Xeon Platinum 8380 Fedora

2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on openSUSE Tumbleweed 20210929 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2110034-TJ-2110022TJ12
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

Timed Code Compilation 5 Tests
C/C++ Compiler Tests 14 Tests
Compression Tests 3 Tests
CPU Massive 25 Tests
Creator Workloads 15 Tests
Cryptography 2 Tests
Database Test Suite 5 Tests
Encoding 4 Tests
Fortran Tests 2 Tests
Game Development 4 Tests
Go Language Tests 2 Tests
HPC - High Performance Computing 11 Tests
Java 2 Tests
Common Kernel Benchmarks 7 Tests
Machine Learning 6 Tests
Molecular Dynamics 2 Tests
MPI Benchmarks 3 Tests
Multi-Core 28 Tests
NVIDIA GPU Compute 5 Tests
Intel oneAPI 5 Tests
OpenMPI Tests 4 Tests
Programmer / Developer System Benchmarks 11 Tests
Python 2 Tests
Renderers 4 Tests
Scientific Computing 2 Tests
Server 11 Tests
Server CPU Tests 21 Tests
Single-Threaded 6 Tests
Video Encoding 4 Tests
Common Workstation Benchmarks 4 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Fedora 35 Beta
September 30 2021
  18 Hours, 4 Minutes
Ubuntu 21.10 Oct1
October 01 2021
  17 Hours, 48 Minutes
openSUSE Tumbleweed
October 02 2021
  18 Hours, 46 Minutes
Invert Hiding All Results Option
  18 Hours, 13 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


Xeon Platinum 8380 FedoraProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelCompilerFile-SystemScreen ResolutionDesktopDisplay ServerVulkanFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads)Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS)Intel Device 0998504GB7682GB INTEL SSDPF2KX076TZASPEEDVE2282 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFPFedora Linux 355.14.7-300.fc35.x86_64 (x86_64)GCC 11.2.1 20210728xfs1920x1080Ubuntu 21.105.13.0-16-generic (x86_64)GNOME Shell 40.5X Server1.1.182GCC 11.2.0ext47682GB INTEL SSDPF2KX076TZ + 15GB Ultra USB 3.0openSUSE Tumbleweed 202109295.14.6-1-default (x86_64)KDE PlasmaX Server 1.20.13GCC 11.2.1 20210816 [revision 056e324ce46a7924b5cf10f61010cf9dd2ca10e9]btrfsOpenBenchmarking.orgKernel Details- Fedora 35 Beta: Transparent Huge Pages: madvise- Ubuntu 21.10 Oct1: Transparent Huge Pages: madvise- openSUSE Tumbleweed: Transparent Huge Pages: alwaysEnvironment 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 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: 4096Processor Details- Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd0002a0Java 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)Python Details- Fedora 35 Beta: Python 3.10.0rc2- Ubuntu 21.10 Oct1: Python 3.9.7- openSUSE Tumbleweed: Python 3.8.12Security 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

Fedora 35 BetaUbuntu 21.10 Oct1openSUSE TumbleweedResult OverviewPhoronix Test Suite100%155%211%266%322%Apache HTTP ServerNAS Parallel BenchmarksPostgreSQL pgbenchTimed Wasmer CompilationPHPBench7-Zip CompressionPyPerformanceSQLite SpeedtestPyBenchGNU GMP GMPbenchnginxJPEG XL libjxlLevelDBDaCapo BenchmarkStress-NGTNNSVT-AV1RenaissanceoneDNNChaos Group V-RAYMobile Neural NetworkEmbreeCoremarkStockfishRodiniaApache CassandraSVT-VP9Zstd CompressionBlenderLZ4 CompressionGitIntel Open Image DenoiseSecureMarkOpenVKLNCNNSVT-HEVCx265Google SynthMarkAppleseedOSPrayHigh Performance Conjugate GradientTimed LLVM CompilationsimdjsonNAMDGROMACSOpenSSLTensorFlow Lite

Xeon Platinum 8380 Fedorastress-ng: Context Switchingapache: 200npb: SP.Bnpb: LU.Cnpb: BT.Cnpb: SP.Cnpb: MG.Cnpb: EP.Dpgbench: 100 - 500 - Read Write - Average Latencypgbench: 100 - 500 - Read Writepgbench: 100 - 250 - Read Write - Average Latencypgbench: 100 - 250 - Read Writeapache: 100npb: FT.Cnpb: CG.Cnpb: IS.Drocksdb: Rand Fill Syncstress-ng: Forkingrenaissance: Finagle HTTP Requestsnode-express-loadtest: build-wasmer: Time To Compilepyperformance: raytracephpbench: PHP Benchmark Suitepyperformance: python_startupjpegxl: JPEG - 7stress-ng: MMAPnginx: 100compress-7zip: Compress Speed Testsqlite-speedtest: Timed Time - Size 1,000renaissance: Apache Spark Bayesbuild-godot: Time To Compilegmpbench: Total Timepybench: Total For Average Test Timestnn: CPU - DenseNetjpegxl: PNG - 8leveldb: Hot Readstress-ng: Semaphoresrocksdb: Rand Readsvt-av1: Preset 8 - Bosphorus 4Kstress-ng: MEMFDnginx: 1000nginx: 500jpegxl: PNG - 7dacapobench: H2jpegxl: JPEG - 8renaissance: Akka Unbalanced Cobwebbed Treeembree: Pathtracer ISPC - Crownncnn: CPU - vgg16ncnn: CPU - googlenetrenaissance: Rand Forestdacapobench: Tradebeanscompress-zstd: 19, Long Mode - Compression Speedcompress-zstd: 19 - Compression Speedtensorflow-lite: Mobilenet Floatmnn: mobilenet-v1-1.0pyperformance: 2to3renaissance: Genetic Algorithm Using Jenetics + Futuresonnx: bertsquad-10 - OpenMP CPUonnx: shufflenet-v2-10 - OpenMP CPUcompress-lz4: 3 - Compression Speedrodinia: OpenMP LavaMDv-ray: CPUcompress-lz4: 9 - Compression Speedcoremark: CoreMark Size 666 - Iterations Per Secondcompress-zstd: 8 - Compression Speedsvt-hevc: 7 - Bosphorus 1080pncnn: CPU - blazefaceembree: Pathtracer - Crownstockfish: Total Timeblender: Barbershop - CPU-Onlystress-ng: Cryptotnn: CPU - SqueezeNet v2svt-vp9: Visual Quality Optimized - Bosphorus 1080pbuild-nodejs: Time To Compilencnn: CPU - resnet50cassandra: Writesmnn: inception-v3svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080px265: Bosphorus 4Kstress-ng: CPU Cacheembree: Pathtracer ISPC - Asian Dragonsvt-av1: Preset 4 - Bosphorus 4Konednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUstress-ng: SENDFILErenaissance: Savina Reactors.IOappleseed: Material Testerrenaissance: Apache Spark ALSgit: Time To Complete Common Git Commandsncnn: CPU - efficientnet-b0simdjson: Kostyaoidn: RT.hdr_alb_nrm.3840x2160simdjson: DistinctUserIDstress-ng: Memory Copyingsecuremark: SecureMark-TLSonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUtensorflow-lite: Inception V4simdjson: LargeRandncnn: CPU - mnasnetbuild-linux-kernel: Time To Compileblender: BMW27 - CPU-Onlyopenvkl: vklBenchmark ISPCsimdjson: PartialTweetsospray: San Miguel - Path Tracertensorflow-lite: SqueezeNetrocksdb: Read Rand Write Randrocksdb: Update Randncnn: CPU-v3-v3 - mobilenet-v3compress-zstd: 19, Long Mode - Decompression Speedsvt-hevc: 1 - Bosphorus 1080pembree: Pathtracer - Asian Dragononednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUtensorflow-lite: NASNet Mobileappleseed: Disney Materialmnn: resnet-v2-50appleseed: Emilyblender: Classroom - CPU-Onlystress-ng: Glibc Qsort Data Sortingncnn: CPU - shufflenet-v2stress-ng: Matrix Mathncnn: CPU-v2-v2 - mobilenet-v2build-llvm: Ninjabuild-llvm: Ninjasynthmark: VoiceMark_100compress-lz4: 9 - Decompression Speedonnx: yolov4 - OpenMP CPUopenssl: SHA256rocksdb: Rand Fillncnn: CPU - squeezenet_ssdrenaissance: ALS Movie Lenscompress-zstd: 19 - Decompression Speedhpcg: ospray: Magnetic Reconnection - SciViscompress-lz4: 3 - Decompression Speedstress-ng: Mallocbuild-llvm: Unix Makefilesbuild-llvm: Unix Makefilesstress-ng: Glibc C String Functionsncnn: CPU - regnety_400mtnn: CPU - SqueezeNet v1.1stress-ng: CPU Stressnamd: ATPase Simulation - 327,506 Atomsonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUopenssl: RSA4096openssl: RSA4096onnx: fcn-resnet101-11 - OpenMP CPUgromacs: MPI CPU - water_GMX50_barex265: Bosphorus 1080ponednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUtensorflow-lite: Inception ResNet V2stress-ng: Vector Mathncnn: CPU - mobilenetstress-ng: RdRandospray: San Miguel - SciVispgbench: 100 - 500 - Read Only - Average Latencypgbench: 100 - 500 - Read Onlyapache: 1000nginx: 200pyperformance: pickle_pure_pythonpyperformance: django_templatepyperformance: regex_compilepyperformance: crypto_pyaespyperformance: json_loadspyperformance: pathlibpyperformance: nbodypyperformance: floatpyperformance: chaostnn: CPU - MobileNet v2ncnn: CPU - yolov4-tinyncnn: CPU - alexnetncnn: CPU - resnet18mnn: MobileNetV2_224mnn: SqueezeNetV1.0mnn: squeezenetv1.1mnn: mobilenetV3stress-ng: System V Message Passingstress-ng: IO_uringstress-ng: NUMApgbench: 100 - 250 - Read Only - Average Latencypgbench: 100 - 250 - Read Onlytensorflow-lite: Mobilenet Quantonednn: IP Shapes 3D - bf16bf16bf16 - CPUonednn: IP Shapes 1D - bf16bf16bf16 - CPUcompress-zstd: 8 - Decompression Speeddacapobench: Jythonrodinia: OpenMP Streamclusterrodinia: OpenMP LeukocyteFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4484674.8539792.0323009.9938573.1948296.1723991.7135006.332725.0118.292273357.6633263040137.6636258.0820482.791878.5010059969885.738137.7545344.81252576166616.140.424719.5888737.6029014559.7701017.861.6223776.811574130.7750.66205.5209177476.8136920611930.1173895.47216774.28213760.917.241077615.6836175.664.755429.0223.541537.21699344.681.240682.01.9465246932.16871263043.8345.7276352843.192387052.9764712026.8168.456.9662.1289180079720109.6014074.7474.022172.7826.0215582922.304207.3411.9115.93105.49492.952684.3491225384.8721211.3194.0726323172.462.32914.482.442.874.1613309.14228244449.1047103720.8611.4325.86329.862713.6310.4249724.48844589632011.662729.430.3281.93273.2350283310.283.06641719.122178.07379673.64978.2911.67290055.8111.99132.315131.309543.4307149.65485919874023310103323.8518146.42658.239.6784111.117136.81399403296.43199.621206.0637933317.1037.97366.322126640.320.280293.6344217706.51187546.84749.04926.992.13007594597277479.3821.31666960.2190.910.267187552259961.48204764.9751655.820613726.228.7161128132396.21925.419.6914.582.7954.6723.8401.9944098551.27336629.2045.250.25299158337665.72.990456.509173104.653868.17948.9185272694.8043438.03113702.80177749.25192540.5091411.13117164.528873.2416.270307318.0393112030630.2391713.2539438.333023.767108666266.207753.2731857.20348778475716.840.723838.7672553.0930654862.546973.573.737450310114538.9540.66182.2639460605.8632437389031.6973770.87191181.80189131.997.301070416.3935585.266.337928.6622.401562.31679344.180.242433.41.8445156835.26481194345.3346.5766327544.322282293.3808472034.8174.246.9964.4883176162289108.6813702.9576.861178.7398.28126.2715094221.614214.1612.0816.10107.67342.944680.8871197035.9821433.8190.7224683095.660.81914.322.452.944.2213002.21223678449.0107103860.8511.2825.28429.532683.7110.4250687.88667619441211.562689.529.7483.04163.2916884493.381.86237818.794178.45403773.41964.6511.70292343.6611.85131.763129.937550.5277210.7541584766341079979924.0318067.62646.440.0345110.197193.71407281590.86200.787205.2817962720.7137.70368.220126295.660.278473.6148117798.21191217.94769.03826.952.12241595226278044.7021.26666871.1390.910.2691859821106682.07168716.2060459.121513330.526.1152148136441.99725.159.3514.092.7314.4213.7701.9493578020.4791421.6744.940.26993715641710.63.966546.509612917.447278.28253.42024430641.91196788.5123088.4538035.5548701.2624132.7136360.072873.1350.652987220.6861209978274.5637549.0120496.772040.2990874.215995.942.77662762817119.949.824697.2778818.8735464472.6521171.83828.412053940.1310.76179.58910452079.7934.2684285.00208713.17206192.348.15957917.5732549.371.839131.6021.511428.81557348.087.139087.21.9955566431.546.3344.1606669045.512393687.0019071946.5176.056.6964.8851183803628105.3214258.2774.832178.98101.79926.9415070822.326212.8812.3016.45108.90603.036664.1411231359.8820867.5189.120033175.660.78814.132.502.904.1213314.82229049438.6426938740.8711.1729.202743.6510.6449661.211.432743.430.0483.50013.2305982944.683.33899418.854175.52580372.44980.6211.84294254.0211.82133.642131.767543.0437115.35844779927023.7418282.92671.039.8828111.117153.21410532156.00199.274206.8277905372.4937.77365.690127127.440.278993.6323117744.01193325.79.07627.062.12178596888278157.6521.27666960.0090.910.2821794700206714.39195437.7270567.924817331.829.4191174177383.43225.698.5313.352.8765.0613.7602.0693045985.3275341.647.110.29791205837729.32.775606.633893026.350228.17851.066OpenBenchmarking.org

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Context SwitchingFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed5M10M15M20M25MSE +/- 44099.63, N = 3SE +/- 62581.85, N = 3SE +/- 216887.99, N = 34484674.855272694.8024430641.91-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Context SwitchingFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4M8M12M16M20MMin: 4396478.22 / Avg: 4484674.85 / Max: 4529363.58Min: 5148461 / Avg: 5272694.8 / Max: 5348000.14Min: 24184064.85 / Avg: 24430641.91 / Max: 24862995.181. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 200Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed40K80K120K160K200KSE +/- 95.62, N = 3SE +/- 196.67, N = 3SE +/- 1483.04, N = 339792.0343438.03196788.511. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 200Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed30K60K90K120K150KMin: 39600.87 / Avg: 39792.03 / Max: 39892.33Min: 43044.9 / Avg: 43438.03 / Max: 43645.64Min: 193848.38 / Avg: 196788.51 / Max: 198597.681. (CC) gcc options: -shared -fPIC -O2

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20K40K60K80K100KSE +/- 145.01, N = 3SE +/- 647.01, N = 3SE +/- 83.49, N = 323009.99113702.8023088.45-lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20K40K60K80K100KMin: 22846.23 / Avg: 23009.99 / Max: 23299.17Min: 112450.57 / Avg: 113702.8 / Max: 114611.39Min: 22938.92 / Avg: 23088.45 / Max: 23227.571. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed40K80K120K160K200KSE +/- 164.50, N = 3SE +/- 2506.74, N = 3SE +/- 166.83, N = 338573.19177749.2538035.55-lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed30K60K90K120K150KMin: 38319.33 / Avg: 38573.19 / Max: 38881.36Min: 172966.75 / Avg: 177749.25 / Max: 181443.22Min: 37726.05 / Avg: 38035.55 / Max: 38298.271. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed40K80K120K160K200KSE +/- 146.19, N = 3SE +/- 703.72, N = 3SE +/- 121.21, N = 348296.17192540.5048701.26-lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed30K60K90K120K150KMin: 48019.73 / Avg: 48296.17 / Max: 48516.83Min: 191270.41 / Avg: 192540.5 / Max: 193700.71Min: 48459.05 / Avg: 48701.26 / Max: 48831.071. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20K40K60K80K100KSE +/- 124.15, N = 3SE +/- 167.98, N = 3SE +/- 56.62, N = 323991.7191411.1324132.71-lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed16K32K48K64K80KMin: 23762.15 / Avg: 23991.71 / Max: 24188.45Min: 91090.64 / Avg: 91411.13 / Max: 91658.62Min: 24021.78 / Avg: 24132.71 / Max: 24207.831. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed30K60K90K120K150KSE +/- 437.96, N = 3SE +/- 163.67, N = 3SE +/- 289.17, N = 1535006.33117164.5236360.07-lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20K40K60K80K100KMin: 34474.47 / Avg: 35006.33 / Max: 35874.98Min: 116862.52 / Avg: 117164.52 / Max: 117424.9Min: 35120.63 / Avg: 36360.07 / Max: 38368.491. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2K4K6K8K10KSE +/- 2.07, N = 3SE +/- 85.67, N = 15SE +/- 22.87, N = 32725.018873.242873.13-lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed15003000450060007500Min: 2722.28 / Avg: 2725.01 / Max: 2729.06Min: 8378.31 / Avg: 8873.24 / Max: 9434Min: 2834.04 / Avg: 2873.13 / Max: 2913.251. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average LatencyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1122334455SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.29, N = 318.2916.2750.651. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average LatencyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1020304050Min: 18.27 / Avg: 18.29 / Max: 18.31Min: 16.25 / Avg: 16.27 / Max: 16.3Min: 50.07 / Avg: 50.65 / Max: 511. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read WriteFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed7K14K21K28K35KSE +/- 15.32, N = 3SE +/- 28.91, N = 3SE +/- 57.41, N = 3273353073198721. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read WriteFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed5K10K15K20K25KMin: 27308.29 / Avg: 27334.68 / Max: 27361.37Min: 30675.61 / Avg: 30731.36 / Max: 30772.52Min: 9803.79 / Avg: 9871.96 / Max: 9986.071. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed510152025SE +/- 0.006, N = 3SE +/- 0.015, N = 3SE +/- 0.173, N = 157.6638.03920.6861. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed510152025Min: 7.65 / Avg: 7.66 / Max: 7.67Min: 8.01 / Avg: 8.04 / Max: 8.07Min: 19.12 / Avg: 20.69 / Max: 21.881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read WriteFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed7K14K21K28K35KSE +/- 24.31, N = 3SE +/- 56.97, N = 3SE +/- 102.11, N = 153263031120120991. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read WriteFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed6K12K18K24K30KMin: 32603.36 / Avg: 32630.44 / Max: 32678.94Min: 31021.08 / Avg: 31119.96 / Max: 31218.42Min: 11428.8 / Avg: 12099.01 / Max: 13078.041. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 100Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20K40K60K80K100KSE +/- 260.52, N = 3SE +/- 155.07, N = 3SE +/- 189.85, N = 340137.6630630.2378274.561. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 100Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed14K28K42K56K70KMin: 39789.21 / Avg: 40137.66 / Max: 40647.36Min: 30404.35 / Avg: 30630.23 / Max: 30927.22Min: 78072.23 / Avg: 78274.56 / Max: 78653.981. (CC) gcc options: -shared -fPIC -O2

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20K40K60K80K100KSE +/- 61.28, N = 3SE +/- 1097.42, N = 4SE +/- 260.09, N = 336258.0891713.2537549.01-lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed16K32K48K64K80KMin: 36186.47 / Avg: 36258.08 / Max: 36380.03Min: 90297.43 / Avg: 91713.25 / Max: 94986.87Min: 37276.08 / Avg: 37549.01 / Max: 38068.971. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed8K16K24K32K40KSE +/- 165.30, N = 3SE +/- 166.82, N = 3SE +/- 293.17, N = 1520482.7939438.3320496.77-lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed7K14K21K28K35KMin: 20164.22 / Avg: 20482.79 / Max: 20718.59Min: 39109.37 / Avg: 39438.33 / Max: 39651.05Min: 17456.82 / Avg: 20496.77 / Max: 22403.61. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed6001200180024003000SE +/- 15.01, N = 15SE +/- 34.41, N = 3SE +/- 22.51, N = 51878.503023.762040.29-lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed5001000150020002500Min: 1768.34 / Avg: 1878.5 / Max: 1942.92Min: 2963.44 / Avg: 3023.76 / Max: 3082.6Min: 1951.74 / Avg: 2040.29 / Max: 2076.771. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.1.0

Facebook RocksDB

This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Random Fill SyncFedora 35 BetaUbuntu 21.10 Oct120K40K60K80K100KSE +/- 127.95, N = 3SE +/- 41.53, N = 310059971086-lpthread1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Random Fill SyncFedora 35 BetaUbuntu 21.10 Oct120K40K60K80K100KMin: 100391 / Avg: 100598.67 / Max: 100832Min: 71038 / Avg: 71086.33 / Max: 711691. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Test: Random Fill Sync

openSUSE Tumbleweed: The test quit with a non-zero exit status.

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: ForkingFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20K40K60K80K100KSE +/- 285.04, N = 3SE +/- 167.74, N = 3SE +/- 1208.39, N = 369885.7366266.2090874.21-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: ForkingFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed16K32K48K64K80KMin: 69316.46 / Avg: 69885.73 / Max: 70196.52Min: 65931.23 / Avg: 66266.2 / Max: 66449.82Min: 88478.25 / Avg: 90874.21 / Max: 92346.321. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Finagle HTTP RequestsFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2K4K6K8K10KSE +/- 87.49, N = 5SE +/- 24.54, N = 3SE +/- 45.95, N = 108137.77753.25995.9MIN: 7124.61 / MAX: 9249.1MIN: 6906.75 / MAX: 8669.47MIN: 4960.89 / MAX: 6791.24
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Finagle HTTP RequestsFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed14002800420056007000Min: 7929.41 / Avg: 8137.69 / Max: 8437.58Min: 7716.12 / Avg: 7753.23 / Max: 7799.59Min: 5850.93 / Avg: 5995.87 / Max: 6324.6

Node.js Express HTTP Load Test

A Node.js Express server with a Node-based loadtest client for facilitating HTTP benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterNode.js Express HTTP Load TestFedora 35 BetaUbuntu 21.10 Oct116003200480064008000SE +/- 50.24, N = 7SE +/- 83.00, N = 15545373181. Fedora 35 Beta: Nodejs2. Ubuntu 21.10 Oct1: Nodejs v12.22.5
OpenBenchmarking.orgRequests Per Second, More Is BetterNode.js Express HTTP Load TestFedora 35 BetaUbuntu 21.10 Oct113002600390052006500Min: 5210 / Avg: 5452.86 / Max: 5604Min: 6493 / Avg: 7318.4 / Max: 75711. Fedora 35 Beta: Nodejs2. Ubuntu 21.10 Oct1: Nodejs v12.22.5

Timed Wasmer Compilation

This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 1.0.2Time To CompileFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1326395265SE +/- 0.28, N = 3SE +/- 0.81, N = 3SE +/- 0.10, N = 344.8157.2042.781. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 1.0.2Time To CompileFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1122334455Min: 44.26 / Avg: 44.81 / Max: 45.12Min: 55.68 / Avg: 57.2 / Max: 58.44Min: 42.63 / Avg: 42.78 / Max: 42.971. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed140280420560700SE +/- 1.15, N = 3SE +/- 2.40, N = 3SE +/- 2.40, N = 3525487627
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed110220330440550Min: 523 / Avg: 525 / Max: 527Min: 484 / Avg: 487.33 / Max: 492Min: 624 / Avg: 627.33 / Max: 632

PHPBench

PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed200K400K600K800K1000KSE +/- 927.32, N = 3SE +/- 2476.56, N = 3SE +/- 6997.85, N = 3761666784757628171
OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed140K280K420K560K700KMin: 759821 / Avg: 761666 / Max: 762752Min: 779870 / Avg: 784757 / Max: 787899Min: 616592 / Avg: 628171.33 / Max: 640769

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startupFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed510152025SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 316.116.819.9
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startupFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed510152025Min: 16.1 / Avg: 16.13 / Max: 16.2Min: 16.7 / Avg: 16.8 / Max: 17Min: 19.9 / Avg: 19.93 / Max: 20

JPEG XL libjxl

The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.5Input: JPEG - Encode Speed: 7Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1122334455SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.19, N = 340.4240.7249.821. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.5Input: JPEG - Encode Speed: 7Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1020304050Min: 40.35 / Avg: 40.42 / Max: 40.46Min: 40.64 / Avg: 40.72 / Max: 40.77Min: 49.5 / Avg: 49.82 / Max: 50.151. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: MMAPFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed10002000300040005000SE +/- 31.54, N = 3SE +/- 35.72, N = 3SE +/- 27.26, N = 34719.583838.764697.27-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: MMAPFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed8001600240032004000Min: 4656.86 / Avg: 4719.58 / Max: 4756.74Min: 3767.32 / Avg: 3838.76 / Max: 3875.12Min: 4642.82 / Avg: 4697.27 / Max: 4726.71. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 100Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20K40K60K80K100KSE +/- 990.65, N = 3SE +/- 279.85, N = 3SE +/- 706.36, N = 388737.6072553.0978818.871. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 100Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed15K30K45K60K75KMin: 87043.73 / Avg: 88737.6 / Max: 90474.62Min: 72254.73 / Avg: 72553.09 / Max: 73112.37Min: 77513.64 / Avg: 78818.87 / Max: 79939.581. (CC) gcc options: -lcrypt -lz -O3 -march=native

7-Zip Compression

This is a test of 7-Zip using p7zip with its integrated benchmark feature or upstream 7-Zip for the Windows x64 build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed80K160K240K320K400KSE +/- 963.93, N = 3SE +/- 1662.75, N = 3SE +/- 1321.31, N = 32901453065483546441. (CXX) g++ options: -pipe -lpthread
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed60K120K180K240K300KMin: 289087 / Avg: 290145.33 / Max: 292070Min: 304064 / Avg: 306548.33 / Max: 309705Min: 352049 / Avg: 354643.67 / Max: 3563751. (CXX) g++ options: -pipe -lpthread

SQLite Speedtest

This is a benchmark of SQLite's speedtest1 benchmark program with an increased problem size of 1,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1632486480SE +/- 0.24, N = 3SE +/- 0.29, N = 3SE +/- 0.35, N = 359.7762.5572.651. (CC) gcc options: -O2 -lz
OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1428425670Min: 59.53 / Avg: 59.77 / Max: 60.25Min: 62.13 / Avg: 62.55 / Max: 63.12Min: 72.29 / Avg: 72.65 / Max: 73.361. (CC) gcc options: -O2 -lz

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark BayesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed30060090012001500SE +/- 6.57, N = 15SE +/- 13.05, N = 3SE +/- 5.25, N = 31017.8973.51171.8MIN: 579.09 / MAX: 1750.79MIN: 563.96 / MAX: 2393.66MIN: 760.63 / MAX: 1711.61
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark BayesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2004006008001000Min: 980.88 / Avg: 1017.76 / Max: 1075.4Min: 948.87 / Avg: 973.51 / Max: 993.26Min: 1163.97 / Avg: 1171.78 / Max: 1181.77

Timed Godot Game Engine Compilation

This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileFedora 35 BetaUbuntu 21.10 Oct11632486480SE +/- 0.57, N = 3SE +/- 0.35, N = 361.6273.74
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileFedora 35 BetaUbuntu 21.10 Oct11428425670Min: 61.02 / Avg: 61.62 / Max: 62.76Min: 73.17 / Avg: 73.74 / Max: 74.39

Time To Compile

openSUSE Tumbleweed: The test quit with a non-zero exit status.

GNU GMP GMPbench

GMPbench is a test of the GNU Multiple Precision Arithmetic (GMP) Library. GMPbench is a single-threaded integer benchmark that leverages the GMP library to stress the CPU with widening integer multiplication. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGMPbench Score, More Is BetterGNU GMP GMPbench 6.2.1Total TimeFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed100020003000400050003776.84503.03828.41. (CC) gcc options: -O3 -fomit-frame-pointer -lm

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed30060090012001500SE +/- 1.20, N = 3SE +/- 3.53, N = 3SE +/- 2.60, N = 3115710111205
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2004006008001000Min: 1155 / Avg: 1156.67 / Max: 1159Min: 1004 / Avg: 1010.67 / Max: 1016Min: 1201 / Avg: 1205.33 / Max: 1210

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed10002000300040005000SE +/- 39.90, N = 3SE +/- 42.45, N = 9SE +/- 25.06, N = 34130.784538.953940.13MIN: 3864.4 / MAX: 6001.74MIN: 3855.45 / MAX: 5657.12MIN: 3844.12 / MAX: 5377.021. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed8001600240032004000Min: 4085.98 / Avg: 4130.77 / Max: 4210.37Min: 4325.81 / Avg: 4538.95 / Max: 4721.43Min: 3899.64 / Avg: 3940.13 / Max: 3985.941. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

JPEG XL libjxl

The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.5Input: PNG - Encode Speed: 8Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.1710.3420.5130.6840.855SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.660.660.761. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.5Input: PNG - Encode Speed: 8Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 0.66 / Avg: 0.66 / Max: 0.66Min: 0.66 / Avg: 0.66 / Max: 0.67Min: 0.75 / Avg: 0.76 / Max: 0.761. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed50100150200250SE +/- 1.49, N = 12SE +/- 2.09, N = 3SE +/- 1.86, N = 3205.52182.26179.591. (CXX) g++ options: -O3 -lsnappy
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200Min: 191.25 / Avg: 205.52 / Max: 210.9Min: 178.5 / Avg: 182.26 / Max: 185.71Min: 176.13 / Avg: 179.59 / Max: 182.511. (CXX) g++ options: -O3 -lsnappy

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: SemaphoresFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2M4M6M8M10MSE +/- 59631.32, N = 15SE +/- 13361.80, N = 3SE +/- 10836.85, N = 39177476.819460605.8610452079.79-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: SemaphoresFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2M4M6M8M10MMin: 8775744.74 / Avg: 9177476.81 / Max: 9550194.31Min: 9436464.73 / Avg: 9460605.86 / Max: 9482602.04Min: 10431898.71 / Avg: 10452079.79 / Max: 10469015.421. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

Facebook RocksDB

This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Random ReadFedora 35 BetaUbuntu 21.10 Oct180M160M240M320M400MSE +/- 3798260.75, N = 15SE +/- 3508008.09, N = 3369206119324373890-lpthread1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Random ReadFedora 35 BetaUbuntu 21.10 Oct160M120M180M240M300MMin: 352353036 / Avg: 369206119.27 / Max: 385198166Min: 317358746 / Avg: 324373889.67 / Max: 3279772831. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Test: Random Read

openSUSE Tumbleweed: The test quit with a non-zero exit status.

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4KFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed816243240SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 330.1231.7034.271. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4KFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed714212835Min: 29.92 / Avg: 30.12 / Max: 30.33Min: 31.49 / Avg: 31.7 / Max: 31.86Min: 34.1 / Avg: 34.27 / Max: 34.431. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: MEMFDFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed9001800270036004500SE +/- 29.44, N = 3SE +/- 42.24, N = 3SE +/- 40.65, N = 33895.473770.874285.00-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: MEMFDFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed7001400210028003500Min: 3836.59 / Avg: 3895.47 / Max: 3925.35Min: 3686.46 / Avg: 3770.87 / Max: 3816.29Min: 4203.78 / Avg: 4285 / Max: 4328.691. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1000Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed50K100K150K200K250KSE +/- 1273.13, N = 3SE +/- 1255.09, N = 3SE +/- 1394.69, N = 3216774.28191181.80208713.171. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1000Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed40K80K120K160K200KMin: 215454.85 / Avg: 216774.28 / Max: 219319.98Min: 188812.63 / Avg: 191181.8 / Max: 193084.75Min: 206556.61 / Avg: 208713.17 / Max: 211323.571. (CC) gcc options: -lcrypt -lz -O3 -march=native

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 500Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed50K100K150K200K250KSE +/- 1347.25, N = 3SE +/- 1647.60, N = 8SE +/- 1280.05, N = 3213760.91189131.99206192.341. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 500Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed40K80K120K160K200KMin: 211128.16 / Avg: 213760.91 / Max: 215574.02Min: 178097.96 / Avg: 189131.99 / Max: 193272.99Min: 204345.45 / Avg: 206192.34 / Max: 208651.141. (CC) gcc options: -lcrypt -lz -O3 -march=native

JPEG XL libjxl

The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.5Input: PNG - Encode Speed: 7Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 37.247.308.151. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.5Input: PNG - Encode Speed: 7Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215Min: 7.1 / Avg: 7.24 / Max: 7.32Min: 7.27 / Avg: 7.3 / Max: 7.33Min: 8.12 / Avg: 8.15 / Max: 8.221. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2K4K6K8K10KSE +/- 92.48, N = 4SE +/- 60.40, N = 4SE +/- 86.76, N = 710776107049579
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2K4K6K8K10KMin: 10512 / Avg: 10776.25 / Max: 10944Min: 10602 / Avg: 10704.25 / Max: 10876Min: 9251 / Avg: 9579.29 / Max: 9972

JPEG XL libjxl

The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.5Input: JPEG - Encode Speed: 8Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed48121620SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 315.6816.3917.571. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.5Input: JPEG - Encode Speed: 8Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed48121620Min: 15.64 / Avg: 15.68 / Max: 15.72Min: 16.38 / Avg: 16.39 / Max: 16.41Min: 17.39 / Avg: 17.57 / Max: 17.671. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Akka Unbalanced Cobwebbed TreeFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed8K16K24K32K40KSE +/- 202.86, N = 3SE +/- 413.78, N = 3SE +/- 99.39, N = 336175.635585.232549.3MIN: 27438.31 / MAX: 36484.8MIN: 28027.65 / MAX: 36206.47MIN: 25316.88 / MAX: 32683.86
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Akka Unbalanced Cobwebbed TreeFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed6K12K18K24K30KMin: 35793.5 / Avg: 36175.6 / Max: 36484.8Min: 34801.09 / Avg: 35585.16 / Max: 36206.47Min: 32355.28 / Avg: 32549.25 / Max: 32683.86

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1632486480SE +/- 0.23, N = 3SE +/- 0.19, N = 3SE +/- 1.01, N = 364.7666.3471.84MIN: 58.83 / MAX: 86.81MIN: 60.19 / MAX: 87.34MIN: 62.35 / MAX: 92.25
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1428425670Min: 64.4 / Avg: 64.76 / Max: 65.18Min: 66.03 / Avg: 66.34 / Max: 66.67Min: 69.83 / Avg: 71.84 / Max: 72.95

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed714212835SE +/- 0.53, N = 3SE +/- 0.69, N = 3SE +/- 0.38, N = 329.0228.6631.60MIN: 27.43 / MAX: 51.97MIN: 26.84 / MAX: 44.36MIN: 30.64 / MAX: 53.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed714212835Min: 27.96 / Avg: 29.02 / Max: 29.56Min: 27.46 / Avg: 28.66 / Max: 29.84Min: 31.07 / Avg: 31.6 / Max: 32.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed612182430SE +/- 0.69, N = 3SE +/- 0.55, N = 3SE +/- 0.26, N = 323.5422.4021.51MIN: 21.5 / MAX: 30.2MIN: 20.93 / MAX: 33.61MIN: 20.58 / MAX: 51.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed510152025Min: 22.17 / Avg: 23.54 / Max: 24.31Min: 21.65 / Avg: 22.4 / Max: 23.47Min: 21.1 / Avg: 21.51 / Max: 221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Random ForestFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed30060090012001500SE +/- 20.09, N = 3SE +/- 9.03, N = 3SE +/- 9.00, N = 31537.21562.31428.8MIN: 1298.32 / MAX: 1875.3MIN: 1381.5 / MAX: 1982.68MIN: 1268.67 / MAX: 1723.65
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Random ForestFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed30060090012001500Min: 1497.07 / Avg: 1537.21 / Max: 1558.77Min: 1544.74 / Avg: 1562.34 / Max: 1574.61Min: 1412.67 / Avg: 1428.83 / Max: 1443.78

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4K8K12K16K20KSE +/- 54.13, N = 4SE +/- 104.31, N = 4SE +/- 59.52, N = 4169931679315573
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3K6K9K12K15KMin: 16890 / Avg: 16993 / Max: 17089Min: 16492 / Avg: 16793 / Max: 16967Min: 15460 / Avg: 15572.75 / Max: 15725

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1122334455SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.33, N = 1544.644.148.01. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1020304050Min: 44.5 / Avg: 44.63 / Max: 44.8Min: 43.9 / Avg: 44.1 / Max: 44.3Min: 46.5 / Avg: 47.95 / Max: 50.21. (CC) gcc options: -O3 -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100SE +/- 0.58, N = 3SE +/- 0.49, N = 3SE +/- 1.11, N = 381.280.287.11. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100Min: 80.1 / Avg: 81.17 / Max: 82.1Min: 79.6 / Avg: 80.23 / Max: 81.2Min: 84.9 / Avg: 87.1 / Max: 88.51. (CC) gcc options: -O3 -pthread -lz

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed9K18K27K36K45KSE +/- 428.49, N = 4SE +/- 460.68, N = 15SE +/- 291.38, N = 340682.042433.439087.2
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed7K14K21K28K35KMin: 39472.5 / Avg: 40682 / Max: 41487.8Min: 39210.5 / Avg: 42433.39 / Max: 45193.8Min: 38642.6 / Avg: 39087.23 / Max: 39635.8

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenet-v1-1.0Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.44890.89781.34671.79562.2445SE +/- 0.028, N = 15SE +/- 0.011, N = 3SE +/- 0.014, N = 151.9461.8441.995MIN: 1.64 / MAX: 3.96MIN: 1.79 / MAX: 2.06MIN: 1.68 / MAX: 4.111. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenet-v1-1.0Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 1.76 / Avg: 1.95 / Max: 2.16Min: 1.82 / Avg: 1.84 / Max: 1.86Min: 1.89 / Avg: 2 / Max: 2.061. (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

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: 2to3Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed120240360480600SE +/- 0.67, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3524515556
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: 2to3Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed100200300400500Min: 523 / Avg: 523.67 / Max: 525Min: 515 / Avg: 515 / Max: 515Min: 556 / Avg: 556 / Max: 556

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Genetic Algorithm Using Jenetics + FuturesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed15003000450060007500SE +/- 12.88, N = 3SE +/- 31.29, N = 3SE +/- 19.46, N = 36932.16835.26431.5MIN: 6640.26 / MAX: 7236.52MIN: 6576.23 / MAX: 7037.67MIN: 6260.99 / MAX: 6606.28
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Genetic Algorithm Using Jenetics + FuturesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed12002400360048006000Min: 6910.53 / Avg: 6932.08 / Max: 6955.08Min: 6776.92 / Avg: 6835.24 / Max: 6884.05Min: 6411.25 / Avg: 6431.53 / Max: 6470.45

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.8.2Model: bertsquad-10 - Device: OpenMP CPUFedora 35 BetaUbuntu 21.10 Oct1150300450600750SE +/- 11.30, N = 12SE +/- 11.11, N = 126876481. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.8.2Model: bertsquad-10 - Device: OpenMP CPUFedora 35 BetaUbuntu 21.10 Oct1120240360480600Min: 636.5 / Avg: 687.33 / Max: 742Min: 600.5 / Avg: 648.21 / Max: 718.51. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Model: bertsquad-10 - Device: OpenMP CPU

openSUSE Tumbleweed: The test quit with a non-zero exit status.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.8.2Model: shufflenet-v2-10 - Device: OpenMP CPUFedora 35 BetaUbuntu 21.10 Oct13K6K9K12K15KSE +/- 75.14, N = 3SE +/- 76.96, N = 312630119431. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.8.2Model: shufflenet-v2-10 - Device: OpenMP CPUFedora 35 BetaUbuntu 21.10 Oct12K4K6K8K10KMin: 12522.5 / Avg: 12629.67 / Max: 12774.5Min: 11811.5 / Avg: 11942.67 / Max: 120781. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Model: shufflenet-v2-10 - Device: OpenMP CPU

openSUSE Tumbleweed: The test quit with a non-zero exit status.

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1122334455SE +/- 0.21, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 343.8345.3346.331. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed918273645Min: 43.42 / Avg: 43.83 / Max: 44.08Min: 45.31 / Avg: 45.33 / Max: 45.34Min: 46.18 / Avg: 46.33 / Max: 46.41. (CC) gcc options: -O3

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1122334455SE +/- 0.14, N = 3SE +/- 0.48, N = 3SE +/- 0.02, N = 345.7346.5844.161. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed918273645Min: 45.47 / Avg: 45.73 / Max: 45.96Min: 46.1 / Avg: 46.58 / Max: 47.53Min: 44.13 / Avg: 44.16 / Max: 44.21. (CXX) g++ options: -O2 -lOpenCL

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5Mode: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed14K28K42K56K70KSE +/- 313.94, N = 3SE +/- 366.67, N = 3SE +/- 474.67, N = 3635286327566690
OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5Mode: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed12K24K36K48K60KMin: 62915 / Avg: 63527.67 / Max: 63953Min: 62646 / Avg: 63274.67 / Max: 63916Min: 65741 / Avg: 66690.33 / Max: 67169

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1020304050SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 343.1944.3245.511. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed918273645Min: 43.15 / Avg: 43.19 / Max: 43.25Min: 44.28 / Avg: 44.32 / Max: 44.34Min: 45.49 / Avg: 45.51 / Max: 45.541. (CC) gcc options: -O3

Coremark

This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed500K1000K1500K2000K2500KSE +/- 1803.26, N = 3SE +/- 1699.80, N = 3SE +/- 647.62, N = 32387052.982282293.382393687.001. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed400K800K1200K1600K2000KMin: 2384056.62 / Avg: 2387052.98 / Max: 2390289.45Min: 2279527 / Avg: 2282293.38 / Max: 2285387.8Min: 2392523.36 / Avg: 2393687 / Max: 2394761.461. (CC) gcc options: -O2 -lrt" -lrt

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Compression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed400800120016002000SE +/- 11.57, N = 3SE +/- 26.80, N = 15SE +/- 18.62, N = 152026.82034.81946.51. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Compression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed400800120016002000Min: 2004.6 / Avg: 2026.77 / Max: 2043.6Min: 1886.1 / Avg: 2034.77 / Max: 2198.5Min: 1814.5 / Avg: 1946.48 / Max: 2075.61. (CC) gcc options: -O3 -pthread -lz

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200SE +/- 1.78, N = 3SE +/- 1.40, N = 3SE +/- 1.94, N = 3168.45174.24176.051. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed306090120150Min: 165.43 / Avg: 168.45 / Max: 171.58Min: 171.97 / Avg: 174.24 / Max: 176.78Min: 173.31 / Avg: 176.05 / Max: 179.81. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazefaceFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 36.966.996.69MIN: 6.49 / MAX: 80.35MIN: 6.64 / MAX: 21.95MIN: 6.39 / MAX: 29.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazefaceFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215Min: 6.75 / Avg: 6.96 / Max: 7.23Min: 6.84 / Avg: 6.99 / Max: 7.13Min: 6.6 / Avg: 6.69 / Max: 6.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: CrownFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1428425670SE +/- 0.33, N = 3SE +/- 0.41, N = 3SE +/- 0.63, N = 362.1364.4964.89MIN: 56.23 / MAX: 79.17MIN: 57 / MAX: 81.16MIN: 58.06 / MAX: 79.85
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: CrownFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1326395265Min: 61.69 / Avg: 62.13 / Max: 62.77Min: 63.7 / Avg: 64.49 / Max: 65.1Min: 63.66 / Avg: 64.89 / Max: 65.72

Stockfish

This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total TimeFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed40M80M120M160M200MSE +/- 2135846.30, N = 3SE +/- 1179013.88, N = 15SE +/- 1975441.20, N = 41800797201761622891838036281. (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
OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total TimeFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed30M60M90M120M150MMin: 177356207 / Avg: 180079720.33 / Max: 184291455Min: 167703893 / Avg: 176162289.2 / Max: 185550612Min: 177915639 / Avg: 183803628 / Max: 1863573101. (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

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-OnlyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100SE +/- 0.45, N = 3SE +/- 0.41, N = 3SE +/- 0.10, N = 3109.60108.68105.32
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-OnlyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100Min: 109.03 / Avg: 109.6 / Max: 110.5Min: 108.19 / Avg: 108.68 / Max: 109.49Min: 105.14 / Avg: 105.32 / Max: 105.5

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: CryptoFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3K6K9K12K15KSE +/- 121.13, N = 3SE +/- 121.61, N = 3SE +/- 69.86, N = 314074.7413702.9514258.27-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: CryptoFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2K4K6K8K10KMin: 13861.35 / Avg: 14074.74 / Max: 14280.76Min: 13470.59 / Avg: 13702.95 / Max: 13881.39Min: 14118.98 / Avg: 14258.27 / Max: 14337.341. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100SE +/- 0.68, N = 3SE +/- 0.73, N = 3SE +/- 0.97, N = 374.0276.8674.83MIN: 73.16 / MAX: 108.66MIN: 74.8 / MAX: 111.63MIN: 73.54 / MAX: 109.891. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1530456075Min: 73.29 / Avg: 74.02 / Max: 75.38Min: 75.64 / Avg: 76.86 / Max: 78.18Min: 73.81 / Avg: 74.83 / Max: 76.781. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200SE +/- 0.94, N = 3SE +/- 1.56, N = 3SE +/- 2.13, N = 4172.78178.73178.981. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed306090120150Min: 171.74 / Avg: 172.78 / Max: 174.65Min: 175.62 / Avg: 178.73 / Max: 180.58Min: 176.04 / Avg: 178.98 / Max: 185.111. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To CompileUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100SE +/- 1.08, N = 3SE +/- 0.20, N = 398.28101.80
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To CompileUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100Min: 96.17 / Avg: 98.28 / Max: 99.7Min: 101.56 / Avg: 101.8 / Max: 102.2

Time To Compile

Fedora 35 Beta: The test quit with a non-zero exit status.

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed612182430SE +/- 0.46, N = 3SE +/- 0.33, N = 3SE +/- 0.18, N = 326.0226.2726.94MIN: 24.31 / MAX: 109.88MIN: 24.88 / MAX: 49.42MIN: 25.98 / MAX: 51.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed612182430Min: 25.11 / Avg: 26.02 / Max: 26.61Min: 25.66 / Avg: 26.27 / Max: 26.81Min: 26.59 / Avg: 26.94 / Max: 27.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Apache Cassandra

This is a benchmark of the Apache Cassandra NoSQL database management system making use of cassandra-stress. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.0Test: WritesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed30K60K90K120K150KSE +/- 1278.73, N = 12SE +/- 1249.39, N = 12SE +/- 1662.83, N = 5155829150942150708
OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.0Test: WritesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed30K60K90K120K150KMin: 149929 / Avg: 155828.5 / Max: 163540Min: 141730 / Avg: 150941.58 / Max: 156179Min: 148271 / Avg: 150708.4 / Max: 157138

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: inception-v3Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed510152025SE +/- 0.13, N = 15SE +/- 0.07, N = 3SE +/- 0.07, N = 1522.3021.6122.33MIN: 20.26 / MAX: 74.34MIN: 21.21 / MAX: 49.74MIN: 20.68 / MAX: 57.271. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: inception-v3Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed510152025Min: 20.98 / Avg: 22.3 / Max: 23.07Min: 21.47 / Avg: 21.61 / Max: 21.7Min: 21.87 / Avg: 22.33 / Max: 22.71. (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

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed50100150200250SE +/- 2.30, N = 3SE +/- 2.62, N = 4SE +/- 0.87, N = 3207.34214.16212.881. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200Min: 203.72 / Avg: 207.34 / Max: 211.62Min: 207.16 / Avg: 214.16 / Max: 219.05Min: 211.4 / Avg: 212.88 / Max: 214.421. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215SE +/- 0.07, N = 3SE +/- 0.13, N = 3SE +/- 0.03, N = 311.9112.0812.30-lnuma1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed48121620Min: 11.78 / Avg: 11.91 / Max: 11.99Min: 11.94 / Avg: 12.08 / Max: 12.33Min: 12.26 / Avg: 12.3 / Max: 12.351. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: CPU CacheFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed48121620SE +/- 0.00, N = 3SE +/- 0.15, N = 7SE +/- 0.16, N = 1515.9316.1016.45-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: CPU CacheFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed48121620Min: 15.93 / Avg: 15.93 / Max: 15.94Min: 15.93 / Avg: 16.1 / Max: 16.97Min: 15.94 / Avg: 16.45 / Max: 17.911. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian DragonFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100SE +/- 1.36, N = 3SE +/- 0.69, N = 3SE +/- 0.39, N = 3105.49107.67108.91MIN: 83.1 / MAX: 112.05MIN: 93.4 / MAX: 112.5MIN: 98.82 / MAX: 113.45
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian DragonFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100Min: 102.78 / Avg: 105.49 / Max: 107.09Min: 106.3 / Avg: 107.67 / Max: 108.42Min: 108.14 / Avg: 108.91 / Max: 109.41

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 4KFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.68311.36622.04932.73243.4155SE +/- 0.009, N = 3SE +/- 0.010, N = 3SE +/- 0.008, N = 32.9522.9443.0361. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 4KFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 2.94 / Avg: 2.95 / Max: 2.97Min: 2.92 / Avg: 2.94 / Max: 2.96Min: 3.02 / Avg: 3.04 / Max: 3.051. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed150300450600750SE +/- 2.89, N = 3SE +/- 1.86, N = 3SE +/- 2.84, N = 3684.35680.89664.14MIN: 657.34MIN: 656.45MIN: 635.071. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed120240360480600Min: 680.18 / Avg: 684.35 / Max: 689.9Min: 678.8 / Avg: 680.89 / Max: 684.6Min: 658.86 / Avg: 664.14 / Max: 668.591. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: SENDFILEFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed300K600K900K1200K1500KSE +/- 2812.18, N = 3SE +/- 3029.22, N = 3SE +/- 3465.96, N = 31225384.871197035.981231359.88-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: SENDFILEFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed200K400K600K800K1000KMin: 1220049.24 / Avg: 1225384.87 / Max: 1229593.25Min: 1191731.61 / Avg: 1197035.98 / Max: 1202223.16Min: 1227870.41 / Avg: 1231359.88 / Max: 1238291.761. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Savina Reactors.IOFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed5K10K15K20K25KSE +/- 237.18, N = 9SE +/- 137.67, N = 3SE +/- 192.41, N = 721211.321433.820867.5MIN: 19932.49 / MAX: 35430.03MIN: 21161.41 / MAX: 34384.9MIN: 19932.9 / MAX: 33572.83
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Savina Reactors.IOFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4K8K12K16K20KMin: 19932.49 / Avg: 21211.34 / Max: 22158.38Min: 21161.41 / Avg: 21433.76 / Max: 21605.06Min: 19932.9 / Avg: 20867.52 / Max: 21393.21

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Material TesterFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200194.07190.72189.12

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark ALSFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed7001400210028003500SE +/- 11.53, N = 3SE +/- 14.07, N = 3SE +/- 14.30, N = 33172.43095.63175.6MIN: 2851.96 / MAX: 3598.58MIN: 2795.88 / MAX: 3565.03MIN: 2949.88 / MAX: 3682.83
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark ALSFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed6001200180024003000Min: 3152.45 / Avg: 3172.38 / Max: 3192.39Min: 3077.62 / Avg: 3095.59 / Max: 3123.33Min: 3154.64 / Avg: 3175.6 / Max: 3202.94

Git

This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git CommandsFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1428425670SE +/- 0.17, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 362.3360.8260.791. Fedora 35 Beta: git version 2.32.02. Ubuntu 21.10 Oct1: git version 2.32.03. openSUSE Tumbleweed: git version 2.33.0
OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git CommandsFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1224364860Min: 62.06 / Avg: 62.33 / Max: 62.64Min: 60.76 / Avg: 60.82 / Max: 60.93Min: 60.5 / Avg: 60.79 / Max: 61.011. Fedora 35 Beta: git version 2.32.02. Ubuntu 21.10 Oct1: git version 2.32.03. openSUSE Tumbleweed: git version 2.33.0

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed48121620SE +/- 0.16, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 314.4814.3214.13MIN: 13.79 / MAX: 36.23MIN: 13.59 / MAX: 30MIN: 13.49 / MAX: 81.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed48121620Min: 14.16 / Avg: 14.48 / Max: 14.65Min: 14.24 / Avg: 14.32 / Max: 14.36Min: 13.95 / Avg: 14.13 / Max: 14.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: KostyaFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.56251.1251.68752.252.8125SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.442.452.501. (CXX) g++ options: -O3
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: KostyaFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 2.44 / Avg: 2.44 / Max: 2.45Min: 2.45 / Avg: 2.45 / Max: 2.46Min: 2.5 / Avg: 2.5 / Max: 2.511. (CXX) g++ options: -O3

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.66151.3231.98452.6463.3075SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 32.872.942.90
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 2.86 / Avg: 2.87 / Max: 2.88Min: 2.93 / Avg: 2.94 / Max: 2.95Min: 2.89 / Avg: 2.9 / Max: 2.92

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: DistinctUserIDFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.94951.8992.84853.7984.7475SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.164.224.121. (CXX) g++ options: -O3
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: DistinctUserIDFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 4.13 / Avg: 4.16 / Max: 4.18Min: 4.21 / Avg: 4.22 / Max: 4.22Min: 4.11 / Avg: 4.12 / Max: 4.121. (CXX) g++ options: -O3

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Memory CopyingFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3K6K9K12K15KSE +/- 14.60, N = 3SE +/- 9.05, N = 3SE +/- 9.88, N = 313309.1413002.2113314.82-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Memory CopyingFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2K4K6K8K10KMin: 13279.99 / Avg: 13309.14 / Max: 13325.24Min: 12988.01 / Avg: 13002.21 / Max: 13019.04Min: 13302.18 / Avg: 13314.82 / Max: 13334.281. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

SecureMark

SecureMark is an objective, standardized benchmarking framework for measuring the efficiency of cryptographic processing solutions developed by EEMBC. SecureMark-TLS is benchmarking Transport Layer Security performance with a focus on IoT/edge computing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed50K100K150K200K250KSE +/- 167.73, N = 3SE +/- 89.85, N = 3SE +/- 2712.83, N = 42282442236782290491. (CC) gcc options: -pedantic -O3
OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed40K80K120K160K200KMin: 227927.47 / Avg: 228244.11 / Max: 228498.34Min: 223498.92 / Avg: 223678.38 / Max: 223776.14Min: 220925.28 / Avg: 229048.84 / Max: 232214.691. (CC) gcc options: -pedantic -O3

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed100200300400500SE +/- 1.50, N = 3SE +/- 1.75, N = 3SE +/- 0.99, N = 3449.10449.01438.64MIN: 434.71MIN: 432.78MIN: 424.551. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed80160240320400Min: 446.89 / Avg: 449.1 / Max: 451.97Min: 445.6 / Avg: 449.01 / Max: 451.38Min: 437.54 / Avg: 438.64 / Max: 440.621. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed150K300K450K600K750KSE +/- 2809.76, N = 3SE +/- 8598.94, N = 3SE +/- 4289.94, N = 3710372710386693874
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed120K240K360K480K600KMin: 704882 / Avg: 710372.33 / Max: 714155Min: 695547 / Avg: 710386 / Max: 725334Min: 687993 / Avg: 693874.33 / Max: 702225

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: LargeRandomFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.19580.39160.58740.78320.979SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.860.850.871. (CXX) g++ options: -O3
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: LargeRandomFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 0.86 / Avg: 0.86 / Max: 0.87Min: 0.85 / Avg: 0.85 / Max: 0.85Min: 0.87 / Avg: 0.87 / Max: 0.871. (CXX) g++ options: -O3

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215SE +/- 0.12, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 311.4311.2811.17MIN: 10.82 / MAX: 63.44MIN: 10.8 / MAX: 21.3MIN: 10.76 / MAX: 34.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215Min: 11.24 / Avg: 11.43 / Max: 11.65Min: 11.21 / Avg: 11.28 / Max: 11.36Min: 11.07 / Avg: 11.17 / Max: 11.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.14Time To CompileFedora 35 BetaUbuntu 21.10 Oct1612182430SE +/- 0.31, N = 14SE +/- 0.27, N = 1425.8625.28
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.14Time To CompileFedora 35 BetaUbuntu 21.10 Oct1612182430Min: 25.36 / Avg: 25.86 / Max: 29.79Min: 24.53 / Avg: 25.28 / Max: 28.47

Time To Compile

openSUSE Tumbleweed: The test quit with a non-zero exit status.

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-OnlyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed714212835SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.05, N = 329.8629.5329.20
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-OnlyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed714212835Min: 29.75 / Avg: 29.86 / Max: 29.92Min: 29.39 / Avg: 29.53 / Max: 29.76Min: 29.11 / Avg: 29.2 / Max: 29.26

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.0Benchmark: vklBenchmark ISPCFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed60120180240300SE +/- 0.00, N = 3SE +/- 1.00, N = 3SE +/- 1.53, N = 3271268274MIN: 19 / MAX: 6480MIN: 17 / MAX: 6328MIN: 19 / MAX: 6475
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.0Benchmark: vklBenchmark ISPCFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed50100150200250Min: 271 / Avg: 271 / Max: 271Min: 267 / Avg: 268 / Max: 270Min: 272 / Avg: 274 / Max: 277

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: PartialTweetsFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.83481.66962.50443.33924.174SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 33.633.713.651. (CXX) g++ options: -O3
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: PartialTweetsFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 3.62 / Avg: 3.63 / Max: 3.64Min: 3.71 / Avg: 3.71 / Max: 3.71Min: 3.63 / Avg: 3.65 / Max: 3.671. (CXX) g++ options: -O3

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 310.4210.4210.64MIN: 8.85 / MAX: 10.64MIN: 8.93 / MAX: 10.64MIN: 9.35 / MAX: 10.87
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215Min: 10.42 / Avg: 10.42 / Max: 10.42Min: 10.42 / Avg: 10.42 / Max: 10.42Min: 10.64 / Avg: 10.64 / Max: 10.64

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed11K22K33K44K55KSE +/- 133.66, N = 3SE +/- 429.09, N = 3SE +/- 634.50, N = 349724.450687.849661.2
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed9K18K27K36K45KMin: 49475.3 / Avg: 49724.37 / Max: 49933Min: 50217.4 / Avg: 50687.8 / Max: 51544.6Min: 48670.6 / Avg: 49661.23 / Max: 50843.4

Facebook RocksDB

This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Read Random Write RandomFedora 35 BetaUbuntu 21.10 Oct1200K400K600K800K1000KSE +/- 1134.93, N = 3SE +/- 632.48, N = 3884458866761-lpthread1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Read Random Write RandomFedora 35 BetaUbuntu 21.10 Oct1150K300K450K600K750KMin: 882235 / Avg: 884458.33 / Max: 885966Min: 865823 / Avg: 866761 / Max: 8679651. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Test: Read Random Write Random

openSUSE Tumbleweed: The test quit with a non-zero exit status.

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Update RandomFedora 35 BetaUbuntu 21.10 Oct120K40K60K80K100KSE +/- 85.06, N = 3SE +/- 68.05, N = 39632094412-lpthread1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Update RandomFedora 35 BetaUbuntu 21.10 Oct120K40K60K80K100KMin: 96155 / Avg: 96319.67 / Max: 96439Min: 94314 / Avg: 94412.33 / Max: 945431. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Test: Update Random

openSUSE Tumbleweed: The test quit with a non-zero exit status.

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215SE +/- 0.16, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 311.6611.5611.43MIN: 11.15 / MAX: 87.96MIN: 11.08 / MAX: 27.23MIN: 10.89 / MAX: 35.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215Min: 11.44 / Avg: 11.66 / Max: 11.98Min: 11.46 / Avg: 11.56 / Max: 11.68Min: 11.31 / Avg: 11.43 / Max: 11.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed6001200180024003000SE +/- 7.22, N = 3SE +/- 4.30, N = 3SE +/- 3.12, N = 152729.42689.52743.41. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed5001000150020002500Min: 2715 / Avg: 2729.43 / Max: 2736.9Min: 2681.3 / Avg: 2689.53 / Max: 2695.8Min: 2722.2 / Avg: 2743.36 / Max: 2758.11. (CC) gcc options: -O3 -pthread -lz

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed714212835SE +/- 0.15, N = 3SE +/- 0.38, N = 3SE +/- 0.12, N = 330.3229.7430.041. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed714212835Min: 30.05 / Avg: 30.32 / Max: 30.58Min: 29.32 / Avg: 29.74 / Max: 30.5Min: 29.89 / Avg: 30.04 / Max: 30.271. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian DragonFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100SE +/- 0.43, N = 3SE +/- 0.88, N = 3SE +/- 0.76, N = 381.9383.0483.50MIN: 66.46 / MAX: 92.34MIN: 68.13 / MAX: 92.75MIN: 69.84 / MAX: 93.01
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian DragonFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1632486480Min: 81.09 / Avg: 81.93 / Max: 82.5Min: 81.28 / Avg: 83.04 / Max: 83.93Min: 81.98 / Avg: 83.5 / Max: 84.3

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.74061.48122.22182.96243.703SE +/- 0.00672, N = 3SE +/- 0.00691, N = 3SE +/- 0.00222, N = 33.235023.291683.23059MIN: 3.03MIN: 3.1MIN: 3.031. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 3.22 / Avg: 3.24 / Max: 3.25Min: 3.28 / Avg: 3.29 / Max: 3.31Min: 3.23 / Avg: 3.23 / Max: 3.231. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20K40K60K80K100KSE +/- 951.18, N = 3SE +/- 910.87, N = 3SE +/- 597.75, N = 1583310.284493.382944.6
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed15K30K45K60K75KMin: 81919.8 / Avg: 83310.17 / Max: 85129.8Min: 82818.6 / Avg: 84493.33 / Max: 85951.6Min: 78997.8 / Avg: 82944.65 / Max: 87902.9

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Disney MaterialFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2040608010083.0781.8683.34

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: resnet-v2-50Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed510152025SE +/- 0.06, N = 15SE +/- 0.04, N = 3SE +/- 0.14, N = 1519.1218.7918.85MIN: 17.96 / MAX: 58.25MIN: 18.18 / MAX: 41.67MIN: 17.43 / MAX: 35.371. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: resnet-v2-50Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed510152025Min: 18.76 / Avg: 19.12 / Max: 19.58Min: 18.72 / Avg: 18.79 / Max: 18.86Min: 17.93 / Avg: 18.85 / Max: 20.251. (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

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: EmilyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200178.07178.45175.53

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-OnlyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1632486480SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.11, N = 373.6473.4172.44
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-OnlyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1428425670Min: 73.6 / Avg: 73.64 / Max: 73.66Min: 73.26 / Avg: 73.41 / Max: 73.61Min: 72.29 / Avg: 72.44 / Max: 72.65

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Glibc Qsort Data SortingFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2004006008001000SE +/- 3.60, N = 3SE +/- 2.76, N = 3SE +/- 4.75, N = 3978.29964.65980.62-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Glibc Qsort Data SortingFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2004006008001000Min: 971.13 / Avg: 978.29 / Max: 982.6Min: 959.16 / Avg: 964.65 / Max: 967.93Min: 971.16 / Avg: 980.62 / Max: 986.031. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.02, N = 211.6711.7011.84MIN: 11.33 / MAX: 33.34MIN: 11.31 / MAX: 27.37MIN: 11.48 / MAX: 35.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215Min: 11.61 / Avg: 11.67 / Max: 11.74Min: 11.5 / Avg: 11.7 / Max: 11.91Min: 11.82 / Avg: 11.84 / Max: 11.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Matrix MathFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed60K120K180K240K300KSE +/- 1378.00, N = 3SE +/- 1006.85, N = 3SE +/- 962.16, N = 3290055.81292343.66294254.02-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Matrix MathFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed50K100K150K200K250KMin: 287400.43 / Avg: 290055.81 / Max: 292022.54Min: 290695.25 / Avg: 292343.66 / Max: 294169.51Min: 292346.39 / Avg: 294254.02 / Max: 295426.91. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 311.9911.8511.82MIN: 11.5 / MAX: 58.74MIN: 11.35 / MAX: 27.09MIN: 11.3 / MAX: 61.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215Min: 11.83 / Avg: 11.99 / Max: 12.11Min: 11.75 / Avg: 11.85 / Max: 11.93Min: 11.69 / Avg: 11.82 / Max: 12.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Timed LLVM Compilation

This test times how long it takes to build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: NinjaFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed306090120150SE +/- 0.50, N = 3SE +/- 0.18, N = 3SE +/- 0.33, N = 3132.32131.76133.64
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: NinjaFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed306090120150Min: 131.63 / Avg: 132.32 / Max: 133.28Min: 131.42 / Avg: 131.76 / Max: 132.03Min: 133.12 / Avg: 133.64 / Max: 134.24

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: NinjaFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed306090120150SE +/- 0.12, N = 3SE +/- 0.73, N = 3SE +/- 0.49, N = 3131.31129.94131.77
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: NinjaFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100Min: 131.13 / Avg: 131.31 / Max: 131.54Min: 128.83 / Avg: 129.94 / Max: 131.32Min: 131.18 / Avg: 131.77 / Max: 132.73

Google SynthMark

SynthMark is a cross platform tool for benchmarking CPU performance under a variety of real-time audio workloads. It uses a polyphonic synthesizer model to provide standardized tests for latency, jitter and computational throughput. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVoices, More Is BetterGoogle SynthMark 20201109Test: VoiceMark_100Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed120240360480600SE +/- 5.97, N = 3SE +/- 4.10, N = 3SE +/- 0.76, N = 3543.43550.53543.041. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast
OpenBenchmarking.orgVoices, More Is BetterGoogle SynthMark 20201109Test: VoiceMark_100Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed100200300400500Min: 536.04 / Avg: 543.43 / Max: 555.25Min: 542.35 / Avg: 550.53 / Max: 554.99Min: 541.73 / Avg: 543.04 / Max: 544.341. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed15003000450060007500SE +/- 6.85, N = 3SE +/- 4.39, N = 3SE +/- 2.18, N = 37149.67210.77115.31. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed13002600390052006500Min: 7140.4 / Avg: 7149.6 / Max: 7163Min: 7203.3 / Avg: 7210.73 / Max: 7218.5Min: 7112.7 / Avg: 7115.27 / Max: 7119.61. (CC) gcc options: -O3

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.8.2Model: yolov4 - Device: OpenMP CPUFedora 35 BetaUbuntu 21.10 Oct1120240360480600SE +/- 3.82, N = 3SE +/- 3.17, N = 35485411. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.8.2Model: yolov4 - Device: OpenMP CPUFedora 35 BetaUbuntu 21.10 Oct1100200300400500Min: 540.5 / Avg: 548 / Max: 553Min: 537.5 / Avg: 540.67 / Max: 5471. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Model: yolov4 - Device: OpenMP CPU

openSUSE Tumbleweed: The test quit with a non-zero exit status.

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed13000M26000M39000M52000M65000MSE +/- 82194161.08, N = 3SE +/- 72337526.63, N = 3SE +/- 25810526.81, N = 35919874023358476634107584477992701. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed10000M20000M30000M40000M50000MMin: 59047093290 / Avg: 59198740233.33 / Max: 59329518630Min: 58379122060 / Avg: 58476634106.67 / Max: 58617946620Min: 58405961420 / Avg: 58447799270 / Max: 584949049401. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Facebook RocksDB

This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Random FillFedora 35 BetaUbuntu 21.10 Oct120K40K60K80K100KSE +/- 237.03, N = 3SE +/- 88.17, N = 310103399799-lpthread1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Random FillFedora 35 BetaUbuntu 21.10 Oct120K40K60K80K100KMin: 100619 / Avg: 101033 / Max: 101440Min: 99674 / Avg: 99798.67 / Max: 999691. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Test: Random Fill

openSUSE Tumbleweed: The test quit with a non-zero exit status.

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed612182430SE +/- 0.31, N = 3SE +/- 0.03, N = 3SE +/- 0.17, N = 323.8524.0323.74MIN: 22.87 / MAX: 53.7MIN: 23.37 / MAX: 39.78MIN: 23.05 / MAX: 47.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed612182430Min: 23.34 / Avg: 23.85 / Max: 24.41Min: 23.97 / Avg: 24.03 / Max: 24.08Min: 23.54 / Avg: 23.74 / Max: 24.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: ALS Movie LensFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4K8K12K16K20KSE +/- 8.48, N = 3SE +/- 48.52, N = 3SE +/- 170.25, N = 318146.418067.618282.9MIN: 18137.86 / MAX: 20327.55MIN: 17747.45 / MAX: 19660.26MIN: 17522.47 / MAX: 20593.65
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: ALS Movie LensFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3K6K9K12K15KMin: 18137.86 / Avg: 18146.36 / Max: 18163.32Min: 18001.79 / Avg: 18067.58 / Max: 18162.24Min: 17957.63 / Avg: 18282.92 / Max: 18532.73

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed6001200180024003000SE +/- 2.68, N = 3SE +/- 1.25, N = 3SE +/- 1.88, N = 32658.22646.42671.01. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed5001000150020002500Min: 2653.1 / Avg: 2658.17 / Max: 2662.2Min: 2644.4 / Avg: 2646.43 / Max: 2648.7Min: 2667.8 / Avg: 2671.03 / Max: 2674.31. (CC) gcc options: -O3 -pthread -lz

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed918273645SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 339.6840.0339.88-lmpi_cxx-lmpi_cxx1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi
OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed816243240Min: 39.61 / Avg: 39.68 / Max: 39.8Min: 39.98 / Avg: 40.03 / Max: 40.11Min: 39.72 / Avg: 39.88 / Max: 39.971. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100SE +/- 0.00, N = 3SE +/- 0.93, N = 12SE +/- 0.00, N = 3111.11110.19111.11MIN: 35.71MIN: 38.46 / MAX: 111.11MIN: 71.43 / MAX: 125
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100Min: 111.11 / Avg: 111.11 / Max: 111.11Min: 100 / Avg: 110.19 / Max: 111.11Min: 111.11 / Avg: 111.11 / Max: 111.11

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Decompression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed15003000450060007500SE +/- 4.43, N = 3SE +/- 8.27, N = 3SE +/- 22.71, N = 37136.87193.77153.21. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Decompression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed12002400360048006000Min: 7130.9 / Avg: 7136.83 / Max: 7145.5Min: 7184.9 / Avg: 7193.67 / Max: 7210.2Min: 7107.8 / Avg: 7153.2 / Max: 7177.31. (CC) gcc options: -O3

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: MallocFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed300M600M900M1200M1500MSE +/- 1327143.46, N = 3SE +/- 1275570.42, N = 3SE +/- 2944431.91, N = 31399403296.431407281590.861410532156.00-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: MallocFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed200M400M600M800M1000MMin: 1397710860.54 / Avg: 1399403296.43 / Max: 1402020298.07Min: 1404774076.24 / Avg: 1407281590.86 / Max: 1408942186.65Min: 1404643307.85 / Avg: 1410532156 / Max: 1413488344.691. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

Timed LLVM Compilation

This test times how long it takes to build the LLVM compiler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Unix MakefilesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200SE +/- 0.64, N = 3SE +/- 0.16, N = 3SE +/- 1.74, N = 3199.62200.79199.27
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Unix MakefilesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200Min: 198.85 / Avg: 199.62 / Max: 200.89Min: 200.49 / Avg: 200.79 / Max: 201.01Min: 195.95 / Avg: 199.27 / Max: 201.81

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Unix MakefilesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed50100150200250SE +/- 0.84, N = 3SE +/- 1.46, N = 3SE +/- 1.62, N = 3206.06205.28206.83
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Unix MakefilesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200Min: 205.14 / Avg: 206.06 / Max: 207.75Min: 203.02 / Avg: 205.28 / Max: 208.01Min: 203.95 / Avg: 206.83 / Max: 209.55

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Glibc C String FunctionsFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed2M4M6M8M10MSE +/- 37222.74, N = 3SE +/- 23928.16, N = 3SE +/- 79663.70, N = 57933317.107962720.717905372.49-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Glibc C String FunctionsFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1.4M2.8M4.2M5.6M7MMin: 7865539.33 / Avg: 7933317.1 / Max: 7993874.84Min: 7916432.59 / Avg: 7962720.71 / Max: 7996387.49Min: 7599423.87 / Avg: 7905372.49 / Max: 8030402.661. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: regnety_400mFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed918273645SE +/- 0.69, N = 3SE +/- 0.26, N = 3SE +/- 0.37, N = 337.9737.7037.77MIN: 36.19 / MAX: 116.99MIN: 36.75 / MAX: 54MIN: 36.58 / MAX: 220.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: regnety_400mFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed816243240Min: 36.59 / Avg: 37.97 / Max: 38.73Min: 37.36 / Avg: 37.7 / Max: 38.21Min: 37.04 / Avg: 37.77 / Max: 38.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed80160240320400SE +/- 0.23, N = 3SE +/- 0.09, N = 3SE +/- 0.10, N = 3366.32368.22365.69MIN: 365.87 / MAX: 368.51MIN: 366.43 / MAX: 370.9MIN: 365.33 / MAX: 366.761. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed70140210280350Min: 366.06 / Avg: 366.32 / Max: 366.78Min: 368.05 / Avg: 368.22 / Max: 368.34Min: 365.49 / Avg: 365.69 / Max: 365.811. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: CPU StressFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed30K60K90K120K150KSE +/- 348.55, N = 3SE +/- 304.54, N = 3SE +/- 209.48, N = 3126640.32126295.66127127.44-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: CPU StressFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20K40K60K80K100KMin: 125960.37 / Avg: 126640.32 / Max: 127113.36Min: 125750.75 / Avg: 126295.66 / Max: 126803.78Min: 126742.06 / Avg: 127127.44 / Max: 127462.451. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.06310.12620.18930.25240.3155SE +/- 0.00098, N = 3SE +/- 0.00056, N = 3SE +/- 0.00043, N = 30.280290.278470.27899
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed12345Min: 0.28 / Avg: 0.28 / Max: 0.28Min: 0.28 / Avg: 0.28 / Max: 0.28Min: 0.28 / Avg: 0.28 / Max: 0.28

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.81771.63542.45313.27084.0885SE +/- 0.03712, N = 13SE +/- 0.03462, N = 13SE +/- 0.03316, N = 143.634423.614813.63231MIN: 3.5MIN: 3.49MIN: 3.51. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 3.58 / Avg: 3.63 / Max: 4.08Min: 3.56 / Avg: 3.61 / Max: 4.02Min: 3.59 / Avg: 3.63 / Max: 4.061. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4K8K12K16K20KSE +/- 117.95, N = 3SE +/- 89.21, N = 3SE +/- 136.84, N = 317706.517798.217744.01. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3K6K9K12K15KMin: 17470.9 / Avg: 17706.53 / Max: 17834Min: 17671.4 / Avg: 17798.2 / Max: 17970.3Min: 17580.6 / Avg: 17743.97 / Max: 18015.81. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed300K600K900K1200K1500KSE +/- 1029.19, N = 3SE +/- 92.73, N = 3SE +/- 843.27, N = 31187546.81191217.91193325.71. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed200K400K600K800K1000KMin: 1185787.9 / Avg: 1187546.8 / Max: 1189352.2Min: 1191034.8 / Avg: 1191217.87 / Max: 1191335.1Min: 1192134.5 / Avg: 1193325.73 / Max: 1194955.31. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.8.2Model: fcn-resnet101-11 - Device: OpenMP CPUFedora 35 BetaUbuntu 21.10 Oct1100200300400500SE +/- 3.28, N = 3SE +/- 5.35, N = 34744761. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.8.2Model: fcn-resnet101-11 - Device: OpenMP CPUFedora 35 BetaUbuntu 21.10 Oct180160240320400Min: 467 / Avg: 473.5 / Max: 477.5Min: 468.5 / Avg: 475.5 / Max: 4861. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Model: fcn-resnet101-11 - Device: OpenMP CPU

openSUSE Tumbleweed: The test quit with a non-zero exit status.

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021.2Implementation: MPI CPU - Input: water_GMX50_bareFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215SE +/- 0.019, N = 3SE +/- 0.101, N = 4SE +/- 0.031, N = 39.0499.0389.0761. (CXX) g++ options: -O3
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021.2Implementation: MPI CPU - Input: water_GMX50_bareFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215Min: 9.01 / Avg: 9.05 / Max: 9.07Min: 8.74 / Avg: 9.04 / Max: 9.15Min: 9.03 / Avg: 9.08 / Max: 9.141. (CXX) g++ options: -O3

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed612182430SE +/- 0.23, N = 3SE +/- 0.33, N = 3SE +/- 0.26, N = 326.9926.9527.06-lnuma1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed612182430Min: 26.74 / Avg: 26.99 / Max: 27.44Min: 26.3 / Avg: 26.95 / Max: 27.4Min: 26.8 / Avg: 27.06 / Max: 27.581. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.47930.95861.43791.91722.3965SE +/- 0.01900, N = 3SE +/- 0.02486, N = 3SE +/- 0.01577, N = 32.130072.122412.12178MIN: 2.03MIN: 2.03MIN: 2.031. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 2.11 / Avg: 2.13 / Max: 2.17Min: 2.1 / Avg: 2.12 / Max: 2.17Min: 2.11 / Avg: 2.12 / Max: 2.151. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed130K260K390K520K650KSE +/- 1535.68, N = 3SE +/- 1247.99, N = 3SE +/- 1116.87, N = 3594597595226596888
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed100K200K300K400K500KMin: 591663 / Avg: 594596.67 / Max: 596851Min: 592877 / Avg: 595226.33 / Max: 597131Min: 594656 / Avg: 596887.67 / Max: 598087

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Vector MathFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed60K120K180K240K300KSE +/- 874.10, N = 3SE +/- 1011.65, N = 3SE +/- 530.40, N = 3277479.38278044.70278157.65-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Vector MathFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed50K100K150K200K250KMin: 275741.89 / Avg: 277479.38 / Max: 278515.43Min: 276033.39 / Avg: 278044.7 / Max: 279240.84Min: 277097.13 / Avg: 278157.65 / Max: 278708.631. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenetFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed510152025SE +/- 0.29, N = 3SE +/- 0.10, N = 3SE +/- 0.12, N = 321.3121.2621.27MIN: 20.36 / MAX: 43.83MIN: 20.42 / MAX: 37.9MIN: 20.31 / MAX: 44.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenetFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed510152025Min: 20.89 / Avg: 21.31 / Max: 21.87Min: 21.08 / Avg: 21.26 / Max: 21.44Min: 21.07 / Avg: 21.27 / Max: 21.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: RdRandFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed140K280K420K560K700KSE +/- 2353.71, N = 3SE +/- 2315.78, N = 3SE +/- 2321.64, N = 3666960.21666871.13666960.00-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: RdRandFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed120K240K360K480K600KMin: 662254.77 / Avg: 666960.21 / Max: 669431.35Min: 662240.7 / Avg: 666871.13 / Max: 669275.13Min: 662316.86 / Avg: 666960 / Max: 6693131. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 390.9190.9190.91MIN: 76.92 / MAX: 100MIN: 62.5 / MAX: 100MIN: 66.67 / MAX: 100
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed20406080100Min: 90.91 / Avg: 90.91 / Max: 90.91Min: 90.91 / Avg: 90.91 / Max: 90.91Min: 90.91 / Avg: 90.91 / Max: 90.91

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.06350.1270.19050.2540.3175SE +/- 0.002, N = 7SE +/- 0.003, N = 12SE +/- 0.009, N = 120.2670.2690.2821. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed12345Min: 0.26 / Avg: 0.27 / Max: 0.28Min: 0.26 / Avg: 0.27 / Max: 0.3Min: 0.25 / Avg: 0.28 / Max: 0.331. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed400K800K1200K1600K2000KSE +/- 17223.30, N = 7SE +/- 21829.42, N = 12SE +/- 55194.33, N = 121875522185982117947001. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed300K600K900K1200K1500KMin: 1803159.48 / Avg: 1875521.67 / Max: 1938352.1Min: 1687849.27 / Avg: 1859821.29 / Max: 1921815.57Min: 1531503.88 / Avg: 1794699.62 / Max: 2024730.161. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1000Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed40K80K120K160K200KSE +/- 2706.83, N = 15SE +/- 4897.09, N = 15SE +/- 2044.57, N = 359961.48106682.07206714.391. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1000Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed40K80K120K160K200KMin: 43156.01 / Avg: 59961.48 / Max: 82767.71Min: 63871.22 / Avg: 106682.07 / Max: 136488.72Min: 202665.74 / Avg: 206714.39 / Max: 209235.81. (CC) gcc options: -shared -fPIC -O2

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 200Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed40K80K120K160K200KSE +/- 1162.78, N = 3SE +/- 9412.84, N = 12SE +/- 2237.18, N = 4204764.97168716.20195437.721. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 200Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed40K80K120K160K200KMin: 202558.93 / Avg: 204764.97 / Max: 206505.36Min: 89816.83 / Avg: 168716.2 / Max: 184534.36Min: 188859.13 / Avg: 195437.72 / Max: 198611.541. (CC) gcc options: -lcrypt -lz -O3 -march=native

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed150300450600750SE +/- 2.91, N = 3SE +/- 11.89, N = 15SE +/- 17.37, N = 15516604705
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed120240360480600Min: 511 / Avg: 515.67 / Max: 521Min: 515 / Avg: 603.73 / Max: 640Min: 617 / Avg: 705.13 / Max: 768

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1530456075SE +/- 0.55, N = 6SE +/- 1.57, N = 15SE +/- 0.43, N = 355.859.167.9
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1326395265Min: 54.1 / Avg: 55.83 / Max: 57.7Min: 52.7 / Avg: 59.07 / Max: 70.9Min: 67.3 / Avg: 67.87 / Max: 68.7

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed50100150200250SE +/- 0.67, N = 3SE +/- 4.40, N = 15SE +/- 2.18, N = 8206215248
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200Min: 205 / Avg: 205.67 / Max: 207Min: 198 / Avg: 215.27 / Max: 252Min: 241 / Avg: 248 / Max: 259

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200SE +/- 1.20, N = 3SE +/- 3.15, N = 15SE +/- 3.19, N = 15137133173
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed306090120150Min: 135 / Avg: 137.33 / Max: 139Min: 119 / Avg: 132.8 / Max: 148Min: 159 / Avg: 173.33 / Max: 198

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed714212835SE +/- 0.15, N = 3SE +/- 0.63, N = 12SE +/- 0.63, N = 1526.230.531.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed714212835Min: 25.9 / Avg: 26.17 / Max: 26.4Min: 28 / Avg: 30.53 / Max: 35.2Min: 28.2 / Avg: 31.77 / Max: 36.5

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed714212835SE +/- 0.00, N = 3SE +/- 0.37, N = 13SE +/- 0.48, N = 1528.726.129.4
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed714212835Min: 28.7 / Avg: 28.7 / Max: 28.7Min: 22.1 / Avg: 26.07 / Max: 26.7Min: 25 / Avg: 29.43 / Max: 30.4

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbodyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200SE +/- 1.59, N = 5SE +/- 3.55, N = 15SE +/- 4.08, N = 15161152191
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbodyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200Min: 155 / Avg: 160.8 / Max: 164Min: 136 / Avg: 151.87 / Max: 176Min: 175 / Avg: 191.4 / Max: 219

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: floatFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200SE +/- 0.00, N = 3SE +/- 3.67, N = 15SE +/- 3.40, N = 15128148174
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: floatFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed306090120150Min: 128 / Avg: 128 / Max: 128Min: 133 / Avg: 148.4 / Max: 170Min: 159 / Avg: 174.07 / Max: 200

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaosFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed4080120160200SE +/- 1.20, N = 3SE +/- 1.45, N = 3SE +/- 3.05, N = 15132136177
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaosFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed306090120150Min: 130 / Avg: 131.67 / Max: 134Min: 133 / Avg: 135.67 / Max: 138Min: 161 / Avg: 176.53 / Max: 204

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed100200300400500SE +/- 2.74, N = 3SE +/- 9.53, N = 15SE +/- 4.98, N = 15396.22442.00383.43MIN: 370.89 / MAX: 614MIN: 372.63 / MAX: 552.29MIN: 368.91 / MAX: 634.271. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed80160240320400Min: 391.73 / Avg: 396.22 / Max: 401.19Min: 377.05 / Avg: 442 / Max: 510.03Min: 370.46 / Avg: 383.43 / Max: 431.961. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed612182430SE +/- 0.90, N = 3SE +/- 0.32, N = 3SE +/- 0.13, N = 325.4125.1525.69MIN: 23.83 / MAX: 184.26MIN: 23.85 / MAX: 84.28MIN: 24.71 / MAX: 109.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed612182430Min: 24.34 / Avg: 25.41 / Max: 27.21Min: 24.77 / Avg: 25.15 / Max: 25.79Min: 25.47 / Avg: 25.69 / Max: 25.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215SE +/- 0.19, N = 3SE +/- 0.42, N = 3SE +/- 0.13, N = 39.699.358.53MIN: 9.11 / MAX: 10.82MIN: 8.28 / MAX: 26.19MIN: 8.1 / MAX: 10.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215Min: 9.32 / Avg: 9.69 / Max: 9.9Min: 8.57 / Avg: 9.35 / Max: 10.02Min: 8.33 / Avg: 8.53 / Max: 8.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed48121620SE +/- 0.51, N = 3SE +/- 0.56, N = 3SE +/- 0.17, N = 314.5814.0913.35MIN: 13.23 / MAX: 37.67MIN: 12.98 / MAX: 28.95MIN: 12.86 / MAX: 37.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed48121620Min: 13.56 / Avg: 14.58 / Max: 15.18Min: 13.32 / Avg: 14.09 / Max: 15.18Min: 13.15 / Avg: 13.35 / Max: 13.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: MobileNetV2_224Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.64711.29421.94132.58843.2355SE +/- 0.041, N = 15SE +/- 0.030, N = 3SE +/- 0.053, N = 152.7952.7312.876MIN: 2.34 / MAX: 9.08MIN: 2.59 / MAX: 3.08MIN: 2.29 / MAX: 7.071. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: MobileNetV2_224Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 2.58 / Avg: 2.79 / Max: 3.08Min: 2.7 / Avg: 2.73 / Max: 2.79Min: 2.66 / Avg: 2.88 / Max: 3.311. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: SqueezeNetV1.0Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1.13872.27743.41614.55485.6935SE +/- 0.145, N = 15SE +/- 0.011, N = 3SE +/- 0.060, N = 154.6724.4215.061MIN: 3.84 / MAX: 10.88MIN: 4.35 / MAX: 6.74MIN: 3.87 / MAX: 12.431. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: SqueezeNetV1.0Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 3.96 / Avg: 4.67 / Max: 5.39Min: 4.41 / Avg: 4.42 / Max: 4.44Min: 4.46 / Avg: 5.06 / Max: 5.351. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: squeezenetv1.1Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.8641.7282.5923.4564.32SE +/- 0.051, N = 15SE +/- 0.132, N = 3SE +/- 0.059, N = 153.8403.7703.760MIN: 3.24 / MAX: 7.6MIN: 3.32 / MAX: 7.99MIN: 3.24 / MAX: 7.681. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: squeezenetv1.1Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 3.44 / Avg: 3.84 / Max: 4.02Min: 3.64 / Avg: 3.77 / Max: 4.03Min: 3.34 / Avg: 3.76 / Max: 4.041. (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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV3Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.46550.9311.39651.8622.3275SE +/- 0.043, N = 15SE +/- 0.007, N = 3SE +/- 0.033, N = 151.9941.9492.069MIN: 1.61 / MAX: 4.44MIN: 1.87 / MAX: 2.15MIN: 1.65 / MAX: 4.521. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV3Fedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 1.71 / Avg: 1.99 / Max: 2.27Min: 1.94 / Avg: 1.95 / Max: 1.96Min: 1.86 / Avg: 2.07 / Max: 2.251. (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

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: System V Message PassingFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed900K1800K2700K3600K4500KSE +/- 108355.40, N = 12SE +/- 28851.31, N = 9SE +/- 6099.95, N = 34098551.273578020.473045985.32-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: System V Message PassingFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed700K1400K2100K2800K3500KMin: 3359785.04 / Avg: 4098551.27 / Max: 4523039.81Min: 3509117.61 / Avg: 3578020.47 / Max: 3771607.33Min: 3034256.76 / Avg: 3045985.32 / Max: 30547581. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: IO_uringFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed70K140K210K280K350KSE +/- 3586.50, N = 15SE +/- 355.13, N = 3SE +/- 1647.54, N = 15336629.2091421.6775341.64-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: IO_uringFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed60K120K180K240K300KMin: 305965.19 / Avg: 336629.2 / Max: 356643.96Min: 90979.83 / Avg: 91421.67 / Max: 92124.18Min: 54996.42 / Avg: 75341.64 / Max: 78216.161. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: NUMAFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1020304050SE +/- 0.46, N = 6SE +/- 0.16, N = 3SE +/- 0.44, N = 1545.2544.947.11-latomic-latomic1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: NUMAFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed918273645Min: 43.7 / Avg: 45.25 / Max: 46.87Min: 44.64 / Avg: 44.94 / Max: 45.19Min: 5.01 / Avg: 7.11 / Max: 10.051. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average LatencyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.06680.13360.20040.26720.334SE +/- 0.004, N = 3SE +/- 0.008, N = 12SE +/- 0.037, N = 120.2520.2690.2971. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average LatencyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed12345Min: 0.25 / Avg: 0.25 / Max: 0.26Min: 0.25 / Avg: 0.27 / Max: 0.33Min: 0.24 / Avg: 0.3 / Max: 0.71. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read OnlyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed200K400K600K800K1000KSE +/- 13107.59, N = 3SE +/- 24147.73, N = 12SE +/- 53555.93, N = 129915839371569120581. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read OnlyFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed200K400K600K800K1000KMin: 966459.32 / Avg: 991583.38 / Max: 1010627.14Min: 762315.93 / Avg: 937155.67 / Max: 1014279.42Min: 359469.89 / Avg: 912058.17 / Max: 1057649.711. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed9K18K27K36K45KSE +/- 64.05, N = 3SE +/- 690.99, N = 15SE +/- 365.12, N = 1537665.741710.637729.3
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed7K14K21K28K35KMin: 37541.6 / Avg: 37665.67 / Max: 37755.3Min: 38271.4 / Avg: 41710.57 / Max: 45429.6Min: 35599.9 / Avg: 37729.29 / Max: 40340.8

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed0.89251.7852.67753.574.4625SE +/- 0.09261, N = 15SE +/- 0.67784, N = 12SE +/- 0.07237, N = 152.990453.966542.77560MIN: 1.97MIN: 2.09MIN: 1.761. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810Min: 2.35 / Avg: 2.99 / Max: 3.66Min: 2.74 / Avg: 3.97 / Max: 11.33Min: 2.12 / Avg: 2.78 / Max: 3.011. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810SE +/- 0.83207, N = 15SE +/- 0.68437, N = 15SE +/- 0.70452, N = 156.509176.509616.63389MIN: 3.15MIN: 3.46MIN: 3.11. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215Min: 3.59 / Avg: 6.51 / Max: 17.9Min: 4.2 / Avg: 6.51 / Max: 15.71Min: 3.48 / Avg: 6.63 / Max: 16.111. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Decompression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed7001400210028003500SE +/- 2.92, N = 3SE +/- 97.11, N = 13SE +/- 59.69, N = 153104.62917.43026.31. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Decompression SpeedFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed5001000150020002500Min: 3098.8 / Avg: 3104.63 / Max: 3107.7Min: 2130.6 / Avg: 2917.42 / Max: 3104.3Min: 2389.5 / Avg: 3026.25 / Max: 3147.61. (CC) gcc options: -O3 -pthread -lz

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed12002400360048006000SE +/- 161.36, N = 20SE +/- 123.29, N = 20SE +/- 140.36, N = 20538647275022
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed9001800270036004500Min: 4376 / Avg: 5385.95 / Max: 6582Min: 4350 / Avg: 4726.5 / Max: 6326Min: 4111 / Avg: 5022.3 / Max: 5805

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed246810SE +/- 0.195, N = 12SE +/- 0.076, N = 3SE +/- 0.071, N = 158.1798.2828.1781. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed3691215Min: 7.41 / Avg: 8.18 / Max: 10.16Min: 8.16 / Avg: 8.28 / Max: 8.42Min: 7.85 / Avg: 8.18 / Max: 8.841. (CXX) g++ options: -O2 -lOpenCL

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1224364860SE +/- 0.77, N = 15SE +/- 0.54, N = 15SE +/- 1.06, N = 1548.9253.4251.071. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteFedora 35 BetaUbuntu 21.10 Oct1openSUSE Tumbleweed1122334455Min: 43.72 / Avg: 48.92 / Max: 54.28Min: 48.44 / Avg: 53.42 / Max: 57.72Min: 43.98 / Avg: 51.07 / Max: 60.411. (CXX) g++ options: -O2 -lOpenCL

186 Results Shown

Stress-NG
Apache HTTP Server
NAS Parallel Benchmarks:
  SP.B
  LU.C
  BT.C
  SP.C
  MG.C
  EP.D
PostgreSQL pgbench:
  100 - 500 - Read Write - Average Latency
  100 - 500 - Read Write
PostgreSQL pgbench:
  100 - 250 - Read Write - Average Latency
  100 - 250 - Read Write
Apache HTTP Server
NAS Parallel Benchmarks:
  FT.C
  CG.C
  IS.D
Facebook RocksDB
Stress-NG
Renaissance
Node.js Express HTTP Load Test
Timed Wasmer Compilation
PyPerformance
PHPBench
PyPerformance
JPEG XL libjxl
Stress-NG
nginx
7-Zip Compression
SQLite Speedtest
Renaissance
Timed Godot Game Engine Compilation
GNU GMP GMPbench
PyBench
TNN
JPEG XL libjxl
LevelDB
Stress-NG
Facebook RocksDB
SVT-AV1
Stress-NG
nginx:
  1000
  500
JPEG XL libjxl
DaCapo Benchmark
JPEG XL libjxl
Renaissance
Embree
NCNN:
  CPU - vgg16
  CPU - googlenet
Renaissance
DaCapo Benchmark
Zstd Compression:
  19, Long Mode - Compression Speed
  19 - Compression Speed
TensorFlow Lite
Mobile Neural Network
PyPerformance
Renaissance
ONNX Runtime:
  bertsquad-10 - OpenMP CPU
  shufflenet-v2-10 - OpenMP CPU
LZ4 Compression
Rodinia
Chaos Group V-RAY
LZ4 Compression
Coremark
Zstd Compression
SVT-HEVC
NCNN
Embree
Stockfish
Blender
Stress-NG
TNN
SVT-VP9
Timed Node.js Compilation
NCNN
Apache Cassandra
Mobile Neural Network
SVT-VP9
x265
Stress-NG
Embree
SVT-AV1
oneDNN
Stress-NG
Renaissance
Appleseed
Renaissance
Git
NCNN
simdjson
Intel Open Image Denoise
simdjson
Stress-NG
SecureMark
oneDNN
TensorFlow Lite
simdjson
NCNN
Timed Linux Kernel Compilation
Blender
OpenVKL
simdjson
OSPray
TensorFlow Lite
Facebook RocksDB:
  Read Rand Write Rand
  Update Rand
NCNN
Zstd Compression
SVT-HEVC
Embree
oneDNN
TensorFlow Lite
Appleseed
Mobile Neural Network
Appleseed
Blender
Stress-NG
NCNN
Stress-NG
NCNN
Timed LLVM Compilation
Timed LLVM Compilation
Google SynthMark
LZ4 Compression
ONNX Runtime
OpenSSL
Facebook RocksDB
NCNN
Renaissance
Zstd Compression
High Performance Conjugate Gradient
OSPray
LZ4 Compression
Stress-NG
Timed LLVM Compilation
Timed LLVM Compilation
Stress-NG
NCNN
TNN
Stress-NG
NAMD
oneDNN
OpenSSL:
  RSA4096:
    sign/s
    verify/s
ONNX Runtime
GROMACS
x265
oneDNN
TensorFlow Lite
Stress-NG
NCNN
Stress-NG
OSPray
PostgreSQL pgbench:
  100 - 500 - Read Only - Average Latency
  100 - 500 - Read Only
Apache HTTP Server
nginx
PyPerformance:
  pickle_pure_python
  django_template
  regex_compile
  crypto_pyaes
  json_loads
  pathlib
  nbody
  float
  chaos
TNN
NCNN:
  CPU - yolov4-tiny
  CPU - alexnet
  CPU - resnet18
Mobile Neural Network:
  MobileNetV2_224
  SqueezeNetV1.0
  squeezenetv1.1
  mobilenetV3
Stress-NG:
  System V Message Passing
  IO_uring
  NUMA
PostgreSQL pgbench:
  100 - 250 - Read Only - Average Latency
  100 - 250 - Read Only
TensorFlow Lite
oneDNN:
  IP Shapes 3D - bf16bf16bf16 - CPU
  IP Shapes 1D - bf16bf16bf16 - CPU
Zstd Compression
DaCapo Benchmark
Rodinia:
  OpenMP Streamcluster
  OpenMP Leukocyte