Benchmarks for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2203262-NE-AMDEPYC7770 AMD EPYC 7773X Linux Benchmarks - Phoronix Test Suite AMD EPYC 7773X Linux Benchmarks Benchmarks for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2203262-NE-AMDEPYC7770&grs&sor&rro .
AMD EPYC 7773X Linux Benchmarks Processor Motherboard Chipset Memory Disk Graphics Network OS Kernel Display Server Vulkan Compiler File-System Screen Resolution EPYC 7773X AMD EPYC 7773X AMD 7773X AMD EPYC 7773X 64-Core @ 2.20GHz (64 Cores / 128 Threads) AMD DAYTONA_X (TYM1008C BIOS) AMD Starship/Matisse 8 x 32 GB DDR4-3200MT/s 36ASF4G72PZ-3G2E2 800GB INTEL SSDPF21Q800GB ASPEED 2 x Mellanox MT27710 Ubuntu 22.04 5.17.0-051700rc8-generic (x86_64) X Server 1.1.182 GCC 11.2.0 ext4 1024x768 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-iOLsLC/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-iOLsLC/gcc-11-11.2.0/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 - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001228 Python Details - Python 3.9.10 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
AMD EPYC 7773X Linux Benchmarks cpuminer-opt: Ringcoin onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU onnx: super-resolution-10 - CPU cpuminer-opt: Deepcoin onnx: yolov4 - CPU cpuminer-opt: Magi npb: EP.D cpuminer-opt: Triple SHA-256, Onecoin pyhpc: CPU - PyTorch - 4194304 - Equation of State svt-av1: Preset 12 - Bosphorus 1080p rodinia: OpenMP HotSpot3D graph500: 26 graph500: 26 pyhpc: CPU - JAX - 4194304 - Equation of State cpuminer-opt: Skeincoin svt-hevc: 7 - Bosphorus 1080p graph500: 26 askap: tConvolve OpenMP - Gridding onednn: IP Shapes 3D - u8s8f32 - CPU cpuminer-opt: Quad SHA-256, Pyrite graph500: 26 luxcorerender: Rainbow Colors and Prism - CPU rodinia: OpenMP Leukocyte cpuminer-opt: Myriad-Groestl incompact3d: input.i3d 193 Cells Per Direction onnx: shufflenet-v2-10 - CPU mt-dgemm: Sustained Floating-Point Rate npb: SP.B pyhpc: CPU - TensorFlow - 4194304 - Equation of State lczero: BLAS onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU rodinia: OpenMP Streamcluster luxcorerender: Orange Juice - CPU pyhpc: CPU - PyTorch - 4194304 - Isoneutral Mixing stress-ng: Context Switching npb: IS.D pyhpc: CPU - JAX - 1048576 - Equation of State pgbench: 100 - 500 - Read Write pgbench: 100 - 500 - Read Write - Average Latency stockfish: Total Time compress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compression cpuminer-opt: Blake-2 S openfoam: Motorbike 30M onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU pyhpc: CPU - JAX - 1048576 - Isoneutral Mixing kvazaar: Bosphorus 4K - Ultra Fast npb: LU.C pyhpc: CPU - PyTorch - 1048576 - Equation of State svt-av1: Preset 10 - Bosphorus 1080p npb: EP.C stress-ng: IO_uring onednn: Deconvolution Batch shapes_3d - f32 - CPU svt-av1: Preset 4 - Bosphorus 1080p svt-av1: Preset 8 - Bosphorus 4K pgbench: 100 - 100 - Read Write pgbench: 100 - 100 - Read Write - Average Latency luxcorerender: DLSC - CPU pyhpc: CPU - PyTorch - 1048576 - Isoneutral Mixing pgbench: 100 - 50 - Read Write pgbench: 100 - 50 - Read Write - Average Latency luxcorerender: Danish Mood - CPU pgbench: 1000 - 500 - Read Only - Average Latency pgbench: 1000 - 500 - Read Only svt-av1: Preset 8 - Bosphorus 1080p npb: CG.C luxcorerender: LuxCore Benchmark - CPU embree: Pathtracer - Asian Dragon svt-av1: Preset 10 - Bosphorus 4K pyhpc: CPU - Numba - 1048576 - Isoneutral Mixing pyhpc: CPU - Numba - 4194304 - Isoneutral Mixing toybrot: C++ Tasks compress-7zip: Compression Rating svt-hevc: 10 - Bosphorus 1080p pyhpc: CPU - JAX - 4194304 - Isoneutral Mixing asmfish: 1024 Hash Memory, 26 Depth povray: Trace Time v-ray: CPU lczero: Eigen pyhpc: CPU - Numpy - 1048576 - Isoneutral Mixing cloverleaf: Lagrangian-Eulerian Hydrodynamics build-mplayer: Time To Compile build-gem5: Time To Compile pgbench: 100 - 250 - Read Write pgbench: 100 - 250 - Read Write - Average Latency askap: tConvolve MPI - Gridding ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU kvazaar: Bosphorus 4K - Very Fast onednn: Recurrent Neural Network Training - f32 - CPU svt-av1: Preset 4 - Bosphorus 4K build2: Time To Compile pyhpc: CPU - Numpy - 4194304 - Isoneutral Mixing rays1bench: Large Scene svt-av1: Preset 12 - Bosphorus 4K pgbench: 100 - 50 - Read Only - Average Latency blender: Pabellon Barcelona - CPU-Only qe: AUSURF112 incompact3d: input.i3d 129 Cells Per Direction gromacs: MPI CPU - water_GMX50_bare pgbench: 1000 - 250 - Read Only - Average Latency onednn: Deconvolution Batch shapes_1d - f32 - CPU pgbench: 100 - 250 - Read Only pgbench: 1000 - 100 - Read Write - Average Latency pgbench: 1000 - 100 - Read Write stress-ng: Atomic npb: FT.C pgbench: 100 - 500 - Read Only - Average Latency pgbench: 100 - 250 - Read Only - Average Latency numpy: stress-ng: Glibc C String Functions pgbench: 100 - 500 - Read Only pyhpc: CPU - Aesara - 4194304 - Equation of State pgbench: 1000 - 250 - Read Only lulesh: build-llvm: Ninja pgbench: 1000 - 50 - Read Only rodinia: OpenMP CFD Solver embree: Pathtracer ISPC - Asian Dragon Obj pgbench: 100 - 100 - Read Only - Average Latency pgbench: 100 - 100 - Read Only npb: MG.C ospray: particle_volume/pathtracer/real_time build-nodejs: Time To Compile build-llvm: Unix Makefiles pgbench: 1000 - 100 - Read Only - Average Latency cpuminer-opt: Garlicoin onednn: IP Shapes 1D - f32 - CPU rocksdb: Read While Writing astcenc: Exhaustive toybrot: C++ Threads ospray-studio: 3 - 1080p - 1 - Path Tracer m-queens: Time To Solve pgbench: 1000 - 250 - Read Write - Average Latency pgbench: 1000 - 250 - Read Write stress-ng: NUMA pgbench: 100 - 50 - Read Only pgbench: 1000 - 50 - Read Write stress-ng: MMAP toktx: UASTC 3 + Zstd Compression 19 draco: Church Facade draco: Lion pyhpc: CPU - Numba - 4194304 - Equation of State pgbench: 1000 - 100 - Read Only primesieve: 1e12 Prime Number Generation astcenc: Medium appleseed: Emily pgbench: 1000 - 50 - Read Write - Average Latency build-godot: Time To Compile nwchem: C240 Buckyball cpuminer-opt: x25x embree: Pathtracer - Crown pyhpc: CPU - Numpy - 1048576 - Equation of State openfoam: Motorbike 60M toybrot: TBB toktx: Zstd Compression 19 rocksdb: Rand Read ospray-studio: 2 - 1080p - 16 - Path Tracer ospray-studio: 3 - 1080p - 32 - Path Tracer rodinia: OpenMP LavaMD build-wasmer: Time To Compile stress-ng: Socket Activity cpuminer-opt: LBC, LBRY Credits embree: Pathtracer ISPC - Crown liquid-dsp: 64 - 256 - 57 ngspice: C2670 npb: SP.C onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU openssl: RSA4096 pyhpc: CPU - Numpy - 4194304 - Equation of State incompact3d: X3D-benchmarking input.i3d blender: Barbershop - CPU-Only onednn: Recurrent Neural Network Inference - f32 - CPU rocksdb: Update Rand ospray: gravity_spheres_volume/dim_512/scivis/real_time ospray: particle_volume/scivis/real_time onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU ospray-studio: 1 - 1080p - 16 - Path Tracer onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU stress-ng: SENDFILE build-gcc: Time To Compile brl-cad: VGR Performance Metric ospray: particle_volume/ao/real_time liquid-dsp: 128 - 256 - 57 pyhpc: CPU - Aesara - 1048576 - Isoneutral Mixing onednn: Recurrent Neural Network Inference - u8s8f32 - CPU toktx: Zstd Compression 9 ospray-studio: 1 - 1080p - 32 - Path Tracer embree: Pathtracer ISPC - Asian Dragon ospray: gravity_spheres_volume/dim_512/ao/real_time blender: Classroom - CPU-Only stress-ng: Malloc quantlib: onednn: IP Shapes 3D - f32 - CPU rocksdb: Read Rand Write Rand askap: tConvolve MT - Degridding stress-ng: Memory Copying onednn: Convolution Batch Shapes Auto - f32 - CPU stress-ng: MEMFD askap: tConvolve MT - Gridding ospray-studio: 1 - 1080p - 1 - Path Tracer ospray-studio: 2 - 1080p - 1 - Path Tracer npb: BT.C toybrot: OpenMP pgbench: 1000 - 500 - Read Write - Average Latency pgbench: 1000 - 500 - Read Write ospray-studio: 2 - 1080p - 32 - Path Tracer openssl: SHA256 ngspice: C7552 amg: build-linux-kernel: defconfig appleseed: Disney Material compress-7zip: Decompression Rating namd: ATPase Simulation - 327,506 Atoms stress-ng: Glibc Qsort Data Sorting minife: Small ospray-studio: 3 - 1080p - 16 - Path Tracer toktx: UASTC 4 + Zstd Compression 19 ospray: gravity_spheres_volume/dim_512/pathtracer/real_time n-queens: Elapsed Time gpaw: Carbon Nanotube tachyon: Total Time pyhpc: CPU - Aesara - 4194304 - Isoneutral Mixing stress-ng: Vector Math build-linux-kernel: allmodconfig openssl: RSA4096 appleseed: Material Tester embree: Pathtracer - Asian Dragon Obj stress-ng: System V Message Passing astcenc: Thorough stress-ng: CPU Stress toktx: UASTC 3 hpcg: blender: Fishy Cat - CPU-Only rocksdb: Seq Fill onednn: Recurrent Neural Network Training - u8s8f32 - CPU stress-ng: Crypto stress-ng: Forking stress-ng: Matrix Math stress-ng: Semaphores pyhpc: CPU - TensorFlow - 1048576 - Equation of State pyhpc: CPU - Aesara - 1048576 - Equation of State pyhpc: CPU - Numba - 1048576 - Equation of State onnx: fcn-resnet101-11 - CPU blender: BMW27 - CPU-Only stress-ng: CPU Cache pgbench: 1000 - 50 - Read Only - Average Latency askap: Hogbom Clean OpenMP askap: tConvolve OpenMP - Degridding askap: tConvolve MPI - Degridding openvkl: vklBenchmark Scalar openvkl: vklBenchmark ISPC oidn: RTLightmap.hdr.4096x4096 oidn: RT.ldr_alb_nrm.3840x2160 oidn: RT.hdr_alb_nrm.3840x2160 parboil: OpenMP LBM EPYC 7773X AMD EPYC 7773X AMD 7773X 36.96 4.75269 1.96053 4417 59610 361 2706.58 4653.17 118190 0.118 686.577 94.43 339260000 268226000 0.053 256530 314.3 595928000 22188 0.605726 63780 615933000 25.68 39.575 116180 17.1823597 13063 29.457515 138163.14 0.168 5298 1.30094 5.622 14 1.611 6157698.82 2782.01 0.022 70661 7.076 168120931 2.543 585460 16.02 0.386596 0.134 62.35 261179.07 0.028 403.239 5052.44 1842135.72 3.03052 7.589 84.354 81522 1.227 9.41 0.342 70106 0.713 7.34 0.452 1105462 196.39 38420.81 7.59 80.0652 161.214 0.367 1.554 7422 396660 623.7 0.661 158355881 10.54 59113 5216 0.581 11.31 10.796 194.408 77211 3.238 36827.5 1201.49 0.875948 40.73 886.031 4.145 62.038 2.4 304.45 211.034 0.07 89.22 386.42 4.5369482 7.166 0.229 8.02731 1562316 1.543 64802 126475.88 64208.35 0.323 0.16 426.52 7397152.01 1547901 0.424 1092431 21840.619 140.793 654363 6.822 64.1248 0.099 1013194 60162.18 316.861 132.65 206.382 0.107 1649.67 1.25407 9995001 11.4184 7047 627 10.885 4.145 60313 233.66 709272 62469 1143.21 8.905 6298 5290 0.296 937666 4.589 4.6051 122.467526 0.8 47.941 2199.2 1565.76 68.0179 0.183 119.31 7006 20.111 276582763 8581 20075 44.427 63.273 17550.1 185460 62.6103 2807300000 155.426 89121.25 657.252 13667.8 1.065 575.434998 275.04 656.481 315370 8.72023 69.65 887.784 8499 0.736474 1119510.19 776.844 744905 72.5146 2939500000 0.367 659.061 3.408 17099 72.161 9.10231 72.83 1606428610.69 2322.6 1.187 3521479 8286.11 12392.52 0.839175 1267.98 5483.63 530 534 169658.95 7532 9.366 53384 17212 77295739610 114.107 1054655000 25.477 57.32824 409802 0.37403 645.83 22593.6 10063 60.517 13.6589 2.443 57.938 28.1718 1.708 298492.58 233.096 897876.2 148.743882 72.5369 9426628.4 6.4687 147632.95 4.738 19.6786 36.73 319924 888.03 14973.7 75988 206189.39 8446018.43 0.036 0.107 0.074 173 28.26 12.74 0.076 806.452 19018.3 32294.8 102 176 0.81 1.65 1.65 79.23 42950 2295.14 5486.28 122300 665.552 107.592 298909000 238903000 245770 341.1 646862000 20481.2 69070 662914000 27.61 42.487 116030 17.2316799 30.668516 146542.01 5575 5.907 13.41 2910.19 67917 7.362 174759227 2.479 590510 16.67 61.22 251848.99 415.953 5237.79 7.675 86.559 78821 1.269 9.21 68181 0.733 7.38 0.447 1117340 197.632 38745.62 7.54 80.0108 157.12 7245 393285 615.38 158777712 10.355 5116 11.10 10.997 190.885 75866 3.295 36192.5 1194.17 41.38 4.183 61.112 308.98 209.913 0.071 388.99 4.47657299 7.071 0.226 1549282 1.563 63973 64170.34 0.323 0.161 421.53 1548226 1104789 21597.783 139.266 657459 6.76 63.9861 0.099 1013179 60483.51 317.102 133.917 206.741 0.106 1652.42 11.4329 6997 625 10.801 4.163 60059 232.81 705546 62692 1149.1 8.947 6341 5324 943998 4.591 4.5766 0.798 48.154 2186.2 1575 67.8064 119.47 6970 20.056 8618 20142 44.302 63.131 184680 62.8741 2818900000 155.562 89473.38 13671.4 574.784973 8.74566 69.8143 8478 775.397 72.5692 2942500000 3.401 17102 72.1747 9.095 2317 8272.03 1266.83 5479.22 530 534 169343.55 7537 9.38 53304 17224 77341787750 114.221 1055936000 25.516 409242 0.37417 22591.3 10059 60.504 13.6519 2.44 28.205 232.827 898143.3 72.5217 6.4734 4.735 19.6896 0.076 806.452 19018.3 32294.8 102 176 0.81 1.65 1.65 30.3 10.4921 3.16172 6706 58150 470 2830.04 4653.01 136230 0.136 595.79 101.051 336751000 266205000 0.059 233440 343.84 604283000 20481.2 0.559299 66000 627605000 26.63 39.926 123990 18.2551613 12312 28.913128 143689.5 0.177 5379 1.36697 5.895 13.34 1.69 5879171.86 2782.78 0.023 67592 7.397 167400779 2.439 609780 16.07 0.401409 0.139 60.12 260875.7 0.027 401.107 5103.77 1908001.84 3.13792 7.852 87.258 78985 1.266 9.13 0.352 68479 0.73 7.18 0.44 1135454 192.474 37738.61 7.74 78.0285 159.545 0.376 1.592 7301 387703 629.59 0.676 155386596 10.329 57962 5196 0.592 11.11 10.853 191.182 76215 3.28 36827.5 1181.75 0.890446 41.25 899.94 4.209 61.127 2.436 307.33 213 0.07 90.47 383.7 4.48201895 7.163 0.229 8.13289 1542188 1.56 64101 128080.47 63406.26 0.319 0.162 426.78 7488758.35 1566167 0.429 1092755 21749.38 139.264 661198 6.752 63.469 0.098 1023408 60754.02 314.09 133.205 204.787 0.107 1637.28 1.24333 9912022 11.5135 7054 630 10.809 4.177 59851 234.6 710842 62245 1151.4 8.966 6303 5326 0.294 938463 4.619 4.5754 123.256848 0.803 48.232 2188.7 1571.01 68.1866 0.182 119.94 7001 20.009 275200675 8623 20172 44.505 62.992 17625.65 185250 62.8561 2813400000 156.065 89271.13 654.694 13619.8 1.069 576.926819 276.03 658.771 314318 8.71677 69.5876 890.636 8505 0.734164 1122873.84 774.539 742743 72.7138 2934500000 0.368 657.311 3.399 17144 71.9884 9.07886 73.01 1602472159.46 2318 1.18972 3529385 8268.02 12418.84 0.837436 1265.5 5473.06 529 535 169478.3 7546 9.383 53288 17242 77427390920 114.289 1056319000 25.503 57.408921 409463 0.37454 644.97 22564.1 10072 60.581 13.642 2.443 57.869 28.1797 1.706 298837.95 232.863 897194.4 148.614133 72.5806 9433754.46 6.4723 147735.12 4.737 19.6837 36.71 320048 888.345 14970.53 76000.4 206162.79 8445532.57 0.036 0.107 0.074 173 28.26 12.74 0.076 806.452 19018.3 32294.8 102 176 0.81 1.65 1.65 OpenBenchmarking.org
Cpuminer-Opt Algorithm: Ringcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Ringcoin AMD 7773X EPYC 7773X AMD EPYC 7773X 20 40 60 80 100 30.30 36.96 79.23 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU AMD 7773X EPYC 7773X 3 6 9 12 15 10.49210 4.75269 MIN: 9.12 MIN: 4.4 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU AMD 7773X EPYC 7773X 0.7114 1.4228 2.1342 2.8456 3.557 3.16172 1.96053 MIN: 1.74 MIN: 1.54 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
ONNX Runtime Model: super-resolution-10 - Device: CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.10 Model: super-resolution-10 - Device: CPU EPYC 7773X AMD 7773X 1400 2800 4200 5600 7000 4417 6706 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
Cpuminer-Opt Algorithm: Deepcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Deepcoin AMD EPYC 7773X AMD 7773X EPYC 7773X 13K 26K 39K 52K 65K 42950 58150 59610 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
ONNX Runtime Model: yolov4 - Device: CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.10 Model: yolov4 - Device: CPU EPYC 7773X AMD 7773X 100 200 300 400 500 361 470 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
Cpuminer-Opt Algorithm: Magi OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Magi AMD EPYC 7773X EPYC 7773X AMD 7773X 600 1200 1800 2400 3000 2295.14 2706.58 2830.04 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
NAS Parallel Benchmarks Test / Class: EP.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D AMD 7773X EPYC 7773X AMD EPYC 7773X 1200 2400 3600 4800 6000 4653.01 4653.17 5486.28 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
Cpuminer-Opt Algorithm: Triple SHA-256, Onecoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Triple SHA-256, Onecoin EPYC 7773X AMD EPYC 7773X AMD 7773X 30K 60K 90K 120K 150K 118190 122300 136230 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
PyHPC Benchmarks Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Equation of State AMD 7773X EPYC 7773X 0.0306 0.0612 0.0918 0.1224 0.153 0.136 0.118
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 12 - Input: Bosphorus 1080p AMD 7773X AMD EPYC 7773X EPYC 7773X 150 300 450 600 750 595.79 665.55 686.58 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Rodinia Test: OpenMP HotSpot3D OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP HotSpot3D AMD EPYC 7773X AMD 7773X EPYC 7773X 20 40 60 80 100 107.59 101.05 94.43 1. (CXX) g++ options: -O2 -lOpenCL
Graph500 Scale: 26 OpenBenchmarking.org sssp max_TEPS, More Is Better Graph500 3.0 Scale: 26 AMD EPYC 7773X AMD 7773X EPYC 7773X 70M 140M 210M 280M 350M 298909000 336751000 339260000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
Graph500 Scale: 26 OpenBenchmarking.org sssp median_TEPS, More Is Better Graph500 3.0 Scale: 26 AMD EPYC 7773X AMD 7773X EPYC 7773X 60M 120M 180M 240M 300M 238903000 266205000 268226000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
PyHPC Benchmarks Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Equation of State AMD 7773X EPYC 7773X 0.0133 0.0266 0.0399 0.0532 0.0665 0.059 0.053
Cpuminer-Opt Algorithm: Skeincoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Skeincoin AMD 7773X AMD EPYC 7773X EPYC 7773X 50K 100K 150K 200K 250K 233440 245770 256530 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
SVT-HEVC Tuning: 7 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p EPYC 7773X AMD EPYC 7773X AMD 7773X 70 140 210 280 350 314.30 341.10 343.84 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Graph500 Scale: 26 OpenBenchmarking.org bfs median_TEPS, More Is Better Graph500 3.0 Scale: 26 EPYC 7773X AMD 7773X AMD EPYC 7773X 140M 280M 420M 560M 700M 595928000 604283000 646862000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
ASKAP Test: tConvolve OpenMP - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Gridding AMD EPYC 7773X AMD 7773X EPYC 7773X 5K 10K 15K 20K 25K 20481.2 20481.2 22188.0 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU EPYC 7773X AMD 7773X 0.1363 0.2726 0.4089 0.5452 0.6815 0.605726 0.559299 MIN: 0.55 MIN: 0.52 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Cpuminer-Opt Algorithm: Quad SHA-256, Pyrite OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Quad SHA-256, Pyrite EPYC 7773X AMD 7773X AMD EPYC 7773X 15K 30K 45K 60K 75K 63780 66000 69070 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Graph500 Scale: 26 OpenBenchmarking.org bfs max_TEPS, More Is Better Graph500 3.0 Scale: 26 EPYC 7773X AMD 7773X AMD EPYC 7773X 140M 280M 420M 560M 700M 615933000 627605000 662914000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
LuxCoreRender Scene: Rainbow Colors and Prism - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Rainbow Colors and Prism - Acceleration: CPU EPYC 7773X AMD 7773X AMD EPYC 7773X 6 12 18 24 30 25.68 26.63 27.61 MIN: 22.83 / MAX: 26.25 MIN: 23.78 / MAX: 27.25 MIN: 24.43 / MAX: 28.25
Rodinia Test: OpenMP Leukocyte OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Leukocyte AMD EPYC 7773X AMD 7773X EPYC 7773X 10 20 30 40 50 42.49 39.93 39.58 1. (CXX) g++ options: -O2 -lOpenCL
Cpuminer-Opt Algorithm: Myriad-Groestl OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Myriad-Groestl AMD EPYC 7773X EPYC 7773X AMD 7773X 30K 60K 90K 120K 150K 116030 116180 123990 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Xcompact3d Incompact3d Input: input.i3d 193 Cells Per Direction OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction AMD 7773X AMD EPYC 7773X EPYC 7773X 4 8 12 16 20 18.26 17.23 17.18 1. (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
ONNX Runtime Model: shufflenet-v2-10 - Device: CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.10 Model: shufflenet-v2-10 - Device: CPU AMD 7773X EPYC 7773X 3K 6K 9K 12K 15K 12312 13063 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
ACES DGEMM Sustained Floating-Point Rate OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate AMD 7773X EPYC 7773X AMD EPYC 7773X 7 14 21 28 35 28.91 29.46 30.67 1. (CC) gcc options: -O3 -march=native -fopenmp
NAS Parallel Benchmarks Test / Class: SP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B EPYC 7773X AMD 7773X AMD EPYC 7773X 30K 60K 90K 120K 150K 138163.14 143689.50 146542.01 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
PyHPC Benchmarks Device: CPU - Backend: TensorFlow - Project Size: 4194304 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: TensorFlow - Project Size: 4194304 - Benchmark: Equation of State AMD 7773X EPYC 7773X 0.0398 0.0796 0.1194 0.1592 0.199 0.177 0.168
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: BLAS EPYC 7773X AMD 7773X AMD EPYC 7773X 1200 2400 3600 4800 6000 5298 5379 5575 1. (CXX) g++ options: -flto -pthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU AMD 7773X EPYC 7773X 0.3076 0.6152 0.9228 1.2304 1.538 1.36697 1.30094 MIN: 1.12 MIN: 1.09 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster AMD EPYC 7773X AMD 7773X EPYC 7773X 1.3291 2.6582 3.9873 5.3164 6.6455 5.907 5.895 5.622 1. (CXX) g++ options: -O2 -lOpenCL
LuxCoreRender Scene: Orange Juice - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: CPU AMD 7773X AMD EPYC 7773X EPYC 7773X 4 8 12 16 20 13.34 13.41 14.00 MIN: 11.87 / MAX: 15.74 MIN: 11.94 / MAX: 15.84 MIN: 12.24 / MAX: 15.77
PyHPC Benchmarks Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Isoneutral Mixing AMD 7773X EPYC 7773X 0.3803 0.7606 1.1409 1.5212 1.9015 1.690 1.611
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Context Switching AMD 7773X EPYC 7773X 1.3M 2.6M 3.9M 5.2M 6.5M 5879171.86 6157698.82 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
NAS Parallel Benchmarks Test / Class: IS.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D EPYC 7773X AMD 7773X AMD EPYC 7773X 600 1200 1800 2400 3000 2782.01 2782.78 2910.19 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
PyHPC Benchmarks Device: CPU - Backend: JAX - Project Size: 1048576 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: JAX - Project Size: 1048576 - Benchmark: Equation of State AMD 7773X EPYC 7773X 0.0052 0.0104 0.0156 0.0208 0.026 0.023 0.022
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Write AMD 7773X AMD EPYC 7773X EPYC 7773X 15K 30K 45K 60K 75K 67592 67917 70661 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency AMD 7773X AMD EPYC 7773X EPYC 7773X 2 4 6 8 10 7.397 7.362 7.076 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 13 Total Time AMD 7773X EPYC 7773X AMD EPYC 7773X 40M 80M 120M 160M 200M 167400779 168120931 174759227 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver
Parallel BZIP2 Compression FreeBSD-13.0-RELEASE-amd64-memstick.img Compression OpenBenchmarking.org Seconds, Fewer Is Better Parallel BZIP2 Compression 1.1.13 FreeBSD-13.0-RELEASE-amd64-memstick.img Compression EPYC 7773X AMD EPYC 7773X AMD 7773X 0.5722 1.1444 1.7166 2.2888 2.861 2.543 2.479 2.439 1. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
Cpuminer-Opt Algorithm: Blake-2 S OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Blake-2 S EPYC 7773X AMD EPYC 7773X AMD 7773X 130K 260K 390K 520K 650K 585460 590510 609780 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenFOAM Input: Motorbike 30M OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 8 Input: Motorbike 30M AMD EPYC 7773X AMD 7773X EPYC 7773X 4 8 12 16 20 16.67 16.07 16.02 1. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU AMD 7773X EPYC 7773X 0.0903 0.1806 0.2709 0.3612 0.4515 0.401409 0.386596 MIN: 0.37 MIN: 0.37 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
PyHPC Benchmarks Device: CPU - Backend: JAX - Project Size: 1048576 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: JAX - Project Size: 1048576 - Benchmark: Isoneutral Mixing AMD 7773X EPYC 7773X 0.0313 0.0626 0.0939 0.1252 0.1565 0.139 0.134
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast AMD 7773X AMD EPYC 7773X EPYC 7773X 14 28 42 56 70 60.12 61.22 62.35 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C AMD EPYC 7773X AMD 7773X EPYC 7773X 60K 120K 180K 240K 300K 251848.99 260875.70 261179.07 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
PyHPC Benchmarks Device: CPU - Backend: PyTorch - Project Size: 1048576 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: PyTorch - Project Size: 1048576 - Benchmark: Equation of State EPYC 7773X AMD 7773X 0.0063 0.0126 0.0189 0.0252 0.0315 0.028 0.027
SVT-AV1 Encoder Mode: Preset 10 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 10 - Input: Bosphorus 1080p AMD 7773X EPYC 7773X AMD EPYC 7773X 90 180 270 360 450 401.11 403.24 415.95 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C EPYC 7773X AMD 7773X AMD EPYC 7773X 1100 2200 3300 4400 5500 5052.44 5103.77 5237.79 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
Stress-NG Test: IO_uring OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: IO_uring EPYC 7773X AMD 7773X 400K 800K 1200K 1600K 2000K 1842135.72 1908001.84 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU AMD 7773X EPYC 7773X 0.706 1.412 2.118 2.824 3.53 3.13792 3.03052 MIN: 2.03 MIN: 1.98 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 4 - Input: Bosphorus 1080p EPYC 7773X AMD EPYC 7773X AMD 7773X 2 4 6 8 10 7.589 7.675 7.852 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 8 - Input: Bosphorus 4K EPYC 7773X AMD EPYC 7773X AMD 7773X 20 40 60 80 100 84.35 86.56 87.26 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write AMD EPYC 7773X AMD 7773X EPYC 7773X 20K 40K 60K 80K 100K 78821 78985 81522 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency AMD EPYC 7773X AMD 7773X EPYC 7773X 0.2855 0.571 0.8565 1.142 1.4275 1.269 1.266 1.227 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
LuxCoreRender Scene: DLSC - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: CPU AMD 7773X AMD EPYC 7773X EPYC 7773X 3 6 9 12 15 9.13 9.21 9.41 MIN: 8.98 / MAX: 9.88 MIN: 9.04 / MAX: 9.93 MIN: 9.28 / MAX: 9.89
PyHPC Benchmarks Device: CPU - Backend: PyTorch - Project Size: 1048576 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: PyTorch - Project Size: 1048576 - Benchmark: Isoneutral Mixing AMD 7773X EPYC 7773X 0.0792 0.1584 0.2376 0.3168 0.396 0.352 0.342
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write AMD EPYC 7773X AMD 7773X EPYC 7773X 15K 30K 45K 60K 75K 68181 68479 70106 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency AMD EPYC 7773X AMD 7773X EPYC 7773X 0.1649 0.3298 0.4947 0.6596 0.8245 0.733 0.730 0.713 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
LuxCoreRender Scene: Danish Mood - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Danish Mood - Acceleration: CPU AMD 7773X EPYC 7773X AMD EPYC 7773X 2 4 6 8 10 7.18 7.34 7.38 MIN: 2.91 / MAX: 8.42 MIN: 3 / MAX: 8.55 MIN: 2.99 / MAX: 8.61
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 500 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 500 - Mode: Read Only - Average Latency EPYC 7773X AMD EPYC 7773X AMD 7773X 0.1017 0.2034 0.3051 0.4068 0.5085 0.452 0.447 0.440 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 500 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 500 - Mode: Read Only EPYC 7773X AMD EPYC 7773X AMD 7773X 200K 400K 600K 800K 1000K 1105462 1117340 1135454 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 8 - Input: Bosphorus 1080p AMD 7773X EPYC 7773X AMD EPYC 7773X 40 80 120 160 200 192.47 196.39 197.63 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C AMD 7773X EPYC 7773X AMD EPYC 7773X 8K 16K 24K 32K 40K 37738.61 38420.81 38745.62 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
LuxCoreRender Scene: LuxCore Benchmark - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: LuxCore Benchmark - Acceleration: CPU AMD EPYC 7773X EPYC 7773X AMD 7773X 2 4 6 8 10 7.54 7.59 7.74 MIN: 2.88 / MAX: 8.85 MIN: 2.91 / MAX: 8.9 MIN: 2.94 / MAX: 9.05
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon AMD 7773X AMD EPYC 7773X EPYC 7773X 20 40 60 80 100 78.03 80.01 80.07 MIN: 76.21 / MAX: 79.31 MIN: 78.13 / MAX: 81.16 MIN: 78.33 / MAX: 81.16
SVT-AV1 Encoder Mode: Preset 10 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 10 - Input: Bosphorus 4K AMD EPYC 7773X AMD 7773X EPYC 7773X 40 80 120 160 200 157.12 159.55 161.21 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
PyHPC Benchmarks Device: CPU - Backend: Numba - Project Size: 1048576 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Numba - Project Size: 1048576 - Benchmark: Isoneutral Mixing AMD 7773X EPYC 7773X 0.0846 0.1692 0.2538 0.3384 0.423 0.376 0.367
PyHPC Benchmarks Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Isoneutral Mixing AMD 7773X EPYC 7773X 0.3582 0.7164 1.0746 1.4328 1.791 1.592 1.554
toyBrot Fractal Generator Implementation: C++ Tasks OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: C++ Tasks EPYC 7773X AMD 7773X AMD EPYC 7773X 1600 3200 4800 6400 8000 7422 7301 7245 1. (CXX) g++ options: -O3 -lpthread
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 21.06 Test: Compression Rating AMD 7773X AMD EPYC 7773X EPYC 7773X 80K 160K 240K 320K 400K 387703 393285 396660 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
SVT-HEVC Tuning: 10 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p AMD EPYC 7773X EPYC 7773X AMD 7773X 140 280 420 560 700 615.38 623.70 629.59 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
PyHPC Benchmarks Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Isoneutral Mixing AMD 7773X EPYC 7773X 0.1521 0.3042 0.4563 0.6084 0.7605 0.676 0.661
asmFish 1024 Hash Memory, 26 Depth OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth AMD 7773X EPYC 7773X AMD EPYC 7773X 30M 60M 90M 120M 150M 155386596 158355881 158777712
POV-Ray Trace Time OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time EPYC 7773X AMD EPYC 7773X AMD 7773X 3 6 9 12 15 10.54 10.36 10.33 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -R/usr/lib -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
Chaos Group V-RAY Mode: CPU OpenBenchmarking.org vsamples, More Is Better Chaos Group V-RAY 5 Mode: CPU AMD 7773X EPYC 7773X 13K 26K 39K 52K 65K 57962 59113
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: Eigen AMD EPYC 7773X AMD 7773X EPYC 7773X 1100 2200 3300 4400 5500 5116 5196 5216 1. (CXX) g++ options: -flto -pthread
PyHPC Benchmarks Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Isoneutral Mixing AMD 7773X EPYC 7773X 0.1332 0.2664 0.3996 0.5328 0.666 0.592 0.581
CloverLeaf Lagrangian-Eulerian Hydrodynamics OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf Lagrangian-Eulerian Hydrodynamics EPYC 7773X AMD 7773X AMD EPYC 7773X 3 6 9 12 15 11.31 11.11 11.10 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
Timed MPlayer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed MPlayer Compilation 1.5 Time To Compile AMD EPYC 7773X AMD 7773X EPYC 7773X 3 6 9 12 15 11.00 10.85 10.80
Timed Gem5 Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Gem5 Compilation 21.2 Time To Compile EPYC 7773X AMD 7773X AMD EPYC 7773X 40 80 120 160 200 194.41 191.18 190.89
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write AMD EPYC 7773X AMD 7773X EPYC 7773X 17K 34K 51K 68K 85K 75866 76215 77211 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency AMD EPYC 7773X AMD 7773X EPYC 7773X 0.7414 1.4828 2.2242 2.9656 3.707 3.295 3.280 3.238 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
ASKAP Test: tConvolve MPI - Gridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding AMD EPYC 7773X EPYC 7773X AMD 7773X 8K 16K 24K 32K 40K 36192.5 36827.5 36827.5 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping AMD 7773X AMD EPYC 7773X EPYC 7773X 300 600 900 1200 1500 1181.75 1194.17 1201.49 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU AMD 7773X EPYC 7773X 0.2004 0.4008 0.6012 0.8016 1.002 0.890446 0.875948 MIN: 0.58 MIN: 0.57 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.1 Video Input: Bosphorus 4K - Video Preset: Very Fast EPYC 7773X AMD 7773X AMD EPYC 7773X 9 18 27 36 45 40.73 41.25 41.38 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU AMD 7773X EPYC 7773X 200 400 600 800 1000 899.94 886.03 MIN: 879.51 MIN: 872.98 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 4 - Input: Bosphorus 4K EPYC 7773X AMD EPYC 7773X AMD 7773X 0.947 1.894 2.841 3.788 4.735 4.145 4.183 4.209 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.13 Time To Compile EPYC 7773X AMD 7773X AMD EPYC 7773X 14 28 42 56 70 62.04 61.13 61.11
PyHPC Benchmarks Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Isoneutral Mixing AMD 7773X EPYC 7773X 0.5481 1.0962 1.6443 2.1924 2.7405 2.436 2.400
rays1bench Large Scene OpenBenchmarking.org mrays/s, More Is Better rays1bench 2020-01-09 Large Scene EPYC 7773X AMD 7773X AMD EPYC 7773X 70 140 210 280 350 304.45 307.33 308.98
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 12 - Input: Bosphorus 4K AMD EPYC 7773X EPYC 7773X AMD 7773X 50 100 150 200 250 209.91 211.03 213.00 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency AMD EPYC 7773X AMD 7773X EPYC 7773X 0.016 0.032 0.048 0.064 0.08 0.071 0.070 0.070 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Pabellon Barcelona - Compute: CPU-Only AMD 7773X EPYC 7773X 20 40 60 80 100 90.47 89.22
Quantum ESPRESSO Input: AUSURF112 OpenBenchmarking.org Seconds, Fewer Is Better Quantum ESPRESSO 7.0 Input: AUSURF112 AMD EPYC 7773X EPYC 7773X AMD 7773X 80 160 240 320 400 388.99 386.42 383.70 1. (F9X) gfortran options: -pthread -fopenmp -ldevXlib -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3_omp -lfftw3 -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
Xcompact3d Incompact3d Input: input.i3d 129 Cells Per Direction OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 129 Cells Per Direction EPYC 7773X AMD 7773X AMD EPYC 7773X 1.0208 2.0416 3.0624 4.0832 5.104 4.53694820 4.48201895 4.47657299 1. (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
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2021.2 Implementation: MPI CPU - Input: water_GMX50_bare AMD EPYC 7773X AMD 7773X EPYC 7773X 2 4 6 8 10 7.071 7.163 7.166 1. (CXX) g++ options: -O3
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 250 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 250 - Mode: Read Only - Average Latency AMD 7773X EPYC 7773X AMD EPYC 7773X 0.0515 0.103 0.1545 0.206 0.2575 0.229 0.229 0.226 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU AMD 7773X EPYC 7773X 2 4 6 8 10 8.13289 8.02731 MIN: 7.34 MIN: 7.26 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only AMD 7773X AMD EPYC 7773X EPYC 7773X 300K 600K 900K 1200K 1500K 1542188 1549282 1562316 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 100 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 100 - Mode: Read Write - Average Latency AMD EPYC 7773X AMD 7773X EPYC 7773X 0.3517 0.7034 1.0551 1.4068 1.7585 1.563 1.560 1.543 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 100 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 100 - Mode: Read Write AMD EPYC 7773X AMD 7773X EPYC 7773X 14K 28K 42K 56K 70K 63973 64101 64802 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Atomic EPYC 7773X AMD 7773X 30K 60K 90K 120K 150K 126475.88 128080.47 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
NAS Parallel Benchmarks Test / Class: FT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C AMD 7773X AMD EPYC 7773X EPYC 7773X 14K 28K 42K 56K 70K 63406.26 64170.34 64208.35 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency AMD EPYC 7773X EPYC 7773X AMD 7773X 0.0727 0.1454 0.2181 0.2908 0.3635 0.323 0.323 0.319 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency AMD 7773X AMD EPYC 7773X EPYC 7773X 0.0365 0.073 0.1095 0.146 0.1825 0.162 0.161 0.160 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Numpy Benchmark OpenBenchmarking.org Score, More Is Better Numpy Benchmark AMD EPYC 7773X EPYC 7773X AMD 7773X 90 180 270 360 450 421.53 426.52 426.78
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Glibc C String Functions EPYC 7773X AMD 7773X 1.6M 3.2M 4.8M 6.4M 8M 7397152.01 7488758.35 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Only EPYC 7773X AMD EPYC 7773X AMD 7773X 300K 600K 900K 1200K 1500K 1547901 1548226 1566167 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PyHPC Benchmarks Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Equation of State AMD 7773X EPYC 7773X 0.0965 0.193 0.2895 0.386 0.4825 0.429 0.424
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 250 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 250 - Mode: Read Only EPYC 7773X AMD 7773X AMD EPYC 7773X 200K 400K 600K 800K 1000K 1092431 1092755 1104789 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
LULESH OpenBenchmarking.org z/s, More Is Better LULESH 2.0.3 AMD EPYC 7773X AMD 7773X EPYC 7773X 5K 10K 15K 20K 25K 21597.78 21749.38 21840.62 1. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 13.0 Build System: Ninja EPYC 7773X AMD EPYC 7773X AMD 7773X 30 60 90 120 150 140.79 139.27 139.26
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 50 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 50 - Mode: Read Only EPYC 7773X AMD EPYC 7773X AMD 7773X 140K 280K 420K 560K 700K 654363 657459 661198 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP CFD Solver EPYC 7773X AMD EPYC 7773X AMD 7773X 2 4 6 8 10 6.822 6.760 6.752 1. (CXX) g++ options: -O2 -lOpenCL
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Obj AMD 7773X AMD EPYC 7773X EPYC 7773X 14 28 42 56 70 63.47 63.99 64.12 MIN: 61.94 / MAX: 64.86 MIN: 62.57 / MAX: 65.15 MIN: 62.58 / MAX: 65.21
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency AMD EPYC 7773X EPYC 7773X AMD 7773X 0.0223 0.0446 0.0669 0.0892 0.1115 0.099 0.099 0.098 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only AMD EPYC 7773X EPYC 7773X AMD 7773X 200K 400K 600K 800K 1000K 1013179 1013194 1023408 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C EPYC 7773X AMD EPYC 7773X AMD 7773X 13K 26K 39K 52K 65K 60162.18 60483.51 60754.02 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
OSPray Benchmark: particle_volume/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: particle_volume/pathtracer/real_time AMD 7773X EPYC 7773X AMD EPYC 7773X 70 140 210 280 350 314.09 316.86 317.10
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 17.3 Time To Compile AMD EPYC 7773X AMD 7773X EPYC 7773X 30 60 90 120 150 133.92 133.21 132.65
Timed LLVM Compilation Build System: Unix Makefiles OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 13.0 Build System: Unix Makefiles AMD EPYC 7773X EPYC 7773X AMD 7773X 50 100 150 200 250 206.74 206.38 204.79
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 100 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 100 - Mode: Read Only - Average Latency AMD 7773X EPYC 7773X AMD EPYC 7773X 0.0241 0.0482 0.0723 0.0964 0.1205 0.107 0.107 0.106 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Cpuminer-Opt Algorithm: Garlicoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Garlicoin AMD 7773X EPYC 7773X AMD EPYC 7773X 400 800 1200 1600 2000 1637.28 1649.67 1652.42 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU EPYC 7773X AMD 7773X 0.2822 0.5644 0.8466 1.1288 1.411 1.25407 1.24333 MIN: 1.12 MIN: 1.12 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Read While Writing AMD 7773X EPYC 7773X 2M 4M 6M 8M 10M 9912022 9995001 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.2 Preset: Exhaustive AMD 7773X AMD EPYC 7773X EPYC 7773X 3 6 9 12 15 11.51 11.43 11.42 1. (CXX) g++ options: -O3 -flto -pthread
toyBrot Fractal Generator Implementation: C++ Threads OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: C++ Threads AMD 7773X EPYC 7773X AMD EPYC 7773X 1500 3000 4500 6000 7500 7054 7047 6997 1. (CXX) g++ options: -O3 -lpthread
OSPray Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer AMD 7773X EPYC 7773X AMD EPYC 7773X 140 280 420 560 700 630 627 625 1. (CXX) g++ options: -O3 -lm -ldl
m-queens Time To Solve OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.2 Time To Solve EPYC 7773X AMD 7773X AMD EPYC 7773X 3 6 9 12 15 10.89 10.81 10.80 1. (CXX) g++ options: -fopenmp -O2 -march=native
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 250 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 250 - Mode: Read Write - Average Latency AMD 7773X AMD EPYC 7773X EPYC 7773X 0.9398 1.8796 2.8194 3.7592 4.699 4.177 4.163 4.145 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 250 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 250 - Mode: Read Write AMD 7773X AMD EPYC 7773X EPYC 7773X 13K 26K 39K 52K 65K 59851 60059 60313 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: NUMA AMD EPYC 7773X EPYC 7773X AMD 7773X 50 100 150 200 250 232.81 233.66 234.60 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only AMD EPYC 7773X EPYC 7773X AMD 7773X 150K 300K 450K 600K 750K 705546 709272 710842 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 50 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 50 - Mode: Read Write AMD 7773X EPYC 7773X AMD EPYC 7773X 13K 26K 39K 52K 65K 62245 62469 62692 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: MMAP EPYC 7773X AMD EPYC 7773X AMD 7773X 200 400 600 800 1000 1143.21 1149.10 1151.40 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
KTX-Software toktx Settings: UASTC 3 + Zstd Compression 19 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 3 + Zstd Compression 19 AMD 7773X AMD EPYC 7773X EPYC 7773X 3 6 9 12 15 8.966 8.947 8.905
Google Draco Model: Church Facade OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.0 Model: Church Facade AMD EPYC 7773X AMD 7773X EPYC 7773X 1400 2800 4200 5600 7000 6341 6303 6298 1. (CXX) g++ options: -O3
Google Draco Model: Lion OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.0 Model: Lion AMD 7773X AMD EPYC 7773X EPYC 7773X 1100 2200 3300 4400 5500 5326 5324 5290 1. (CXX) g++ options: -O3
PyHPC Benchmarks Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Equation of State EPYC 7773X AMD 7773X 0.0666 0.1332 0.1998 0.2664 0.333 0.296 0.294
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 100 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 100 - Mode: Read Only EPYC 7773X AMD 7773X AMD EPYC 7773X 200K 400K 600K 800K 1000K 937666 938463 943998 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Primesieve 1e12 Prime Number Generation OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 7.7 1e12 Prime Number Generation AMD 7773X AMD EPYC 7773X EPYC 7773X 1.0393 2.0786 3.1179 4.1572 5.1965 4.619 4.591 4.589 1. (CXX) g++ options: -O3
ASTC Encoder Preset: Medium OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.2 Preset: Medium EPYC 7773X AMD EPYC 7773X AMD 7773X 1.0361 2.0722 3.1083 4.1444 5.1805 4.6051 4.5766 4.5754 1. (CXX) g++ options: -O3 -flto -pthread
Appleseed Scene: Emily OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Emily AMD 7773X EPYC 7773X 30 60 90 120 150 123.26 122.47
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 50 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 50 - Mode: Read Write - Average Latency AMD 7773X EPYC 7773X AMD EPYC 7773X 0.1807 0.3614 0.5421 0.7228 0.9035 0.803 0.800 0.798 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 Time To Compile AMD 7773X AMD EPYC 7773X EPYC 7773X 11 22 33 44 55 48.23 48.15 47.94
NWChem Input: C240 Buckyball OpenBenchmarking.org Seconds, Fewer Is Better NWChem 7.0.2 Input: C240 Buckyball EPYC 7773X AMD 7773X AMD EPYC 7773X 500 1000 1500 2000 2500 2199.2 2188.7 2186.2 1. (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 -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2
Cpuminer-Opt Algorithm: x25x OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: x25x EPYC 7773X AMD 7773X AMD EPYC 7773X 300 600 900 1200 1500 1565.76 1571.01 1575.00 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Crown AMD EPYC 7773X EPYC 7773X AMD 7773X 15 30 45 60 75 67.81 68.02 68.19 MIN: 66.26 / MAX: 72.8 MIN: 66.44 / MAX: 73.21 MIN: 66.69 / MAX: 73.2
PyHPC Benchmarks Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Equation of State EPYC 7773X AMD 7773X 0.0412 0.0824 0.1236 0.1648 0.206 0.183 0.182
OpenFOAM Input: Motorbike 60M OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 8 Input: Motorbike 60M AMD 7773X AMD EPYC 7773X EPYC 7773X 30 60 90 120 150 119.94 119.47 119.31 1. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm
toyBrot Fractal Generator Implementation: TBB OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: TBB EPYC 7773X AMD 7773X AMD EPYC 7773X 1500 3000 4500 6000 7500 7006 7001 6970 1. (CXX) g++ options: -O3 -lpthread
KTX-Software toktx Settings: Zstd Compression 19 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: Zstd Compression 19 EPYC 7773X AMD EPYC 7773X AMD 7773X 5 10 15 20 25 20.11 20.06 20.01
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Random Read AMD 7773X EPYC 7773X 60M 120M 180M 240M 300M 275200675 276582763 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OSPray Studio Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer AMD 7773X AMD EPYC 7773X EPYC 7773X 2K 4K 6K 8K 10K 8623 8618 8581 1. (CXX) g++ options: -O3 -lm -ldl
OSPray Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer AMD 7773X AMD EPYC 7773X EPYC 7773X 4K 8K 12K 16K 20K 20172 20142 20075 1. (CXX) g++ options: -O3 -lm -ldl
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD AMD 7773X EPYC 7773X AMD EPYC 7773X 10 20 30 40 50 44.51 44.43 44.30 1. (CXX) g++ options: -O2 -lOpenCL
Timed Wasmer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 2.2 Time To Compile EPYC 7773X AMD EPYC 7773X AMD 7773X 14 28 42 56 70 63.27 63.13 62.99 1. (CC) gcc options: -m64 -ldl -lxkbcommon -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Socket Activity EPYC 7773X AMD 7773X 4K 8K 12K 16K 20K 17550.10 17625.65 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: LBC, LBRY Credits AMD EPYC 7773X AMD 7773X EPYC 7773X 40K 80K 120K 160K 200K 184680 185250 185460 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown EPYC 7773X AMD 7773X AMD EPYC 7773X 14 28 42 56 70 62.61 62.86 62.87 MIN: 61.42 / MAX: 67.24 MIN: 61.42 / MAX: 67.17 MIN: 61.55 / MAX: 67.22
Liquid-DSP Threads: 64 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 64 - Buffer Length: 256 - Filter Length: 57 EPYC 7773X AMD 7773X AMD EPYC 7773X 600M 1200M 1800M 2400M 3000M 2807300000 2813400000 2818900000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Ngspice Circuit: C2670 OpenBenchmarking.org Seconds, Fewer Is Better Ngspice 34 Circuit: C2670 AMD 7773X AMD EPYC 7773X EPYC 7773X 30 60 90 120 150 156.07 155.56 155.43 1. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lSM -lICE
NAS Parallel Benchmarks Test / Class: SP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C EPYC 7773X AMD 7773X AMD EPYC 7773X 20K 40K 60K 80K 100K 89121.25 89271.13 89473.38 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU EPYC 7773X AMD 7773X 140 280 420 560 700 657.25 654.69 MIN: 637.88 MIN: 636.26 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 AMD 7773X EPYC 7773X AMD EPYC 7773X 3K 6K 9K 12K 15K 13619.8 13667.8 13671.4 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
PyHPC Benchmarks Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Equation of State AMD 7773X EPYC 7773X 0.2405 0.481 0.7215 0.962 1.2025 1.069 1.065
Xcompact3d Incompact3d Input: X3D-benchmarking input.i3d OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: X3D-benchmarking input.i3d AMD 7773X EPYC 7773X AMD EPYC 7773X 120 240 360 480 600 576.93 575.43 574.78 1. (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
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Barbershop - Compute: CPU-Only AMD 7773X EPYC 7773X 60 120 180 240 300 276.03 275.04
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU AMD 7773X EPYC 7773X 140 280 420 560 700 658.77 656.48 MIN: 638.87 MIN: 638.62 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Facebook RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Update Random AMD 7773X EPYC 7773X 70K 140K 210K 280K 350K 314318 315370 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OSPray Benchmark: gravity_spheres_volume/dim_512/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time AMD 7773X EPYC 7773X AMD EPYC 7773X 2 4 6 8 10 8.71677 8.72023 8.74566
OSPray Benchmark: particle_volume/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: particle_volume/scivis/real_time AMD 7773X EPYC 7773X AMD EPYC 7773X 16 32 48 64 80 69.59 69.65 69.81
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU AMD 7773X EPYC 7773X 200 400 600 800 1000 890.64 887.78 MIN: 875.34 MIN: 874.38 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OSPray Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer AMD 7773X EPYC 7773X AMD EPYC 7773X 2K 4K 6K 8K 10K 8505 8499 8478 1. (CXX) g++ options: -O3 -lm -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU EPYC 7773X AMD 7773X 0.1657 0.3314 0.4971 0.6628 0.8285 0.736474 0.734164 MIN: 0.7 MIN: 0.7 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: SENDFILE EPYC 7773X AMD 7773X 200K 400K 600K 800K 1000K 1119510.19 1122873.84 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
Timed GCC Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GCC Compilation 11.2.0 Time To Compile EPYC 7773X AMD EPYC 7773X AMD 7773X 200 400 600 800 1000 776.84 775.40 774.54
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.32.2 VGR Performance Metric AMD 7773X EPYC 7773X 160K 320K 480K 640K 800K 742743 744905 1. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -ldl -lm
OSPray Benchmark: particle_volume/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: particle_volume/ao/real_time EPYC 7773X AMD EPYC 7773X AMD 7773X 16 32 48 64 80 72.51 72.57 72.71
Liquid-DSP Threads: 128 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 AMD 7773X EPYC 7773X AMD EPYC 7773X 600M 1200M 1800M 2400M 3000M 2934500000 2939500000 2942500000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
PyHPC Benchmarks Device: CPU - Backend: Aesara - Project Size: 1048576 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Aesara - Project Size: 1048576 - Benchmark: Isoneutral Mixing AMD 7773X EPYC 7773X 0.0828 0.1656 0.2484 0.3312 0.414 0.368 0.367
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU EPYC 7773X AMD 7773X 140 280 420 560 700 659.06 657.31 MIN: 637.66 MIN: 638.06 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
KTX-Software toktx Settings: Zstd Compression 9 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: Zstd Compression 9 EPYC 7773X AMD EPYC 7773X AMD 7773X 0.7668 1.5336 2.3004 3.0672 3.834 3.408 3.401 3.399
OSPray Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer AMD 7773X AMD EPYC 7773X EPYC 7773X 4K 8K 12K 16K 20K 17144 17102 17099 1. (CXX) g++ options: -O3 -lm -ldl
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon AMD 7773X EPYC 7773X AMD EPYC 7773X 16 32 48 64 80 71.99 72.16 72.17 MIN: 70.25 / MAX: 73.11 MIN: 70.31 / MAX: 73.29 MIN: 70.41 / MAX: 73.31
OSPray Benchmark: gravity_spheres_volume/dim_512/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: gravity_spheres_volume/dim_512/ao/real_time AMD 7773X AMD EPYC 7773X EPYC 7773X 3 6 9 12 15 9.07886 9.09500 9.10231
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Classroom - Compute: CPU-Only AMD 7773X EPYC 7773X 16 32 48 64 80 73.01 72.83
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Malloc AMD 7773X EPYC 7773X 300M 600M 900M 1200M 1500M 1602472159.46 1606428610.69 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
QuantLib OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.21 AMD EPYC 7773X AMD 7773X EPYC 7773X 500 1000 1500 2000 2500 2317.0 2318.0 2322.6 1. (CXX) g++ options: -O3 -march=native -rdynamic
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU AMD 7773X EPYC 7773X 0.2677 0.5354 0.8031 1.0708 1.3385 1.18972 1.18700 MIN: 1.09 MIN: 1.1 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Facebook RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Read Random Write Random EPYC 7773X AMD 7773X 800K 1600K 2400K 3200K 4000K 3521479 3529385 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
ASKAP Test: tConvolve MT - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Degridding AMD 7773X AMD EPYC 7773X EPYC 7773X 2K 4K 6K 8K 10K 8268.02 8272.03 8286.11 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Memory Copying EPYC 7773X AMD 7773X 3K 6K 9K 12K 15K 12392.52 12418.84 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU EPYC 7773X AMD 7773X 0.1888 0.3776 0.5664 0.7552 0.944 0.839175 0.837436 MIN: 0.79 MIN: 0.8 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: MEMFD AMD 7773X AMD EPYC 7773X EPYC 7773X 300 600 900 1200 1500 1265.50 1266.83 1267.98 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
ASKAP Test: tConvolve MT - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Gridding AMD 7773X AMD EPYC 7773X EPYC 7773X 1200 2400 3600 4800 6000 5473.06 5479.22 5483.63 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OSPray Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer AMD EPYC 7773X EPYC 7773X AMD 7773X 110 220 330 440 550 530 530 529 1. (CXX) g++ options: -O3 -lm -ldl
OSPray Studio Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer AMD 7773X AMD EPYC 7773X EPYC 7773X 120 240 360 480 600 535 534 534 1. (CXX) g++ options: -O3 -lm -ldl
NAS Parallel Benchmarks Test / Class: BT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C AMD EPYC 7773X AMD 7773X EPYC 7773X 40K 80K 120K 160K 200K 169343.55 169478.30 169658.95 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
toyBrot Fractal Generator Implementation: OpenMP OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: OpenMP AMD 7773X AMD EPYC 7773X EPYC 7773X 1600 3200 4800 6400 8000 7546 7537 7532 1. (CXX) g++ options: -O3 -lpthread
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 500 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 500 - Mode: Read Write - Average Latency AMD 7773X AMD EPYC 7773X EPYC 7773X 3 6 9 12 15 9.383 9.380 9.366 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 500 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 500 - Mode: Read Write AMD 7773X AMD EPYC 7773X EPYC 7773X 11K 22K 33K 44K 55K 53288 53304 53384 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OSPray Studio Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer AMD 7773X AMD EPYC 7773X EPYC 7773X 4K 8K 12K 16K 20K 17242 17224 17212 1. (CXX) g++ options: -O3 -lm -ldl
OpenSSL Algorithm: SHA256 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.0 Algorithm: SHA256 EPYC 7773X AMD EPYC 7773X AMD 7773X 17000M 34000M 51000M 68000M 85000M 77295739610 77341787750 77427390920 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Ngspice Circuit: C7552 OpenBenchmarking.org Seconds, Fewer Is Better Ngspice 34 Circuit: C7552 AMD 7773X AMD EPYC 7773X EPYC 7773X 30 60 90 120 150 114.29 114.22 114.11 1. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lSM -lICE
Algebraic Multi-Grid Benchmark OpenBenchmarking.org Figure Of Merit, More Is Better Algebraic Multi-Grid Benchmark 1.2 EPYC 7773X AMD EPYC 7773X AMD 7773X 200M 400M 600M 800M 1000M 1054655000 1055936000 1056319000 1. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.16 Build: defconfig AMD EPYC 7773X AMD 7773X EPYC 7773X 6 12 18 24 30 25.52 25.50 25.48
Appleseed Scene: Disney Material OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Disney Material AMD 7773X EPYC 7773X 13 26 39 52 65 57.41 57.33
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 21.06 Test: Decompression Rating AMD EPYC 7773X AMD 7773X EPYC 7773X 90K 180K 270K 360K 450K 409242 409463 409802 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms AMD 7773X AMD EPYC 7773X EPYC 7773X 0.0843 0.1686 0.2529 0.3372 0.4215 0.37454 0.37417 0.37403
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Glibc Qsort Data Sorting AMD 7773X EPYC 7773X 140 280 420 560 700 644.97 645.83 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
miniFE Problem Size: Small OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small AMD 7773X AMD EPYC 7773X EPYC 7773X 5K 10K 15K 20K 25K 22564.1 22591.3 22593.6 1. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi
OSPray Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer AMD 7773X EPYC 7773X AMD EPYC 7773X 2K 4K 6K 8K 10K 10072 10063 10059 1. (CXX) g++ options: -O3 -lm -ldl
KTX-Software toktx Settings: UASTC 4 + Zstd Compression 19 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 4 + Zstd Compression 19 AMD 7773X EPYC 7773X AMD EPYC 7773X 14 28 42 56 70 60.58 60.52 60.50
OSPray Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time AMD 7773X AMD EPYC 7773X EPYC 7773X 4 8 12 16 20 13.64 13.65 13.66
N-Queens Elapsed Time OpenBenchmarking.org Seconds, Fewer Is Better N-Queens 1.0 Elapsed Time AMD 7773X EPYC 7773X AMD EPYC 7773X 0.5497 1.0994 1.6491 2.1988 2.7485 2.443 2.443 2.440 1. (CC) gcc options: -static -fopenmp -O3 -march=native
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 22.1 Input: Carbon Nanotube EPYC 7773X AMD 7773X 13 26 39 52 65 57.94 57.87 1. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi
Tachyon Total Time OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.99.2 Total Time AMD EPYC 7773X AMD 7773X EPYC 7773X 7 14 21 28 35 28.21 28.18 28.17 1. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
PyHPC Benchmarks Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Isoneutral Mixing EPYC 7773X AMD 7773X 0.3843 0.7686 1.1529 1.5372 1.9215 1.708 1.706
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Vector Math EPYC 7773X AMD 7773X 60K 120K 180K 240K 300K 298492.58 298837.95 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
Timed Linux Kernel Compilation Build: allmodconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.16 Build: allmodconfig EPYC 7773X AMD 7773X AMD EPYC 7773X 50 100 150 200 250 233.10 232.86 232.83
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 AMD 7773X EPYC 7773X AMD EPYC 7773X 200K 400K 600K 800K 1000K 897194.4 897876.2 898143.3 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Appleseed Scene: Material Tester OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Material Tester EPYC 7773X AMD 7773X 30 60 90 120 150 148.74 148.61
Embree Binary: Pathtracer - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon Obj AMD EPYC 7773X EPYC 7773X AMD 7773X 16 32 48 64 80 72.52 72.54 72.58 MIN: 70.53 / MAX: 73.81 MIN: 70.59 / MAX: 73.94 MIN: 70.82 / MAX: 73.8
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: System V Message Passing EPYC 7773X AMD 7773X 2M 4M 6M 8M 10M 9426628.40 9433754.46 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
ASTC Encoder Preset: Thorough OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.2 Preset: Thorough AMD EPYC 7773X AMD 7773X EPYC 7773X 2 4 6 8 10 6.4734 6.4723 6.4687 1. (CXX) g++ options: -O3 -flto -pthread
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: CPU Stress EPYC 7773X AMD 7773X 30K 60K 90K 120K 150K 147632.95 147735.12 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
KTX-Software toktx Settings: UASTC 3 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 3 EPYC 7773X AMD 7773X AMD EPYC 7773X 1.0661 2.1322 3.1983 4.2644 5.3305 4.738 4.737 4.735
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 EPYC 7773X AMD 7773X AMD EPYC 7773X 5 10 15 20 25 19.68 19.68 19.69 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Fishy Cat - Compute: CPU-Only EPYC 7773X AMD 7773X 8 16 24 32 40 36.73 36.71
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Sequential Fill EPYC 7773X AMD 7773X 70K 140K 210K 280K 350K 319924 320048 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU AMD 7773X EPYC 7773X 200 400 600 800 1000 888.35 888.03 MIN: 875.33 MIN: 872.53 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Crypto AMD 7773X EPYC 7773X 3K 6K 9K 12K 15K 14970.53 14973.70 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Forking EPYC 7773X AMD 7773X 16K 32K 48K 64K 80K 75988.0 76000.4 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Matrix Math AMD 7773X EPYC 7773X 40K 80K 120K 160K 200K 206162.79 206189.39 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Semaphores AMD 7773X EPYC 7773X 2M 4M 6M 8M 10M 8445532.57 8446018.43 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
PyHPC Benchmarks Device: CPU - Backend: TensorFlow - Project Size: 1048576 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: TensorFlow - Project Size: 1048576 - Benchmark: Equation of State AMD 7773X EPYC 7773X 0.0081 0.0162 0.0243 0.0324 0.0405 0.036 0.036
PyHPC Benchmarks Device: CPU - Backend: Aesara - Project Size: 1048576 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Aesara - Project Size: 1048576 - Benchmark: Equation of State AMD 7773X EPYC 7773X 0.0241 0.0482 0.0723 0.0964 0.1205 0.107 0.107
PyHPC Benchmarks Device: CPU - Backend: Numba - Project Size: 1048576 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Numba - Project Size: 1048576 - Benchmark: Equation of State AMD 7773X EPYC 7773X 0.0167 0.0334 0.0501 0.0668 0.0835 0.074 0.074
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.10 Model: fcn-resnet101-11 - Device: CPU EPYC 7773X AMD 7773X 40 80 120 160 200 173 173 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: BMW27 - Compute: CPU-Only AMD 7773X EPYC 7773X 7 14 21 28 35 28.26 28.26
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: CPU Cache EPYC 7773X AMD 7773X 3 6 9 12 15 12.74 12.74 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic
PostgreSQL pgbench Scaling Factor: 1000 - Clients: 50 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 1000 - Clients: 50 - Mode: Read Only - Average Latency AMD 7773X AMD EPYC 7773X EPYC 7773X 0.0171 0.0342 0.0513 0.0684 0.0855 0.076 0.076 0.076 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
ASKAP Test: Hogbom Clean OpenMP OpenBenchmarking.org Iterations Per Second, More Is Better ASKAP 1.0 Test: Hogbom Clean OpenMP EPYC 7773X AMD EPYC 7773X AMD 7773X 200 400 600 800 1000 806.45 806.45 806.45 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ASKAP Test: tConvolve OpenMP - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Degridding EPYC 7773X AMD EPYC 7773X AMD 7773X 4K 8K 12K 16K 20K 19018.3 19018.3 19018.3 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ASKAP Test: tConvolve MPI - Degridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding EPYC 7773X AMD EPYC 7773X AMD 7773X 7K 14K 21K 28K 35K 32294.8 32294.8 32294.8 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenVKL Benchmark: vklBenchmark Scalar OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.0 Benchmark: vklBenchmark Scalar EPYC 7773X AMD EPYC 7773X AMD 7773X 20 40 60 80 100 102 102 102 MIN: 9 / MAX: 3503 MIN: 9 / MAX: 3520 MIN: 9 / MAX: 3497
OpenVKL Benchmark: vklBenchmark ISPC OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.0 Benchmark: vklBenchmark ISPC EPYC 7773X AMD EPYC 7773X AMD 7773X 40 80 120 160 200 176 176 176 MIN: 19 / MAX: 4403 MIN: 19 / MAX: 4413 MIN: 19 / MAX: 4412
Intel Open Image Denoise Run: RTLightmap.hdr.4096x4096 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RTLightmap.hdr.4096x4096 EPYC 7773X AMD EPYC 7773X AMD 7773X 0.1823 0.3646 0.5469 0.7292 0.9115 0.81 0.81 0.81
Intel Open Image Denoise Run: RT.ldr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.ldr_alb_nrm.3840x2160 EPYC 7773X AMD EPYC 7773X AMD 7773X 0.3713 0.7426 1.1139 1.4852 1.8565 1.65 1.65 1.65
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 EPYC 7773X AMD EPYC 7773X AMD 7773X 0.3713 0.7426 1.1139 1.4852 1.8565 1.65 1.65 1.65
Phoronix Test Suite v10.8.4