2 x AMD EPYC 9654 96-Core testing with a AMD Titanite_4G (RTI1002E BIOS) and ASPEED on Clear Linux OS 38100 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2301263-NE-CLEARSAPP02 Clear Sapphire - Phoronix Test Suite Clear Sapphire 2 x AMD EPYC 9654 96-Core testing with a AMD Titanite_4G (RTI1002E BIOS) and ASPEED on Clear Linux OS 38100 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2301263-NE-CLEARSAPP02&grs&sor&rro .
Clear Sapphire Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Display Server Compiler File-System Screen Resolution Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads) Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) Intel Device 1bce 1008GB 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96 ASPEED VGA HDMI 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T Clear Linux OS 38100 6.1.7-1247.native (x86_64) X Server 1.21.1.6 GCC 12.2.1 20230112 releases/gcc-12.2.0-345-gc142b30b3a + Clang 15.0.6 + LLVM 15.0.6 ext4 640x480 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads) AMD Titanite_4G (RTI1002E BIOS) AMD Device 14a4 1520GB 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 Broadcom NetXtreme BCM5720 PCIe OpenBenchmarking.org Kernel Details - Transparent Huge Pages: always Environment Details - FFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,--enable-new-dtags" CXXFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mrelax-cmpxchg-loop -fvisibility-inlines-hidden -Wl,--enable-new-dtags -std=gnu++17" FCFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,-sort-common -Wl,--enable-new-dtags" CFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mrelax-cmpxchg-loop" THEANO_FLAGS="floatX=float32,openmp=true,gcc.cxxflags="-ftree-vectorize -mavx"" Compiler Details - --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-gnu-indirect-function --enable-host-shared --enable-languages=c,c++,fortran,go,jit --enable-ld=default --enable-libstdcxx-pch --enable-linux-futex --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=x86-64-v3 --with-gcc-major-version-only --with-glibc-version=2.35 --with-gnu-ld --with-isl --with-pic --with-ppl=yes --with-tune=sapphirerapids --with-zstd Processor Details - Clear Linux: 8490H 2P: Scaling Governor: intel_pstate performance (EPP: default) - CPU Microcode: 0x2b0000c0 - Clear Linux: EPYC 9654 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10110d - Clear Linux: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10110d Java Details - OpenJDK Runtime Environment (build 18.0.2-internal+0-adhoc.mockbuild.corretto-18-18.0.2.9.1) Python Details - Python 3.11.0 Security Details - Clear Linux: 8490H 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected - Clear Linux: EPYC 9654 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - Clear Linux: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Clear Sapphire onednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU stress-ng: Context Switching stress-ng: Memory Copying onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onnx: yolov4 - CPU - Standard stress-ng: Mutex minibude: OpenMP - BM1 minibude: OpenMP - BM1 stress-ng: Malloc onnx: fcn-resnet101-11 - CPU - Standard namd: ATPase Simulation - 327,506 Atoms stress-ng: Forking hpcg: kvazaar: Bosphorus 4K - Slow kvazaar: Bosphorus 4K - Medium blender: Barbershop - CPU-Only stress-ng: Vector Math minibude: OpenMP - BM2 minibude: OpenMP - BM2 stress-ng: Semaphores embree: Pathtracer ISPC - Crown liquid-dsp: 240 - 256 - 57 onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU blender: Classroom - CPU-Only onnx: bertsquad-12 - CPU - Standard stress-ng: Glibc C String Functions stress-ng: SENDFILE renaissance: Akka Unbalanced Cobwebbed Tree compress-zstd: 8 - Compression Speed uvg266: Bosphorus 4K - Medium embree: Pathtracer ISPC - Asian Dragon cpuminer-opt: Triple SHA-256, Onecoin embree: Pathtracer ISPC - Asian Dragon Obj cpuminer-opt: LBC, LBRY Credits compress-zstd: 8, Long Mode - Decompression Speed cpuminer-opt: x25x incompact3d: input.i3d 193 Cells Per Direction stress-ng: Crypto stress-ng: Matrix Math compress-zstd: 19 - Decompression Speed compress-zstd: 8 - Decompression Speed astcenc: Exhaustive lczero: Eigen oidn: RT.hdr_alb_nrm.3840x2160 liquid-dsp: 128 - 256 - 57 compress-zstd: 19, Long Mode - Decompression Speed dacapobench: H2 stress-ng: MMAP astcenc: Thorough stress-ng: MEMFD compress-zstd: 8, Long Mode - Compression Speed cpuminer-opt: scrypt numenta-nab: KNN CAD nwchem: C240 Buckyball numenta-nab: Earthgecko Skyline ospray: particle_volume/ao/real_time astcenc: Fast avifenc: 6 renaissance: Genetic Algorithm Using Jenetics + Futures pyperformance: nbody renaissance: Apache Spark Bayes numenta-nab: Bayesian Changepoint pyperformance: regex_compile compress-zstd: 19 - Compression Speed numenta-nab: Windowed Gaussian ospray: gravity_spheres_volume/dim_512/ao/real_time openvkl: vklBenchmark ISPC dacapobench: Jython mysqlslap: 1024 pybench: Total For Average Test Times numenta-nab: Contextual Anomaly Detector OSE avifenc: 2 pyperformance: json_loads numenta-nab: Relative Entropy kvazaar: Bosphorus 4K - Super Fast renaissance: Apache Spark ALS astcenc: Medium avifenc: 0 renaissance: Rand Forest kvazaar: Bosphorus 4K - Ultra Fast renaissance: Apache Spark PageRank kvazaar: Bosphorus 4K - Very Fast stress-ng: IO_uring renaissance: ALS Movie Lens pyperformance: float pyperformance: python_startup uvg266: Bosphorus 4K - Very Fast uvg266: Bosphorus 4K - Super Fast uvg266: Bosphorus 4K - Ultra Fast pyperformance: 2to3 pyperformance: raytrace simdjson: LargeRand renaissance: Finagle HTTP Requests pyperformance: pickle_pure_python pyperformance: crypto_pyaes pyperformance: go pyperformance: django_template simdjson: PartialTweets phpbench: PHP Benchmark Suite pyperformance: pathlib simdjson: TopTweet stress-ng: System V Message Passing pyperformance: chaos clickhouse: 100M Rows Hits Dataset, Third Run clickhouse: 100M Rows Hits Dataset, Second Run clickhouse: 100M Rows Hits Dataset, First Run / Cold Cache brl-cad: VGR Performance Metric stress-ng: Futex stress-ng: NUMA stress-ng: CPU Cache stress-ng: Atomic stress-ng: Socket Activity pgbench: 100 - 1000 - Read Write - Average Latency pgbench: 100 - 1000 - Read Write pgbench: 100 - 800 - Read Write - Average Latency pgbench: 100 - 800 - Read Write svt-av1: Preset 12 - Bosphorus 4K svt-av1: Preset 13 - Bosphorus 4K renaissance: Scala Dotty renaissance: Savina Reactors.IO gromacs: MPI CPU - water_GMX50_bare onednn: IP Shapes 3D - bf16bf16bf16 - CPU onednn: IP Shapes 1D - bf16bf16bf16 - CPU onnx: ArcFace ResNet-100 - CPU - Standard onnx: GPT-2 - CPU - Standard onnx: super-resolution-10 - CPU - Standard compress-zstd: 19, Long Mode - Compression Speed Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.560616 27204245.35 7851.21 489.127 564 59688403.75 132.289 3307.227 363422967.84 507 0.26307 56447.75 62.4462 33.27 33.92 147.37 534773.07 183.963 4599.072 20839432.55 99.1441 7209766667 0.249854 586.438 36.53 868 19260094.31 2140625.32 17042.9 2942.9 29.13 131.3481 2094367 114.2266 667438 3243.6 5002.69 6.18280959 203339.63 551787.07 2635.9 3204.2 8.4382 11894 4.28 7172733333 2795.3 2494 4223.46 85.8491 3631.89 822.5 3644.05 86.275 1834.3 66.814 34.6997 821.5846 2.453 2026.2 63.3 449.0 21.695 104 97.8 4.270 38.0961 1142 2679 792 664 32.442 37.557 18.3 10.759 70.41 2073.0 525.4013 67.334 646.5 72.14 2704.1 70.58 51657.61 9105.6 53.7 8.36 55.89 56.85 57.28 201 214 1.29 10387.6 219 58.6 109 26.7 5.79 2022000 11.9 6.74 34967285.00 52.2 535.16 530.44 504.28 4231422 167854.27 15.80 15.90 17822.07 98576.81 14.243 70213 10.523 76025 224.364 213.445 644.9 9853.7 14.980 1.51936 0.976622 1739 11120 11707 51.6 2.39780 112301150.26 25271.94 1388.72 302 130850928.40 288.922 7223.043 773890342.11 246 0.12870 4133.05 43.6135 64.94 65.68 78.01 1004273.56 343.951 8598.759 38286893.79 180.6866 13033666667 0.449399 1037.96 20.41 636 33924057.66 3160659.42 29426.5 4996.6 48.11 211.2885 3350626 184.2731 1074053 4970.9 7674.58 6.39028160 310827.69 823901.71 3840.6 4637.9 12.0979 8337 3.04 9889700000 3821.2 3390 5646.69 114.7577 2748.61 1087.8 4797.21 66.604 1466.5 54.268 42.5697 765.0848 2.009 1677.4 76.0 375.6 18.626 87.6 114.2 3.739 44.5377 1332 3125 705 755 28.620 33.294 16.2 9.645 77.94 1862.2 556.6794 60.577 593.4 79.19 2551.0 77.23 48522.08 8554.7 56.9 8.00 58.41 59.22 58.66 193 223 1.24 10803.3 225 60.0 112 27.3 5.85 1993673 12 6.66 34597345.44 52.7 3097472.10 63.01 51.40 208201.40 102162.24 14.608 68796 10.923 73652 258.442 226.934 625.0 9999.3 18.711 1.97020 4.81910 1151 5981 6453 54.6 2.37655 113443848.34 25149.30 1540.56 232 127500171.07 289.299 7232.468 779076525.72 243 0.12863 4099.20 85.8376 65.01 65.54 78.95 1003872.99 342.450 8561.237 38317964.95 181.4164 13047666667 0.448353 1052.702 20.43 490 34041789.97 3745383.09 29003.5 4933.4 48.07 212.9215 3387347 184.1431 1075000 4978.1 7584.87 4.17020929 310982.35 823465.88 3845.5 4638.3 12.0706 8815 3.05 9886800000 3842.2 3422 5691.19 114.7892 2737.60 1080.8 4793.62 66.693 1458.3 53.139 42.6274 672.1021 2.007 1665.0 75.8 387.6 18.272 88.2 116.0 3.641 44.4272 1334 3111 696 749 30.212 33.135 16.2 9.654 78.48 1912.5 500.6625 60.803 584.2 79.76 2450.5 76.91 48493.70 8651.9 57.1 7.88 59.27 60.13 60.02 192 224 1.24 10800.0 227 60.3 112 27.4 5.93 1979213 12.1 6.65 34562392.22 52.2 3071495.29 60.86 51.20 272067.02 112224.53 14.695 68349 11.228 71275 236.887 207.354 578.0 8672.4 17.828 1.75315 4.16919 894 5705 5417 55.7 OpenBenchmarking.org
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 0.5395 1.079 1.6185 2.158 2.6975 SE +/- 0.019785, N = 9 SE +/- 0.018337, N = 3 SE +/- 0.007878, N = 3 2.397800 2.376550 0.560616 MIN: 1.99 MIN: 1.97 MIN: 0.44 1. (CXX) g++ options: -O3 -march=native -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Context Switching Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 20M 40M 60M 80M 100M SE +/- 118201.25, N = 3 SE +/- 434697.20, N = 3 SE +/- 330195.92, N = 3 27204245.35 112301150.26 113443848.34 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Memory Copying Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 5K 10K 15K 20K 25K SE +/- 8.38, N = 3 SE +/- 102.52, N = 3 SE +/- 283.80, N = 15 7851.21 25149.30 25271.94 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 300 600 900 1200 1500 SE +/- 17.06, N = 3 SE +/- 18.64, N = 3 SE +/- 2.29, N = 3 1540.56 1388.72 489.13 MIN: 1477.95 MIN: 1325.47 MIN: 471.03 1. (CXX) g++ options: -O3 -march=native -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 120 240 360 480 600 SE +/- 0.60, N = 3 SE +/- 2.65, N = 12 SE +/- 0.17, N = 3 232 302 564 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -ffunction-sections -fdata-sections -march=native -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Stress-NG Test: Mutex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Mutex Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 30M 60M 90M 120M 150M SE +/- 124816.60, N = 3 SE +/- 71254.14, N = 3 SE +/- 1710955.16, N = 3 59688403.75 127500171.07 130850928.40 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
miniBUDE Implementation: OpenMP - Input Deck: BM1 OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 60 120 180 240 300 SE +/- 1.23, N = 7 SE +/- 0.24, N = 10 SE +/- 0.09, N = 10 132.29 288.92 289.30 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
miniBUDE Implementation: OpenMP - Input Deck: BM1 OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 1600 3200 4800 6400 8000 SE +/- 30.77, N = 7 SE +/- 6.09, N = 10 SE +/- 2.25, N = 10 3307.23 7223.04 7232.47 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Malloc Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 200M 400M 600M 800M 1000M SE +/- 1102560.16, N = 3 SE +/- 1462259.31, N = 3 SE +/- 1128975.32, N = 3 363422967.84 773890342.11 779076525.72 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 110 220 330 440 550 SE +/- 1.45, N = 3 SE +/- 3.00, N = 3 SE +/- 2.92, N = 3 243 246 507 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -ffunction-sections -fdata-sections -march=native -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0592 0.1184 0.1776 0.2368 0.296 SE +/- 0.00330, N = 3 SE +/- 0.00038, N = 3 SE +/- 0.00011, N = 3 0.26307 0.12870 0.12863
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Forking Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 12K 24K 36K 48K 60K SE +/- 8.76, N = 3 SE +/- 4.75, N = 3 SE +/- 312.44, N = 3 4099.20 4133.05 56447.75 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P Clear Linux 20 40 60 80 100 SE +/- 0.02, N = 3 SE +/- 0.14, N = 3 SE +/- 0.42, N = 3 43.61 62.45 85.84 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi
Kvazaar Video Input: Bosphorus 4K - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 15 30 45 60 75 SE +/- 0.04, N = 3 SE +/- 0.31, N = 5 SE +/- 0.30, N = 5 33.27 64.94 65.01 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 15 30 45 60 75 SE +/- 0.10, N = 3 SE +/- 0.17, N = 5 SE +/- 0.28, N = 5 33.92 65.54 65.68 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -lpthread -lm -lrt
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.4 Blend File: Barbershop - Compute: CPU-Only Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 30 60 90 120 150 SE +/- 1.23, N = 3 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 147.37 78.95 78.01
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Vector Math Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 200K 400K 600K 800K 1000K SE +/- 110.65, N = 3 SE +/- 23.11, N = 3 SE +/- 22.18, N = 3 534773.07 1003872.99 1004273.56 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
miniBUDE Implementation: OpenMP - Input Deck: BM2 OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 70 140 210 280 350 SE +/- 1.55, N = 3 SE +/- 1.97, N = 4 SE +/- 1.68, N = 4 183.96 342.45 343.95 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
miniBUDE Implementation: OpenMP - Input Deck: BM2 OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 2K 4K 6K 8K 10K SE +/- 38.68, N = 3 SE +/- 49.24, N = 4 SE +/- 42.08, N = 4 4599.07 8561.24 8598.76 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Semaphores Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 8M 16M 24M 32M 40M SE +/- 22111.46, N = 3 SE +/- 86170.88, N = 3 SE +/- 169599.87, N = 3 20839432.55 38286893.79 38317964.95 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 40 80 120 160 200 SE +/- 0.40, N = 6 SE +/- 0.50, N = 8 SE +/- 0.55, N = 8 99.14 180.69 181.42 MIN: 78.31 / MAX: 136.06 MIN: 133.01 / MAX: 206.61 MIN: 140.55 / MAX: 204.2
Liquid-DSP Threads: 240 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 240 - Buffer Length: 256 - Filter Length: 57 Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 3000M 6000M 9000M 12000M 15000M SE +/- 3877427.56, N = 3 SE +/- 3844187.53, N = 3 SE +/- 13678856.35, N = 3 7209766667 13033666667 13047666667 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -pthread -lm -lc -lliquid
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 0.1011 0.2022 0.3033 0.4044 0.5055 SE +/- 0.005428, N = 15 SE +/- 0.003761, N = 15 SE +/- 0.001245, N = 7 0.449399 0.448353 0.249854 MIN: 0.32 MIN: 0.33 MIN: 0.21 1. (CXX) g++ options: -O3 -march=native -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 200 400 600 800 1000 SE +/- 9.48, N = 15 SE +/- 10.05, N = 3 SE +/- 0.10, N = 3 1052.70 1037.96 586.44 MIN: 955.43 MIN: 990.8 MIN: 563.39 1. (CXX) g++ options: -O3 -march=native -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.4 Blend File: Classroom - Compute: CPU-Only Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 8 16 24 32 40 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 36.53 20.43 20.41
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 200 400 600 800 1000 SE +/- 3.55, N = 3 SE +/- 1.53, N = 3 SE +/- 11.88, N = 3 490 636 868 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -ffunction-sections -fdata-sections -march=native -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Glibc C String Functions Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 7M 14M 21M 28M 35M SE +/- 247947.31, N = 3 SE +/- 288633.70, N = 8 SE +/- 281854.05, N = 15 19260094.31 33924057.66 34041789.97 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: SENDFILE Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 800K 1600K 2400K 3200K 4000K SE +/- 5240.70, N = 3 SE +/- 31076.17, N = 3 SE +/- 45875.47, N = 3 2140625.32 3160659.42 3745383.09 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Akka Unbalanced Cobwebbed Tree Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 6K 12K 18K 24K 30K SE +/- 370.12, N = 9 SE +/- 296.83, N = 3 SE +/- 128.63, N = 3 29426.5 29003.5 17042.9 MIN: 19199.83 / MAX: 31858.56 MIN: 20271.46 / MAX: 29909.89 MIN: 12570.6 / MAX: 17239.96
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8 - Compression Speed Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 1100 2200 3300 4400 5500 SE +/- 33.68, N = 3 SE +/- 15.70, N = 3 SE +/- 21.10, N = 3 2942.9 4933.4 4996.6 1. *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
uvg266 Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 11 22 33 44 55 SE +/- 0.03, N = 3 SE +/- 0.18, N = 4 SE +/- 0.36, N = 4 29.13 48.07 48.11 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 50 100 150 200 250 SE +/- 0.77, N = 7 SE +/- 0.44, N = 9 SE +/- 0.40, N = 9 131.35 211.29 212.92 MIN: 103.02 / MAX: 173.94 MIN: 204.87 / MAX: 224.27 MIN: 206.18 / MAX: 223.02
Cpuminer-Opt Algorithm: Triple SHA-256, Onecoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Triple SHA-256, Onecoin Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 700K 1400K 2100K 2800K 3500K SE +/- 16269.33, N = 3 SE +/- 36423.01, N = 5 SE +/- 5126.51, N = 3 2094367 3350626 3387347 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
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 Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 40 80 120 160 200 SE +/- 1.61, N = 3 SE +/- 0.32, N = 4 SE +/- 0.52, N = 4 114.23 184.14 184.27 MIN: 89.56 / MAX: 148.79 MIN: 179.27 / MAX: 193.3 MIN: 179.01 / MAX: 193.84
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: LBC, LBRY Credits Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 200K 400K 600K 800K 1000K SE +/- 7329.77, N = 5 SE +/- 256.93, N = 3 SE +/- 1402.08, N = 3 667438 1074053 1075000 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Zstd Compression Compression Level: 8, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8, Long Mode - Decompression Speed Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 1100 2200 3300 4400 5500 SE +/- 40.64, N = 6 SE +/- 3.40, N = 3 SE +/- 12.23, N = 3 3243.6 4970.9 4978.1 1. *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
Cpuminer-Opt Algorithm: x25x OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: x25x Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 1600 3200 4800 6400 8000 SE +/- 1.75, N = 3 SE +/- 29.73, N = 3 SE +/- 16.54, N = 3 5002.69 7584.87 7674.58 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -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 Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P Clear Linux 2 4 6 8 10 SE +/- 0.03622397, N = 6 SE +/- 0.03285028, N = 6 SE +/- 0.01513938, N = 8 6.39028160 6.18280959 4.17020929 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Crypto Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 70K 140K 210K 280K 350K SE +/- 149.73, N = 3 SE +/- 130.18, N = 3 SE +/- 116.86, N = 3 203339.63 310827.69 310982.35 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Matrix Math Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 200K 400K 600K 800K 1000K SE +/- 234.85, N = 3 SE +/- 14.38, N = 3 SE +/- 140.19, N = 3 551787.07 823465.88 823901.71 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Decompression Speed Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 800 1600 2400 3200 4000 SE +/- 18.09, N = 15 SE +/- 1.69, N = 7 SE +/- 1.71, N = 15 2635.9 3840.6 3845.5 1. *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8 - Decompression Speed Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 1000 2000 3000 4000 5000 SE +/- 23.01, N = 3 SE +/- 3.63, N = 3 SE +/- 4.71, N = 3 3204.2 4637.9 4638.3 1. *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Exhaustive Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 3 6 9 12 15 SE +/- 0.0035, N = 5 SE +/- 0.0116, N = 6 SE +/- 0.0219, N = 6 8.4382 12.0706 12.0979 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -flto -pthread
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: Eigen Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 3K 6K 9K 12K 15K SE +/- 108.40, N = 9 SE +/- 49.36, N = 3 SE +/- 139.81, N = 3 8337 8815 11894 1. (CXX) g++ options: -flto -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -pthread
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 Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 0.963 1.926 2.889 3.852 4.815 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 6 3.04 3.05 4.28
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 Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 2000M 4000M 6000M 8000M 10000M SE +/- 102638026.31, N = 3 SE +/- 1113552.87, N = 3 SE +/- 7145161.53, N = 3 7172733333 9886800000 9889700000 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -pthread -lm -lc -lliquid
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19, Long Mode - Decompression Speed Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 800 1600 2400 3200 4000 SE +/- 4.60, N = 12 SE +/- 7.60, N = 3 SE +/- 2.85, N = 15 2795.3 3821.2 3842.2 1. *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
DaCapo Benchmark Java Test: H2 OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 700 1400 2100 2800 3500 SE +/- 21.28, N = 20 SE +/- 24.47, N = 20 SE +/- 30.82, N = 20 3422 3390 2494
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: MMAP Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 1200 2400 3600 4800 6000 SE +/- 0.80, N = 3 SE +/- 4.47, N = 3 SE +/- 1.40, N = 3 4223.46 5646.69 5691.19 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
ASTC Encoder Preset: Thorough OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Thorough Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 30 60 90 120 150 SE +/- 0.04, N = 6 SE +/- 0.07, N = 7 SE +/- 0.14, N = 7 85.85 114.76 114.79 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -flto -pthread
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: MEMFD Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 800 1600 2400 3200 4000 SE +/- 5.64, N = 3 SE +/- 5.98, N = 3 SE +/- 1.38, N = 3 2737.60 2748.61 3631.89 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Zstd Compression Compression Level: 8, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8, Long Mode - Compression Speed Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 200 400 600 800 1000 SE +/- 7.71, N = 6 SE +/- 3.44, N = 3 SE +/- 10.39, N = 3 822.5 1080.8 1087.8 1. *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
Cpuminer-Opt Algorithm: scrypt OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: scrypt Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 1000 2000 3000 4000 5000 SE +/- 23.43, N = 3 SE +/- 1.26, N = 3 SE +/- 1.60, N = 3 3644.05 4793.62 4797.21 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Numenta Anomaly Benchmark Detector: KNN CAD OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: KNN CAD Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 20 40 60 80 100 SE +/- 0.58, N = 3 SE +/- 0.23, N = 3 SE +/- 0.33, N = 3 86.28 66.69 66.60
NWChem Input: C240 Buckyball OpenBenchmarking.org Seconds, Fewer Is Better NWChem 7.0.2 Input: C240 Buckyball Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 400 800 1200 1600 2000 1834.3 1466.5 1458.3 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 -lcomex -lm -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2
Numenta Anomaly Benchmark Detector: Earthgecko Skyline OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 15 30 45 60 75 SE +/- 0.64, N = 3 SE +/- 0.80, N = 15 SE +/- 0.74, N = 3 66.81 54.27 53.14
OSPRay Benchmark: particle_volume/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: particle_volume/ao/real_time Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 10 20 30 40 50 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 34.70 42.57 42.63
ASTC Encoder Preset: Fast OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Fast Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 200 400 600 800 1000 SE +/- 2.57, N = 5 SE +/- 4.28, N = 6 SE +/- 6.31, N = 6 672.10 765.08 821.58 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -flto -pthread
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 6 Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.5519 1.1038 1.6557 2.2076 2.7595 SE +/- 0.005, N = 10 SE +/- 0.002, N = 10 SE +/- 0.002, N = 7 2.453 2.009 2.007 1. (CXX) g++ options: -O3 -fPIC -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -lm
Renaissance Test: Genetic Algorithm Using Jenetics + Futures OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Genetic Algorithm Using Jenetics + Futures Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 400 800 1200 1600 2000 SE +/- 23.45, N = 3 SE +/- 7.45, N = 3 SE +/- 5.95, N = 3 2026.2 1677.4 1665.0 MIN: 1895.15 / MAX: 2139.35 MIN: 1620.99 / MAX: 1745.53 MIN: 1554.78 / MAX: 1738.21
PyPerformance Benchmark: nbody OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: nbody Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 20 40 60 80 100 SE +/- 0.18, N = 3 SE +/- 0.07, N = 3 SE +/- 0.17, N = 3 76.0 75.8 63.3
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark Bayes Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 100 200 300 400 500 SE +/- 1.22, N = 3 SE +/- 4.04, N = 3 SE +/- 1.01, N = 3 449.0 387.6 375.6 MIN: 295.86 / MAX: 720.71 MIN: 236.1 / MAX: 595.28 MIN: 244.91 / MAX: 682.26
Numenta Anomaly Benchmark Detector: Bayesian Changepoint OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 5 10 15 20 25 SE +/- 0.25, N = 15 SE +/- 0.18, N = 3 SE +/- 0.17, N = 15 21.70 18.63 18.27
PyPerformance Benchmark: regex_compile OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: regex_compile Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 104.0 88.2 87.6
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Compression Speed Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 30 60 90 120 150 SE +/- 0.74, N = 15 SE +/- 1.00, N = 7 SE +/- 0.96, N = 15 97.8 114.2 116.0 1. *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
Numenta Anomaly Benchmark Detector: Windowed Gaussian OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.9608 1.9216 2.8824 3.8432 4.804 SE +/- 0.018, N = 8 SE +/- 0.023, N = 9 SE +/- 0.029, N = 9 4.270 3.739 3.641
OSPRay Benchmark: gravity_spheres_volume/dim_512/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 10 20 30 40 50 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 SE +/- 0.14, N = 3 38.10 44.43 44.54
OpenVKL Benchmark: vklBenchmark ISPC OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.3.1 Benchmark: vklBenchmark ISPC Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 300 600 900 1200 1500 SE +/- 4.33, N = 3 SE +/- 2.85, N = 3 SE +/- 16.23, N = 3 1142 1332 1334 MIN: 194 / MAX: 5100 MIN: 333 / MAX: 4562 MIN: 331 / MAX: 5092
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 700 1400 2100 2800 3500 SE +/- 9.49, N = 8 SE +/- 7.25, N = 8 SE +/- 7.23, N = 8 3125 3111 2679
MariaDB Clients: 1024 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.8.2 Clients: 1024 Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 200 400 600 800 1000 SE +/- 7.35, N = 3 SE +/- 10.04, N = 3 SE +/- 5.90, N = 3 696 705 792 1. (CXX) g++ options: -fPIC -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -pie -fstack-protector -shared -lrt -lpthread -lz -ldl -lm -lstdc++
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 160 320 480 640 800 SE +/- 1.20, N = 3 SE +/- 2.60, N = 3 SE +/- 0.82, N = 4 755 749 664
Numenta Anomaly Benchmark Detector: Contextual Anomaly Detector OSE OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Contextual Anomaly Detector OSE Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 8 16 24 32 40 SE +/- 0.39, N = 4 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 32.44 30.21 28.62
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 2 Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 9 18 27 36 45 SE +/- 0.15, N = 3 SE +/- 0.32, N = 3 SE +/- 0.15, N = 3 37.56 33.29 33.14 1. (CXX) g++ options: -O3 -fPIC -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -lm
PyPerformance Benchmark: json_loads OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: json_loads Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 18.3 16.2 16.2
Numenta Anomaly Benchmark Detector: Relative Entropy OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 3 6 9 12 15 SE +/- 0.038, N = 5 SE +/- 0.098, N = 6 SE +/- 0.056, N = 5 10.759 9.654 9.645
Kvazaar Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 20 40 60 80 100 SE +/- 0.55, N = 10 SE +/- 0.64, N = 6 SE +/- 0.24, N = 6 70.41 77.94 78.48 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -lpthread -lm -lrt
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark ALS Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 400 800 1200 1600 2000 SE +/- 5.16, N = 3 SE +/- 20.05, N = 3 SE +/- 21.37, N = 3 2073.0 1912.5 1862.2 MIN: 1941.42 / MAX: 3230.55 MIN: 1772.33 / MAX: 2265.01 MIN: 1666.18 / MAX: 2218.13
ASTC Encoder Preset: Medium OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Medium Clear Linux Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P 120 240 360 480 600 SE +/- 1.40, N = 8 SE +/- 1.59, N = 7 SE +/- 0.92, N = 8 500.66 525.40 556.68 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -flto -pthread
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 0 Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 15 30 45 60 75 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 SE +/- 0.17, N = 3 67.33 60.80 60.58 1. (CXX) g++ options: -O3 -fPIC -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -lm
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Random Forest Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 140 280 420 560 700 SE +/- 6.37, N = 5 SE +/- 2.61, N = 3 SE +/- 5.64, N = 6 646.5 593.4 584.2 MIN: 581.7 / MAX: 773.51 MIN: 536.42 / MAX: 709.21 MIN: 512.73 / MAX: 725.6
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 20 40 60 80 100 SE +/- 0.65, N = 6 SE +/- 0.65, N = 6 SE +/- 0.81, N = 6 72.14 79.19 79.76 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -lpthread -lm -lrt
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark PageRank Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 600 1200 1800 2400 3000 SE +/- 29.19, N = 3 SE +/- 23.16, N = 15 SE +/- 28.19, N = 15 2704.1 2551.0 2450.5 MIN: 2424.36 / MAX: 2742.43 MIN: 2107.47 / MAX: 2809.93 MIN: 1985.5 / MAX: 2709.64
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 20 40 60 80 100 SE +/- 0.66, N = 6 SE +/- 0.55, N = 6 SE +/- 0.64, N = 6 70.58 76.91 77.23 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -lpthread -lm -lrt
Stress-NG Test: IO_uring OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: IO_uring Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 11K 22K 33K 44K 55K SE +/- 203.39, N = 3 SE +/- 107.85, N = 3 SE +/- 35.22, N = 3 48493.70 48522.08 51657.61 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Renaissance Test: ALS Movie Lens OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: ALS Movie Lens Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 2K 4K 6K 8K 10K SE +/- 95.99, N = 4 SE +/- 118.91, N = 9 SE +/- 62.83, N = 12 9105.6 8651.9 8554.7 MIN: 8667.04 / MAX: 9936.24 MIN: 7297.19 / MAX: 9790.29 MIN: 7473.52 / MAX: 10039.49
PyPerformance Benchmark: float OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: float Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 13 26 39 52 65 SE +/- 0.15, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 57.1 56.9 53.7
PyPerformance Benchmark: python_startup OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: python_startup Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.10, N = 3 SE +/- 0.00, N = 3 8.36 8.00 7.88
uvg266 Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 13 26 39 52 65 SE +/- 0.39, N = 5 SE +/- 0.40, N = 5 SE +/- 0.36, N = 5 55.89 58.41 59.27 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17
uvg266 Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 13 26 39 52 65 SE +/- 0.44, N = 5 SE +/- 0.53, N = 5 SE +/- 0.39, N = 15 56.85 59.22 60.13 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17
uvg266 Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 13 26 39 52 65 SE +/- 0.52, N = 5 SE +/- 0.53, N = 15 SE +/- 0.62, N = 15 57.28 58.66 60.02 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17
PyPerformance Benchmark: 2to3 OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: 2to3 Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 201 193 192
PyPerformance Benchmark: raytrace OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: raytrace Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 50 100 150 200 250 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 224 223 214
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: LargeRandom Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 0.2903 0.5806 0.8709 1.1612 1.4515 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.24 1.24 1.29 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Finagle HTTP Requests Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 2K 4K 6K 8K 10K SE +/- 100.96, N = 6 SE +/- 113.71, N = 4 SE +/- 131.33, N = 12 10803.3 10800.0 10387.6 MIN: 9487.14 / MAX: 11273.39 MIN: 9740.37 / MAX: 11088.94 MIN: 8501.57 / MAX: 11367.76
PyPerformance Benchmark: pickle_pure_python OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pickle_pure_python Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 50 100 150 200 250 SE +/- 0.58, N = 3 SE +/- 0.58, N = 3 SE +/- 0.00, N = 3 227 225 219
PyPerformance Benchmark: crypto_pyaes OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: crypto_pyaes Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 13 26 39 52 65 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 60.3 60.0 58.6
PyPerformance Benchmark: go OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: go Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 112 112 109
PyPerformance Benchmark: django_template OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: django_template Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 27.4 27.3 26.7
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: PartialTweets Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 1.3343 2.6686 4.0029 5.3372 6.6715 SE +/- 0.01, N = 3 SE +/- 0.06, N = 5 SE +/- 0.00, N = 3 5.79 5.85 5.93 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 400K 800K 1200K 1600K 2000K SE +/- 19191.23, N = 5 SE +/- 4431.47, N = 5 SE +/- 7368.91, N = 5 1979213 1993673 2022000
PyPerformance Benchmark: pathlib OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pathlib Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 12.1 12.0 11.9
simdjson Throughput Test: TopTweet OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: TopTweet Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 6.65 6.66 6.74 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: System V Message Passing Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 7M 14M 21M 28M 35M SE +/- 35838.24, N = 3 SE +/- 37069.81, N = 3 SE +/- 273980.47, N = 10 34562392.22 34597345.44 34967285.00 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
PyPerformance Benchmark: chaos OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: chaos Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 12 24 36 48 60 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 52.7 52.2 52.2
Meta Performance Per Watts Performance Per Watts OpenBenchmarking.org Performance Per Watts, More Is Better Meta Performance Per Watts Performance Per Watts Clear Linux Clear Linux: EPYC 9654 2P 1100 2200 3300 4400 5500 4923.04 4937.64
ClickHouse 100M Rows Hits Dataset, Third Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Clear Linux: 8490H 2P 120 240 360 480 600 SE +/- 1.04, N = 3 535.16 MIN: 60.06 / MAX: 6000
ClickHouse 100M Rows Hits Dataset, Second Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run Clear Linux: 8490H 2P 110 220 330 440 550 SE +/- 2.62, N = 3 530.44 MIN: 63.9 / MAX: 5454.55
ClickHouse 100M Rows Hits Dataset, First Run / Cold Cache OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache Clear Linux: 8490H 2P 110 220 330 440 550 SE +/- 1.60, N = 3 504.28 MIN: 60.73 / MAX: 5454.55
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.34 VGR Performance Metric 8490H 2P 900K 1800K 2700K 3600K 4500K 4231422 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -std=c++14 -fvisibility=hidden -fno-strict-aliasing -fno-common -ftemplate-depth-128 -ggdb3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6 -lSM -lICE -lXext -lXi
CPU Power Consumption Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Watts CPU Power Consumption Monitor Phoronix Test Suite System Monitoring Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 130 260 390 520 650 Min: 62.29 / Avg: 477.92 / Max: 756.4 Min: 15.47 / Avg: 350.9 / Max: 746.4 Min: 19 / Avg: 320.04 / Max: 757.24
uvg266 CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 132.7 430.9 534.1 Clear Linux: EPYC 9654 2P 47.3 273.5 384.2 Clear Linux 41.9 271.5 377.2 OpenBenchmarking.org Watts, Fewer Is Better uvg266 0.4.1 CPU Power Consumption Monitor 140 280 420 560 700
uvg266 Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second Per Watt, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0497 0.0994 0.1491 0.1988 0.2485 0.133 0.214 0.221
uvg266 CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 130.9 441.2 561.4 Clear Linux 44.6 292.7 408.1 Clear Linux: EPYC 9654 2P 44.9 290.5 408.2 OpenBenchmarking.org Watts, Fewer Is Better uvg266 0.4.1 CPU Power Consumption Monitor 140 280 420 560 700
uvg266 Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second Per Watt, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0461 0.0922 0.1383 0.1844 0.2305 0.129 0.204 0.205
uvg266 CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 136.3 458.0 573.2 Clear Linux: EPYC 9654 2P 45.5 303.8 423.5 Clear Linux 40.8 298.6 418.8 OpenBenchmarking.org Watts, Fewer Is Better uvg266 0.4.1 CPU Power Consumption Monitor 140 280 420 560 700
uvg266 Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second Per Watt, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0446 0.0892 0.1338 0.1784 0.223 0.122 0.192 0.198
uvg266 CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 129 550 644 Clear Linux: EPYC 9654 2P 47 438 605 Clear Linux 48 429 597 OpenBenchmarking.org Watts, Fewer Is Better uvg266 0.4.1 CPU Power Consumption Monitor 200 400 600 800 1000
uvg266 Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second Per Watt, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0252 0.0504 0.0756 0.1008 0.126 0.053 0.110 0.112
Liquid-DSP CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 120 604 754 Clear Linux 47 557 666 Clear Linux: EPYC 9654 2P 53 556 672 OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 2021.01.31 CPU Power Consumption Monitor 200 400 600 800 1000
Liquid-DSP Threads: 240 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 2021.01.31 Threads: 240 - Buffer Length: 256 - Filter Length: 57 Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 5M 10M 15M 20M 25M 11939483.46 23414150.14 23455551.35
Liquid-DSP CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 127 606 753 Clear Linux: EPYC 9654 2P 44 522 637 Clear Linux 42 518 629 OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 2021.01.31 CPU Power Consumption Monitor 200 400 600 800 1000
Liquid-DSP Threads: 128 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 4M 8M 12M 16M 20M 11834462.78 18932461.59 19097015.65
ASTC Encoder CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 132 431 754 Clear Linux: EPYC 9654 2P 51 309 666 Clear Linux 47 307 667 OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.0 CPU Power Consumption Monitor 200 400 600 800 1000
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.0 Preset: Exhaustive Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0088 0.0176 0.0264 0.0352 0.044 0.020 0.039 0.039
ASTC Encoder CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 130 377 738 Clear Linux 49 246 653 Clear Linux: EPYC 9654 2P 47 242 654 OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.0 CPU Power Consumption Monitor 200 400 600 800 1000
ASTC Encoder Preset: Thorough OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.0 Preset: Thorough Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 0.1067 0.2134 0.3201 0.4268 0.5335 0.228 0.467 0.474
ASTC Encoder CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 131 303 664 Clear Linux: EPYC 9654 2P 41 183 562 Clear Linux 48 181 565 OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.0 CPU Power Consumption Monitor 200 400 600 800 1000
ASTC Encoder Preset: Medium OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.0 Preset: Medium Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 0.6847 1.3694 2.0541 2.7388 3.4235 1.732 2.763 3.043
ASTC Encoder CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 130 394 668 Clear Linux 44 286 534 Clear Linux: EPYC 9654 2P 47 278 543 OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.0 CPU Power Consumption Monitor 200 400 600 800 1000
ASTC Encoder Preset: Fast OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.0 Preset: Fast Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 0.6203 1.2406 1.8609 2.4812 3.1015 2.086 2.347 2.757
libavif avifenc CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 125 287 694 Clear Linux: EPYC 9654 2P 44 147 408 Clear Linux 44 145 352 OpenBenchmarking.org Watts, Fewer Is Better libavif avifenc 0.11 CPU Power Consumption Monitor 200 400 600 800 1000
libavif avifenc CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 133 397 737 Clear Linux 45 246 472 Clear Linux: EPYC 9654 2P 53 245 461 OpenBenchmarking.org Watts, Fewer Is Better libavif avifenc 0.11 CPU Power Consumption Monitor 200 400 600 800 1000
libavif avifenc CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 134 433 724 Clear Linux: EPYC 9654 2P 33 274 481 Clear Linux 45 273 476 OpenBenchmarking.org Watts, Fewer Is Better libavif avifenc 0.11 CPU Power Consumption Monitor 200 400 600 800 1000
Kvazaar CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128.6 381.9 492.9 Clear Linux: EPYC 9654 2P 38.9 237.7 354.4 Clear Linux 29.2 235.9 355.0 OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor 130 260 390 520 650
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0761 0.1522 0.2283 0.3044 0.3805 0.189 0.333 0.338
Kvazaar CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 132.3 411.3 535.0 Clear Linux: EPYC 9654 2P 41.7 260.9 387.9 Clear Linux 49.2 257.3 387.1 OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor 140 280 420 560 700
Kvazaar Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0686 0.1372 0.2058 0.2744 0.343 0.171 0.299 0.305
Kvazaar CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128.8 433.2 568.4 Clear Linux: EPYC 9654 2P 48.0 279.1 424.2 Clear Linux 44.6 278.4 421.2 OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor 140 280 420 560 700
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 0.0623 0.1246 0.1869 0.2492 0.3115 0.163 0.276 0.277
Kvazaar CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128.1 489.5 589.9 Clear Linux: EPYC 9654 2P 52.9 384.0 584.9 Clear Linux 51.6 378.5 580.9 OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor 160 320 480 640 800
Kvazaar Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0389 0.0778 0.1167 0.1556 0.1945 0.069 0.171 0.173
Kvazaar CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 136.3 498.5 589.1 Clear Linux 52.9 384.7 582.7 Clear Linux: EPYC 9654 2P 53.9 383.2 589.8 OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor 160 320 480 640 800
Kvazaar Video Input: Bosphorus 4K - Video Preset: Slow OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.038 0.076 0.114 0.152 0.19 0.067 0.169 0.169
Xcompact3d Incompact3d CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 127 500 749 Clear Linux: EPYC 9654 2P 44 405 660 Clear Linux 41 344 642 OpenBenchmarking.org Watts, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 CPU Power Consumption Monitor 200 400 600 800 1000
High Performance Conjugate Gradient CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 127 684 720 Clear Linux: EPYC 9654 2P 48 608 663 Clear Linux 43 588 683 OpenBenchmarking.org Watts, Fewer Is Better High Performance Conjugate Gradient 3.1 CPU Power Consumption Monitor 200 400 600 800 1000
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s Per Watt, More Is Better High Performance Conjugate Gradient 3.1 Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P Clear Linux 0.0329 0.0658 0.0987 0.1316 0.1645 0.072 0.091 0.146
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 129 638 754 Clear Linux: EPYC 9654 2P 46 597 688 Clear Linux 47 591 679 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: Mutex OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Mutex Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 50K 100K 150K 200K 250K 93528.29 215853.94 219027.60
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 131.4 527.8 588.3 Clear Linux: EPYC 9654 2P 51.8 340.4 390.5 Clear Linux 43.3 337.8 381.2 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 160 320 480 640 800
Stress-NG Test: Futex OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Futex Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 2K 4K 6K 8K 10K 318.05 9091.38 9100.34
Stress-NG Test: Futex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Futex Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 700K 1400K 2100K 2800K 3500K SE +/- 3457.07, N = 15 SE +/- 29815.22, N = 3 SE +/- 26901.92, N = 3 167854.27 3071495.29 3097472.10 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 135.7 390.8 440.7 Clear Linux: EPYC 9654 2P 53.4 258.2 323.3 Clear Linux 45.1 255.0 332.6 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 120 240 360 480 600
Stress-NG Test: IO_uring OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: IO_uring Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 40 80 120 160 200 132.17 187.90 190.17
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 129 628 752 Clear Linux 48 599 689 Clear Linux: EPYC 9654 2P 53 598 695 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: SENDFILE Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 1300 2600 3900 5200 6500 3409.28 5282.43 6257.35
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 132 634 755 Clear Linux 37 481 557 Clear Linux: EPYC 9654 2P 50 477 559 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: NUMA Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 0.0297 0.0594 0.0891 0.1188 0.1485 0.025 0.127 0.132
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: NUMA Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 14 28 42 56 70 SE +/- 0.02, N = 3 SE +/- 1.05, N = 15 SE +/- 0.12, N = 3 15.80 60.86 63.01 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 136 591 660 Clear Linux: EPYC 9654 2P 53 411 469 Clear Linux 45 407 464 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: MMAP Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 4 8 12 16 20 7.151 13.727 13.988
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 133 582 654 Clear Linux: EPYC 9654 2P 51 403 462 Clear Linux 45 398 455 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: MEMFD Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 2 4 6 8 10 6.245 6.817 6.870
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 131 629 751 Clear Linux: EPYC 9654 2P 52 614 713 Clear Linux 47 607 706 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Malloc Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 300K 600K 900K 1200K 1500K 577946.03 1260057.85 1284436.46
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 130 349 755 Clear Linux: EPYC 9654 2P 52 215 449 Clear Linux 46 214 471 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: CPU Cache Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.054 0.108 0.162 0.216 0.27 0.046 0.239 0.240
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: CPU Cache Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 12 24 36 48 60 SE +/- 0.01, N = 3 SE +/- 0.83, N = 15 SE +/- 0.21, N = 3 15.90 51.20 51.40 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 126.9 508.2 559.9 Clear Linux: EPYC 9654 2P 46.4 325.6 374.0 Clear Linux 42.8 320.2 363.3 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 140 280 420 560 700
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Atomic Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 200 400 600 800 1000 35.07 639.41 849.69
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Atomic Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 60K 120K 180K 240K 300K SE +/- 235.40, N = 15 SE +/- 15718.21, N = 15 SE +/- 31981.50, N = 15 17822.07 208201.40 272067.02 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 135 630 754 Clear Linux: EPYC 9654 2P 44 597 686 Clear Linux 28 584 674 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Context Switching Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 40K 80K 120K 160K 200K 43149.70 188157.68 194395.73
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128 634 755 Clear Linux: EPYC 9654 2P 52 616 704 Clear Linux 29 610 692 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Socket Activity Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 40 80 120 160 200 155.58 165.83 184.04
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Socket Activity Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 20K 40K 60K 80K 100K SE +/- 8680.33, N = 12 SE +/- 877.37, N = 8 SE +/- 9969.26, N = 15 98576.81 102162.24 112224.53 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128.2 492.1 551.4 Clear Linux: EPYC 9654 2P 51.2 414.3 481.3 Clear Linux 36.4 409.6 478.5 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 140 280 420 560 700
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Semaphores Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 20K 40K 60K 80K 100K 42351.88 92423.02 93551.52
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128 563 632 Clear Linux: EPYC 9654 2P 53 385 441 Clear Linux 47 382 432 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: System V Message Passing Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 20K 40K 60K 80K 100K 62111.25 89800.17 90475.76
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 137 634 747 Clear Linux: EPYC 9654 2P 47 403 476 Clear Linux 45 396 468 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Forking Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 20 40 60 80 100 10.25 10.36 88.98
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 134 629 754 Clear Linux: EPYC 9654 2P 55 569 658 Clear Linux 47 563 651 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Matrix Math Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 300 600 900 1200 1500 877.21 1448.32 1461.74
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 127 631 721 Clear Linux: EPYC 9654 2P 55 555 638 Clear Linux 39 533 626 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Vector Math Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 400 800 1200 1600 2000 848.12 1808.77 1883.36
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: EPYC 9654 2P 53 641 730 Clear Linux 41 634 721 Clear Linux: 8490H 2P 129 629 754 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Glibc C String Functions Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 11K 22K 33K 44K 55K 30597.48 52936.17 53681.46
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 131 626 721 Clear Linux: EPYC 9654 2P 44 487 561 Clear Linux 47 477 546 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Memory Copying Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 12 24 36 48 60 12.54 51.90 52.72
Stress-NG CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 127 626 711 Clear Linux: EPYC 9654 2P 45 554 637 Clear Linux 44 548 630 OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor 200 400 600 800 1000
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Crypto Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 120 240 360 480 600 324.94 560.96 567.41
ClickHouse CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128 413 678 OpenBenchmarking.org Watts, Fewer Is Better ClickHouse 22.12.3.5 CPU Power Consumption Monitor 200 400 600 800 1000
ClickHouse 100M Rows Hits Dataset, Third Run OpenBenchmarking.org Queries Per Minute, Geo Mean Per Watt, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Clear Linux: 8490H 2P 0.2918 0.5836 0.8754 1.1672 1.459 1.297
BRL-CAD CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better BRL-CAD 7.34 CPU Power Consumption Monitor Clear Linux: 8490H 2P 90 180 270 360 450 Min: 130.75 / Avg: 340.87 / Max: 528.56
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric Per Watt, More Is Better BRL-CAD 7.34 VGR Performance Metric Clear Linux: 8490H 2P 3K 6K 9K 12K 15K 12413.45
MariaDB CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 135.5 405.8 421.5 Clear Linux: EPYC 9654 2P 50.8 295.0 315.3 Clear Linux 52.9 291.2 340.5 OpenBenchmarking.org Watts, Fewer Is Better MariaDB 10.8.2 CPU Power Consumption Monitor 110 220 330 440 550
MariaDB Clients: 1024 OpenBenchmarking.org Queries Per Second Per Watt, More Is Better MariaDB 10.8.2 Clients: 1024 Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.5378 1.0756 1.6134 2.1512 2.689 1.952 2.390 2.390
PostgreSQL CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 135.9 510.3 591.0 Clear Linux: EPYC 9654 2P 45.6 404.3 483.9 Clear Linux 48.5 395.5 482.8 OpenBenchmarking.org Watts, Fewer Is Better PostgreSQL 15 CPU Power Consumption Monitor 160 320 480 640 800
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 4 8 12 16 20 SE +/- 0.30, N = 12 SE +/- 0.32, N = 12 SE +/- 0.01, N = 3 14.70 14.61 14.24 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 15K 30K 45K 60K 75K SE +/- 1359.28, N = 12 SE +/- 1422.48, N = 12 SE +/- 51.90, N = 3 68349 68796 70213 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -lpgcommon -lpgport -lpq -lm
PostgreSQL CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 136.4 499.1 588.0 Clear Linux: EPYC 9654 2P 51.7 397.2 482.8 Clear Linux 46.9 384.3 461.7 OpenBenchmarking.org Watts, Fewer Is Better PostgreSQL 15 CPU Power Consumption Monitor 160 320 480 640 800
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 3 6 9 12 15 SE +/- 0.15, N = 3 SE +/- 0.30, N = 9 SE +/- 0.03, N = 3 11.23 10.92 10.52 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Write Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 16K 32K 48K 64K 80K SE +/- 963.04, N = 3 SE +/- 1898.65, N = 9 SE +/- 214.33, N = 3 71275 73652 76025 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -lpgcommon -lpgport -lpq -lm
Embree CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 133 435 639 Clear Linux 26 330 648 Clear Linux: EPYC 9654 2P 31 325 641 OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor 200 400 600 800 1000
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 0.1249 0.2498 0.3747 0.4996 0.6245 0.228 0.550 0.555
Embree CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 132 392 695 Clear Linux 15 260 627 Clear Linux: EPYC 9654 2P 23 260 631 OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor 200 400 600 800 1000
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.1593 0.3186 0.4779 0.6372 0.7965 0.291 0.708 0.708
Embree CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 131 444 683 Clear Linux: EPYC 9654 2P 20 294 631 Clear Linux 17 287 629 OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor 200 400 600 800 1000
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.1667 0.3334 0.5001 0.6668 0.8335 0.296 0.719 0.741
SVT-AV1 CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 130.2 298.2 506.4 Clear Linux 42.0 166.1 322.5 Clear Linux: EPYC 9654 2P 49.1 164.4 331.4 OpenBenchmarking.org Watts, Fewer Is Better SVT-AV1 1.4 CPU Power Consumption Monitor 130 260 390 520 650
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 4K Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 0.3537 0.7074 1.0611 1.4148 1.7685 0.752 1.427 1.572
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 4K Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 60 120 180 240 300 SE +/- 1.05, N = 6 SE +/- 5.47, N = 15 SE +/- 8.59, N = 15 224.36 236.89 258.44 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 123.8 286.0 480.6 Clear Linux 41.6 159.4 306.2 Clear Linux: EPYC 9654 2P 47.2 157.5 308.6 OpenBenchmarking.org Watts, Fewer Is Better SVT-AV1 1.4 CPU Power Consumption Monitor 120 240 360 480 600
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 4K Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 0.3242 0.6484 0.9726 1.2968 1.621 0.746 1.301 1.441
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 4K Clear Linux Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P 50 100 150 200 250 SE +/- 5.97, N = 15 SE +/- 2.96, N = 15 SE +/- 7.24, N = 15 207.35 213.45 226.93 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Numenta Anomaly Benchmark CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 133.1 348.3 540.7 Clear Linux: EPYC 9654 2P 49.1 212.0 374.1 Clear Linux 46.3 209.7 375.9 OpenBenchmarking.org Watts, Fewer Is Better Numenta Anomaly Benchmark 1.1 CPU Power Consumption Monitor 140 280 420 560 700
Numenta Anomaly Benchmark CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 133 462 704 Clear Linux: EPYC 9654 2P 53 281 501 Clear Linux 50 280 488 OpenBenchmarking.org Watts, Fewer Is Better Numenta Anomaly Benchmark 1.1 CPU Power Consumption Monitor 200 400 600 800 1000
Numenta Anomaly Benchmark CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 124.8 412.0 552.8 Clear Linux: EPYC 9654 2P 44.9 251.5 420.7 Clear Linux 44.0 249.3 416.1 OpenBenchmarking.org Watts, Fewer Is Better Numenta Anomaly Benchmark 1.1 CPU Power Consumption Monitor 140 280 420 560 700
Numenta Anomaly Benchmark CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128.3 318.6 527.6 Clear Linux 43.8 194.1 355.8 Clear Linux: EPYC 9654 2P 51.0 192.9 361.8 OpenBenchmarking.org Watts, Fewer Is Better Numenta Anomaly Benchmark 1.1 CPU Power Consumption Monitor 130 260 390 520 650
Numenta Anomaly Benchmark CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 129.0 290.8 520.5 Clear Linux: EPYC 9654 2P 32.7 164.1 355.7 Clear Linux 44.8 163.3 349.9 OpenBenchmarking.org Watts, Fewer Is Better Numenta Anomaly Benchmark 1.1 CPU Power Consumption Monitor 130 260 390 520 650
Numenta Anomaly Benchmark CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 129.9 360.5 549.2 Clear Linux 52.3 217.2 388.0 Clear Linux: EPYC 9654 2P 51.7 216.5 372.0 OpenBenchmarking.org Watts, Fewer Is Better Numenta Anomaly Benchmark 1.1 CPU Power Consumption Monitor 140 280 420 560 700
PyPerformance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 136.3 234.3 320.1 Clear Linux: EPYC 9654 2P 46.2 200.0 218.6 Clear Linux 47.9 199.0 217.8 OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor 80 160 240 320 400
PyPerformance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 131.4 234.0 350.5 Clear Linux: EPYC 9654 2P 46.2 202.2 219.0 Clear Linux 39.8 201.6 218.0 OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor 100 200 300 400 500
PyPerformance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 134.3 351.1 366.5 Clear Linux: EPYC 9654 2P 52.1 208.9 218.7 Clear Linux 49.5 207.7 217.5 OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor 100 200 300 400 500
PyPerformance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 135.4 232.3 296.8 Clear Linux 48.3 196.1 217.9 Clear Linux: EPYC 9654 2P 51.5 196.0 218.9 OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor 70 140 210 280 350
PyPerformance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 135.8 335.2 363.0 Clear Linux: EPYC 9654 2P 50.8 200.6 218.5 Clear Linux 44.4 199.5 217.6 OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor 100 200 300 400 500
PyPerformance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 132.7 234.4 343.7 Clear Linux: EPYC 9654 2P 51.6 195.9 218.5 Clear Linux 50.6 195.1 217.7 OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor 80 160 240 320 400
PyPerformance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 133.2 234.5 348.4 Clear Linux: EPYC 9654 2P 48.4 197.5 218.3 Clear Linux 29.2 196.6 217.4 OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor 100 200 300 400 500
PyPerformance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 130.6 234.3 354.5 Clear Linux: EPYC 9654 2P 52.8 191.0 218.3 Clear Linux 42.2 189.4 217.4 OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor 100 200 300 400 500
PyPerformance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 133.2 316.3 359.5 Clear Linux: EPYC 9654 2P 48.1 191.6 218.7 Clear Linux 43.4 190.5 217.7 OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor 100 200 300 400 500
PyPerformance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 132.5 289.8 356.1 Clear Linux: EPYC 9654 2P 44.9 195.9 219.0 Clear Linux 48.1 195.4 217.8 OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor 100 200 300 400 500
PyPerformance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 134.5 231.9 299.4 Clear Linux: EPYC 9654 2P 46.7 192.8 218.4 Clear Linux 46.5 191.2 217.6 OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor 80 160 240 320 400
PyPerformance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 123.5 232.7 353.5 Clear Linux: EPYC 9654 2P 46.0 190.7 218.7 Clear Linux 34.0 189.2 217.8 OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor 100 200 300 400 500
PyPerformance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 134.9 333.4 358.4 Clear Linux: EPYC 9654 2P 53.1 201.9 218.6 Clear Linux 26.1 200.6 217.5 OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor 100 200 300 400 500
PyBench CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 130.9 214.4 298.5 Clear Linux 39.4 186.8 217.8 Clear Linux: EPYC 9654 2P 48.3 186.5 218.5 OpenBenchmarking.org Watts, Fewer Is Better PyBench 2018-02-16 CPU Power Consumption Monitor 80 160 240 320 400
PHPBench CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 131.8 207.6 271.9 Clear Linux 35.2 172.8 217.7 Clear Linux: EPYC 9654 2P 51.9 171.7 218.7 OpenBenchmarking.org Watts, Fewer Is Better PHPBench 0.8.1 CPU Power Consumption Monitor 70 140 210 280 350
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score Per Watt, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 2K 4K 6K 8K 10K 9741.06 11452.08 11611.68
Renaissance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 132.3 396.2 412.6 Clear Linux: EPYC 9654 2P 43.0 231.5 251.3 Clear Linux 46.6 229.5 250.0 OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor 110 220 330 440 550
Renaissance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 135.7 362.8 407.1 Clear Linux: EPYC 9654 2P 45.5 225.7 275.2 Clear Linux 45.7 222.3 251.4 OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor 110 220 330 440 550
Renaissance CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 120 240 360 480 600 Min: 135.75 / Avg: 640.36 / Max: 702.13 Min: 47.66 / Avg: 503.08 / Max: 575.15 Min: 30.3 / Avg: 494.69 / Max: 554.76
Renaissance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 134.5 361.1 422.7 Clear Linux: EPYC 9654 2P 42.1 213.9 263.3 Clear Linux 52.5 211.8 260.1 OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor 110 220 330 440 550
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Scala Dotty Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 140 280 420 560 700 SE +/- 10.05, N = 15 SE +/- 10.77, N = 15 SE +/- 2.60, N = 3 644.9 625.0 578.0 MIN: 515.92 / MAX: 950.96 MIN: 492.3 / MAX: 932.64 MIN: 492.04 / MAX: 909.55
Renaissance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 131.4 375.6 398.6 Clear Linux: EPYC 9654 2P 46.5 221.7 246.5 Clear Linux 41.9 220.0 244.6 OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor 110 220 330 440 550
Renaissance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 133 463 671 Clear Linux 51 291 447 Clear Linux: EPYC 9654 2P 51 290 456 OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor 200 400 600 800 1000
Renaissance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 137.8 365.9 407.6 Clear Linux: EPYC 9654 2P 46.9 212.8 248.7 Clear Linux 50.9 210.9 246.6 OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor 110 220 330 440 550
Renaissance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 131.3 398.0 426.5 Clear Linux: EPYC 9654 2P 27.1 236.6 259.0 Clear Linux 48.6 235.0 255.2 OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor 110 220 330 440 550
Renaissance CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 120 240 360 480 600 Min: 126.9 / Avg: 396.68 / Max: 689.1 Min: 53.78 / Avg: 248.38 / Max: 389.37 Min: 41.8 / Avg: 237.74 / Max: 417.37
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Savina Reactors.IO Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P Clear Linux 2K 4K 6K 8K 10K SE +/- 101.90, N = 3 SE +/- 138.98, N = 12 SE +/- 274.01, N = 12 9999.3 9853.7 8672.4 MIN: 9868.41 / MAX: 17072.77 MIN: 9315.85 / MAX: 17034.6 MIN: 7489.86 / MAX: 15895.97
Renaissance CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128.7 439.5 560.1 Clear Linux: EPYC 9654 2P 46.9 335.9 434.2 Clear Linux 52.5 329.2 426.4 OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor 140 280 420 560 700
DaCapo Benchmark CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 129.9 278.1 397.8 Clear Linux: EPYC 9654 2P 50.0 146.1 248.5 Clear Linux 40.2 144.6 248.4 OpenBenchmarking.org Watts, Fewer Is Better DaCapo Benchmark 9.12-MR1 CPU Power Consumption Monitor 110 220 330 440 550
DaCapo Benchmark CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 135.0 310.8 402.9 Clear Linux: EPYC 9654 2P 45.1 167.7 265.1 Clear Linux 37.0 165.0 262.6 OpenBenchmarking.org Watts, Fewer Is Better DaCapo Benchmark 9.12-MR1 CPU Power Consumption Monitor 110 220 330 440 550
NWChem CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better NWChem 7.0.2 CPU Power Consumption Monitor Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 130 260 390 520 650 Min: 131.37 / Avg: 695.57 / Max: 740.37 Min: 51.41 / Avg: 664.88 / Max: 699.68 Min: 52.4 / Avg: 653.87 / Max: 684.74
simdjson CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 129.7 333.6 351.1 Clear Linux: EPYC 9654 2P 42.9 209.4 219.5 Clear Linux 52.4 208.1 218.0 OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor 100 200 300 400 500
simdjson Throughput Test: TopTweet OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: TopTweet Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0072 0.0144 0.0216 0.0288 0.036 0.020 0.032 0.032
simdjson CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 130.6 333.3 358.9 Clear Linux: EPYC 9654 2P 35.8 206.7 220.5 Clear Linux 45.5 205.7 219.1 OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor 100 200 300 400 500
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: LargeRandom Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0014 0.0028 0.0042 0.0056 0.007 0.004 0.006 0.006
simdjson CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 127.7 332.4 349.6 Clear Linux: EPYC 9654 2P 48.0 210.1 222.5 Clear Linux 29.7 208.0 218.8 OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor 100 200 300 400 500
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: PartialTweets Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0065 0.013 0.0195 0.026 0.0325 0.017 0.028 0.029
GROMACS CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 124 613 754 Clear Linux 45 530 711 Clear Linux: EPYC 9654 2P 49 522 697 OpenBenchmarking.org Watts, Fewer Is Better GROMACS 2022.1 CPU Power Consumption Monitor 200 400 600 800 1000
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day Per Watt, More Is Better GROMACS 2022.1 Implementation: MPI CPU - Input: water_GMX50_bare Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 0.0081 0.0162 0.0243 0.0324 0.0405 0.024 0.034 0.036
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2022.1 Implementation: MPI CPU - Input: water_GMX50_bare Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.90, N = 12 SE +/- 0.01, N = 3 14.98 17.83 18.71 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17
NAMD CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 123 587 753 Clear Linux 48 315 676 Clear Linux: EPYC 9654 2P 55 306 680 OpenBenchmarking.org Watts, Fewer Is Better NAMD 2.14 CPU Power Consumption Monitor 200 400 600 800 1000
miniBUDE CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 130 552 756 Clear Linux: EPYC 9654 2P 46 485 643 Clear Linux 43 475 638 OpenBenchmarking.org Watts, Fewer Is Better miniBUDE 20210901 CPU Power Consumption Monitor 200 400 600 800 1000
miniBUDE Implementation: OpenMP - Input Deck: BM2 OpenBenchmarking.org Billion Interactions/s Per Watt, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.1622 0.3244 0.4866 0.6488 0.811 0.333 0.709 0.721
miniBUDE CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 124.4 376.3 582.5 Clear Linux: EPYC 9654 2P 48.2 280.8 624.0 Clear Linux 38.4 270.8 616.1 OpenBenchmarking.org Watts, Fewer Is Better miniBUDE 20210901 CPU Power Consumption Monitor 160 320 480 640 800
miniBUDE Implementation: OpenMP - Input Deck: BM1 OpenBenchmarking.org Billion Interactions/s Per Watt, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.2403 0.4806 0.7209 0.9612 1.2015 0.352 1.029 1.068
Cpuminer-Opt CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 126 630 753 Clear Linux: EPYC 9654 2P 35 627 737 Clear Linux 44 617 727 OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.20.3 CPU Power Consumption Monitor 200 400 600 800 1000
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.20.3 Algorithm: LBC, LBRY Credits Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 400 800 1200 1600 2000 1060.18 1714.18 1741.63
Cpuminer-Opt CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128 627 754 Clear Linux: EPYC 9654 2P 55 564 647 Clear Linux 53 555 639 OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.20.3 CPU Power Consumption Monitor 200 400 600 800 1000
Cpuminer-Opt Algorithm: x25x OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.20.3 Algorithm: x25x Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 4 8 12 16 20 7.984 13.600 13.661
Cpuminer-Opt CPU Power Consumption Monitor Min Avg Max Clear Linux: EPYC 9654 2P 44 654 757 Clear Linux 43 643 746 Clear Linux: 8490H 2P 123 627 754 OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.20.3 CPU Power Consumption Monitor 200 400 600 800 1000
Cpuminer-Opt Algorithm: Triple SHA-256, Onecoin OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Triple SHA-256, Onecoin Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 1100 2200 3300 4400 5500 3339.58 5126.05 5264.44
Cpuminer-Opt CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 131 629 754 Clear Linux: EPYC 9654 2P 42 589 680 Clear Linux 53 580 676 OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.20.3 CPU Power Consumption Monitor 200 400 600 800 1000
Cpuminer-Opt Algorithm: scrypt OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.20.3 Algorithm: scrypt Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 2 4 6 8 10 5.794 8.145 8.261
oneDNN CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 131 653 755 Clear Linux: EPYC 9654 2P 47 505 607 Clear Linux 50 491 598 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 3.0 CPU Power Consumption Monitor 200 400 600 800 1000
oneDNN CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 130 653 753 Clear Linux: EPYC 9654 2P 39 506 594 Clear Linux 16 501 585 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 3.0 CPU Power Consumption Monitor 200 400 600 800 1000
oneDNN CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 123 530 750 Clear Linux: EPYC 9654 2P 33 393 600 Clear Linux 42 389 611 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 3.0 CPU Power Consumption Monitor 200 400 600 800 1000
oneDNN Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 0.4433 0.8866 1.3299 1.7732 2.2165 SE +/- 0.02694, N = 15 SE +/- 0.08522, N = 15 SE +/- 0.00444, N = 5 1.97020 1.75315 1.51936 MIN: 1.35 MIN: 1.22 MIN: 1.15 1. (CXX) g++ options: -O3 -march=native -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
oneDNN CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 125 580 752 Clear Linux: EPYC 9654 2P 43 433 629 Clear Linux 43 428 606 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 3.0 CPU Power Consumption Monitor 200 400 600 800 1000
oneDNN Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU Clear Linux: EPYC 9654 2P Clear Linux Clear Linux: 8490H 2P 1.0843 2.1686 3.2529 4.3372 5.4215 SE +/- 0.177585, N = 15 SE +/- 0.272228, N = 12 SE +/- 0.004589, N = 4 4.819100 4.169190 0.976622 MIN: 2.71 MIN: 2.46 MIN: 0.82 1. (CXX) g++ options: -O3 -march=native -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
oneDNN CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 125 583 708 Clear Linux: EPYC 9654 2P 47 492 617 Clear Linux 46 481 607 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 3.0 CPU Power Consumption Monitor 200 400 600 800 1000
oneDNN CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 124 458 741 Clear Linux: EPYC 9654 2P 39 363 600 Clear Linux 30 355 587 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 3.0 CPU Power Consumption Monitor 200 400 600 800 1000
Blender CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128 667 754 Clear Linux: EPYC 9654 2P 51 627 696 Clear Linux 53 623 685 OpenBenchmarking.org Watts, Fewer Is Better Blender 3.4 CPU Power Consumption Monitor 200 400 600 800 1000
Blender CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 130 631 754 Clear Linux: EPYC 9654 2P 51 554 677 Clear Linux 48 539 670 OpenBenchmarking.org Watts, Fewer Is Better Blender 3.4 CPU Power Consumption Monitor 200 400 600 800 1000
OSPRay CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128 687 728 Clear Linux: EPYC 9654 2P 47 584 602 Clear Linux 50 571 588 OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor 200 400 600 800 1000
OSPRay Benchmark: particle_volume/ao/real_time OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: particle_volume/ao/real_time Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0169 0.0338 0.0507 0.0676 0.0845 0.051 0.073 0.075
OSPRay CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 120 662 740 Clear Linux: EPYC 9654 2P 19 583 627 Clear Linux 19 573 614 OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor 200 400 600 800 1000
OSPRay Benchmark: gravity_spheres_volume/dim_512/ao/real_time OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0176 0.0352 0.0528 0.0704 0.088 0.058 0.076 0.078
Intel Open Image Denoise CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 134 414 726 Clear Linux: EPYC 9654 2P 46 287 571 Clear Linux 22 278 564 OpenBenchmarking.org Watts, Fewer Is Better Intel Open Image Denoise 1.4.0 CPU Power Consumption Monitor 200 400 600 800 1000
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec Per Watt, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 0.0025 0.005 0.0075 0.01 0.0125 0.010 0.011 0.011
OpenVKL CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better OpenVKL 1.3.1 CPU Power Consumption Monitor Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 130 260 390 520 650 Min: 62.29 / Avg: 559.18 / Max: 732.51 Min: 52.67 / Avg: 493.46 / Max: 664.3 Min: 40.7 / Avg: 491.72 / Max: 665.25
OpenVKL Benchmark: vklBenchmark ISPC OpenBenchmarking.org Items / Sec Per Watt, More Is Better OpenVKL 1.3.1 Benchmark: vklBenchmark ISPC Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 0.6095 1.219 1.8285 2.438 3.0475 2.042 2.703 2.709
LeelaChessZero CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128 538 703 Clear Linux 53 375 509 Clear Linux: EPYC 9654 2P 46 373 509 OpenBenchmarking.org Watts, Fewer Is Better LeelaChessZero 0.28 CPU Power Consumption Monitor 200 400 600 800 1000
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second Per Watt, More Is Better LeelaChessZero 0.28 Backend: Eigen Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 6 12 18 24 30 22.10 22.37 23.49
ONNX Runtime CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 72 614 636 Clear Linux: EPYC 9654 2P 48 447 467 Clear Linux 44 440 460 OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor 200 400 600 800 1000
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 0.6377 1.2754 1.9131 2.5508 3.1885 2.030 2.573 2.834
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 400 800 1200 1600 2000 SE +/- 5.33, N = 3 SE +/- 26.51, N = 11 SE +/- 17.61, N = 6 894 1151 1739 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -ffunction-sections -fdata-sections -march=native -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime CPU Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 80 160 240 320 400 Min: 126.24 / Avg: 432.84 / Max: 457.84 Min: 40.77 / Avg: 244.28 / Max: 253.15 Min: 34.17 / Avg: 243.48 / Max: 251.53
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 6 12 18 24 30 23.43 24.48 25.69
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 2K 4K 6K 8K 10K SE +/- 7.78, N = 3 SE +/- 178.04, N = 12 SE +/- 299.17, N = 12 5705 5981 11120 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -ffunction-sections -fdata-sections -march=native -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 123.3 559.2 577.4 Clear Linux: EPYC 9654 2P 50.7 374.8 389.2 Clear Linux 53.3 372.3 387.7 OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor 140 280 420 560 700
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard Clear Linux Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P 0.3818 0.7636 1.1454 1.5272 1.909 1.316 1.552 1.697
ONNX Runtime CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128.5 432.6 443.5 Clear Linux: EPYC 9654 2P 43.1 256.6 267.4 Clear Linux 46.1 252.3 261.9 OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor 120 240 360 480 600
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 6 12 18 24 30 21.48 25.14 27.06
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 3K 6K 9K 12K 15K SE +/- 28.14, N = 3 SE +/- 323.96, N = 9 SE +/- 76.22, N = 3 5417 6453 11707 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -ffunction-sections -fdata-sections -march=native -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 123 654 682 Clear Linux: EPYC 9654 2P 55 494 524 Clear Linux 53 491 517 OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor 200 400 600 800 1000
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 0.1744 0.3488 0.5232 0.6976 0.872 0.495 0.497 0.775
ONNX Runtime CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 125 606 629 Clear Linux: EPYC 9654 2P 43 442 461 Clear Linux 53 435 455 OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor 200 400 600 800 1000
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard Clear Linux Clear Linux: EPYC 9654 2P Clear Linux: 8490H 2P 0.2093 0.4186 0.6279 0.8372 1.0465 0.533 0.683 0.930
Zstd Compression CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 127.0 365.1 426.3 Clear Linux 38.1 216.9 258.9 Clear Linux: EPYC 9654 2P 37.2 216.1 258.7 OpenBenchmarking.org Watts, Fewer Is Better Zstd Compression CPU Power Consumption Monitor 110 220 330 440 550
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s Per Watt, More Is Better Zstd Compression Compression Level: 19, Long Mode - Decompression Speed Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 4 8 12 16 20 7.655 17.680 17.713
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19, Long Mode - Compression Speed Clear Linux: 8490H 2P Clear Linux: EPYC 9654 2P Clear Linux 13 26 39 52 65 SE +/- 0.86, N = 12 SE +/- 0.12, N = 3 SE +/- 0.96, N = 15 51.6 54.6 55.7 1. *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
Zstd Compression CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128.2 385.0 500.1 Clear Linux 45.5 228.1 300.0 Clear Linux: EPYC 9654 2P 41.2 227.2 298.8 OpenBenchmarking.org Watts, Fewer Is Better Zstd Compression CPU Power Consumption Monitor 130 260 390 520 650
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s Per Watt, More Is Better Zstd Compression Compression Level: 19 - Decompression Speed Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 4 8 12 16 20 6.846 16.856 16.907
Zstd Compression CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128.0 369.4 416.7 Clear Linux 47.3 218.8 264.2 Clear Linux: EPYC 9654 2P 32.9 218.1 264.4 OpenBenchmarking.org Watts, Fewer Is Better Zstd Compression CPU Power Consumption Monitor 110 220 330 440 550
Zstd Compression Compression Level: 8, Long Mode - Decompression Speed OpenBenchmarking.org MB/s Per Watt, More Is Better Zstd Compression Compression Level: 8, Long Mode - Decompression Speed Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 5 10 15 20 25 8.781 22.757 22.791
Zstd Compression CPU Power Consumption Monitor Min Avg Max Clear Linux: 8490H 2P 128.2 417.3 573.3 Clear Linux 34.5 249.3 345.4 Clear Linux: EPYC 9654 2P 43.7 248.3 347.1 OpenBenchmarking.org Watts, Fewer Is Better Zstd Compression CPU Power Consumption Monitor 140 280 420 560 700
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s Per Watt, More Is Better Zstd Compression Compression Level: 8 - Decompression Speed Clear Linux: 8490H 2P Clear Linux Clear Linux: EPYC 9654 2P 5 10 15 20 25 7.678 18.602 18.681
Phoronix Test Suite v10.8.4