Benchmarks by Michael Larabel for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2302279-NE-AMDPSTATE10 AMD P-State Linux 6.3 Testing - Phoronix Test Suite AMD P-State Linux 6.3 Testing Benchmarks by Michael Larabel for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2302279-NE-AMDPSTATE10&rdt&gru .
AMD P-State Linux 6.3 Testing Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Vulkan Compiler File-System Screen Resolution amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 2 x AMD EPYC 7773X 64-Core @ 3.53GHz (128 Cores / 256 Threads) AMD DAYTONA_X (RYM1009B BIOS) AMD Starship/Matisse 512GB 800GB INTEL SSDPF21Q800GB ASPEED VE228 2 x Mellanox MT27710 Ubuntu 22.04 6.2.0-phx (x86_64) GNOME Shell 42.5 X Server 1.21.1.3 1.3.224 GCC 11.3.0 + LLVM 14.0.0 ext4 1920x1080 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads) OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - amd_pstate_epp powersave balance_performance: Scaling Governor: amd_pstate_epp powersave (EPP: balance_performance) - CPU Microcode: 0xa001229 - amd_pstate_epp performance balance_performance: Scaling Governor: amd_pstate_epp performance (EPP: performance) - CPU Microcode: 0xa001229 - amd_pstate_epp powersave power: Scaling Governor: amd_pstate_epp powersave (EPP: power) - CPU Microcode: 0xa001229 - amd_pstate_epp performance performance: Scaling Governor: amd_pstate_epp performance (EPP: performance) - CPU Microcode: 0xa001229 - amd_pstate schedutil: Scaling Governor: amd-pstate schedutil (Boost: Enabled) - CPU Microcode: 0xa001229 - amd_pstate performance: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa001229 - amd_pstate powersave: Scaling Governor: amd-pstate powersave (Boost: Enabled) - CPU Microcode: 0xa001229 - amd_pstate ondemand: Scaling Governor: amd-pstate ondemand (Boost: Enabled) - CPU Microcode: 0xa001229 - acpi_cpufreq schedutil: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001229 - acpi_cpufreq ondemand: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001229 - acpi_cpufreq performance: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229 Python Details - Python 3.10.6 Security Details - 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
AMD P-State Linux 6.3 Testing openvino: Person Detection FP16 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU embree: Pathtracer ISPC - Crown embree: Pathtracer ISPC - Asian Dragon kvazaar: Bosphorus 4K - Medium kvazaar: Bosphorus 4K - Super Fast kvazaar: Bosphorus 4K - Ultra Fast svt-av1: Preset 4 - Bosphorus 4K svt-av1: Preset 12 - Bosphorus 4K svt-av1: Preset 13 - Bosphorus 4K uvg266: Bosphorus 4K - Medium uvg266: Bosphorus 4K - Super Fast uvg266: Bosphorus 4K - Ultra Fast vpxenc: Speed 5 - Bosphorus 4K vvenc: Bosphorus 4K - Fast vvenc: Bosphorus 4K - Faster x265: Bosphorus 4K tensorflow: CPU - 256 - AlexNet tensorflow: CPU - 256 - GoogLeNet openvkl: vklBenchmark ISPC openvkl: vklBenchmark Scalar deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream compress-zstd: 19 - Compression Speed compress-zstd: 19 - Decompression Speed compress-zstd: 19, Long Mode - Compression Speed compress-zstd: 19, Long Mode - Decompression Speed compress-7zip: Compression Rating compress-7zip: Decompression Rating gromacs: MPI CPU - water_GMX50_bare cockroach: MoVR - 512 cockroach: KV, 10% Reads - 512 cockroach: KV, 95% Reads - 512 clickhouse: 100M Rows Hits Dataset, First Run / Cold Cache clickhouse: 100M Rows Hits Dataset, Second Run clickhouse: 100M Rows Hits Dataset, Third Run stargate: 192000 - 1024 nginx: 500 phpbench: PHP Benchmark Suite pgbench: 100 - 500 - Read Only pgbench: 100 - 800 - Read Only pgbench: 100 - 1000 - Read Only pgbench: 100 - 500 - Read Write pgbench: 100 - 800 - Read Write pgbench: 100 - 1000 - Read Write brl-cad: VGR Performance Metric namd: ATPase Simulation - 327,506 Atoms pybench: Total For Average Test Times ospray-studio: 1 - 4K - 1 - Path Tracer ospray-studio: 3 - 4K - 1 - Path Tracer ospray-studio: 1 - 4K - 32 - Path Tracer ospray-studio: 3 - 4K - 32 - Path Tracer pgbench: 100 - 500 - Read Only - Average Latency pgbench: 100 - 800 - Read Only - Average Latency pgbench: 100 - 1000 - Read Only - Average Latency pgbench: 100 - 500 - Read Write - Average Latency pgbench: 100 - 800 - Read Write - Average Latency pgbench: 100 - 1000 - Read Write - Average Latency openvino: Person Detection FP16 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream incompact3d: X3D-benchmarking input.i3d openfoam: drivaerFastback, Medium Mesh Size - Mesh Time openfoam: drivaerFastback, Medium Mesh Size - Execution Time build-gem5: Time To Compile build-godot: Time To Compile build-linux-kernel: defconfig build-linux-kernel: allmodconfig build-nodejs: Time To Compile blender: Classroom - CPU-Only blender: Fishy Cat - CPU-Only blender: Barbershop - CPU-Only blender: Pabellon Barcelona - CPU-Only amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 15.52 53.09 3738.04 267.15 5291.45 3654.51 35205.47 122.5014 92.2064 29.42 47.97 50.67 3.453 175.455 170.265 24.28 39.96 41.13 11.63 3.359 6.326 18.56 87.75 38.41 514 364 72.8451 926.2028 310.296 403.291 830.0967 610.7001 108.1971 307.0385 73.0239 16.0 1278.3 8.91 1195.0 500471 716703 11.079 641.8 44725.5 75876.4 355.12 373.47 372.98 2.059259 146738.16 687682 1288550 1248266 1207540 28873 24275 21978 2853983 0.22286 1003 1101 1304 35438 41798 0.390 0.641 0.828 17.372 32.961 45.509 4030.03 1195.35 17.10 239.05 24.17 17.49 3.51 869.2150 68.9182 205.6828 158.1292 76.9866 104.5730 587.7380 207.6114 868.0756 264.910481 116.05227 167.409 157.102 41.898 25.521 176.495 111.949 37.94 19.17 141.79 45.99 15.54 53.07 3748.17 266.96 5294.97 3670.78 35601.83 123.1458 94.7841 31.99 54.69 56.14 4.158 186.048 194.103 27.01 46.26 47.25 13.37 4.022 7.397 20.55 97.12 40.19 516 374 72.9497 929.7894 310.4330 404.9534 830.0131 609.6137 108.1954 307.6420 72.9379 17.6 1278.6 9.28 1203.6 522348 726521 11.179 761.0 50217.2 86214.8 395.53 409.86 406.99 2.348079 147764.25 697478 1306099 1241726 1209033 35610 26830 24299 2905181 0.22270 998 1103 1299 35573 41650 0.383 0.644 0.827 14.638 29.823 41.177 4015.91 1195.60 17.06 239.29 24.16 17.41 3.45 868.8719 68.7056 205.4179 157.5501 76.9790 104.7553 587.8421 207.4377 867.9275 264.590464 114.86885 170.71478 149.767 37.321 22.623 172.884 105.529 37.68 18.80 140.18 45.72 15.50 52.91 3730.66 268.24 5277.02 3645.60 36975.34 121.2970 93.7279 20.66 45.56 41.83 2.443 155.770 145.323 17.33 33.79 33.76 7.95 2.471 4.769 15.33 65.63 31.64 477 346 72.7952 931.6005 309.3788 403.5860 829.6035 609.8987 108.1498 307.7129 73.0501 15.2 1269.8 8.72 1186.0 459617 661420 11.131 570.5 43287.2 74380.0 339.68 349.30 353.17 1.801238 145614.76 671207 1292798 1245914 1226429 28682 24173 21522 2863951 0.22450 1008 1102 1303 35243 41532 0.387 0.642 0.815 17.486 33.129 46.474 4033.63 1199.87 17.14 238.16 24.24 17.53 3.32 868.9246 68.5591 205.6999 158.0751 77.0202 104.6604 587.7795 207.3328 867.0199 263.300232 116.28282 169.24992 173.201 47.935 30.833 184.470 120.483 38.35 19.74 143.04 46.73 15.55 52.79 3744.85 266.56 5291.00 3679.31 36507.11 122.8729 93.5012 32.30 54.77 55.85 4.181 173.314 188.423 27.06 46.31 46.08 12.83 4.023 7.352 20.63 96.73 40.39 512 385 73.0561 931.5821 310.7448 404.5464 830.3241 610.3155 108.1144 307.8920 73.1372 17.5 1276.2 9.26 1203.3 514443 733882 11.074 763.4 49015.5 86477.3 392.95 407.73 394.98 2.346447 152654.86 700287 1286042 1240406 1226743 32286 27596 26085 2980719 0.22021 1010 1101 1302 35210 41686 0.389 0.645 0.815 15.529 29.000 38.341 4005.03 1203.52 17.07 239.70 24.17 17.37 3.38 868.2616 68.5813 205.3031 157.7002 76.9051 104.6233 587.6097 207.1853 866.9818 264.824544 116.19384 167.81864 148.503 37.011 22.530 172.857 105.825 37.57 18.95 140.36 45.75 14.63 50.35 1416.77 265.31 5029.05 2062.04 33751.58 116.7530 88.8022 14.39 26.21 26.54 3.322 90.277 72.221 12.25 25.43 21.65 3.06 3.136 6.230 16.36 36.50 26.63 468 327 70.7499 897.6375 299.5680 388.6392 809.9048 587.4762 104.8933 297.1387 71.0074 17.1 1261.8 9.20 1191.5 394982 699228 8.482 195.9 41485.5 72179.6 252.79 254.40 251.84 0.811418 138510.00 711125 636088 704929 714980 19298 12397 12613 2836504 0.23420 987 1166 1376 36976 43705 0.796 1.146 1.411 27.744 66.387 81.192 4262.29 1260.49 46.49 240.82 25.43 32.42 3.55 895.1272 71.1617 212.6277 164.2008 78.8686 108.6614 605.6728 214.4729 893.4282 267.536092 127.85527 182.43689 156.945 41.940 25.392 182.768 113.131 40.04 20.26 147.46 48.49 15.52 53.03 3749.69 267.30 5292.08 3678.91 36428.76 123.0248 93.6050 32.00 53.77 55.27 4.184 182.358 191.046 26.89 45.41 45.46 13.32 4.021 7.306 20.74 97.50 40.89 534 374 72.9079 930.4932 310.3004 404.2950 830.8519 609.9637 108.4041 307.2669 73.2692 17.6 1188.1 9.31 1171.2 530689 746376 11.053 766.8 49340.4 82071.4 394.32 404.95 406.41 2.363070 151325.01 701215 1311837 1268688 1230841 32858 27880 24904 2815356 0.22464 1010 1098 1300 35186 41588 0.381 0.630 0.812 15.257 28.715 40.155 4030.79 1195.23 17.05 239.02 24.17 17.37 3.39 867.8993 68.6499 205.4057 157.7992 76.9068 104.7278 586.8584 207.6741 866.9595 265.312622 116.10875 168.799 146.644 37.053 22.519 173.636 104.934 37.73 18.89 140.35 45.77 2.54 8.38 596.04 51.52 830.31 202.83 5175.96 19.6685 24.7917 4.83 7.43 7.72 0.558 36.647 32.265 3.97 6.77 6.88 1.86 0.568 1.157 4.37 16.54 8.74 102 72 12.9683 215.5167 56.6582 70.8684 147.6880 109.7693 18.2048 55.2245 13.0028 1.97 146.1 1.06 140.1 100970 104287 2.167 126.8 11461.4 16811.8 66.81 75.86 76.66 0.301450 27774.70 79570 318480 317360 312245 6686 5465 4973 405614 1.40982 8775 67000 68548 291743 332950 1.571 2.522 3.203 75.984 146.572 201.101 24236.97 7565.21 107.17 1229.86 153.78 315.26 24.55 4864.7028 295.4918 1124.3046 884.2913 431.9597 577.7688 3485.2129 1143.0555 4868.1057 540.544881 773.96684 773.03283 1100.363 258.873 156.783 1094.374 752.986 254.46 124.48 933.41 297.67 15.24 52.48 1960.30 279.33 5224.83 1915.37 35501.21 121.8576 92.8004 30.32 52.17 52.60 3.865 171.877 161.778 24.58 41.57 41.90 8.47 3.676 6.646 19.29 75.69 37.03 514 363 72.5195 931.2032 309.5958 401.7313 834.4638 607.3304 107.4707 306.3994 72.4101 17.2 1280.5 9.13 1178.0 485387 739016 9.550 574.8 45780.3 75334.7 297.77 306.46 310.66 1.358549 122126.56 705341 1037703 997742 955977 32486 19056 17875 2863742 0.22289 1004 1118 1322 35440 41897 0.490 0.815 1.069 16.436 41.988 55.954 4103.64 1210.76 36.35 228.75 24.48 35.39 3.40 876.4961 68.5979 206.1379 158.9464 76.5661 105.1513 589.6910 208.0910 876.3321 262.403117 119.63471 167.90491 153.903 40.812 24.520 177.063 109.813 37.85 19.18 141.91 46.19 15.41 53.06 3741.06 266.14 5292.42 3663.48 36248.38 122.7055 93.7615 22.97 52.32 52.93 4.013 167.611 144.342 21.21 40.71 40.82 14.36 3.767 7.347 20.67 79.36 39.24 531 376 73.1026 932.0027 310.0940 404.2730 828.8966 609.7624 108.1330 307.7165 73.0290 17.4 1270.9 9.29 1203.2 475861 748549 11.173 438.2 47827.0 79962.2 351.21 362.27 352.85 2.346112 146083.16 698785 1291471 1258066 1237871 28016 23743 22567 3021171 0.22025 999 1103 1306 35505 42130 0.389 0.636 0.808 17.909 33.723 44.364 4054.30 1195.76 17.09 239.94 24.17 17.44 3.41 868.8157 68.5451 205.4931 157.8251 77.0980 104.7469 587.7789 207.2711 866.6223 263.625285 116.43538 166.47566 149.222 37.576 22.610 172.606 106.466 37.61 18.90 140.55 45.95 15.44 52.76 3689.97 264.82 5250.15 3621.58 35666.69 120.7998 92.9537 32.36 54.78 55.58 4.090 180.332 180.343 27.20 45.19 44.50 10.72 3.974 7.373 19.90 94.62 40.00 524 357 72.7729 929.7910 308.6765 403.2806 829.1745 608.3023 107.8991 306.6822 72.7821 17.5 1264.7 9.21 1203.2 507039 740039 10.853 698.0 49459.9 81782.3 351.39 357.63 357.94 2.326770 149876.52 708218 1124224 1074500 1082794 29347 23493 22279 2814269 0.22290 1006 1120 1322 35628 42264 0.445 0.745 0.924 17.194 34.059 44.891 4041.31 1203.42 17.33 241.17 24.36 17.65 3.44 872.8912 68.7068 206.4473 158.0475 77.0107 105.0236 588.6134 207.8753 872.0650 264.797139 120.10383 168.99869 152.990 38.365 23.440 174.946 107.143 37.92 19.00 141.98 45.92 15.49 53.12 3741.35 268.04 5291.81 3655.41 32979.74 123.0519 91.3724 32.09 55.03 55.92 4.182 180.860 189.131 26.93 46.07 46.45 14.17 4.050 7.320 20.96 95.71 40.42 524 367 73.1592 928.5381 310.6145 404.1304 828.8161 609.0422 108.1608 307.1658 73.2510 17.5 1272.8 9.12 1209.1 528289 742955 11.125 765.2 49731.9 86045.2 393.15 410.46 401.81 2.367074 147285.78 699816 1285905 1234869 1202637 33019 27093 25252 2921572 0.22441 1002 1104 1306 35406 41859 0.389 0.648 0.832 15.183 29.537 39.602 4032.10 1195.14 17.09 238.32 24.17 17.48 3.72 869.1872 68.7650 205.2817 157.8814 77.0588 104.8041 587.3828 207.5798 867.8296 263.627543 115.75608 164.04046 147.002 37.384 22.652 173.634 105.541 37.71 19.01 140.45 45.85 OpenBenchmarking.org
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 15.52 15.54 15.50 15.55 14.63 15.52 2.54 15.24 15.41 15.44 15.49 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 12 24 36 48 60 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.35, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 53.09 53.07 52.91 52.79 50.35 53.03 8.38 52.48 53.06 52.76 53.12 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 800 1600 2400 3200 4000 SE +/- 1.15, N = 3 SE +/- 0.22, N = 3 SE +/- 0.85, N = 3 SE +/- 0.90, N = 3 SE +/- 78.31, N = 12 SE +/- 1.03, N = 3 SE +/- 0.14, N = 3 SE +/- 176.75, N = 15 SE +/- 1.38, N = 3 SE +/- 1.17, N = 3 SE +/- 0.08, N = 3 3738.04 3748.17 3730.66 3744.85 1416.77 3749.69 596.04 1960.30 3741.06 3689.97 3741.35 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 60 120 180 240 300 SE +/- 1.00, N = 3 SE +/- 1.18, N = 3 SE +/- 0.60, N = 3 SE +/- 2.34, N = 3 SE +/- 0.47, N = 3 SE +/- 0.60, N = 3 SE +/- 0.34, N = 15 SE +/- 0.14, N = 3 SE +/- 1.35, N = 3 SE +/- 1.08, N = 3 SE +/- 1.06, N = 3 267.15 266.96 268.24 266.56 265.31 267.30 51.52 279.33 266.14 264.82 268.04 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 1100 2200 3300 4400 5500 SE +/- 0.95, N = 3 SE +/- 1.37, N = 3 SE +/- 1.46, N = 3 SE +/- 0.41, N = 3 SE +/- 0.59, N = 3 SE +/- 2.23, N = 3 SE +/- 0.10, N = 3 SE +/- 1.03, N = 3 SE +/- 0.71, N = 3 SE +/- 0.47, N = 3 SE +/- 0.80, N = 3 5291.45 5294.97 5277.02 5291.00 5029.05 5292.08 830.31 5224.83 5292.42 5250.15 5291.81 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 800 1600 2400 3200 4000 SE +/- 3.07, N = 3 SE +/- 6.01, N = 3 SE +/- 8.08, N = 3 SE +/- 3.54, N = 3 SE +/- 113.70, N = 15 SE +/- 4.65, N = 3 SE +/- 1.43, N = 15 SE +/- 155.56, N = 12 SE +/- 6.58, N = 3 SE +/- 13.56, N = 3 SE +/- 4.78, N = 3 3654.51 3670.78 3645.60 3679.31 2062.04 3678.91 202.83 1915.37 3663.48 3621.58 3655.41 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 8K 16K 24K 32K 40K SE +/- 1060.84, N = 15 SE +/- 724.32, N = 12 SE +/- 894.45, N = 15 SE +/- 1139.15, N = 15 SE +/- 909.70, N = 12 SE +/- 1205.35, N = 12 SE +/- 15.51, N = 3 SE +/- 946.71, N = 12 SE +/- 1216.09, N = 15 SE +/- 1008.62, N = 15 SE +/- 342.83, N = 5 35205.47 35601.83 36975.34 36507.11 33751.58 36428.76 5175.96 35501.21 36248.38 35666.69 32979.74 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer ISPC - Model: Crown amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 30 60 90 120 150 SE +/- 0.25, N = 7 SE +/- 0.11, N = 7 SE +/- 0.21, N = 6 SE +/- 0.18, N = 7 SE +/- 0.22, N = 7 SE +/- 0.14, N = 7 SE +/- 0.02, N = 3 SE +/- 0.24, N = 7 SE +/- 0.15, N = 7 SE +/- 0.33, N = 7 SE +/- 0.13, N = 7 122.50 123.15 121.30 122.87 116.75 123.02 19.67 121.86 122.71 120.80 123.05 MIN: 118.44 / MAX: 132.08 MIN: 120.42 / MAX: 134.1 MIN: 107.62 / MAX: 132.2 MIN: 119.52 / MAX: 133.96 MIN: 112.31 / MAX: 126.6 MIN: 120.25 / MAX: 132.77 MIN: 117.58 / MAX: 131.5 MIN: 119.75 / MAX: 131.8 MIN: 116.78 / MAX: 132.34 MIN: 119.92 / MAX: 135.17
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer ISPC - Model: Asian Dragon amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 20 40 60 80 100 SE +/- 0.79, N = 15 SE +/- 0.87, N = 15 SE +/- 0.91, N = 15 SE +/- 0.93, N = 15 SE +/- 0.79, N = 15 SE +/- 0.98, N = 15 SE +/- 0.02, N = 3 SE +/- 1.15, N = 15 SE +/- 0.79, N = 6 SE +/- 0.85, N = 6 SE +/- 0.72, N = 15 92.21 94.78 93.73 93.50 88.80 93.61 24.79 92.80 93.76 92.95 91.37 MIN: 87.15 / MAX: 100.61 MIN: 86.18 / MAX: 101.48 MIN: 86.21 / MAX: 102.02 MIN: 87.15 / MAX: 102.17 MIN: 82.24 / MAX: 97.26 MIN: 86.72 / MAX: 102.65 MIN: 24.19 / MAX: 25.44 MIN: 85.44 / MAX: 101.26 MIN: 88.79 / MAX: 100.41 MIN: 88.86 / MAX: 98.52 MIN: 86.16 / MAX: 99.08
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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 8 16 24 32 40 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 SE +/- 0.15, N = 3 SE +/- 0.14, N = 3 SE +/- 0.13, N = 3 29.42 31.99 20.66 32.30 14.39 32.00 4.83 30.32 22.97 32.36 32.09 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 12 24 36 48 60 SE +/- 0.60, N = 15 SE +/- 0.60, N = 5 SE +/- 1.49, N = 15 SE +/- 0.44, N = 5 SE +/- 0.13, N = 3 SE +/- 0.51, N = 5 SE +/- 0.08, N = 3 SE +/- 0.26, N = 4 SE +/- 0.20, N = 4 SE +/- 0.50, N = 5 SE +/- 0.52, N = 5 47.97 54.69 45.56 54.77 26.21 53.77 7.43 52.17 52.32 54.78 55.03 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 13 26 39 52 65 SE +/- 0.70, N = 15 SE +/- 0.40, N = 5 SE +/- 1.47, N = 15 SE +/- 0.46, N = 5 SE +/- 0.10, N = 3 SE +/- 0.11, N = 5 SE +/- 0.07, N = 3 SE +/- 0.50, N = 4 SE +/- 0.44, N = 5 SE +/- 0.48, N = 5 SE +/- 0.48, N = 5 50.67 56.14 41.83 55.85 26.54 55.27 7.72 52.60 52.93 55.58 55.92 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 4 - Input: Bosphorus 4K amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 0.9414 1.8828 2.8242 3.7656 4.707 SE +/- 0.013, N = 3 SE +/- 0.008, N = 3 SE +/- 0.007, N = 3 SE +/- 0.016, N = 3 SE +/- 0.022, N = 3 SE +/- 0.005, N = 3 SE +/- 0.001, N = 3 SE +/- 0.020, N = 3 SE +/- 0.003, N = 3 SE +/- 0.025, N = 3 SE +/- 0.002, N = 3 3.453 4.158 2.443 4.181 3.322 4.184 0.558 3.865 4.013 4.090 4.182 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 40 80 120 160 200 SE +/- 2.85, N = 15 SE +/- 3.08, N = 15 SE +/- 1.61, N = 15 SE +/- 2.85, N = 15 SE +/- 1.29, N = 15 SE +/- 3.27, N = 15 SE +/- 0.49, N = 12 SE +/- 2.56, N = 15 SE +/- 2.84, N = 15 SE +/- 3.33, N = 15 SE +/- 3.08, N = 15 175.46 186.05 155.77 173.31 90.28 182.36 36.65 171.88 167.61 180.33 180.86 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 40 80 120 160 200 SE +/- 1.23, N = 12 SE +/- 1.60, N = 7 SE +/- 1.22, N = 6 SE +/- 2.12, N = 15 SE +/- 0.85, N = 15 SE +/- 1.88, N = 15 SE +/- 0.14, N = 3 SE +/- 1.52, N = 7 SE +/- 1.54, N = 15 SE +/- 1.37, N = 10 SE +/- 2.47, N = 15 170.27 194.10 145.32 188.42 72.22 191.05 32.27 161.78 144.34 180.34 189.13 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.19, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 24.28 27.01 17.33 27.06 12.25 26.89 3.97 24.58 21.21 27.20 26.93
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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 11 22 33 44 55 SE +/- 0.28, N = 4 SE +/- 0.22, N = 4 SE +/- 0.58, N = 15 SE +/- 0.28, N = 4 SE +/- 0.09, N = 3 SE +/- 0.18, N = 4 SE +/- 0.01, N = 3 SE +/- 0.33, N = 4 SE +/- 0.25, N = 4 SE +/- 0.30, N = 4 SE +/- 0.16, N = 4 39.96 46.26 33.79 46.31 25.43 45.41 6.77 41.57 40.71 45.19 46.07
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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 11 22 33 44 55 SE +/- 0.43, N = 4 SE +/- 0.33, N = 4 SE +/- 0.67, N = 15 SE +/- 0.28, N = 4 SE +/- 0.08, N = 3 SE +/- 0.49, N = 5 SE +/- 0.04, N = 3 SE +/- 0.19, N = 4 SE +/- 0.18, N = 4 SE +/- 0.30, N = 4 SE +/- 0.21, N = 4 41.13 47.25 33.76 46.08 21.65 45.46 6.88 41.90 40.82 44.50 46.45
VP9 libvpx Encoding Speed: Speed 5 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.13 Speed: Speed 5 - Input: Bosphorus 4K amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 4 8 12 16 20 SE +/- 0.12, N = 3 SE +/- 0.27, N = 15 SE +/- 0.14, N = 15 SE +/- 0.41, N = 12 SE +/- 0.04, N = 12 SE +/- 0.26, N = 15 SE +/- 0.01, N = 3 SE +/- 0.10, N = 12 SE +/- 0.01, N = 3 SE +/- 0.12, N = 15 SE +/- 0.20, N = 3 11.63 13.37 7.95 12.83 3.06 13.32 1.86 8.47 14.36 10.72 14.17 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
VVenC Video Input: Bosphorus 4K - Video Preset: Fast OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Fast amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 0.9113 1.8226 2.7339 3.6452 4.5565 SE +/- 0.023, N = 3 SE +/- 0.011, N = 3 SE +/- 0.011, N = 3 SE +/- 0.018, N = 3 SE +/- 0.009, N = 3 SE +/- 0.021, N = 3 SE +/- 0.002, N = 3 SE +/- 0.009, N = 3 SE +/- 0.007, N = 3 SE +/- 0.014, N = 3 SE +/- 0.005, N = 3 3.359 4.022 2.471 4.023 3.136 4.021 0.568 3.676 3.767 3.974 4.050 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
VVenC Video Input: Bosphorus 4K - Video Preset: Faster OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Faster amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 2 4 6 8 10 SE +/- 0.045, N = 3 SE +/- 0.075, N = 3 SE +/- 0.018, N = 3 SE +/- 0.083, N = 4 SE +/- 0.049, N = 3 SE +/- 0.084, N = 4 SE +/- 0.008, N = 3 SE +/- 0.030, N = 3 SE +/- 0.068, N = 3 SE +/- 0.043, N = 3 SE +/- 0.075, N = 3 6.326 7.397 4.769 7.352 6.230 7.306 1.157 6.646 7.347 7.373 7.320 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 5 10 15 20 25 SE +/- 0.08, N = 3 SE +/- 0.16, N = 3 SE +/- 0.18, N = 3 SE +/- 0.18, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.19, N = 3 SE +/- 0.16, N = 3 SE +/- 0.17, N = 3 SE +/- 0.23, N = 3 18.56 20.55 15.33 20.63 16.36 20.74 4.37 19.29 20.67 19.90 20.96 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
TensorFlow Device: CPU - Batch Size: 256 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: AlexNet amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.63, N = 6 SE +/- 0.28, N = 3 SE +/- 0.31, N = 3 SE +/- 0.36, N = 3 SE +/- 0.01, N = 3 SE +/- 0.66, N = 3 SE +/- 1.99, N = 9 SE +/- 0.82, N = 9 SE +/- 0.99, N = 3 87.75 97.12 65.63 96.73 36.50 97.50 16.54 75.69 79.36 94.62 95.71
TensorFlow Device: CPU - Batch Size: 256 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: GoogLeNet amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 9 18 27 36 45 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.19, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 38.41 40.19 31.64 40.39 26.63 40.89 8.74 37.03 39.24 40.00 40.42
OpenVKL Benchmark: vklBenchmark ISPC OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.3.1 Benchmark: vklBenchmark ISPC amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 120 240 360 480 600 SE +/- 4.72, N = 7 SE +/- 1.76, N = 3 SE +/- 2.08, N = 3 SE +/- 4.37, N = 3 SE +/- 5.51, N = 3 SE +/- 6.51, N = 4 SE +/- 1.20, N = 3 SE +/- 3.61, N = 3 SE +/- 6.96, N = 3 SE +/- 4.59, N = 8 SE +/- 1.76, N = 3 514 516 477 512 468 534 102 514 531 524 524 MIN: 148 / MAX: 1583 MIN: 150 / MAX: 1507 MIN: 107 / MAX: 1723 MIN: 151 / MAX: 1504 MIN: 146 / MAX: 1159 MIN: 153 / MAX: 1522 MIN: 24 / MAX: 400 MIN: 149 / MAX: 1600 MIN: 153 / MAX: 1787 MIN: 148 / MAX: 1602 MIN: 149 / MAX: 1516
OpenVKL Benchmark: vklBenchmark Scalar OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.3.1 Benchmark: vklBenchmark Scalar amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 80 160 240 320 400 SE +/- 6.08, N = 6 SE +/- 3.82, N = 5 SE +/- 2.19, N = 3 SE +/- 1.20, N = 3 SE +/- 2.31, N = 3 SE +/- 3.95, N = 9 SE +/- 0.33, N = 3 SE +/- 3.76, N = 3 SE +/- 4.33, N = 3 SE +/- 1.76, N = 3 SE +/- 4.13, N = 9 364 374 346 385 327 374 72 363 376 357 367 MIN: 71 / MAX: 1707 MIN: 75 / MAX: 1552 MIN: 62 / MAX: 1800 MIN: 75 / MAX: 1589 MIN: 72 / MAX: 1129 MIN: 74 / MAX: 1559 MIN: 11 / MAX: 516 MIN: 73 / MAX: 1686 MIN: 75 / MAX: 1829 MIN: 75 / MAX: 1532 MIN: 73 / MAX: 1729
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 16 32 48 64 80 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.14, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 72.85 72.95 72.80 73.06 70.75 72.91 12.97 72.52 73.10 72.77 73.16
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 200 400 600 800 1000 SE +/- 3.90, N = 3 SE +/- 2.48, N = 3 SE +/- 0.75, N = 3 SE +/- 1.42, N = 3 SE +/- 0.59, N = 3 SE +/- 1.11, N = 3 SE +/- 0.06, N = 3 SE +/- 0.27, N = 3 SE +/- 0.68, N = 3 SE +/- 1.23, N = 3 SE +/- 1.66, N = 3 926.20 929.79 931.60 931.58 897.64 930.49 215.52 931.20 932.00 929.79 928.54
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 70 140 210 280 350 SE +/- 0.30, N = 3 SE +/- 0.12, N = 3 SE +/- 0.37, N = 3 SE +/- 0.15, N = 3 SE +/- 0.24, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.48, N = 3 SE +/- 0.24, N = 3 SE +/- 0.62, N = 3 SE +/- 0.30, N = 3 310.30 310.43 309.38 310.74 299.57 310.30 56.66 309.60 310.09 308.68 310.61
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 90 180 270 360 450 SE +/- 0.20, N = 3 SE +/- 0.15, N = 3 SE +/- 0.10, N = 3 SE +/- 0.32, N = 3 SE +/- 0.49, N = 3 SE +/- 0.37, N = 3 SE +/- 0.15, N = 3 SE +/- 0.34, N = 3 SE +/- 0.60, N = 3 SE +/- 0.36, N = 3 SE +/- 0.15, N = 3 403.29 404.95 403.59 404.55 388.64 404.30 70.87 401.73 404.27 403.28 404.13
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 200 400 600 800 1000 SE +/- 1.36, N = 3 SE +/- 1.68, N = 3 SE +/- 1.08, N = 3 SE +/- 1.26, N = 3 SE +/- 0.84, N = 3 SE +/- 1.41, N = 3 SE +/- 0.17, N = 3 SE +/- 1.55, N = 3 SE +/- 0.64, N = 3 SE +/- 1.55, N = 3 SE +/- 0.63, N = 3 830.10 830.01 829.60 830.32 809.90 830.85 147.69 834.46 828.90 829.17 828.82
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 130 260 390 520 650 SE +/- 0.85, N = 3 SE +/- 0.26, N = 3 SE +/- 0.24, N = 3 SE +/- 0.35, N = 3 SE +/- 1.22, N = 3 SE +/- 0.82, N = 3 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 SE +/- 1.19, N = 3 SE +/- 0.14, N = 3 SE +/- 0.68, N = 3 610.70 609.61 609.90 610.32 587.48 609.96 109.77 607.33 609.76 608.30 609.04
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 20 40 60 80 100 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 SE +/- 0.20, N = 3 SE +/- 0.00, N = 3 SE +/- 0.18, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 108.20 108.20 108.15 108.11 104.89 108.40 18.20 107.47 108.13 107.90 108.16
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 70 140 210 280 350 SE +/- 0.63, N = 3 SE +/- 0.82, N = 3 SE +/- 0.25, N = 3 SE +/- 0.09, N = 3 SE +/- 0.78, N = 3 SE +/- 0.44, N = 3 SE +/- 0.07, N = 3 SE +/- 0.22, N = 3 SE +/- 0.63, N = 3 SE +/- 0.60, N = 3 SE +/- 0.69, N = 3 307.04 307.64 307.71 307.89 297.14 307.27 55.22 306.40 307.72 306.68 307.17
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 16 32 48 64 80 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 SE +/- 0.18, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 73.02 72.94 73.05 73.14 71.01 73.27 13.00 72.41 73.03 72.78 73.25
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 4 8 12 16 20 SE +/- 0.16, N = 5 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 16.00 17.60 15.20 17.50 17.10 17.60 1.97 17.20 17.40 17.50 17.50 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 300 600 900 1200 1500 SE +/- 3.84, N = 5 SE +/- 4.93, N = 3 SE +/- 2.19, N = 3 SE +/- 6.13, N = 3 SE +/- 1.88, N = 3 SE +/- 28.63, N = 3 SE +/- 0.03, N = 3 SE +/- 5.25, N = 3 SE +/- 2.01, N = 3 SE +/- 1.32, N = 3 SE +/- 0.97, N = 3 1278.3 1278.6 1269.8 1276.2 1261.8 1188.1 146.1 1280.5 1270.9 1264.7 1272.8 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Compression Speed amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.12, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.11, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 8.91 9.28 8.72 9.26 9.20 9.31 1.06 9.13 9.29 9.21 9.12 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 300 600 900 1200 1500 SE +/- 1.23, N = 3 SE +/- 7.42, N = 3 SE +/- 20.88, N = 3 SE +/- 5.97, N = 3 SE +/- 1.07, N = 3 SE +/- 18.37, N = 3 SE +/- 0.15, N = 3 SE +/- 11.54, N = 3 SE +/- 9.03, N = 3 SE +/- 11.09, N = 3 SE +/- 7.61, N = 3 1195.0 1203.6 1186.0 1203.3 1191.5 1171.2 140.1 1178.0 1203.2 1203.2 1209.1 1. (CC) gcc options: -O3 -pthread -lz -llzma
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 110K 220K 330K 440K 550K SE +/- 480.40, N = 3 SE +/- 5053.05, N = 3 SE +/- 3758.30, N = 3 SE +/- 5870.22, N = 4 SE +/- 3670.50, N = 7 SE +/- 6313.35, N = 3 SE +/- 1055.88, N = 3 SE +/- 2092.51, N = 3 SE +/- 3716.48, N = 3 SE +/- 6757.49, N = 3 SE +/- 5372.93, N = 6 500471 522348 459617 514443 394982 530689 100970 485387 475861 507039 528289 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 160K 320K 480K 640K 800K SE +/- 858.55, N = 3 SE +/- 18690.79, N = 3 SE +/- 5960.12, N = 3 SE +/- 10875.45, N = 4 SE +/- 2716.47, N = 7 SE +/- 2158.20, N = 3 SE +/- 136.02, N = 3 SE +/- 1773.36, N = 3 SE +/- 156.12, N = 3 SE +/- 1725.95, N = 3 SE +/- 2437.88, N = 6 716703 726521 661420 733882 699228 746376 104287 739016 748549 740039 742955 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2023 Implementation: MPI CPU - Input: water_GMX50_bare amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 3 6 9 12 15 SE +/- 0.032, N = 3 SE +/- 0.057, N = 3 SE +/- 0.019, N = 3 SE +/- 0.065, N = 3 SE +/- 0.601, N = 12 SE +/- 0.036, N = 3 SE +/- 0.004, N = 3 SE +/- 0.448, N = 15 SE +/- 0.046, N = 3 SE +/- 0.125, N = 15 SE +/- 0.018, N = 3 11.079 11.179 11.131 11.074 8.482 11.053 2.167 9.550 11.173 10.853 11.125 1. (CXX) g++ options: -O3
CockroachDB Workload: MoVR - Concurrency: 512 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: MoVR - Concurrency: 512 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 170 340 510 680 850 SE +/- 2.27, N = 3 SE +/- 1.59, N = 3 SE +/- 1.71, N = 3 SE +/- 2.65, N = 3 SE +/- 2.51, N = 15 SE +/- 1.79, N = 3 SE +/- 0.42, N = 3 SE +/- 4.45, N = 3 SE +/- 0.92, N = 3 SE +/- 3.24, N = 3 SE +/- 3.30, N = 3 641.8 761.0 570.5 763.4 195.9 766.8 126.8 574.8 438.2 698.0 765.2
CockroachDB Workload: KV, 10% Reads - Concurrency: 512 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 512 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 11K 22K 33K 44K 55K SE +/- 451.19, N = 3 SE +/- 504.99, N = 3 SE +/- 530.33, N = 4 SE +/- 207.31, N = 3 SE +/- 410.53, N = 15 SE +/- 526.94, N = 3 SE +/- 162.55, N = 3 SE +/- 457.69, N = 6 SE +/- 524.19, N = 15 SE +/- 590.54, N = 4 SE +/- 577.32, N = 3 44725.5 50217.2 43287.2 49015.5 41485.5 49340.4 11461.4 45780.3 47827.0 49459.9 49731.9
CockroachDB Workload: KV, 95% Reads - Concurrency: 512 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 512 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 20K 40K 60K 80K 100K SE +/- 1522.12, N = 15 SE +/- 262.84, N = 3 SE +/- 99.42, N = 3 SE +/- 465.83, N = 3 SE +/- 1298.96, N = 15 SE +/- 1631.30, N = 15 SE +/- 36.89, N = 3 SE +/- 1169.53, N = 15 SE +/- 1766.85, N = 15 SE +/- 1583.45, N = 15 SE +/- 373.82, N = 3 75876.4 86214.8 74380.0 86477.3 72179.6 82071.4 16811.8 75334.7 79962.2 81782.3 86045.2
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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 90 180 270 360 450 SE +/- 1.39, N = 3 SE +/- 4.76, N = 3 SE +/- 0.77, N = 3 SE +/- 2.11, N = 3 SE +/- 2.12, N = 3 SE +/- 0.63, N = 3 SE +/- 0.36, N = 3 SE +/- 0.46, N = 3 SE +/- 1.22, N = 3 SE +/- 3.45, N = 3 SE +/- 3.06, N = 3 355.12 395.53 339.68 392.95 252.79 394.32 66.81 297.77 351.21 351.39 393.15 MIN: 43.45 / MAX: 4000 MIN: 48.98 / MAX: 4000 MIN: 39.27 / MAX: 3157.89 MIN: 51.28 / MAX: 3750 MIN: 43.29 / MAX: 4000 MIN: 48.47 / MAX: 3750 MIN: 44.15 / MAX: 2068.97 MIN: 49.63 / MAX: 4000 MIN: 47.54 / MAX: 2857.14 MIN: 50.63 / MAX: 3750
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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 90 180 270 360 450 SE +/- 3.92, N = 3 SE +/- 4.88, N = 3 SE +/- 1.73, N = 3 SE +/- 1.07, N = 3 SE +/- 3.86, N = 3 SE +/- 4.90, N = 3 SE +/- 0.06, N = 3 SE +/- 2.11, N = 3 SE +/- 0.20, N = 3 SE +/- 2.51, N = 3 SE +/- 3.72, N = 3 373.47 409.86 349.30 407.73 254.40 404.95 75.86 306.46 362.27 357.63 410.46 MIN: 52.86 / MAX: 3750 MIN: 57.64 / MAX: 4285.71 MIN: 45.25 / MAX: 4000 MIN: 56.66 / MAX: 4285.71 MIN: 47.85 / MAX: 4285.71 MIN: 54.05 / MAX: 4285.71 MIN: 50.98 / MAX: 2222.22 MIN: 50.98 / MAX: 4615.38 MIN: 57.8 / MAX: 3529.41 MIN: 58.42 / MAX: 4615.38
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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 90 180 270 360 450 SE +/- 3.70, N = 3 SE +/- 1.36, N = 3 SE +/- 2.43, N = 3 SE +/- 3.27, N = 3 SE +/- 2.60, N = 3 SE +/- 2.49, N = 3 SE +/- 0.60, N = 3 SE +/- 0.84, N = 3 SE +/- 1.95, N = 3 SE +/- 2.12, N = 3 SE +/- 1.10, N = 3 372.98 406.99 353.17 394.98 251.84 406.41 76.66 310.66 352.85 357.94 401.81 MIN: 54.1 / MAX: 4285.71 MIN: 53.29 / MAX: 3333.33 MIN: 44.91 / MAX: 3000 MIN: 57.97 / MAX: 3529.41 MIN: 48.15 / MAX: 3157.89 MIN: 52.77 / MAX: 3529.41 MIN: 8.52 / MAX: 588.24 MIN: 51.28 / MAX: 2222.22 MIN: 50.59 / MAX: 3529.41 MIN: 56.71 / MAX: 2857.14 MIN: 56.71 / MAX: 3333.33
Stargate Digital Audio Workstation Sample Rate: 192000 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 1024 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 0.5326 1.0652 1.5978 2.1304 2.663 SE +/- 0.017556, N = 15 SE +/- 0.005634, N = 3 SE +/- 0.042633, N = 12 SE +/- 0.031447, N = 3 SE +/- 0.011706, N = 12 SE +/- 0.008972, N = 3 SE +/- 0.000425, N = 3 SE +/- 0.009049, N = 3 SE +/- 0.001977, N = 3 SE +/- 0.003977, N = 3 SE +/- 0.015239, N = 3 2.059259 2.348079 1.801238 2.346447 0.811418 2.363070 0.301450 1.358549 2.346112 2.326770 2.367074 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
nginx Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 500 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 30K 60K 90K 120K 150K SE +/- 1575.56, N = 5 SE +/- 1361.88, N = 3 SE +/- 1620.42, N = 5 SE +/- 2024.19, N = 3 SE +/- 115.95, N = 3 SE +/- 684.93, N = 3 SE +/- 131.35, N = 3 SE +/- 208.90, N = 3 SE +/- 1781.93, N = 4 SE +/- 977.04, N = 3 SE +/- 693.20, N = 3 146738.16 147764.25 145614.76 152654.86 138510.00 151325.01 27774.70 122126.56 146083.16 149876.52 147285.78 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 150K 300K 450K 600K 750K SE +/- 2423.31, N = 3 SE +/- 5808.55, N = 12 SE +/- 981.48, N = 3 SE +/- 4455.74, N = 3 SE +/- 5021.57, N = 3 SE +/- 3225.60, N = 3 SE +/- 423.55, N = 3 SE +/- 5843.40, N = 3 SE +/- 2191.80, N = 3 SE +/- 5594.67, N = 3 SE +/- 4034.04, N = 3 687682 697478 671207 700287 711125 701215 79570 705341 698785 708218 699816
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 300K 600K 900K 1200K 1500K SE +/- 28243.17, N = 11 SE +/- 10261.05, N = 3 SE +/- 16514.38, N = 3 SE +/- 10272.10, N = 3 SE +/- 23969.59, N = 12 SE +/- 2192.30, N = 3 SE +/- 3162.32, N = 6 SE +/- 38153.01, N = 12 SE +/- 24805.29, N = 12 SE +/- 16168.04, N = 3 SE +/- 16034.65, N = 4 1288550 1306099 1292798 1286042 636088 1311837 318480 1037703 1291471 1124224 1285905 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Only amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 300K 600K 900K 1200K 1500K SE +/- 8403.56, N = 3 SE +/- 15062.87, N = 3 SE +/- 2388.78, N = 3 SE +/- 7684.39, N = 3 SE +/- 21438.85, N = 12 SE +/- 9347.57, N = 3 SE +/- 2702.31, N = 8 SE +/- 36540.35, N = 12 SE +/- 716.94, N = 3 SE +/- 11695.71, N = 4 SE +/- 8479.39, N = 3 1248266 1241726 1245914 1240406 704929 1268688 317360 997742 1258066 1074500 1234869 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 300K 600K 900K 1200K 1500K SE +/- 5837.45, N = 3 SE +/- 7063.00, N = 3 SE +/- 3162.21, N = 3 SE +/- 6415.45, N = 3 SE +/- 20475.53, N = 12 SE +/- 13365.19, N = 3 SE +/- 1792.34, N = 3 SE +/- 40789.54, N = 12 SE +/- 5317.94, N = 3 SE +/- 3711.22, N = 3 SE +/- 9650.25, N = 3 1207540 1209033 1226429 1226743 714980 1230841 312245 955977 1237871 1082794 1202637 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Write amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 8K 16K 24K 32K 40K SE +/- 508.85, N = 12 SE +/- 2742.94, N = 12 SE +/- 497.87, N = 12 SE +/- 524.88, N = 12 SE +/- 1491.09, N = 12 SE +/- 539.21, N = 12 SE +/- 295.83, N = 12 SE +/- 2388.98, N = 12 SE +/- 523.79, N = 12 SE +/- 904.79, N = 12 SE +/- 531.49, N = 12 28873 35610 28682 32286 19298 32858 6686 32486 28016 29347 33019 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 6K 12K 18K 24K 30K SE +/- 216.59, N = 3 SE +/- 272.14, N = 3 SE +/- 233.05, N = 12 SE +/- 307.60, N = 4 SE +/- 766.72, N = 9 SE +/- 225.23, N = 12 SE +/- 60.47, N = 12 SE +/- 148.91, N = 3 SE +/- 213.86, N = 12 SE +/- 234.54, N = 3 SE +/- 343.31, N = 3 24275 26830 24173 27596 12397 27880 5465 19056 23743 23493 27093 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 6K 12K 18K 24K 30K SE +/- 214.70, N = 3 SE +/- 174.68, N = 12 SE +/- 224.57, N = 3 SE +/- 207.97, N = 3 SE +/- 734.11, N = 9 SE +/- 63.64, N = 3 SE +/- 29.56, N = 3 SE +/- 179.41, N = 3 SE +/- 232.73, N = 12 SE +/- 157.83, N = 3 SE +/- 72.30, N = 3 21978 24299 21522 26085 12613 24904 4973 17875 22567 22279 25252 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.34 VGR Performance Metric amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 600K 1200K 1800K 2400K 3000K 2853983 2905181 2863951 2980719 2836504 2815356 405614 2863742 3021171 2814269 2921572 1. (CXX) g++ options: -std=c++14 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 0.3172 0.6344 0.9516 1.2688 1.586 SE +/- 0.00272, N = 3 SE +/- 0.00158, N = 4 SE +/- 0.00042, N = 3 SE +/- 0.00124, N = 4 SE +/- 0.00054, N = 3 SE +/- 0.00077, N = 4 SE +/- 0.00490, N = 3 SE +/- 0.00244, N = 3 SE +/- 0.00170, N = 3 SE +/- 0.00142, N = 3 SE +/- 0.00089, N = 4 0.22286 0.22270 0.22450 0.22021 0.23420 0.22464 1.40982 0.22289 0.22025 0.22290 0.22441
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 2K 4K 6K 8K 10K SE +/- 0.88, N = 3 SE +/- 6.01, N = 3 SE +/- 7.22, N = 3 SE +/- 4.04, N = 3 SE +/- 2.85, N = 3 SE +/- 3.28, N = 3 SE +/- 41.93, N = 3 SE +/- 5.81, N = 3 SE +/- 7.81, N = 3 SE +/- 9.13, N = 3 SE +/- 5.81, N = 3 1003 998 1008 1010 987 1010 8775 1004 999 1006 1002
OSPRay Studio Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 14K 28K 42K 56K 70K SE +/- 1.20, N = 3 SE +/- 1.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.88, N = 3 SE +/- 0.88, N = 3 SE +/- 1.15, N = 3 SE +/- 875.42, N = 12 SE +/- 2.03, N = 3 SE +/- 2.85, N = 3 SE +/- 1.20, N = 3 SE +/- 1.00, N = 3 1101 1103 1102 1101 1166 1098 67000 1118 1103 1120 1104 1. (CXX) g++ options: -O3 -lm -ldl
OSPRay Studio Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 15K 30K 45K 60K 75K SE +/- 0.58, N = 3 SE +/- 2.03, N = 3 SE +/- 0.88, N = 3 SE +/- 2.08, N = 3 SE +/- 1.15, N = 3 SE +/- 1.45, N = 3 SE +/- 831.01, N = 12 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 2.19, N = 3 SE +/- 1.45, N = 3 1304 1299 1303 1302 1376 1300 68548 1322 1306 1322 1306 1. (CXX) g++ options: -O3 -lm -ldl
OSPRay Studio Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 60K 120K 180K 240K 300K SE +/- 29.34, N = 3 SE +/- 76.22, N = 3 SE +/- 69.50, N = 3 SE +/- 31.26, N = 3 SE +/- 66.07, N = 3 SE +/- 23.07, N = 3 SE +/- 829.19, N = 3 SE +/- 52.33, N = 3 SE +/- 88.76, N = 3 SE +/- 25.51, N = 3 SE +/- 117.33, N = 3 35438 35573 35243 35210 36976 35186 291743 35440 35505 35628 35406 1. (CXX) g++ options: -O3 -lm -ldl
OSPRay Studio Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 70K 140K 210K 280K 350K SE +/- 62.74, N = 3 SE +/- 58.85, N = 3 SE +/- 90.34, N = 3 SE +/- 36.04, N = 3 SE +/- 7.42, N = 3 SE +/- 83.21, N = 3 SE +/- 671.47, N = 3 SE +/- 85.87, N = 3 SE +/- 70.48, N = 3 SE +/- 28.29, N = 3 SE +/- 98.82, N = 3 41798 41650 41532 41686 43705 41588 332950 41897 42130 42264 41859 1. (CXX) g++ options: -O3 -lm -ldl
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 0.3535 0.707 1.0605 1.414 1.7675 SE +/- 0.010, N = 11 SE +/- 0.003, N = 3 SE +/- 0.005, N = 3 SE +/- 0.003, N = 3 SE +/- 0.025, N = 12 SE +/- 0.001, N = 3 SE +/- 0.016, N = 6 SE +/- 0.020, N = 12 SE +/- 0.009, N = 12 SE +/- 0.006, N = 3 SE +/- 0.005, N = 4 0.390 0.383 0.387 0.389 0.796 0.381 1.571 0.490 0.389 0.445 0.389 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 0.5675 1.135 1.7025 2.27 2.8375 SE +/- 0.004, N = 3 SE +/- 0.008, N = 3 SE +/- 0.001, N = 3 SE +/- 0.004, N = 3 SE +/- 0.033, N = 12 SE +/- 0.005, N = 3 SE +/- 0.022, N = 8 SE +/- 0.033, N = 12 SE +/- 0.001, N = 3 SE +/- 0.008, N = 4 SE +/- 0.004, N = 3 0.641 0.644 0.642 0.645 1.146 0.630 2.522 0.815 0.636 0.745 0.648 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 0.7207 1.4414 2.1621 2.8828 3.6035 SE +/- 0.004, N = 3 SE +/- 0.005, N = 3 SE +/- 0.002, N = 3 SE +/- 0.004, N = 3 SE +/- 0.040, N = 12 SE +/- 0.009, N = 3 SE +/- 0.018, N = 3 SE +/- 0.048, N = 12 SE +/- 0.004, N = 3 SE +/- 0.003, N = 3 SE +/- 0.006, N = 3 0.828 0.827 0.815 0.815 1.411 0.812 3.203 1.069 0.808 0.924 0.832 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 20 40 60 80 100 SE +/- 0.28, N = 12 SE +/- 0.71, N = 12 SE +/- 0.28, N = 12 SE +/- 0.24, N = 12 SE +/- 2.25, N = 12 SE +/- 0.22, N = 12 SE +/- 2.49, N = 12 SE +/- 1.31, N = 12 SE +/- 0.30, N = 12 SE +/- 0.46, N = 12 SE +/- 0.23, N = 12 17.37 14.64 17.49 15.53 27.74 15.26 75.98 16.44 17.91 17.19 15.18 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 30 60 90 120 150 SE +/- 0.29, N = 3 SE +/- 0.30, N = 3 SE +/- 0.32, N = 12 SE +/- 0.32, N = 4 SE +/- 3.77, N = 9 SE +/- 0.24, N = 12 SE +/- 1.56, N = 12 SE +/- 0.33, N = 3 SE +/- 0.30, N = 12 SE +/- 0.34, N = 3 SE +/- 0.37, N = 3 32.96 29.82 33.13 29.00 66.39 28.72 146.57 41.99 33.72 34.06 29.54 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
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 amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 40 80 120 160 200 SE +/- 0.45, N = 3 SE +/- 0.30, N = 12 SE +/- 0.48, N = 3 SE +/- 0.31, N = 3 SE +/- 4.17, N = 9 SE +/- 0.10, N = 3 SE +/- 1.19, N = 3 SE +/- 0.57, N = 3 SE +/- 0.45, N = 12 SE +/- 0.32, N = 3 SE +/- 0.11, N = 3 45.51 41.18 46.47 38.34 81.19 40.16 201.10 55.95 44.36 44.89 39.60 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 5K 10K 15K 20K 25K SE +/- 4.72, N = 3 SE +/- 8.61, N = 3 SE +/- 6.67, N = 3 SE +/- 9.11, N = 3 SE +/- 8.81, N = 3 SE +/- 4.79, N = 3 SE +/- 217.31, N = 3 SE +/- 15.80, N = 3 SE +/- 5.84, N = 3 SE +/- 2.84, N = 3 SE +/- 4.16, N = 3 4030.03 4015.91 4033.63 4005.03 4262.29 4030.79 24236.97 4103.64 4054.30 4041.31 4032.10 MIN: 18903.29 / MAX: 30172.2 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 1600 3200 4800 6400 8000 SE +/- 0.15, N = 3 SE +/- 0.45, N = 3 SE +/- 0.05, N = 3 SE +/- 8.32, N = 3 SE +/- 0.52, N = 3 SE +/- 0.68, N = 3 SE +/- 16.67, N = 3 SE +/- 0.24, N = 3 SE +/- 1.11, N = 3 SE +/- 0.25, N = 3 SE +/- 0.38, N = 3 1195.35 1195.60 1199.87 1203.52 1260.49 1195.23 7565.21 1210.76 1195.76 1203.42 1195.14 MIN: 7058.85 / MAX: 8272.07 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 20 40 60 80 100 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 2.29, N = 12 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 3.03, N = 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 17.10 17.06 17.14 17.07 46.49 17.05 107.17 36.35 17.09 17.33 17.09 MIN: 9.33 / MAX: 84.63 MIN: 9.02 / MAX: 83.41 MIN: 9.37 / MAX: 88.86 MIN: 8.56 / MAX: 80.26 MIN: 8.5 / MAX: 147.24 MIN: 9.39 / MAX: 80.76 MIN: 59.84 / MAX: 344.36 MIN: 7.98 / MAX: 137.61 MIN: 9.24 / MAX: 81.88 MIN: 9.07 / MAX: 83.28 MIN: 9.82 / MAX: 80.61 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 300 600 900 1200 1500 SE +/- 0.82, N = 3 SE +/- 1.09, N = 3 SE +/- 0.51, N = 3 SE +/- 2.12, N = 3 SE +/- 0.48, N = 3 SE +/- 0.54, N = 3 SE +/- 7.94, N = 15 SE +/- 0.15, N = 3 SE +/- 1.21, N = 3 SE +/- 1.01, N = 3 SE +/- 0.97, N = 3 239.05 239.29 238.16 239.70 240.82 239.02 1229.86 228.75 239.94 241.17 238.32 MIN: 599.82 / MAX: 5117.07 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 30 60 90 120 150 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 24.17 24.16 24.24 24.17 25.43 24.17 153.78 24.48 24.17 24.36 24.17 MIN: 78.56 / MAX: 301.88 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 70 140 210 280 350 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 1.86, N = 15 SE +/- 0.02, N = 3 SE +/- 2.16, N = 15 SE +/- 2.27, N = 12 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 17.49 17.41 17.53 17.37 32.42 17.37 315.26 35.39 17.44 17.65 17.48 MIN: 86.78 / MAX: 701.54 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 6 12 18 24 30 SE +/- 0.10, N = 15 SE +/- 0.07, N = 12 SE +/- 0.09, N = 15 SE +/- 0.10, N = 15 SE +/- 0.11, N = 12 SE +/- 0.12, N = 12 SE +/- 0.07, N = 3 SE +/- 0.10, N = 12 SE +/- 0.11, N = 15 SE +/- 0.10, N = 15 SE +/- 0.04, N = 5 3.51 3.45 3.32 3.38 3.55 3.39 24.55 3.40 3.41 3.44 3.72 MIN: 5.27 / MAX: 260.67 1. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 1000 2000 3000 4000 5000 SE +/- 0.37, N = 3 SE +/- 0.32, N = 3 SE +/- 0.34, N = 3 SE +/- 0.36, N = 3 SE +/- 0.52, N = 3 SE +/- 0.55, N = 3 SE +/- 3.96, N = 3 SE +/- 0.23, N = 3 SE +/- 0.13, N = 3 SE +/- 0.08, N = 3 SE +/- 0.34, N = 3 869.22 868.87 868.92 868.26 895.13 867.90 4864.70 876.50 868.82 872.89 869.19
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 60 120 180 240 300 SE +/- 0.28, N = 3 SE +/- 0.18, N = 3 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.11, N = 3 68.92 68.71 68.56 68.58 71.16 68.65 295.49 68.60 68.55 68.71 68.77
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 200 400 600 800 1000 SE +/- 0.17, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 SE +/- 0.01, N = 3 SE +/- 1.11, N = 3 SE +/- 0.25, N = 3 SE +/- 0.09, N = 3 SE +/- 0.31, N = 3 SE +/- 0.17, N = 3 205.68 205.42 205.70 205.30 212.63 205.41 1124.30 206.14 205.49 206.45 205.28
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 200 400 600 800 1000 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.17, N = 3 SE +/- 0.17, N = 3 SE +/- 0.12, N = 3 SE +/- 1.48, N = 3 SE +/- 0.14, N = 3 SE +/- 0.18, N = 3 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 158.13 157.55 158.08 157.70 164.20 157.80 884.29 158.95 157.83 158.05 157.88
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 90 180 270 360 450 SE +/- 0.14, N = 3 SE +/- 0.16, N = 3 SE +/- 0.12, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 SE +/- 0.15, N = 3 SE +/- 0.17, N = 3 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 76.99 76.98 77.02 76.91 78.87 76.91 431.96 76.57 77.10 77.01 77.06
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 120 240 360 480 600 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.25, N = 3 SE +/- 0.14, N = 3 SE +/- 0.31, N = 3 SE +/- 0.05, N = 3 SE +/- 0.20, N = 3 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 104.57 104.76 104.66 104.62 108.66 104.73 577.77 105.15 104.75 105.02 104.80
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 700 1400 2100 2800 3500 SE +/- 0.37, N = 3 SE +/- 0.13, N = 3 SE +/- 0.15, N = 3 SE +/- 0.23, N = 3 SE +/- 0.38, N = 3 SE +/- 0.41, N = 3 SE +/- 0.92, N = 3 SE +/- 0.30, N = 3 SE +/- 0.24, N = 3 SE +/- 0.20, N = 3 SE +/- 0.22, N = 3 587.74 587.84 587.78 587.61 605.67 586.86 3485.21 589.69 587.78 588.61 587.38
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 200 400 600 800 1000 SE +/- 0.29, N = 3 SE +/- 0.48, N = 3 SE +/- 0.11, N = 3 SE +/- 0.11, N = 3 SE +/- 0.54, N = 3 SE +/- 0.30, N = 3 SE +/- 0.96, N = 3 SE +/- 0.15, N = 3 SE +/- 0.52, N = 3 SE +/- 0.26, N = 3 SE +/- 0.28, N = 3 207.61 207.44 207.33 207.19 214.47 207.67 1143.06 208.09 207.27 207.88 207.58
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 1000 2000 3000 4000 5000 SE +/- 0.33, N = 3 SE +/- 0.23, N = 3 SE +/- 0.24, N = 3 SE +/- 0.76, N = 3 SE +/- 0.79, N = 3 SE +/- 0.10, N = 3 SE +/- 2.96, N = 3 SE +/- 0.56, N = 3 SE +/- 0.11, N = 3 SE +/- 0.15, N = 3 SE +/- 0.69, N = 3 868.08 867.93 867.02 866.98 893.43 866.96 4868.11 876.33 866.62 872.07 867.83
Xcompact3d Incompact3d Input: X3D-benchmarking input.i3d OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: X3D-benchmarking input.i3d amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 120 240 360 480 600 SE +/- 0.99, N = 3 SE +/- 1.22, N = 3 SE +/- 0.28, N = 3 SE +/- 0.44, N = 3 SE +/- 0.30, N = 3 SE +/- 0.86, N = 3 SE +/- 0.43, N = 3 SE +/- 0.67, N = 3 SE +/- 0.32, N = 3 SE +/- 0.74, N = 3 SE +/- 0.25, N = 3 264.91 264.59 263.30 264.82 267.54 265.31 540.54 262.40 263.63 264.80 263.63 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
OpenFOAM Input: drivaerFastback, Medium Mesh Size - Mesh Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Mesh Time amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 170 340 510 680 850 116.05 114.87 116.28 116.19 127.86 116.11 773.97 119.63 116.44 120.10 115.76 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
OpenFOAM Input: drivaerFastback, Medium Mesh Size - Execution Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Execution Time amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 170 340 510 680 850 167.41 170.71 169.25 167.82 182.44 168.80 773.03 167.90 166.48 169.00 164.04 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
Timed Gem5 Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Gem5 Compilation 21.2 Time To Compile amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 200 400 600 800 1000 SE +/- 1.30, N = 3 SE +/- 1.78, N = 3 SE +/- 1.51, N = 8 SE +/- 0.95, N = 3 SE +/- 1.72, N = 3 SE +/- 0.56, N = 3 SE +/- 13.66, N = 3 SE +/- 1.36, N = 3 SE +/- 1.73, N = 3 SE +/- 1.68, N = 4 SE +/- 0.41, N = 3 157.10 149.77 173.20 148.50 156.95 146.64 1100.36 153.90 149.22 152.99 147.00
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 Time To Compile amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 60 120 180 240 300 SE +/- 0.44, N = 3 SE +/- 0.05, N = 3 SE +/- 0.43, N = 3 SE +/- 0.27, N = 3 SE +/- 0.30, N = 15 SE +/- 0.46, N = 3 SE +/- 1.50, N = 3 SE +/- 0.12, N = 3 SE +/- 0.36, N = 3 SE +/- 0.38, N = 3 SE +/- 0.23, N = 3 41.90 37.32 47.94 37.01 41.94 37.05 258.87 40.81 37.58 38.37 37.38
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.1 Build: defconfig amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 30 60 90 120 150 SE +/- 0.16, N = 13 SE +/- 0.15, N = 13 SE +/- 0.24, N = 13 SE +/- 0.14, N = 15 SE +/- 0.23, N = 14 SE +/- 0.18, N = 10 SE +/- 1.30, N = 9 SE +/- 0.21, N = 15 SE +/- 0.14, N = 13 SE +/- 0.17, N = 14 SE +/- 0.14, N = 13 25.52 22.62 30.83 22.53 25.39 22.52 156.78 24.52 22.61 23.44 22.65
Timed Linux Kernel Compilation Build: allmodconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.1 Build: allmodconfig amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 200 400 600 800 1000 SE +/- 0.78, N = 3 SE +/- 0.74, N = 3 SE +/- 0.62, N = 3 SE +/- 0.76, N = 3 SE +/- 1.59, N = 3 SE +/- 0.72, N = 3 SE +/- 2.74, N = 3 SE +/- 1.27, N = 3 SE +/- 0.77, N = 3 SE +/- 0.85, N = 3 SE +/- 0.71, N = 3 176.50 172.88 184.47 172.86 182.77 173.64 1094.37 177.06 172.61 174.95 173.63
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 18.8 Time To Compile amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 160 320 480 640 800 SE +/- 0.68, N = 3 SE +/- 0.15, N = 3 SE +/- 0.22, N = 3 SE +/- 0.19, N = 3 SE +/- 0.24, N = 3 SE +/- 0.08, N = 3 SE +/- 0.88, N = 3 SE +/- 0.13, N = 3 SE +/- 0.23, N = 3 SE +/- 0.16, N = 3 SE +/- 0.15, N = 3 111.95 105.53 120.48 105.83 113.13 104.93 752.99 109.81 106.47 107.14 105.54
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.4 Blend File: Classroom - Compute: CPU-Only amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 60 120 180 240 300 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 37.94 37.68 38.35 37.57 40.04 37.73 254.46 37.85 37.61 37.92 37.71
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.4 Blend File: Fishy Cat - Compute: CPU-Only amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 30 60 90 120 150 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.18, N = 3 SE +/- 0.16, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 19.17 18.80 19.74 18.95 20.26 18.89 124.48 19.18 18.90 19.00 19.01
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.4 Blend File: Barbershop - Compute: CPU-Only amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 200 400 600 800 1000 SE +/- 0.14, N = 3 SE +/- 0.14, N = 3 SE +/- 0.33, N = 3 SE +/- 0.20, N = 3 SE +/- 0.32, N = 3 SE +/- 0.10, N = 3 SE +/- 0.78, N = 3 SE +/- 0.24, N = 3 SE +/- 0.28, N = 3 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 141.79 140.18 143.04 140.36 147.46 140.35 933.41 141.91 140.55 141.98 140.45
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.4 Blend File: Pabellon Barcelona - Compute: CPU-Only amd_pstate_epp powersave balance_performance amd_pstate_epp performance balance_performance amd_pstate_epp powersave power amd_pstate_epp performance performance amd_pstate schedutil amd_pstate performance amd_pstate powersave amd_pstate ondemand acpi_cpufreq schedutil acpi_cpufreq ondemand acpi_cpufreq performance 60 120 180 240 300 SE +/- 0.20, N = 3 SE +/- 0.08, N = 3 SE +/- 0.42, N = 3 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.71, N = 3 SE +/- 0.29, N = 3 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 SE +/- 0.15, N = 3 45.99 45.72 46.73 45.75 48.49 45.77 297.67 46.19 45.95 45.92 45.85
Phoronix Test Suite v10.8.4