 0.77, N = 3SE +/- 0.02, N = 3100.628.37MIN: 95.54 / MAX: 114.291. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX10002000300040005000SE +/- 1.58, N = 3SE +/- 6.25, N = 3285.004793.801. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX510152025SE +/- 0.02, N = 3SE +/- 0.03, N = 33.5020.01MIN: 2.11 / MAX: 13.96MIN: 10.21 / MAX: 40.651. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX4K8K12K16K20KSE +/- 0.29, N = 5SE +/- 38.34, N = 326.5316968.101. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX918273645SE +/- 0.42, N = 5SE +/- 0.01, N = 337.705.64MIN: 34.56 / MAX: 47.33MIN: 3.25 / MAX: 24.091. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX400800120016002000SE +/- 0.00, N = 3SE +/- 2.05, N = 33.242039.241. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX70140210280350SE +/- 0.47, N = 3SE +/- 0.02, N = 3308.4223.52MIN: 299.67 / MAX: 324.141. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX120240360480600SE +/- 0.26, N = 3SE +/- 0.29, N = 323.78555.211. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX20406080100SE +/- 0.47, N = 3SE +/- 0.05, N = 342.0586.38MIN: 37.47 / MAX: 166.36MIN: 51.34 / MAX: 158.071. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX2K4K6K8K10KSE +/- 0.58, N = 3SE +/- 38.08, N = 376.449585.341. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX3691215SE +/- 0.10, N = 3SE +/- 0.04, N = 313.0710.00MIN: 11.41 / MAX: 24.95MIN: 5.34 / MAX: 28.561. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX12002400360048006000SE +/- 0.33, N = 3SE +/- 13.90, N = 326.685467.671. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX918273645SE +/- 0.46, N = 3SE +/- 0.02, N = 337.488.76MIN: 33.64 / MAX: 48.73MIN: 6.07 / MAX: 28.471. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX5001000150020002500SE +/- 0.04, N = 3SE +/- 9.61, N = 34.332541.511. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX50100150200250SE +/- 2.13, N = 3SE +/- 0.14, N = 3231.1837.75MIN: 220.77 / MAX: 317.5MIN: 23.66 / MAX: 98.371. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX20K40K60K80K100KSE +/- 8.02, N = 3SE +/- 300.34, N = 3781.7783726.281. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX0.28580.57160.85741.14321.429SE +/- 0.01, N = 3SE +/- 0.00, N = 31.270.90MIN: 0.64 / MAX: 3.24MIN: 0.25 / MAX: 18.191. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX5001000150020002500SE +/- 0.01, N = 3SE +/- 35.73, N = 124.162141.631. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX50100150200250SE +/- 0.76, N = 3SE +/- 0.90, N = 12240.5144.96MIN: 230.79 / MAX: 323.15MIN: 30.33 / MAX: 84.491. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX20K40K60K80K100KSE +/- 3.96, N = 15SE +/- 398.68, N = 3595.73107003.121. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUGPTshop.ai GH200HP Z6 G5 A - Threadripper PRO 7995WX0.37580.75161.12741.50321.879SE +/- 0.01, N = 15SE +/- 0.00, N = 31.670.65MIN: 1.08 / MAX: 4.63MIN: 0.21 / MAX: 20.431. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Phoronix Test Suite v10.8.5