Xeon Platinum 8380 Fedora 2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on Debian 11 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2110054-TJ-2110030TJ29&rdt&grs .
Xeon Platinum 8380 Fedora Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Compiler File-System Screen Resolution Desktop Display Server Vulkan Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads) Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) Intel Device 0998 504GB 7682GB INTEL SSDPF2KX076TZ ASPEED VE228 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP Fedora Linux 35 5.14.7-300.fc35.x86_64 (x86_64) GCC 11.2.1 20210728 xfs 1920x1080 Ubuntu 21.10 5.13.0-16-generic (x86_64) GNOME Shell 40.5 X Server 1.1.182 GCC 11.2.0 ext4 7682GB INTEL SSDPF2KX076TZ + 15GB Ultra USB 3.0 openSUSE Tumbleweed 20210929 5.14.6-1-default (x86_64) KDE Plasma X Server 1.20.13 GCC 11.2.1 20210816 [revision 056e324ce46a7924b5cf10f61010cf9dd2ca10e9] btrfs 7682GB INTEL SSDPF2KX076TZ CentOS Stream 8 4.18.0-338.el8.x86_64 (x86_64) GNOME Shell 3.32.2 X Server GCC 8.5.0 20210514 xfs Debian 11 5.10.0-8-amd64 (x86_64) 1.0.2 GCC 10.2.1 20210110 ext4 OpenBenchmarking.org Kernel Details - Fedora 35 Beta: Transparent Huge Pages: madvise - Ubuntu 21.10 Oct1: Transparent Huge Pages: madvise - openSUSE Tumbleweed: Transparent Huge Pages: always - CentOS Stream: Transparent Huge Pages: always - Debian 11: Transparent Huge Pages: always Environment Details - Fedora 35 Beta: DEBUGINFOD_URLS=https://debuginfod.fedoraproject.org/ - openSUSE Tumbleweed: DEBUGINFOD_URLS=https://debuginfod.opensuse.org/ Compiler Details - Fedora 35 Beta: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver - Ubuntu 21.10 Oct1: --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-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - openSUSE Tumbleweed: --build=x86_64-suse-linux --disable-libcc1 --disable-libssp --disable-libstdcxx-pch --disable-libvtv --disable-werror --enable-cet=auto --enable-checking=release --enable-gnu-indirect-function --enable-host-shared --enable-languages=c,c++,objc,fortran,obj-c++,ada,go,d,jit --enable-libphobos --enable-libstdcxx-allocator=new --enable-link-mutex --enable-linux-futex --enable-multilib --enable-offload-targets=nvptx-none,amdgcn-amdhsa, --enable-plugin --enable-ssp --enable-version-specific-runtime-libs --host=x86_64-suse-linux --mandir=/usr/share/man --with-arch-32=x86-64 --with-build-config=bootstrap-lto-lean --with-gcc-major-version-only --with-slibdir=/lib64 --with-tune=generic --without-cuda-driver --without-system-libunwind - CentOS Stream: --build=x86_64-redhat-linux --disable-libmpx --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver - Debian 11: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --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 Disk Details - Fedora 35 Beta: NONE / attr2,inode64,logbsize=32k,logbufs=8,noquota,relatime,rw,seclabel / Block Size: 4096 - Ubuntu 21.10 Oct1: NONE / errors=remount-ro,relatime,rw / Block Size: 4096 - openSUSE Tumbleweed: NONE / relatime,rw,space_cache,ssd,subvol=/@/home,subvolid=262 / Block Size: 4096 - CentOS Stream: NONE / attr2,inode64,logbsize=32k,logbufs=8,noquota,relatime,rw,seclabel / Block Size: 4096 - Debian 11: NONE / errors=remount-ro,relatime,rw / Block Size: 4096 Processor Details - Fedora 35 Beta: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd0002a0 - Ubuntu 21.10 Oct1: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd0002a0 - openSUSE Tumbleweed: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd0002a0 - CentOS Stream: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd0002a0 - Debian 11: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270 Java Details - Fedora 35 Beta: OpenJDK Runtime Environment 18.9 (build 11.0.12+7) - Ubuntu 21.10 Oct1: OpenJDK Runtime Environment (build 11.0.12+7-Ubuntu-0ubuntu3) - openSUSE Tumbleweed: OpenJDK Runtime Environment (build 11.0.12+7-suse-3.1-x8664) - CentOS Stream: OpenJDK Runtime Environment (build 1.8.0_302-b08) - Debian 11: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2) Python Details - Fedora 35 Beta: Python 3.10.0rc2 - Ubuntu 21.10 Oct1: Python 3.9.7 - openSUSE Tumbleweed: Python 3.8.12 - CentOS Stream: Python 3.6.8 - Debian 11: Python 3.9.2 Security Details - Fedora 35 Beta: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - Ubuntu 21.10 Oct1: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - openSUSE Tumbleweed: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - CentOS Stream: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - Debian 11: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Xeon Platinum 8380 Fedora rocksdb: Rand Fill Sync pgbench: 100 - 250 - Read Write - Average Latency pgbench: 100 - 250 - Read Write rocksdb: Rand Fill rocksdb: Update Rand npb: SP.B apache: 200 npb: LU.C rocksdb: Read Rand Write Rand apache: 100 renaissance: Genetic Algorithm Using Jenetics + Futures npb: BT.C npb: SP.C npb: EP.D npb: MG.C nginx: 100 x265: Bosphorus 1080p renaissance: ALS Movie Lens renaissance: Akka Unbalanced Cobwebbed Tree renaissance: Apache Spark ALS x265: Bosphorus 4K renaissance: Rand Forest svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p node-express-loadtest: svt-vp9: Visual Quality Optimized - Bosphorus 1080p jpegxl: JPEG - 7 svt-av1: Preset 8 - Bosphorus 4K npb: CG.C pyperformance: python_startup svt-hevc: 7 - Bosphorus 1080p jpegxl: JPEG - 8 cassandra: Writes npb: IS.D build-wasmer: Time To Compile svt-av1: Preset 4 - Bosphorus 4K jpegxl: PNG - 7 stress-ng: Memory Copying pyperformance: 2to3 stress-ng: Forking stress-ng: MEMFD renaissance: Savina Reactors.IO appleseed: Emily appleseed: Disney Material stress-ng: MMAP renaissance: Finagle HTTP Requests stress-ng: Semaphores compress-7zip: Compress Speed Test pyperformance: raytrace svt-hevc: 1 - Bosphorus 1080p tensorflow-lite: Mobilenet Float stress-ng: SENDFILE phpbench: PHP Benchmark Suite stress-ng: Vector Math tnn: CPU - DenseNet sqlite-speedtest: Timed Time - Size 1,000 pybench: Total For Average Test Times rodinia: OpenMP LavaMD build-linux-kernel: Time To Compile leveldb: Hot Read build-nodejs: Time To Compile build-godot: Time To Compile gmpbench: Total Time ncnn: CPU - vgg16 ncnn: CPU - googlenet stress-ng: Crypto build-llvm: Unix Makefiles ncnn: CPU-v2-v2 - mobilenet-v2 build-llvm: Unix Makefiles jpegxl: PNG - 8 stress-ng: Matrix Math ncnn: CPU - efficientnet-b0 ncnn: CPU - mnasnet ncnn: CPU-v3-v3 - mobilenet-v3 rocksdb: Rand Read ncnn: CPU - shufflenet-v2 compress-lz4: 3 - Compression Speed stress-ng: CPU Stress ospray: Magnetic Reconnection - SciVis embree: Pathtracer ISPC - Crown compress-lz4: 9 - Compression Speed ncnn: CPU - resnet50 compress-zstd: 19 - Compression Speed tensorflow-lite: NASNet Mobile ncnn: CPU - blazeface ncnn: CPU - mobilenet build-llvm: Ninja ospray: San Miguel - SciVis ncnn: CPU - squeezenet_ssd build-llvm: Ninja ncnn: CPU - regnety_400m compress-zstd: 19, Long Mode - Compression Speed mnn: mobilenet-v1-1.0 onednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU compress-lz4: 3 - Decompression Speed blender: Barbershop - CPU-Only tensorflow-lite: SqueezeNet tensorflow-lite: Inception V4 v-ray: CPU openvkl: vklBenchmark ISPC mnn: inception-v3 onnx: bertsquad-10 - OpenMP CPU onnx: shufflenet-v2-10 - OpenMP CPU stress-ng: Malloc simdjson: PartialTweets compress-lz4: 9 - Decompression Speed openssl: SHA256 mnn: resnet-v2-50 blender: BMW27 - CPU-Only onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU gromacs: MPI CPU - water_GMX50_bare securemark: SecureMark-TLS coremark: CoreMark Size 666 - Iterations Per Second tensorflow-lite: Inception ResNet V2 appleseed: Material Tester simdjson: DistinctUserID onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU embree: Pathtracer - Crown stockfish: Total Time tnn: CPU - SqueezeNet v2 git: Time To Complete Common Git Commands compress-zstd: 19, Long Mode - Decompression Speed stress-ng: Glibc C String Functions simdjson: Kostya compress-zstd: 19 - Decompression Speed blender: Classroom - CPU-Only embree: Pathtracer ISPC - Asian Dragon embree: Pathtracer - Asian Dragon namd: ATPase Simulation - 327,506 Atoms ospray: San Miguel - Path Tracer oidn: RT.hdr_alb_nrm.3840x2160 simdjson: LargeRand hpcg: stress-ng: Glibc Qsort Data Sorting onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU synthmark: VoiceMark_100 onnx: yolov4 - OpenMP CPU openssl: RSA4096 tnn: CPU - SqueezeNet v1.1 onednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU openssl: RSA4096 stress-ng: RdRand onnx: fcn-resnet101-11 - OpenMP CPU pgbench: 100 - 500 - Read Write - Average Latency pgbench: 100 - 500 - Read Write pgbench: 100 - 500 - Read Only - Average Latency pgbench: 100 - 500 - Read Only apache: 1000 nginx: 1000 nginx: 500 nginx: 200 pyperformance: pickle_pure_python pyperformance: django_template pyperformance: regex_compile pyperformance: crypto_pyaes pyperformance: json_loads pyperformance: pathlib pyperformance: nbody pyperformance: float pyperformance: chaos tnn: CPU - MobileNet v2 ncnn: CPU - yolov4-tiny ncnn: CPU - alexnet ncnn: CPU - resnet18 mnn: MobileNetV2_224 mnn: SqueezeNetV1.0 mnn: squeezenetv1.1 mnn: mobilenetV3 stress-ng: System V Message Passing stress-ng: Context Switching stress-ng: CPU Cache stress-ng: IO_uring stress-ng: NUMA pgbench: 100 - 250 - Read Only - Average Latency pgbench: 100 - 250 - Read Only tensorflow-lite: Mobilenet Quant onednn: IP Shapes 3D - bf16bf16bf16 - CPU onednn: IP Shapes 1D - bf16bf16bf16 - CPU compress-zstd: 8 - Decompression Speed compress-zstd: 8 - Compression Speed renaissance: Apache Spark Bayes dacapobench: Tradebeans dacapobench: Jython dacapobench: H2 rodinia: OpenMP Streamcluster rodinia: OpenMP Leukocyte npb: FT.C Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 100599 7.663 32630 101033 96320 23009.99 39792.03 38573.19 884458 40137.66 6932.1 48296.17 23991.71 2725.01 35006.33 88737.60 26.99 18146.4 36175.6 3172.4 11.91 1537.2 207.34 5453 172.78 40.42 30.117 20482.79 16.1 168.45 15.68 155829 1878.50 44.812 2.952 7.24 13309.14 524 69885.73 3895.47 21211.3 178.073796 83.066417 4719.58 8137.7 9177476.81 290145 525 30.32 40682.0 1225384.87 761666 277479.38 4130.775 59.770 1157 45.727 25.863 205.520 61.622 3776.8 29.02 23.54 14074.74 199.621 11.99 206.063 0.66 290055.81 14.48 11.43 11.66 369206119 11.67 43.83 126640.32 111.11 64.7554 43.19 26.02 81.2 83310.2 6.96 21.31 131.309 90.91 23.85 132.315 37.97 44.6 1.946 3.23502 7136.8 109.60 49724.4 710372 63528 271 22.304 687 12630 1399403296.43 3.63 7149.6 59198740233 19.122 29.86 449.104 9.049 228244 2387052.976471 594597 194.072632 4.16 684.349 62.1289 180079720 74.022 62.329 2729.4 7933317.10 2.44 2658.2 73.64 105.4949 81.9327 0.28029 10.42 2.87 0.86 39.6784 978.29 2.13007 543.430 548 17706.5 366.322 3.63442 1187546.8 666960.21 474 18.292 27335 0.267 1875522 59961.48 216774.28 213760.91 204764.97 516 55.8 206 137 26.2 28.7 161 128 132 396.219 25.41 9.69 14.58 2.795 4.672 3.840 1.994 4098551.27 4484674.85 15.93 336629.20 45.25 0.252 991583 37665.7 2.99045 6.50917 3104.6 2026.8 1017.8 16993 5386 10776 8.179 48.918 36258.08 71086 8.039 31120 99799 94412 113702.80 43438.03 177749.25 866761 30630.23 6835.2 192540.50 91411.13 8873.24 117164.52 72553.09 26.95 18067.6 35585.2 3095.6 12.08 1562.3 214.16 7318 178.73 40.72 31.697 39438.33 16.8 174.24 16.39 150942 3023.76 57.203 2.944 7.30 13002.21 515 66266.20 3770.87 21433.8 178.454037 81.862378 3838.76 7753.2 9460605.86 306548 487 29.74 42433.4 1197035.98 784757 278044.70 4538.954 62.546 1011 46.576 25.284 182.263 98.281 73.737 4503 28.66 22.40 13702.95 200.787 11.85 205.281 0.66 292343.66 14.32 11.28 11.56 324373890 11.70 45.33 126295.66 110.19 66.3379 44.32 26.27 80.2 84493.3 6.99 21.26 129.937 90.91 24.03 131.763 37.70 44.1 1.844 3.29168 7193.7 108.68 50687.8 710386 63275 268 21.614 648 11943 1407281590.86 3.71 7210.7 58476634107 18.794 29.53 449.010 9.038 223678 2282293.380847 595226 190.722468 4.22 680.887 64.4883 176162289 76.861 60.819 2689.5 7962720.71 2.45 2646.4 73.41 107.6734 83.0416 0.27847 10.42 2.94 0.85 40.0345 964.65 2.12241 550.527 541 17798.2 368.220 3.61481 1191217.9 666871.13 476 16.270 30731 0.269 1859821 106682.07 191181.80 189131.99 168716.20 604 59.1 215 133 30.5 26.1 152 148 136 441.997 25.15 9.35 14.09 2.731 4.421 3.770 1.949 3578020.47 5272694.80 16.10 91421.67 44.94 0.269 937156 41710.6 3.96654 6.50961 2917.4 2034.8 973.5 16793 4727 10704 8.282 53.420 91713.25 20.686 12099 23088.45 196788.51 38035.55 78274.56 6431.5 48701.26 24132.71 2873.13 36360.07 78818.87 27.06 18282.9 32549.3 3175.6 12.30 1428.8 212.88 178.98 49.82 34.268 20496.77 19.9 176.05 17.57 150708 2040.29 42.776 3.036 8.15 13314.82 556 90874.21 4285.00 20867.5 175.525803 83.338994 4697.27 5995.9 10452079.79 354644 627 30.04 39087.2 1231359.88 628171 278157.65 3940.131 72.652 1205 44.160 179.589 101.799 3828.4 31.60 21.51 14258.27 199.274 11.82 206.827 0.76 294254.02 14.13 11.17 11.43 11.84 46.33 127127.44 111.11 71.8391 45.51 26.94 87.1 82944.6 6.69 21.27 131.767 90.91 23.74 133.642 37.77 48.0 1.995 3.23059 7153.2 105.32 49661.2 693874 66690 274 22.326 1410532156.00 3.65 7115.3 58447799270 18.854 29.20 438.642 9.076 229049 2393687.001907 596888 189.12003 4.12 664.141 64.8851 183803628 74.832 60.788 2743.4 7905372.49 2.50 2671.0 72.44 108.9060 83.5001 0.27899 10.64 2.90 0.87 39.8828 980.62 2.12178 543.043 17744.0 365.690 3.63231 1193325.7 666960.00 50.652 9872 0.282 1794700 206714.39 208713.17 206192.34 195437.72 705 67.9 248 173 31.8 29.4 191 174 177 383.432 25.69 8.53 13.35 2.876 5.061 3.760 2.069 3045985.32 24430641.91 16.45 75341.64 7.11 0.297 912058 37729.3 2.77560 6.63389 3026.3 1946.5 1171.8 15573 5022 9579 8.178 51.066 37549.01 536318 2.715 92097 619860 586633 23861.27 131724.49 39289.66 3806446 118170.02 1688.6 49586.16 24408.10 2605.15 45452.20 213115.03 76.57 6746.7 15061.7 1324.9 27.07 688.7 459.87 10069 361.28 84.36 58.905 22965.29 10.4 304.17 27.99 266050 2034.48 39.757 4.858 11.76 8417.59 353 63225.90 2749.64 14116.6 122.616377 57.698613 3330.78 12432372.72 392910 618 38.01 33155.5 978142.73 640144 223730.72 3667.433 60.538 1184 45.530 21.337 191.577 84.774 4228.8 32.48 23.16 12280.97 174.512 11.57 179.813 0.73 333721.31 14.22 10.96 11.51 332140763 11.79 49.78 111992.39 125 73.3976 48.94 27.30 89.9 75554.9 6.70 21.12 119.737 100 24.79 122.391 38.04 45.1 1.902 3.45007 6931.1 102.30 47473.5 667444 67330 285 22.969 1445156501.92 3.83 7099.9 57290460430 19.436 28.43 438.770 8.719 234638 2333336.340493 580283 192.679047 4.23 664.924 63.6950 183054178 73.942 61.820 2637.9 7842753.42 2.44 2578.4 71.29 108.5165 82.4740 0.27436 10.56 2.94 0.85 40.5930 979.66 2.09939 547.054 17701.1 367.410 3.63602 1186729.8 669870.10 1152.338 39695 86.115 329430 119249.02 200333.56 196943.93 188445.93 540 77.8 208 113 26.3 20.3 125 120 126 365.187 27.63 10.62 14.97 2.720 4.559 3.881 2.128 5648012.33 11482636.32 16.26 10.33 0.255 984861 33738.8 1.73826 3.00178 2987.1 2763.2 523.7 3712 3663 3706 7.965 45.741 38711.61 68379 8.798 28458 93455 89779 115021.70 49245.24 178836.34 837568 28230.81 6985.6 191625.24 90606.08 8509.70 117311.57 74654.34 28.19 18182.4 32557.2 3148.5 13.49 1494.8 203.41 4676 169.81 45.67 30.512 39866.27 17.1 170.57 17.24 149220 3243.03 66.403 2.944 8.15 8288.19 511 57939.36 3915.95 21142.6 179.056715 81.754584 4173.70 5967.3 10070481.32 351256 468 29.69 37543.7 1149339.09 727869 250969.79 3892.993 58.901 978 38.065 24.166 171.136 98.020 73.388 4519 27.17 19.78 13482.89 202.122 10.37 207.298 0.73 300488.84 12.64 10.01 10.22 356094496 10.42 49.48 125486.27 111.11 66.4038 48.49 24.13 86.6 76318.2 6.30 19.34 126.842 90.91 22.69 129.376 34.93 44.7 1.930 3.19617 7475.4 104.77 47638.2 668386 66940 275 22.468 1477294638.69 3.78 7484.3 60273469430 19.756 28.82 427.828 9.150 230202 2372626.656613 570385 185.484738 4.31 654.350 63.8788 178004391 73.833 59.890 2731.6 8138767.03 2.53 2620.1 71.32 107.0315 84.4523 0.27334 10.68 2.91 0.86 40.1957 984.25 2.10779 549.780 17850.1 366.341 3.61866 1191300.7 666684.30 21.268 23512 0.263 1902066 39217.70 204201.05 200482.69 95361.92 555 58.0 198 125 31.5 24.9 138 149 128 375.456 24.33 8.61 13.19 2.892 4.712 3.828 1.967 1764395.47 17724791.00 16.61 258560.94 5.17 0.264 953348 37688.1 1.72474 2.98827 2732.7 1947.7 992.4 16382 5519 9850 7.834 55.253 93063.10 OpenBenchmarking.org
Facebook RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill Sync Fedora 35 Beta Ubuntu 21.10 Oct1 CentOS Stream Debian 11 110K 220K 330K 440K 550K SE +/- 127.95, N = 3 SE +/- 41.53, N = 3 SE +/- 778.68, N = 3 SE +/- 347.37, N = 3 100599 71086 536318 68379 -lpthread -lgflags -lpthread 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 5 10 15 20 25 SE +/- 0.006, N = 3 SE +/- 0.015, N = 3 SE +/- 0.173, N = 15 SE +/- 0.004, N = 3 SE +/- 0.065, N = 15 7.663 8.039 20.686 2.715 8.798 -lpthread -lrt -ldl -lpthread -lrt -ldl 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20K 40K 60K 80K 100K SE +/- 24.31, N = 3 SE +/- 56.97, N = 3 SE +/- 102.11, N = 15 SE +/- 126.73, N = 3 SE +/- 215.99, N = 15 32630 31120 12099 92097 28458 -lpthread -lrt -ldl -lpthread -lrt -ldl 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill Fedora 35 Beta Ubuntu 21.10 Oct1 CentOS Stream Debian 11 130K 260K 390K 520K 650K SE +/- 237.03, N = 3 SE +/- 88.17, N = 3 SE +/- 475.40, N = 3 SE +/- 506.10, N = 3 101033 99799 619860 93455 -lpthread -lgflags -lpthread 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
Facebook RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Update Random Fedora 35 Beta Ubuntu 21.10 Oct1 CentOS Stream Debian 11 130K 260K 390K 520K 650K SE +/- 85.06, N = 3 SE +/- 68.05, N = 3 SE +/- 373.89, N = 3 SE +/- 92.24, N = 3 96320 94412 586633 89779 -lpthread -lgflags -lpthread 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
NAS Parallel Benchmarks Test / Class: SP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20K 40K 60K 80K 100K SE +/- 145.01, N = 3 SE +/- 647.01, N = 3 SE +/- 83.49, N = 3 SE +/- 30.62, N = 3 SE +/- 689.07, N = 3 23009.99 113702.80 23088.45 23861.27 115021.70 -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.1.0
Apache HTTP Server Concurrent Requests: 200 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 200 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 40K 80K 120K 160K 200K SE +/- 95.62, N = 3 SE +/- 196.67, N = 3 SE +/- 1483.04, N = 3 SE +/- 377.88, N = 3 SE +/- 292.03, N = 3 39792.03 43438.03 196788.51 131724.49 49245.24 -pthread -pthread 1. (CC) gcc options: -shared -fPIC -O2
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 40K 80K 120K 160K 200K SE +/- 164.50, N = 3 SE +/- 2506.74, N = 3 SE +/- 166.83, N = 3 SE +/- 272.38, N = 3 SE +/- 1426.63, N = 3 38573.19 177749.25 38035.55 39289.66 178836.34 -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.1.0
Facebook RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read Random Write Random Fedora 35 Beta Ubuntu 21.10 Oct1 CentOS Stream Debian 11 800K 1600K 2400K 3200K 4000K SE +/- 1134.93, N = 3 SE +/- 632.48, N = 3 SE +/- 27840.60, N = 3 SE +/- 627.32, N = 3 884458 866761 3806446 837568 -lpthread -lgflags -lpthread 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
Apache HTTP Server Concurrent Requests: 100 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 100 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 30K 60K 90K 120K 150K SE +/- 260.52, N = 3 SE +/- 155.07, N = 3 SE +/- 189.85, N = 3 SE +/- 636.70, N = 3 SE +/- 246.72, N = 3 40137.66 30630.23 78274.56 118170.02 28230.81 -pthread -pthread 1. (CC) gcc options: -shared -fPIC -O2
Renaissance Test: Genetic Algorithm Using Jenetics + Futures OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Genetic Algorithm Using Jenetics + Futures Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 1500 3000 4500 6000 7500 SE +/- 12.88, N = 3 SE +/- 31.29, N = 3 SE +/- 19.46, N = 3 SE +/- 18.74, N = 15 SE +/- 49.23, N = 3 6932.1 6835.2 6431.5 1688.6 6985.6 MIN: 6640.26 / MAX: 7236.52 MIN: 6576.23 / MAX: 7037.67 MIN: 6260.99 / MAX: 6606.28 MIN: 1415.31 / MAX: 1878.53 MIN: 6692.73 / MAX: 7243.21
NAS Parallel Benchmarks Test / Class: BT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 40K 80K 120K 160K 200K SE +/- 146.19, N = 3 SE +/- 703.72, N = 3 SE +/- 121.21, N = 3 SE +/- 39.53, N = 3 SE +/- 2701.50, N = 3 48296.17 192540.50 48701.26 49586.16 191625.24 -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.1.0
NAS Parallel Benchmarks Test / Class: SP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20K 40K 60K 80K 100K SE +/- 124.15, N = 3 SE +/- 167.98, N = 3 SE +/- 56.62, N = 3 SE +/- 44.46, N = 3 SE +/- 24.84, N = 3 23991.71 91411.13 24132.71 24408.10 90606.08 -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.1.0
NAS Parallel Benchmarks Test / Class: EP.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 2K 4K 6K 8K 10K SE +/- 2.07, N = 3 SE +/- 85.67, N = 15 SE +/- 22.87, N = 3 SE +/- 33.08, N = 3 SE +/- 102.66, N = 4 2725.01 8873.24 2873.13 2605.15 8509.70 -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.1.0
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 30K 60K 90K 120K 150K SE +/- 437.96, N = 3 SE +/- 163.67, N = 3 SE +/- 289.17, N = 15 SE +/- 71.59, N = 3 SE +/- 308.39, N = 3 35006.33 117164.52 36360.07 45452.20 117311.57 -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.1.0
nginx Concurrent Requests: 100 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 100 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 50K 100K 150K 200K 250K SE +/- 990.65, N = 3 SE +/- 279.85, N = 3 SE +/- 706.36, N = 3 SE +/- 1078.58, N = 3 SE +/- 119.69, N = 3 88737.60 72553.09 78818.87 213115.03 74654.34 -ldl -lpthread -ldl -lpthread 1. (CC) gcc options: -lcrypt -lz -O3 -march=native
x265 Video Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20 40 60 80 100 SE +/- 0.23, N = 3 SE +/- 0.33, N = 3 SE +/- 0.26, N = 3 SE +/- 0.92, N = 3 SE +/- 0.20, N = 3 26.99 26.95 27.06 76.57 28.19 -lnuma -lnuma 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
Renaissance Test: ALS Movie Lens OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: ALS Movie Lens Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 4K 8K 12K 16K 20K SE +/- 8.48, N = 3 SE +/- 48.52, N = 3 SE +/- 170.25, N = 3 SE +/- 57.62, N = 3 SE +/- 142.50, N = 3 18146.4 18067.6 18282.9 6746.7 18182.4 MIN: 18137.86 / MAX: 20327.55 MIN: 17747.45 / MAX: 19660.26 MIN: 17522.47 / MAX: 20593.65 MIN: 6623.99 / MAX: 7259.63 MIN: 17943.52 / MAX: 20942.97
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Akka Unbalanced Cobwebbed Tree Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 8K 16K 24K 32K 40K SE +/- 202.86, N = 3 SE +/- 413.78, N = 3 SE +/- 99.39, N = 3 SE +/- 101.37, N = 3 SE +/- 103.65, N = 3 36175.6 35585.2 32549.3 15061.7 32557.2 MIN: 27438.31 / MAX: 36484.8 MIN: 28027.65 / MAX: 36206.47 MIN: 25316.88 / MAX: 32683.86 MIN: 11600.48 / MAX: 15173.74 MIN: 24742.75 / MAX: 32734.09
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark ALS Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 700 1400 2100 2800 3500 SE +/- 11.53, N = 3 SE +/- 14.07, N = 3 SE +/- 14.30, N = 3 SE +/- 6.24, N = 3 SE +/- 17.82, N = 3 3172.4 3095.6 3175.6 1324.9 3148.5 MIN: 2851.96 / MAX: 3598.58 MIN: 2795.88 / MAX: 3565.03 MIN: 2949.88 / MAX: 3682.83 MIN: 1247.72 / MAX: 1457.9 MIN: 2809.07 / MAX: 3507.93
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 6 12 18 24 30 SE +/- 0.07, N = 3 SE +/- 0.13, N = 3 SE +/- 0.03, N = 3 SE +/- 0.41, N = 15 SE +/- 0.12, N = 3 11.91 12.08 12.30 27.07 13.49 -lnuma -lnuma 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Random Forest Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 300 600 900 1200 1500 SE +/- 20.09, N = 3 SE +/- 9.03, N = 3 SE +/- 9.00, N = 3 SE +/- 8.76, N = 3 SE +/- 9.50, N = 3 1537.2 1562.3 1428.8 688.7 1494.8 MIN: 1298.32 / MAX: 1875.3 MIN: 1381.5 / MAX: 1982.68 MIN: 1268.67 / MAX: 1723.65 MIN: 639.51 / MAX: 830.2 MIN: 1315.21 / MAX: 1817.05
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 100 200 300 400 500 SE +/- 2.30, N = 3 SE +/- 2.62, N = 4 SE +/- 0.87, N = 3 SE +/- 3.22, N = 15 SE +/- 2.57, N = 3 207.34 214.16 212.88 459.87 203.41 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Node.js Express HTTP Load Test OpenBenchmarking.org Requests Per Second, More Is Better Node.js Express HTTP Load Test Fedora 35 Beta Ubuntu 21.10 Oct1 CentOS Stream Debian 11 2K 4K 6K 8K 10K SE +/- 50.24, N = 7 SE +/- 83.00, N = 15 SE +/- 137.27, N = 3 SE +/- 36.07, N = 3 5453 7318 10069 4676 1. Fedora 35 Beta: Nodejs 2. Ubuntu 21.10 Oct1: Nodejs
v12.22.5 3. CentOS Stream: Nodejs 4. Debian 11: Nodejs
v12.22.5
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 80 160 240 320 400 SE +/- 0.94, N = 3 SE +/- 1.56, N = 3 SE +/- 2.13, N = 4 SE +/- 2.57, N = 3 SE +/- 1.31, N = 10 172.78 178.73 178.98 361.28 169.81 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
JPEG XL libjxl Input: JPEG - Encode Speed: 7 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: JPEG - Encode Speed: 7 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.19, N = 3 SE +/- 0.38, N = 3 SE +/- 0.22, N = 3 40.42 40.72 49.82 84.36 45.67 -pthread -pthread 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 13 26 39 52 65 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 SE +/- 0.10, N = 3 SE +/- 0.59, N = 3 SE +/- 0.34, N = 4 30.12 31.70 34.27 58.91 30.51 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 9K 18K 27K 36K 45K SE +/- 165.30, N = 3 SE +/- 166.82, N = 3 SE +/- 293.17, N = 15 SE +/- 210.36, N = 3 SE +/- 144.43, N = 3 20482.79 39438.33 20496.77 22965.29 39866.27 -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.1.0
PyPerformance Benchmark: python_startup OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: python_startup Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 16.1 16.8 19.9 10.4 17.1
SVT-HEVC Tuning: 7 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 70 140 210 280 350 SE +/- 1.78, N = 3 SE +/- 1.40, N = 3 SE +/- 1.94, N = 3 SE +/- 2.83, N = 7 SE +/- 0.59, N = 3 168.45 174.24 176.05 304.17 170.57 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
JPEG XL libjxl Input: JPEG - Encode Speed: 8 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: JPEG - Encode Speed: 8 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 SE +/- 0.19, N = 3 SE +/- 0.05, N = 3 15.68 16.39 17.57 27.99 17.24 -pthread -pthread 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Writes Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 60K 120K 180K 240K 300K SE +/- 1278.73, N = 12 SE +/- 1249.39, N = 12 SE +/- 1662.83, N = 5 SE +/- 2434.46, N = 3 SE +/- 1090.13, N = 12 155829 150942 150708 266050 149220
NAS Parallel Benchmarks Test / Class: IS.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 700 1400 2100 2800 3500 SE +/- 15.01, N = 15 SE +/- 34.41, N = 3 SE +/- 22.51, N = 5 SE +/- 4.08, N = 3 SE +/- 33.49, N = 3 1878.50 3023.76 2040.29 2034.48 3243.03 -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.1.0
Timed Wasmer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 1.0.2 Time To Compile Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 15 30 45 60 75 SE +/- 0.28, N = 3 SE +/- 0.81, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 SE +/- 0.92, N = 3 44.81 57.20 42.78 39.76 66.40 1. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 1.0931 2.1862 3.2793 4.3724 5.4655 SE +/- 0.009, N = 3 SE +/- 0.010, N = 3 SE +/- 0.008, N = 3 SE +/- 0.057, N = 3 SE +/- 0.012, N = 3 2.952 2.944 3.036 4.858 2.944 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
JPEG XL libjxl Input: PNG - Encode Speed: 7 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: PNG - Encode Speed: 7 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 7.24 7.30 8.15 11.76 8.15 -pthread -pthread 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Memory Copying Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 3K 6K 9K 12K 15K SE +/- 14.60, N = 3 SE +/- 9.05, N = 3 SE +/- 9.88, N = 3 SE +/- 8.58, N = 3 SE +/- 5.65, N = 3 13309.14 13002.21 13314.82 8417.59 8288.19 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
PyPerformance Benchmark: 2to3 OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: 2to3 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 120 240 360 480 600 SE +/- 0.67, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 524 515 556 353 511
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Forking Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20K 40K 60K 80K 100K SE +/- 285.04, N = 3 SE +/- 167.74, N = 3 SE +/- 1208.39, N = 3 SE +/- 160.06, N = 3 SE +/- 422.96, N = 11 69885.73 66266.20 90874.21 63225.90 57939.36 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: MEMFD Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 900 1800 2700 3600 4500 SE +/- 29.44, N = 3 SE +/- 42.24, N = 3 SE +/- 40.65, N = 3 SE +/- 3.48, N = 3 SE +/- 36.52, N = 3 3895.47 3770.87 4285.00 2749.64 3915.95 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Savina Reactors.IO Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 5K 10K 15K 20K 25K SE +/- 237.18, N = 9 SE +/- 137.67, N = 3 SE +/- 192.41, N = 7 SE +/- 55.04, N = 3 SE +/- 204.63, N = 3 21211.3 21433.8 20867.5 14116.6 21142.6 MIN: 19932.49 / MAX: 35430.03 MIN: 21161.41 / MAX: 34384.9 MIN: 19932.9 / MAX: 33572.83 MIN: 14031.69 / MAX: 21891.76 MIN: 20799.58 / MAX: 33299.35
Appleseed Scene: Emily OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Emily Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 40 80 120 160 200 178.07 178.45 175.53 122.62 179.06
Appleseed Scene: Disney Material OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Disney Material Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20 40 60 80 100 83.07 81.86 83.34 57.70 81.75
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: MMAP Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 1000 2000 3000 4000 5000 SE +/- 31.54, N = 3 SE +/- 35.72, N = 3 SE +/- 27.26, N = 3 SE +/- 2.62, N = 3 SE +/- 33.87, N = 3 4719.58 3838.76 4697.27 3330.78 4173.70 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Finagle HTTP Requests Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed Debian 11 2K 4K 6K 8K 10K SE +/- 87.49, N = 5 SE +/- 24.54, N = 3 SE +/- 45.95, N = 10 SE +/- 69.11, N = 3 8137.7 7753.2 5995.9 5967.3 MIN: 7124.61 / MAX: 9249.1 MIN: 6906.75 / MAX: 8669.47 MIN: 4960.89 / MAX: 6791.24 MIN: 5074.56 / MAX: 6653.57
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Semaphores Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 3M 6M 9M 12M 15M SE +/- 59631.32, N = 15 SE +/- 13361.80, N = 3 SE +/- 10836.85, N = 3 SE +/- 38536.31, N = 3 SE +/- 4341.08, N = 3 9177476.81 9460605.86 10452079.79 12432372.72 10070481.32 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 80K 160K 240K 320K 400K SE +/- 963.93, N = 3 SE +/- 1662.75, N = 3 SE +/- 1321.31, N = 3 SE +/- 2582.50, N = 3 SE +/- 663.09, N = 3 290145 306548 354644 392910 351256 1. (CXX) g++ options: -pipe -lpthread
PyPerformance Benchmark: raytrace OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: raytrace Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 140 280 420 560 700 SE +/- 1.15, N = 3 SE +/- 2.40, N = 3 SE +/- 2.40, N = 3 SE +/- 2.73, N = 3 525 487 627 618 468
SVT-HEVC Tuning: 1 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 9 18 27 36 45 SE +/- 0.15, N = 3 SE +/- 0.38, N = 3 SE +/- 0.12, N = 3 SE +/- 0.23, N = 3 SE +/- 0.15, N = 3 30.32 29.74 30.04 38.01 29.69 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 9K 18K 27K 36K 45K SE +/- 428.49, N = 4 SE +/- 460.68, N = 15 SE +/- 291.38, N = 3 SE +/- 212.25, N = 3 SE +/- 400.47, N = 15 40682.0 42433.4 39087.2 33155.5 37543.7
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: SENDFILE Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 300K 600K 900K 1200K 1500K SE +/- 2812.18, N = 3 SE +/- 3029.22, N = 3 SE +/- 3465.96, N = 3 SE +/- 11609.98, N = 3 SE +/- 4503.68, N = 3 1225384.87 1197035.98 1231359.88 978142.73 1149339.09 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 200K 400K 600K 800K 1000K SE +/- 927.32, N = 3 SE +/- 2476.56, N = 3 SE +/- 6997.85, N = 3 SE +/- 1059.76, N = 3 SE +/- 354.15, N = 3 761666 784757 628171 640144 727869
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Vector Math Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 60K 120K 180K 240K 300K SE +/- 874.10, N = 3 SE +/- 1011.65, N = 3 SE +/- 530.40, N = 3 SE +/- 2638.87, N = 3 SE +/- 388.10, N = 3 277479.38 278044.70 278157.65 223730.72 250969.79 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 1000 2000 3000 4000 5000 SE +/- 39.90, N = 3 SE +/- 42.45, N = 9 SE +/- 25.06, N = 3 SE +/- 1.82, N = 3 SE +/- 13.48, N = 3 4130.78 4538.95 3940.13 3667.43 3892.99 MIN: 3864.4 / MAX: 6001.74 MIN: 3855.45 / MAX: 5657.12 MIN: 3844.12 / MAX: 5377.02 MIN: 3628.97 / MAX: 4137.58 MIN: 3811.63 / MAX: 5185.41 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 16 32 48 64 80 SE +/- 0.24, N = 3 SE +/- 0.29, N = 3 SE +/- 0.35, N = 3 SE +/- 0.22, N = 3 SE +/- 0.24, N = 3 59.77 62.55 72.65 60.54 58.90 -ldl -lpthread -ldl -lpthread 1. (CC) gcc options: -O2 -lz
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 300 600 900 1200 1500 SE +/- 1.20, N = 3 SE +/- 3.53, N = 3 SE +/- 2.60, N = 3 SE +/- 2.73, N = 3 SE +/- 1.33, N = 3 1157 1011 1205 1184 978
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 11 22 33 44 55 SE +/- 0.14, N = 3 SE +/- 0.48, N = 3 SE +/- 0.02, N = 3 SE +/- 0.16, N = 3 SE +/- 0.17, N = 3 45.73 46.58 44.16 45.53 38.07 1. (CXX) g++ options: -O2 -lOpenCL
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.14 Time To Compile Fedora 35 Beta Ubuntu 21.10 Oct1 CentOS Stream Debian 11 6 12 18 24 30 SE +/- 0.31, N = 14 SE +/- 0.27, N = 14 SE +/- 0.19, N = 7 SE +/- 0.27, N = 14 25.86 25.28 21.34 24.17
LevelDB Benchmark: Hot Read OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Hot Read Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 50 100 150 200 250 SE +/- 1.49, N = 12 SE +/- 2.09, N = 3 SE +/- 1.86, N = 3 SE +/- 1.42, N = 3 SE +/- 1.54, N = 3 205.52 182.26 179.59 191.58 171.14 -lpthread -lpthread 1. (CXX) g++ options: -O3 -lsnappy
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 15.11 Time To Compile Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20 40 60 80 100 SE +/- 1.08, N = 3 SE +/- 0.20, N = 3 SE +/- 0.23, N = 3 SE +/- 0.35, N = 3 98.28 101.80 84.77 98.02
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 Fedora 35 Beta Ubuntu 21.10 Oct1 Debian 11 16 32 48 64 80 SE +/- 0.57, N = 3 SE +/- 0.35, N = 3 SE +/- 0.64, N = 3 61.62 73.74 73.39
GNU GMP GMPbench Total Time OpenBenchmarking.org GMPbench Score, More Is Better GNU GMP GMPbench 6.2.1 Total Time Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 1000 2000 3000 4000 5000 3776.8 4503.0 3828.4 4228.8 4519.0 1. (CC) gcc options: -O3 -fomit-frame-pointer -lm
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: vgg16 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 8 16 24 32 40 SE +/- 0.53, N = 3 SE +/- 0.69, N = 3 SE +/- 0.38, N = 3 SE +/- 0.69, N = 8 SE +/- 0.24, N = 3 29.02 28.66 31.60 32.48 27.17 MIN: 27.43 / MAX: 51.97 MIN: 26.84 / MAX: 44.36 MIN: 30.64 / MAX: 53.99 -pthread - MIN: 28.92 / MAX: 58.14 -pthread - MIN: 26.12 / MAX: 28.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: googlenet Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 6 12 18 24 30 SE +/- 0.69, N = 3 SE +/- 0.55, N = 3 SE +/- 0.26, N = 3 SE +/- 0.34, N = 8 SE +/- 0.13, N = 3 23.54 22.40 21.51 23.16 19.78 MIN: 21.5 / MAX: 30.2 MIN: 20.93 / MAX: 33.61 MIN: 20.58 / MAX: 51.46 -pthread - MIN: 21.49 / MAX: 50.91 -pthread - MIN: 18.78 / MAX: 40.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Crypto Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 3K 6K 9K 12K 15K SE +/- 121.13, N = 3 SE +/- 121.61, N = 3 SE +/- 69.86, N = 3 SE +/- 4.10, N = 3 SE +/- 48.53, N = 3 14074.74 13702.95 14258.27 12280.97 13482.89 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Timed LLVM Compilation Build System: Unix Makefiles OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 12.0 Build System: Unix Makefiles Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 40 80 120 160 200 SE +/- 0.64, N = 3 SE +/- 0.16, N = 3 SE +/- 1.74, N = 3 SE +/- 1.12, N = 3 SE +/- 0.91, N = 3 199.62 200.79 199.27 174.51 202.12
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v2-v2 - Model: mobilenet-v2 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 3 6 9 12 15 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.12, N = 3 SE +/- 0.10, N = 8 SE +/- 0.05, N = 3 11.99 11.85 11.82 11.57 10.37 MIN: 11.5 / MAX: 58.74 MIN: 11.35 / MAX: 27.09 MIN: 11.3 / MAX: 61.71 -pthread - MIN: 11 / MAX: 55.53 -pthread - MIN: 10.03 / MAX: 14.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed LLVM Compilation Build System: Unix Makefiles OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 13.0 Build System: Unix Makefiles Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 50 100 150 200 250 SE +/- 0.84, N = 3 SE +/- 1.46, N = 3 SE +/- 1.62, N = 3 SE +/- 1.32, N = 3 SE +/- 1.43, N = 3 206.06 205.28 206.83 179.81 207.30
JPEG XL libjxl Input: PNG - Encode Speed: 8 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: PNG - Encode Speed: 8 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.171 0.342 0.513 0.684 0.855 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.66 0.66 0.76 0.73 0.73 -pthread -pthread 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Matrix Math Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 70K 140K 210K 280K 350K SE +/- 1378.00, N = 3 SE +/- 1006.85, N = 3 SE +/- 962.16, N = 3 SE +/- 434.21, N = 3 SE +/- 905.61, N = 3 290055.81 292343.66 294254.02 333721.31 300488.84 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: efficientnet-b0 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 4 8 12 16 20 SE +/- 0.16, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 SE +/- 0.11, N = 8 SE +/- 0.03, N = 3 14.48 14.32 14.13 14.22 12.64 MIN: 13.79 / MAX: 36.23 MIN: 13.59 / MAX: 30 MIN: 13.49 / MAX: 81.11 -pthread - MIN: 13.29 / MAX: 33.65 -pthread - MIN: 12.1 / MAX: 44.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mnasnet Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 3 6 9 12 15 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.10, N = 8 SE +/- 0.03, N = 3 11.43 11.28 11.17 10.96 10.01 MIN: 10.82 / MAX: 63.44 MIN: 10.8 / MAX: 21.3 MIN: 10.76 / MAX: 34.43 -pthread - MIN: 10.39 / MAX: 62.48 -pthread - MIN: 9.71 / MAX: 13.86 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v3-v3 - Model: mobilenet-v3 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 3 6 9 12 15 SE +/- 0.16, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.19, N = 8 SE +/- 0.05, N = 3 11.66 11.56 11.43 11.51 10.22 MIN: 11.15 / MAX: 87.96 MIN: 11.08 / MAX: 27.23 MIN: 10.89 / MAX: 35.32 -pthread - MIN: 10.62 / MAX: 337.93 -pthread - MIN: 9.82 / MAX: 33.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Read Fedora 35 Beta Ubuntu 21.10 Oct1 CentOS Stream Debian 11 80M 160M 240M 320M 400M SE +/- 3798260.75, N = 15 SE +/- 3508008.09, N = 3 SE +/- 4560879.38, N = 3 SE +/- 509834.26, N = 3 369206119 324373890 332140763 356094496 -lpthread -lgflags -lpthread 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: shufflenet-v2 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.02, N = 2 SE +/- 0.16, N = 8 SE +/- 0.04, N = 3 11.67 11.70 11.84 11.79 10.42 MIN: 11.33 / MAX: 33.34 MIN: 11.31 / MAX: 27.37 MIN: 11.48 / MAX: 35.95 -pthread - MIN: 10.93 / MAX: 148.29 -pthread - MIN: 10.12 / MAX: 11.64 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
LZ4 Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Compression Speed Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 11 22 33 44 55 SE +/- 0.21, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 43.83 45.33 46.33 49.78 49.48 1. (CC) gcc options: -O3
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: CPU Stress Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 30K 60K 90K 120K 150K SE +/- 348.55, N = 3 SE +/- 304.54, N = 3 SE +/- 209.48, N = 3 SE +/- 621.44, N = 3 SE +/- 236.03, N = 3 126640.32 126295.66 127127.44 111992.39 125486.27 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OSPray Demo: Magnetic Reconnection - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: SciVis Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.93, N = 12 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 111.11 110.19 111.11 125.00 111.11 MIN: 35.71 MIN: 38.46 / MAX: 111.11 MIN: 71.43 / MAX: 125 MIN: 90.91 MIN: 71.43 / MAX: 125
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 16 32 48 64 80 SE +/- 0.23, N = 3 SE +/- 0.19, N = 3 SE +/- 1.01, N = 3 SE +/- 0.36, N = 3 SE +/- 0.23, N = 3 64.76 66.34 71.84 73.40 66.40 MIN: 58.83 / MAX: 86.81 MIN: 60.19 / MAX: 87.34 MIN: 62.35 / MAX: 92.25 MIN: 63.6 / MAX: 93.58 MIN: 59.27 / MAX: 88.49
LZ4 Compression Compression Level: 9 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Compression Speed Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 11 22 33 44 55 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 43.19 44.32 45.51 48.94 48.49 1. (CC) gcc options: -O3
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet50 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 6 12 18 24 30 SE +/- 0.46, N = 3 SE +/- 0.33, N = 3 SE +/- 0.18, N = 3 SE +/- 0.37, N = 8 SE +/- 0.09, N = 3 26.02 26.27 26.94 27.30 24.13 MIN: 24.31 / MAX: 109.88 MIN: 24.88 / MAX: 49.42 MIN: 25.98 / MAX: 51.2 -pthread - MIN: 24.85 / MAX: 139.12 -pthread - MIN: 23.19 / MAX: 28.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20 40 60 80 100 SE +/- 0.58, N = 3 SE +/- 0.49, N = 3 SE +/- 1.11, N = 3 SE +/- 0.91, N = 3 SE +/- 0.86, N = 15 81.2 80.2 87.1 89.9 86.6 1. (CC) gcc options: -O3 -pthread -lz
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20K 40K 60K 80K 100K SE +/- 951.18, N = 3 SE +/- 910.87, N = 3 SE +/- 597.75, N = 15 SE +/- 444.21, N = 3 SE +/- 1009.97, N = 3 83310.2 84493.3 82944.6 75554.9 76318.2
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: blazeface Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 2 4 6 8 10 SE +/- 0.14, N = 3 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 8 SE +/- 0.02, N = 3 6.96 6.99 6.69 6.70 6.30 MIN: 6.49 / MAX: 80.35 MIN: 6.64 / MAX: 21.95 MIN: 6.39 / MAX: 29.72 -pthread - MIN: 6.44 / MAX: 16.25 -pthread - MIN: 6.08 / MAX: 8.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mobilenet Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 5 10 15 20 25 SE +/- 0.29, N = 3 SE +/- 0.10, N = 3 SE +/- 0.12, N = 3 SE +/- 0.18, N = 8 SE +/- 0.19, N = 3 21.31 21.26 21.27 21.12 19.34 MIN: 20.36 / MAX: 43.83 MIN: 20.42 / MAX: 37.9 MIN: 20.31 / MAX: 44.32 -pthread - MIN: 19.92 / MAX: 289.63 -pthread - MIN: 18.64 / MAX: 42.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 12.0 Build System: Ninja Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.73, N = 3 SE +/- 0.49, N = 3 SE +/- 0.37, N = 3 SE +/- 0.32, N = 3 131.31 129.94 131.77 119.74 126.84
OSPray Demo: San Miguel - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 90.91 90.91 90.91 100.00 90.91 MIN: 76.92 / MAX: 100 MIN: 62.5 / MAX: 100 MIN: 66.67 / MAX: 100 MIN: 55.56 / MAX: 111.11 MIN: 55.56 / MAX: 100
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: squeezenet_ssd Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 6 12 18 24 30 SE +/- 0.31, N = 3 SE +/- 0.03, N = 3 SE +/- 0.17, N = 3 SE +/- 0.17, N = 8 SE +/- 0.12, N = 3 23.85 24.03 23.74 24.79 22.69 MIN: 22.87 / MAX: 53.7 MIN: 23.37 / MAX: 39.78 MIN: 23.05 / MAX: 47.6 -pthread - MIN: 23.67 / MAX: 211.3 -pthread - MIN: 22.1 / MAX: 42.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 13.0 Build System: Ninja Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 30 60 90 120 150 SE +/- 0.50, N = 3 SE +/- 0.18, N = 3 SE +/- 0.33, N = 3 SE +/- 0.42, N = 3 SE +/- 0.06, N = 3 132.32 131.76 133.64 122.39 129.38
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: regnety_400m Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 9 18 27 36 45 SE +/- 0.69, N = 3 SE +/- 0.26, N = 3 SE +/- 0.37, N = 3 SE +/- 0.33, N = 8 SE +/- 0.15, N = 3 37.97 37.70 37.77 38.04 34.93 MIN: 36.19 / MAX: 116.99 MIN: 36.75 / MAX: 54 MIN: 36.58 / MAX: 220.13 -pthread - MIN: 36.43 / MAX: 179.96 -pthread - MIN: 34.15 / MAX: 36.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Compression Speed Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 11 22 33 44 55 SE +/- 0.09, N = 3 SE +/- 0.12, N = 3 SE +/- 0.33, N = 15 SE +/- 0.26, N = 3 SE +/- 0.46, N = 3 44.6 44.1 48.0 45.1 44.7 1. (CC) gcc options: -O3 -pthread -lz
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenet-v1-1.0 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.4489 0.8978 1.3467 1.7956 2.2445 SE +/- 0.028, N = 15 SE +/- 0.011, N = 3 SE +/- 0.014, N = 15 SE +/- 0.012, N = 15 SE +/- 0.029, N = 15 1.946 1.844 1.995 1.902 1.930 MIN: 1.64 / MAX: 3.96 MIN: 1.79 / MAX: 2.06 MIN: 1.68 / MAX: 4.11 MIN: 1.82 / MAX: 3.51 MIN: 1.72 / MAX: 4.16 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.7763 1.5526 2.3289 3.1052 3.8815 SE +/- 0.00672, N = 3 SE +/- 0.00691, N = 3 SE +/- 0.00222, N = 3 SE +/- 0.00324, N = 3 SE +/- 0.00195, N = 3 3.23502 3.29168 3.23059 3.45007 3.19617 MIN: 3.03 MIN: 3.1 MIN: 3.03 MIN: 3.27 MIN: 3.01 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
LZ4 Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Decompression Speed Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 1600 3200 4800 6400 8000 SE +/- 4.43, N = 3 SE +/- 8.27, N = 3 SE +/- 22.71, N = 3 SE +/- 0.99, N = 3 SE +/- 2.94, N = 3 7136.8 7193.7 7153.2 6931.1 7475.4 1. (CC) gcc options: -O3
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: CPU-Only Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20 40 60 80 100 SE +/- 0.45, N = 3 SE +/- 0.41, N = 3 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.26, N = 3 109.60 108.68 105.32 102.30 104.77
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 11K 22K 33K 44K 55K SE +/- 133.66, N = 3 SE +/- 429.09, N = 3 SE +/- 634.50, N = 3 SE +/- 386.51, N = 3 SE +/- 291.16, N = 3 49724.4 50687.8 49661.2 47473.5 47638.2
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 150K 300K 450K 600K 750K SE +/- 2809.76, N = 3 SE +/- 8598.94, N = 3 SE +/- 4289.94, N = 3 SE +/- 1001.80, N = 3 SE +/- 5246.96, N = 3 710372 710386 693874 667444 668386
Chaos Group V-RAY Mode: CPU OpenBenchmarking.org vsamples, More Is Better Chaos Group V-RAY 5 Mode: CPU Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 14K 28K 42K 56K 70K SE +/- 313.94, N = 3 SE +/- 366.67, N = 3 SE +/- 474.67, N = 3 SE +/- 613.64, N = 3 SE +/- 590.80, N = 3 63528 63275 66690 67330 66940
OpenVKL Benchmark: vklBenchmark ISPC OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.0 Benchmark: vklBenchmark ISPC Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 60 120 180 240 300 SE +/- 0.00, N = 3 SE +/- 1.00, N = 3 SE +/- 1.53, N = 3 SE +/- 1.00, N = 3 SE +/- 1.76, N = 3 271 268 274 285 275 MIN: 19 / MAX: 6480 MIN: 17 / MAX: 6328 MIN: 19 / MAX: 6475 MIN: 17 / MAX: 7189 MIN: 19 / MAX: 6523
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: inception-v3 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 6 12 18 24 30 SE +/- 0.13, N = 15 SE +/- 0.07, N = 3 SE +/- 0.07, N = 15 SE +/- 0.09, N = 15 SE +/- 0.09, N = 15 22.30 21.61 22.33 22.97 22.47 MIN: 20.26 / MAX: 74.34 MIN: 21.21 / MAX: 49.74 MIN: 20.68 / MAX: 57.27 MIN: 22.18 / MAX: 69.91 MIN: 21.6 / MAX: 43.78 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
ONNX Runtime Model: bertsquad-10 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: bertsquad-10 - Device: OpenMP CPU Fedora 35 Beta Ubuntu 21.10 Oct1 150 300 450 600 750 SE +/- 11.30, N = 12 SE +/- 11.11, N = 12 687 648 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
ONNX Runtime Model: shufflenet-v2-10 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: shufflenet-v2-10 - Device: OpenMP CPU Fedora 35 Beta Ubuntu 21.10 Oct1 3K 6K 9K 12K 15K SE +/- 75.14, N = 3 SE +/- 76.96, N = 3 12630 11943 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Malloc Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 300M 600M 900M 1200M 1500M SE +/- 1327143.46, N = 3 SE +/- 1275570.42, N = 3 SE +/- 2944431.91, N = 3 SE +/- 1279759.82, N = 3 SE +/- 703865.20, N = 3 1399403296.43 1407281590.86 1410532156.00 1445156501.92 1477294638.69 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: PartialTweets Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.8618 1.7236 2.5854 3.4472 4.309 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.63 3.71 3.65 3.83 3.78 -pthread -pthread 1. (CXX) g++ options: -O3
LZ4 Compression Compression Level: 9 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Decompression Speed Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 1600 3200 4800 6400 8000 SE +/- 6.85, N = 3 SE +/- 4.39, N = 3 SE +/- 2.18, N = 3 SE +/- 89.50, N = 3 SE +/- 1.03, N = 3 7149.6 7210.7 7115.3 7099.9 7484.3 1. (CC) gcc options: -O3
OpenSSL Algorithm: SHA256 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.0 Algorithm: SHA256 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 13000M 26000M 39000M 52000M 65000M SE +/- 82194161.08, N = 3 SE +/- 72337526.63, N = 3 SE +/- 25810526.81, N = 3 SE +/- 9327770.93, N = 3 SE +/- 115644012.55, N = 3 59198740233 58476634107 58447799270 57290460430 60273469430 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: resnet-v2-50 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 5 10 15 20 25 SE +/- 0.06, N = 15 SE +/- 0.04, N = 3 SE +/- 0.14, N = 15 SE +/- 0.07, N = 15 SE +/- 0.11, N = 15 19.12 18.79 18.85 19.44 19.76 MIN: 17.96 / MAX: 58.25 MIN: 18.18 / MAX: 41.67 MIN: 17.43 / MAX: 35.37 MIN: 18.69 / MAX: 35.88 MIN: 18.11 / MAX: 71.44 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: CPU-Only Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 7 14 21 28 35 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.11, N = 3 29.86 29.53 29.20 28.43 28.82
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 100 200 300 400 500 SE +/- 1.50, N = 3 SE +/- 1.75, N = 3 SE +/- 0.99, N = 3 SE +/- 1.00, N = 3 SE +/- 1.27, N = 3 449.10 449.01 438.64 438.77 427.83 MIN: 434.71 MIN: 432.78 MIN: 424.55 MIN: 423.39 MIN: 410.56 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2021.2 Implementation: MPI CPU - Input: water_GMX50_bare Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 3 6 9 12 15 SE +/- 0.019, N = 3 SE +/- 0.101, N = 4 SE +/- 0.031, N = 3 SE +/- 0.012, N = 3 SE +/- 0.012, N = 3 9.049 9.038 9.076 8.719 9.150 -pthread 1. (CXX) g++ options: -O3
SecureMark Benchmark: SecureMark-TLS OpenBenchmarking.org marks, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 50K 100K 150K 200K 250K SE +/- 167.73, N = 3 SE +/- 89.85, N = 3 SE +/- 2712.83, N = 4 SE +/- 496.73, N = 3 SE +/- 71.66, N = 3 228244 223678 229049 234638 230202 1. (CC) gcc options: -pedantic -O3
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 500K 1000K 1500K 2000K 2500K SE +/- 1803.26, N = 3 SE +/- 1699.80, N = 3 SE +/- 647.62, N = 3 SE +/- 6794.07, N = 3 SE +/- 990.76, N = 3 2387052.98 2282293.38 2393687.00 2333336.34 2372626.66 1. (CC) gcc options: -O2 -lrt" -lrt
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 130K 260K 390K 520K 650K SE +/- 1535.68, N = 3 SE +/- 1247.99, N = 3 SE +/- 1116.87, N = 3 SE +/- 4828.20, N = 3 SE +/- 319.86, N = 3 594597 595226 596888 580283 570385
Appleseed Scene: Material Tester OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Material Tester Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 40 80 120 160 200 194.07 190.72 189.12 192.68 185.48
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: DistinctUserID Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.9698 1.9396 2.9094 3.8792 4.849 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 4.16 4.22 4.12 4.23 4.31 -pthread -pthread 1. (CXX) g++ options: -O3
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 150 300 450 600 750 SE +/- 2.89, N = 3 SE +/- 1.86, N = 3 SE +/- 2.84, N = 3 SE +/- 3.03, N = 3 SE +/- 0.94, N = 3 684.35 680.89 664.14 664.92 654.35 MIN: 657.34 MIN: 656.45 MIN: 635.07 MIN: 630.69 MIN: 624.72 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Crown Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 14 28 42 56 70 SE +/- 0.33, N = 3 SE +/- 0.41, N = 3 SE +/- 0.63, N = 3 SE +/- 0.26, N = 3 SE +/- 0.33, N = 3 62.13 64.49 64.89 63.70 63.88 MIN: 56.23 / MAX: 79.17 MIN: 57 / MAX: 81.16 MIN: 58.06 / MAX: 79.85 MIN: 57.86 / MAX: 80.85 MIN: 56.98 / MAX: 80.8
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 13 Total Time Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 40M 80M 120M 160M 200M SE +/- 2135846.30, N = 3 SE +/- 1179013.88, N = 15 SE +/- 1975441.20, N = 4 SE +/- 1352078.98, N = 15 SE +/- 497776.78, N = 3 180079720 176162289 183803628 183054178 178004391 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20 40 60 80 100 SE +/- 0.68, N = 3 SE +/- 0.73, N = 3 SE +/- 0.97, N = 3 SE +/- 0.12, N = 3 SE +/- 0.65, N = 3 74.02 76.86 74.83 73.94 73.83 MIN: 73.16 / MAX: 108.66 MIN: 74.8 / MAX: 111.63 MIN: 73.54 / MAX: 109.89 MIN: 73.36 / MAX: 74.71 MIN: 72.31 / MAX: 109.8 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
Git Time To Complete Common Git Commands OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 14 28 42 56 70 SE +/- 0.17, N = 3 SE +/- 0.06, N = 3 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 SE +/- 0.23, N = 3 62.33 60.82 60.79 61.82 59.89 1. Fedora 35 Beta: git version 2.32.0 2. Ubuntu 21.10 Oct1: git version 2.32.0 3. openSUSE Tumbleweed: git version 2.33.0 4. CentOS Stream: git version 2.27.0 5. Debian 11: git version 2.30.2
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Decompression Speed Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 600 1200 1800 2400 3000 SE +/- 7.22, N = 3 SE +/- 4.30, N = 3 SE +/- 3.12, N = 15 SE +/- 5.00, N = 3 SE +/- 5.00, N = 3 2729.4 2689.5 2743.4 2637.9 2731.6 1. (CC) gcc options: -O3 -pthread -lz
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Glibc C String Functions Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 2M 4M 6M 8M 10M SE +/- 37222.74, N = 3 SE +/- 23928.16, N = 3 SE +/- 79663.70, N = 5 SE +/- 54028.00, N = 3 SE +/- 36016.76, N = 3 7933317.10 7962720.71 7905372.49 7842753.42 8138767.03 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: Kostya Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.5693 1.1386 1.7079 2.2772 2.8465 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 2.44 2.45 2.50 2.44 2.53 -pthread -pthread 1. (CXX) g++ options: -O3
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 600 1200 1800 2400 3000 SE +/- 2.68, N = 3 SE +/- 1.25, N = 3 SE +/- 1.88, N = 3 SE +/- 5.02, N = 3 SE +/- 5.25, N = 15 2658.2 2646.4 2671.0 2578.4 2620.1 1. (CC) gcc options: -O3 -pthread -lz
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: CPU-Only Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 16 32 48 64 80 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 SE +/- 0.16, N = 3 SE +/- 0.06, N = 3 73.64 73.41 72.44 71.29 71.32
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20 40 60 80 100 SE +/- 1.36, N = 3 SE +/- 0.69, N = 3 SE +/- 0.39, N = 3 SE +/- 0.58, N = 3 SE +/- 1.17, N = 4 105.49 107.67 108.91 108.52 107.03 MIN: 83.1 / MAX: 112.05 MIN: 93.4 / MAX: 112.5 MIN: 98.82 / MAX: 113.45 MIN: 86.28 / MAX: 113.47 MIN: 84.11 / MAX: 114.18
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20 40 60 80 100 SE +/- 0.43, N = 3 SE +/- 0.88, N = 3 SE +/- 0.76, N = 3 SE +/- 0.84, N = 3 SE +/- 0.60, N = 3 81.93 83.04 83.50 82.47 84.45 MIN: 66.46 / MAX: 92.34 MIN: 68.13 / MAX: 92.75 MIN: 69.84 / MAX: 93.01 MIN: 65.97 / MAX: 92.09 MIN: 69.37 / MAX: 93.71
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.0631 0.1262 0.1893 0.2524 0.3155 SE +/- 0.00098, N = 3 SE +/- 0.00056, N = 3 SE +/- 0.00043, N = 3 SE +/- 0.00046, N = 3 SE +/- 0.00049, N = 3 0.28029 0.27847 0.27899 0.27436 0.27334
OSPray Demo: San Miguel - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: Path Tracer Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 10.42 10.42 10.64 10.56 10.68 MIN: 8.85 / MAX: 10.64 MIN: 8.93 / MAX: 10.64 MIN: 9.35 / MAX: 10.87 MIN: 7.35 / MAX: 10.87 MIN: 7.46 / MAX: 10.87
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.6615 1.323 1.9845 2.646 3.3075 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 2.87 2.94 2.90 2.94 2.91
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: LargeRandom Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.1958 0.3916 0.5874 0.7832 0.979 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.86 0.85 0.87 0.85 0.86 -pthread -pthread 1. (CXX) g++ options: -O3
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 9 18 27 36 45 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 SE +/- 0.16, N = 3 39.68 40.03 39.88 40.59 40.20 -lmpi_cxx -lmpi_cxx -pthread -lmpi_cxx -pthread -lmpi_cxx 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Glibc Qsort Data Sorting Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 200 400 600 800 1000 SE +/- 3.60, N = 3 SE +/- 2.76, N = 3 SE +/- 4.75, N = 3 SE +/- 1.46, N = 3 SE +/- 1.67, N = 3 978.29 964.65 980.62 979.66 984.25 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.4793 0.9586 1.4379 1.9172 2.3965 SE +/- 0.01900, N = 3 SE +/- 0.02486, N = 3 SE +/- 0.01577, N = 3 SE +/- 0.00068, N = 3 SE +/- 0.01815, N = 3 2.13007 2.12241 2.12178 2.09939 2.10779 MIN: 2.03 MIN: 2.03 MIN: 2.03 MIN: 2.03 MIN: 2.03 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Google SynthMark Test: VoiceMark_100 OpenBenchmarking.org Voices, More Is Better Google SynthMark 20201109 Test: VoiceMark_100 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 120 240 360 480 600 SE +/- 5.97, N = 3 SE +/- 4.10, N = 3 SE +/- 0.76, N = 3 SE +/- 0.18, N = 3 SE +/- 1.68, N = 3 543.43 550.53 543.04 547.05 549.78 1. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast
ONNX Runtime Model: yolov4 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: yolov4 - Device: OpenMP CPU Fedora 35 Beta Ubuntu 21.10 Oct1 120 240 360 480 600 SE +/- 3.82, N = 3 SE +/- 3.17, N = 3 548 541 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 4K 8K 12K 16K 20K SE +/- 117.95, N = 3 SE +/- 89.21, N = 3 SE +/- 136.84, N = 3 SE +/- 33.51, N = 3 SE +/- 98.91, N = 3 17706.5 17798.2 17744.0 17701.1 17850.1 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 80 160 240 320 400 SE +/- 0.23, N = 3 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 SE +/- 0.52, N = 3 SE +/- 0.27, N = 3 366.32 368.22 365.69 367.41 366.34 MIN: 365.87 / MAX: 368.51 MIN: 366.43 / MAX: 370.9 MIN: 365.33 / MAX: 366.76 MIN: 366.07 / MAX: 368.88 MIN: 365.35 / MAX: 369.09 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.8181 1.6362 2.4543 3.2724 4.0905 SE +/- 0.03712, N = 13 SE +/- 0.03462, N = 13 SE +/- 0.03316, N = 14 SE +/- 0.01063, N = 3 SE +/- 0.03711, N = 13 3.63442 3.61481 3.63231 3.63602 3.61866 MIN: 3.5 MIN: 3.49 MIN: 3.5 MIN: 3.53 MIN: 3.49 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 300K 600K 900K 1200K 1500K SE +/- 1029.19, N = 3 SE +/- 92.73, N = 3 SE +/- 843.27, N = 3 SE +/- 707.09, N = 3 SE +/- 6122.66, N = 3 1187546.8 1191217.9 1193325.7 1186729.8 1191300.7 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Stress-NG Test: RdRand OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: RdRand Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 140K 280K 420K 560K 700K SE +/- 2353.71, N = 3 SE +/- 2315.78, N = 3 SE +/- 2321.64, N = 3 SE +/- 192.36, N = 3 SE +/- 2218.48, N = 3 666960.21 666871.13 666960.00 669870.10 666684.30 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
ONNX Runtime Model: fcn-resnet101-11 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: fcn-resnet101-11 - Device: OpenMP CPU Fedora 35 Beta Ubuntu 21.10 Oct1 100 200 300 400 500 SE +/- 3.28, N = 3 SE +/- 5.35, N = 3 474 476 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 200 400 600 800 1000 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.29, N = 3 SE +/- 292.35, N = 12 SE +/- 0.14, N = 3 18.29 16.27 50.65 1152.34 21.27 -lpthread -lrt -ldl 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Write Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 9K 18K 27K 36K 45K SE +/- 15.32, N = 3 SE +/- 28.91, N = 3 SE +/- 57.41, N = 3 SE +/- 14071.07, N = 12 SE +/- 161.00, N = 3 27335 30731 9872 39695 23512 -lpthread -lrt -ldl -lpthread -lrt -ldl 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20 40 60 80 100 SE +/- 0.002, N = 7 SE +/- 0.003, N = 12 SE +/- 0.009, N = 12 SE +/- 11.761, N = 12 SE +/- 0.003, N = 3 0.267 0.269 0.282 86.115 0.263 -lpthread -lrt -ldl 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Only Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 400K 800K 1200K 1600K 2000K SE +/- 17223.30, N = 7 SE +/- 21829.42, N = 12 SE +/- 55194.33, N = 12 SE +/- 218826.32, N = 12 SE +/- 20778.74, N = 3 1875522 1859821 1794700 329430 1902066 -lpthread -lrt -ldl -lpthread -lrt -ldl 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Apache HTTP Server Concurrent Requests: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 1000 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 40K 80K 120K 160K 200K SE +/- 2706.83, N = 15 SE +/- 4897.09, N = 15 SE +/- 2044.57, N = 3 SE +/- 616.87, N = 3 SE +/- 481.53, N = 15 59961.48 106682.07 206714.39 119249.02 39217.70 -pthread -pthread 1. (CC) gcc options: -shared -fPIC -O2
nginx Concurrent Requests: 1000 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 1000 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 50K 100K 150K 200K 250K SE +/- 1273.13, N = 3 SE +/- 1255.09, N = 3 SE +/- 1394.69, N = 3 SE +/- 1420.39, N = 3 SE +/- 5779.71, N = 12 216774.28 191181.80 208713.17 200333.56 204201.05 -ldl -lpthread -ldl -lpthread 1. (CC) gcc options: -lcrypt -lz -O3 -march=native
nginx Concurrent Requests: 500 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 500 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 50K 100K 150K 200K 250K SE +/- 1347.25, N = 3 SE +/- 1647.60, N = 8 SE +/- 1280.05, N = 3 SE +/- 855.20, N = 3 SE +/- 4340.13, N = 14 213760.91 189131.99 206192.34 196943.93 200482.69 -ldl -lpthread -ldl -lpthread 1. (CC) gcc options: -lcrypt -lz -O3 -march=native
nginx Concurrent Requests: 200 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 200 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 40K 80K 120K 160K 200K SE +/- 1162.78, N = 3 SE +/- 9412.84, N = 12 SE +/- 2237.18, N = 4 SE +/- 589.10, N = 3 SE +/- 273.43, N = 3 204764.97 168716.20 195437.72 188445.93 95361.92 -ldl -lpthread -ldl -lpthread 1. (CC) gcc options: -lcrypt -lz -O3 -march=native
PyPerformance Benchmark: pickle_pure_python OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pickle_pure_python Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 150 300 450 600 750 SE +/- 2.91, N = 3 SE +/- 11.89, N = 15 SE +/- 17.37, N = 15 SE +/- 11.13, N = 15 516 604 705 540 555
PyPerformance Benchmark: django_template OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: django_template Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20 40 60 80 100 SE +/- 0.55, N = 6 SE +/- 1.57, N = 15 SE +/- 0.43, N = 3 SE +/- 0.03, N = 3 SE +/- 1.23, N = 12 55.8 59.1 67.9 77.8 58.0
PyPerformance Benchmark: regex_compile OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: regex_compile Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 50 100 150 200 250 SE +/- 0.67, N = 3 SE +/- 4.40, N = 15 SE +/- 2.18, N = 8 SE +/- 1.50, N = 10 206 215 248 208 198
PyPerformance Benchmark: crypto_pyaes OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: crypto_pyaes Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 40 80 120 160 200 SE +/- 1.20, N = 3 SE +/- 3.15, N = 15 SE +/- 3.19, N = 15 SE +/- 0.33, N = 3 SE +/- 2.42, N = 15 137 133 173 113 125
PyPerformance Benchmark: json_loads OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: json_loads Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 7 14 21 28 35 SE +/- 0.15, N = 3 SE +/- 0.63, N = 12 SE +/- 0.63, N = 15 SE +/- 0.00, N = 3 SE +/- 0.33, N = 14 26.2 30.5 31.8 26.3 31.5
PyPerformance Benchmark: pathlib OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pathlib Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 7 14 21 28 35 SE +/- 0.00, N = 3 SE +/- 0.37, N = 13 SE +/- 0.48, N = 15 SE +/- 0.03, N = 3 SE +/- 0.48, N = 15 28.7 26.1 29.4 20.3 24.9
PyPerformance Benchmark: nbody OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: nbody Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 40 80 120 160 200 SE +/- 1.59, N = 5 SE +/- 3.55, N = 15 SE +/- 4.08, N = 15 SE +/- 0.33, N = 3 SE +/- 1.92, N = 15 161 152 191 125 138
PyPerformance Benchmark: float OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: float Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 3.67, N = 15 SE +/- 3.40, N = 15 SE +/- 0.33, N = 3 SE +/- 2.84, N = 15 128 148 174 120 149
PyPerformance Benchmark: chaos OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: chaos Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 40 80 120 160 200 SE +/- 1.20, N = 3 SE +/- 1.45, N = 3 SE +/- 3.05, N = 15 SE +/- 0.33, N = 3 SE +/- 2.32, N = 15 132 136 177 126 128
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 100 200 300 400 500 SE +/- 2.74, N = 3 SE +/- 9.53, N = 15 SE +/- 4.98, N = 15 SE +/- 0.27, N = 3 SE +/- 3.53, N = 3 396.22 442.00 383.43 365.19 375.46 MIN: 370.89 / MAX: 614 MIN: 372.63 / MAX: 552.29 MIN: 368.91 / MAX: 634.27 MIN: 362.78 / MAX: 370.76 MIN: 369.96 / MAX: 529.5 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: yolov4-tiny Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 7 14 21 28 35 SE +/- 0.90, N = 3 SE +/- 0.32, N = 3 SE +/- 0.13, N = 3 SE +/- 0.48, N = 8 SE +/- 0.18, N = 3 25.41 25.15 25.69 27.63 24.33 MIN: 23.83 / MAX: 184.26 MIN: 23.85 / MAX: 84.28 MIN: 24.71 / MAX: 109.58 -pthread - MIN: 24.53 / MAX: 494.65 -pthread - MIN: 23.21 / MAX: 31.45 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: alexnet Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 3 6 9 12 15 SE +/- 0.19, N = 3 SE +/- 0.42, N = 3 SE +/- 0.13, N = 3 SE +/- 0.16, N = 8 SE +/- 0.02, N = 3 9.69 9.35 8.53 10.62 8.61 MIN: 9.11 / MAX: 10.82 MIN: 8.28 / MAX: 26.19 MIN: 8.1 / MAX: 10.08 -pthread - MIN: 9.47 / MAX: 62.33 -pthread - MIN: 8.26 / MAX: 9.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet18 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 4 8 12 16 20 SE +/- 0.51, N = 3 SE +/- 0.56, N = 3 SE +/- 0.17, N = 3 SE +/- 0.45, N = 8 SE +/- 0.10, N = 3 14.58 14.09 13.35 14.97 13.19 MIN: 13.23 / MAX: 37.67 MIN: 12.98 / MAX: 28.95 MIN: 12.86 / MAX: 37.15 -pthread - MIN: 13.28 / MAX: 140.62 -pthread - MIN: 12.41 / MAX: 20.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: MobileNetV2_224 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.6507 1.3014 1.9521 2.6028 3.2535 SE +/- 0.041, N = 15 SE +/- 0.030, N = 3 SE +/- 0.053, N = 15 SE +/- 0.021, N = 15 SE +/- 0.027, N = 15 2.795 2.731 2.876 2.720 2.892 MIN: 2.34 / MAX: 9.08 MIN: 2.59 / MAX: 3.08 MIN: 2.29 / MAX: 7.07 MIN: 2.36 / MAX: 6.88 MIN: 2.6 / MAX: 5.43 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: SqueezeNetV1.0 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 1.1387 2.2774 3.4161 4.5548 5.6935 SE +/- 0.145, N = 15 SE +/- 0.011, N = 3 SE +/- 0.060, N = 15 SE +/- 0.138, N = 15 SE +/- 0.067, N = 15 4.672 4.421 5.061 4.559 4.712 MIN: 3.84 / MAX: 10.88 MIN: 4.35 / MAX: 6.74 MIN: 3.87 / MAX: 12.43 MIN: 3.96 / MAX: 13.96 MIN: 4.08 / MAX: 10.82 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: squeezenetv1.1 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.8732 1.7464 2.6196 3.4928 4.366 SE +/- 0.051, N = 15 SE +/- 0.132, N = 3 SE +/- 0.059, N = 15 SE +/- 0.053, N = 15 SE +/- 0.052, N = 15 3.840 3.770 3.760 3.881 3.828 MIN: 3.24 / MAX: 7.6 MIN: 3.32 / MAX: 7.99 MIN: 3.24 / MAX: 7.68 MIN: 3.55 / MAX: 6.35 MIN: 3.36 / MAX: 8.14 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenetV3 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.4788 0.9576 1.4364 1.9152 2.394 SE +/- 0.043, N = 15 SE +/- 0.007, N = 3 SE +/- 0.033, N = 15 SE +/- 0.026, N = 15 SE +/- 0.029, N = 15 1.994 1.949 2.069 2.128 1.967 MIN: 1.61 / MAX: 4.44 MIN: 1.87 / MAX: 2.15 MIN: 1.65 / MAX: 4.52 MIN: 1.97 / MAX: 3.92 MIN: 1.77 / MAX: 4.42 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: System V Message Passing Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 1.2M 2.4M 3.6M 4.8M 6M SE +/- 108355.40, N = 12 SE +/- 28851.31, N = 9 SE +/- 6099.95, N = 3 SE +/- 3904.14, N = 3 SE +/- 18167.97, N = 5 4098551.27 3578020.47 3045985.32 5648012.33 1764395.47 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Context Switching Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 5M 10M 15M 20M 25M SE +/- 44099.63, N = 3 SE +/- 62581.85, N = 3 SE +/- 216887.99, N = 3 SE +/- 302996.85, N = 12 SE +/- 334039.54, N = 15 4484674.85 5272694.80 24430641.91 11482636.32 17724791.00 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: CPU Cache Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.15, N = 7 SE +/- 0.16, N = 15 SE +/- 0.22, N = 3 SE +/- 0.26, N = 15 15.93 16.10 16.45 16.26 16.61 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: IO_uring OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: IO_uring Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed Debian 11 70K 140K 210K 280K 350K SE +/- 3586.50, N = 15 SE +/- 355.13, N = 3 SE +/- 1647.54, N = 15 SE +/- 2549.77, N = 3 336629.20 91421.67 75341.64 258560.94 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: NUMA Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 10 20 30 40 50 SE +/- 0.46, N = 6 SE +/- 0.16, N = 3 SE +/- 0.44, N = 15 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 45.25 44.94 7.11 10.33 5.17 -latomic -latomic -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.0668 0.1336 0.2004 0.2672 0.334 SE +/- 0.004, N = 3 SE +/- 0.008, N = 12 SE +/- 0.037, N = 12 SE +/- 0.006, N = 12 SE +/- 0.005, N = 15 0.252 0.269 0.297 0.255 0.264 -lpthread -lrt -ldl -lpthread -lrt -ldl 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 200K 400K 600K 800K 1000K SE +/- 13107.59, N = 3 SE +/- 24147.73, N = 12 SE +/- 53555.93, N = 12 SE +/- 20865.08, N = 12 SE +/- 17790.96, N = 15 991583 937156 912058 984861 953348 -lpthread -lrt -ldl -lpthread -lrt -ldl 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 9K 18K 27K 36K 45K SE +/- 64.05, N = 3 SE +/- 690.99, N = 15 SE +/- 365.12, N = 15 SE +/- 20.26, N = 3 SE +/- 436.15, N = 15 37665.7 41710.6 37729.3 33738.8 37688.1
oneDNN Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 0.8925 1.785 2.6775 3.57 4.4625 SE +/- 0.09261, N = 15 SE +/- 0.67784, N = 12 SE +/- 0.07237, N = 15 SE +/- 0.00524, N = 3 SE +/- 0.00864, N = 3 2.99045 3.96654 2.77560 1.73826 1.72474 MIN: 1.97 MIN: 2.09 MIN: 1.76 MIN: 1.61 MIN: 1.58 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 2 4 6 8 10 SE +/- 0.83207, N = 15 SE +/- 0.68437, N = 15 SE +/- 0.70452, N = 15 SE +/- 0.00479, N = 3 SE +/- 0.03144, N = 3 6.50917 6.50961 6.63389 3.00178 2.98827 MIN: 3.15 MIN: 3.46 MIN: 3.1 MIN: 2.85 MIN: 2.83 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Decompression Speed Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 700 1400 2100 2800 3500 SE +/- 2.92, N = 3 SE +/- 97.11, N = 13 SE +/- 59.69, N = 15 SE +/- 6.29, N = 15 SE +/- 316.10, N = 3 3104.6 2917.4 3026.3 2987.1 2732.7 1. (CC) gcc options: -O3 -pthread -lz
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Compression Speed Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 600 1200 1800 2400 3000 SE +/- 11.57, N = 3 SE +/- 26.80, N = 15 SE +/- 18.62, N = 15 SE +/- 47.99, N = 15 SE +/- 17.22, N = 3 2026.8 2034.8 1946.5 2763.2 1947.7 1. (CC) gcc options: -O3 -pthread -lz
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark Bayes Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 300 600 900 1200 1500 SE +/- 6.57, N = 15 SE +/- 13.05, N = 3 SE +/- 5.25, N = 3 SE +/- 11.98, N = 15 SE +/- 9.44, N = 3 1017.8 973.5 1171.8 523.7 992.4 MIN: 579.09 / MAX: 1750.79 MIN: 563.96 / MAX: 2393.66 MIN: 760.63 / MAX: 1711.61 MIN: 303.94 / MAX: 839.15 MIN: 596.32 / MAX: 1325.39
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradebeans Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 4K 8K 12K 16K 20K SE +/- 54.13, N = 4 SE +/- 104.31, N = 4 SE +/- 59.52, N = 4 SE +/- 153.25, N = 6 SE +/- 66.29, N = 4 16993 16793 15573 3712 16382
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 1200 2400 3600 4800 6000 SE +/- 161.36, N = 20 SE +/- 123.29, N = 20 SE +/- 140.36, N = 20 SE +/- 25.45, N = 4 SE +/- 153.62, N = 16 5386 4727 5022 3663 5519
DaCapo Benchmark Java Test: H2 OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 2K 4K 6K 8K 10K SE +/- 92.48, N = 4 SE +/- 60.40, N = 4 SE +/- 86.76, N = 7 SE +/- 59.07, N = 17 SE +/- 34.71, N = 4 10776 10704 9579 3706 9850
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 2 4 6 8 10 SE +/- 0.195, N = 12 SE +/- 0.076, N = 3 SE +/- 0.071, N = 15 SE +/- 0.096, N = 4 SE +/- 0.119, N = 15 8.179 8.282 8.178 7.965 7.834 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP Leukocyte OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Leukocyte Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 12 24 36 48 60 SE +/- 0.77, N = 15 SE +/- 0.54, N = 15 SE +/- 1.06, N = 15 SE +/- 0.55, N = 15 SE +/- 1.08, N = 15 48.92 53.42 51.07 45.74 55.25 1. (CXX) g++ options: -O2 -lOpenCL
NAS Parallel Benchmarks Test / Class: FT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C Fedora 35 Beta Ubuntu 21.10 Oct1 openSUSE Tumbleweed CentOS Stream Debian 11 20K 40K 60K 80K 100K SE +/- 61.28, N = 3 SE +/- 1097.42, N = 4 SE +/- 260.09, N = 3 SE +/- 29.54, N = 3 SE +/- 1555.67, N = 15 36258.08 91713.25 37549.01 38711.61 93063.10 -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -pthread -pthread -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.1.0
Phoronix Test Suite v10.8.4