EPYC 7F72 Kernel Testing

AMD EPYC 7F72 24-Core testing with a ASRockRack EPYCD8 (P2.10 BIOS) and ASPEED on Ubuntu 20.04 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 2009179-FI-EPYC7F72K52
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:

AV1 3 Tests
Timed Code Compilation 4 Tests
C/C++ Compiler Tests 15 Tests
CPU Massive 30 Tests
Creator Workloads 14 Tests
Database Test Suite 7 Tests
Disk Test Suite 3 Tests
Encoding 5 Tests
Fortran Tests 2 Tests
Game Development 4 Tests
HPC - High Performance Computing 10 Tests
Imaging 3 Tests
Java 3 Tests
Common Kernel Benchmarks 12 Tests
Machine Learning 4 Tests
Molecular Dynamics 2 Tests
Multi-Core 21 Tests
Networking Test Suite 2 Tests
Node.js + NPM Tests 2 Tests
NVIDIA GPU Compute 4 Tests
OCR 2 Tests
Intel oneAPI 2 Tests
OpenMPI Tests 2 Tests
Programmer / Developer System Benchmarks 9 Tests
Python 2 Tests
Renderers 2 Tests
Scientific Computing 4 Tests
Server 13 Tests
Server CPU Tests 21 Tests
Single-Threaded 7 Tests
Video Encoding 5 Tests
Common Workstation Benchmarks 5 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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Linux 5.9-rc4
September 10 2020
  16 Hours, 12 Minutes
Linux 5.8
September 13 2020
  16 Hours, 20 Minutes
page_lock_unfairness 1000
September 14 2020
  15 Hours, 58 Minutes
PLU 0
September 15 2020
  15 Hours, 58 Minutes
PLU 1
September 16 2020
  15 Hours, 45 Minutes
Invert Hiding All Results Option
  16 Hours, 3 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):

Linux 5.9-rc4

Processor: AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash Disk, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel I350

OS: Ubuntu 20.04, Kernel: 5.9.0-rc4-pts (x86_64) 20200910, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x830101c
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.2
Security Notes: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Linux 5.8

Processor: AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash Disk, Graphics: ASPEED, Audio: AMD Starship/Matisse, Network: 2 x Intel I350

OS: Ubuntu 20.04, Kernel: 5.8.0-pts (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768

page_lock_unfairness 1000

PLU 0

Processor: AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash Disk, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel I350

OS: Ubuntu 20.04, Kernel: 5.9.0-rc5-14sep-patch (x86_64) 20200914, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

PLU 1

Processor: AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash Disk, Graphics: ASPEED, Audio: AMD Starship/Matisse, Network: 2 x Intel I350

OS: Ubuntu 20.04, Kernel: 5.9.0-rc5-14sep-patch (x86_64) 20200914, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768

EPYC 7F72 Kernel TestingProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionLinux 5.9-rc4Linux 5.8page_lock_unfairness 1000PLU 0PLU 1AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads)ASRockRack EPYCD8 (P2.10 BIOS)AMD Starship/Matisse126GB3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash DiskASPEEDAMD Starship/MatisseVE2282 x Intel I350Ubuntu 20.045.9.0-rc4-pts (x86_64) 20200910GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.8GCC 9.3.0ext41920x10805.8.0-pts (x86_64)1024x768VE2285.9.0-rc5-14sep-patch (x86_64) 202009141920x10801024x768OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Disk Details- NONE / errors=remount-ro,relatime,rwProcessor Details- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x830101cJava Details- OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)Python Details- Python 3.8.2Security Details- 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Linux 5.9-rc4Linux 5.8page_lock_unfairness 1000PLU 0PLU 1Result OverviewPhoronix Test Suite100%122%143%165%186%Apache SiegeHackbenchRedisIntel Open Image DenoiseNode.js Express HTTP Load TestMemcached mcperfOSBenchApache CassandraJava Gradle BuildNGINX BenchmarkPyPerformanceHigh Performance Conjugate GradientApache BenchmarkTimed Apache CompilationCP2K Molecular DynamicsHimeno Benchmarkx265AOM AV1AI Benchmark AlphaSchbenchTimed Linux Kernel CompilationTimed LLVM CompilationCompile BenchYafaRaySVT-VP9Build2PostgreSQL pgbenchiPerfFS-MarkStress-NGZstd Compressionperf-benchLeelaChessZeroSQLiteSVT-AV1MariaDBSQLite SpeedtestRawTherapeeKeyDBOCRMyPDFpmbenchOpenVKLOpenSSLlibrsvgPlaidMLRodiniaCoremarkBlenderTesseract OCRNode.js Octane Benchmarklibavif avifencNAMDGitNebular Empirical Analysis ToolASTC EncoderRenaissanceTensorFlow LitePyBenchDaCapo Benchmark

EPYC 7F72 Kernel Testingrenaissance: Savina Reactors.IOrenaissance: In-Memory Database Shootoutrenaissance: Apache Spark PageRankjava-gradle-perf: Reactorrenaissance: Akka Unbalanced Cobwebbed Treemysqlslap: 256mcperf: Add - 16mcperf: Set - 16lczero: Eigenmcperf: Append - 16mcperf: Replace - 16mcperf: Prepend - 16plaidml: No - Inference - ResNet 50 - CPUopenvkl: vklBenchmarklczero: BLASai-benchmark: Device AI Scoreai-benchmark: Device Training Scoreai-benchmark: Device Inference Scoremysqlslap: 128build-llvm: Time To Compilerenaissance: Genetic Algorithm Using Jenetics + Futuresmcperf: Delete - 16mcperf: Get - 16renaissance: Rand Forestplaidml: No - Inference - Inception V3 - CPUrenaissance: Apache Spark ALSblender: Classroom - CPU-Onlycp2k: Fayalite-FIST Datamysqlslap: 64plaidml: No - Inference - Mobilenet - CPUhpcg: renaissance: Scala Dottystress-ng: CPU Cacheschbench: 2 - 8cassandra: Writesapache-siege: 250schbench: 4 - 2mcperf: Delete - 1mcperf: Add - 1pgbench: Buffer Test - Normal Load - Read Writepgbench: Buffer Test - Single Thread - Read Writepgbench: Buffer Test - Single Thread - Read Onlypgbench: Buffer Test - Normal Load - Read Onlytensorflow-lite: NASNet Mobileschbench: 2 - 6stress-ng: Context Switchingplaidml: No - Inference - VGG19 - CPUrodinia: OpenMP LavaMDrodinia: OpenMP HotSpot3Dpmbench: 2 - 50%mcperf: Get - 1mcperf: Replace - 1apache-siege: 200mcperf: Prepend - 1yafaray: Total Time For Sample Sceneblender: Fishy Cat - CPU-Onlyastcenc: Exhaustiveplaidml: No - Inference - VGG16 - CPUmysqlslap: 32mcperf: Append - 1nginx: Static Web Page Servingstress-ng: Forkingpmbench: 4 - 50%renaissance: Twitter HTTP Requestsschbench: 4 - 6pyperformance: python_startupsqlite-speedtest: Timed Time - Size 1,000hackbench: 16 - Processkeydb: build2: Time To Compileblender: BMW27 - CPU-Onlytensorflow-lite: Inception V4node-express-loadtest: avifenc: 0tensorflow-lite: Inception ResNet V2pmbench: 1 - 50%pmbench: 8 - 50%pmbench: 1 - 100% Writespmbench: 2 - 100% Writespmbench: 4 - 100% Writespmbench: 8 - 100% Writespmbench: 1 - 100% Readspmbench: 2 - 100% Readspmbench: 8 - 100% Readspmbench: 4 - 100% Readstensorflow-lite: SqueezeNettensorflow-lite: Mobilenet Quanttensorflow-lite: Mobilenet Floathackbench: 32 - Processhimeno: Poisson Pressure Solverschbench: 4 - 8coremark: CoreMark Size 666 - Iterations Per Secondgit: Time To Complete Common Git Commandshackbench: 16 - Threadrodinia: OpenMP Leukocyteredis: SADDrawtherapee: Total Benchmark Timebuild-linux-kernel: Time To Compileperf-bench: Memcpy 1MBstress-ng: Glibc C String Functionsapache-siege: 100namd: ATPase Simulation - 327,506 Atomsethr: TCP - Latency - 1mysqlslap: 16compress-zstd: 19avifenc: 2perf-bench: Epoll Waitmcperf: Set - 1plaidml: No - Inference - IMDB LSTM - CPUredis: GETredis: SETpyperformance: regex_compilestress-ng: Glibc Qsort Data Sortingaom-av1: Speed 0 Two-Passapache: Static Web Page Servingredis: LPOPethr: TCP - Connections/s - 1aom-av1: Speed 6 Realtimenode-octane: schbench: 4 - 4aom-av1: Speed 6 Two-Passstress-ng: CPU Stressstress-ng: NUMAstress-ng: System V Message Passingstress-ng: Memory Copyingstress-ng: MEMFDstress-ng: SENDFILEstress-ng: Cryptostress-ng: MMAPstress-ng: Vector Mathstress-ng: Atomicstress-ng: Matrix Mathstress-ng: Socket Activitystress-ng: Semaphoresperf-bench: Futex Lock-Piperf-bench: Futex Hashcompress-zstd: 3rsvg: SVG Files To PNGtesseract-ocr: Time To OCR 7 Imagescompilebench: Compileethr: HTTP - Bandwidth - 16ethr: UDP - Bandwidth - 16ethr: TCP - Bandwidth - 16ethr: TCP - Latency - 16redis: LPUSHpyperformance: json_loadspybench: Total For Average Test Timesbuild-apache: Time To Compileapache-siege: 50aom-av1: Speed 4 Two-Passoidn: Memorialosbench: Create Processesopenssl: RSA 4096-bit Performanceaom-av1: Speed 8 Realtimehackbench: 8 - Processocrmypdf: Processing 60 Page PDF Documentperf-bench: Sched Pipehackbench: 8 - Threadiperf: 5201 - 10 Seconds - TCP - 20neat: astcenc: Thoroughperf-bench: Memset 1MBdacapobench: Tradebeansrodinia: OpenMP Streamclustersvt-av1: Enc Mode 4 - 1080piperf: 5201 - 10 Seconds - TCP - 32iperf: 5201 - 10 Seconds - UDP - 32iperf: 5201 - 10 Seconds - UDP - 1000Mbit Objective - 32iperf: 5201 - 10 Seconds - TCP - 1iperf: 5201 - 10 Seconds - UDP - 1dacapobench: Tradesoapdacapobench: H2hackbench: 1 - Threadfs-mark: 4000 Files, 32 Sub Dirs, 1MB Sizefs-mark: 5000 Files, 1MB Size, 4 Threadsrodinia: OpenMP CFD Solverhackbench: 4 - Threadx265: H.265 1080p Video Encodinghackbench: 4 - Processdacapobench: Jythonsvt-av1: Enc Mode 8 - 1080pastcenc: Mediumsvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080phackbench: 2 - Threadperf-bench: Syscall Basicosbench: Create Fileshackbench: 2 - Processavifenc: 8avifenc: 10astcenc: Fastosbench: Create Threadsosbench: Memory Allocationsosbench: Launch Programssqlite: 8apache-siege: 1svt-vp9: Visual Quality Optimized - Bosphorus 1080pfs-mark: 1000 Files, 1MB Sizefs-mark: 1000 Files, 1MB Size, No Sync/FSynccompilebench: Read Compiled Treecompilebench: Initial CreateLinux 5.9-rc4Linux 5.8page_lock_unfairness 1000PLU 0PLU 115131.1025229.2453683.318333.12914532.64047039677.139836.5211441622.641885.241932.05.75290.202255332514511874565283.2401800.31359868.960759.61980.27710.412108.752196.64533.876125613.5717.04541655.73153.873918415119657.262560717.239749.931955.1480573064.14629320409.591238403854.02638298874.33410013372.5624.0099.14897.4840.120058072.340974.719552.8242450.590.17686.9881.1229.67284941729.032458.4457705.570.11373405.963418.7972.16527.214407410.6867.81367.281315513838062.08111469900.10070.11560.05430.05770.05900.05860.04460.04460.04470.044687232.258870.858012.256.6884084.74260037993262.69805454.99030.85453.4671620429.8350.53538.7109.2325733436106.8420975.030.8579021.046316102.437.9021072039138.5654.031768092.331444961.84183369.270.3028386.731332716.881269718.6941798463.528853.55578.1912519608.1412488.10825.00387421.396306.14410.72199819.54365322.27101892.2113647.403456386.4023044812198384.529.47528.7431949.982758.07100940.66666667157893.7777777820.941218625.2126.2106823.29726919.662.2618.2849.7539846339.132.2615.01518.87728126516.5203461716.28310.4858.640326530214.3646.7313439833.631821377011.05367740983.894886.91869.810.5969.55060.679.252462456.6816.71369.705.9511726296714.8846365.5585.5485.4135.4222.447109104.05127268.8997914.6196789.89285.77898.42442.33023.05585.6514187.8835098.6553656.008318.95014829.72547137421.637981.5208740015.339855.440102.35.76292.282248331614561860567282.6361823.49459368.258492.51959.97110.432117.255197.15537.09126313.4816.44501649.86551.954017658159490.652558784.837569.432192.6424603117.37559420934.704705408399.06463197790.33510450619.3324.2198.36997.2350.110159073.339296.657546.3439907.889.03886.3580.9929.57286039856.033656.4764896.910.11833384.016437.8272.58927.265407304.6068.00967.011310057860862.56711468970.10100.11290.05440.05820.05990.05860.04460.04450.04470.044586930.658686.157927.751.5914126.67079438999077.15068455.07530.16754.5661817867.4050.97438.6309.2265243354956.8133610.110.8580020.936438100.937.7591113838084.2648.791996950.611600412.63181365.520.2929495.141420279.271296318.3241816463.508898.87579.3213824575.9412739.56748.43385334.226317.76350.33200464.43365355.88101825.5613570.33487114.6422744894848361.729.25528.8591988.912736.14100755.11111111157569.1111111120.961353713.4026.3106223.04636228.062.2618.4343.6689066339.131.2313.08418.94927611614.7623560816.27710.4559.129714521014.5816.6803505633.630959371211.05361741383.239916.01875.510.6447.92559.996.434469856.0576.71365.294.6701723805814.7335524.3215.5965.4565.4221.004677102.88898162.3202324.6167912.29285.09900.72490.73023.05603.1714652.6095136.6403829.360333.73414932.19846841210.941239.9209842749.643050.342968.45.77292.172257341714821935565288.0361840.37561663.061429.61932.10110.252133.737197.25555.002125613.2717.17661648.19954.013817916643478.312459888.641078.532511.1299973098.47060320461.578628405279.01894097724.23310228760.9323.9297.62898.5840.111361061.443038.137615.3544164.889.08686.4381.1229.62283943064.432336.8159757.700.11503427.619428.5972.51225.737408020.5468.85067.001309413799362.27611481900.10090.11350.05440.05820.05850.05770.04460.04460.04470.044887178.358486.757928.855.7504198.94409638993508.76197855.17231.07054.4021622387.0550.62138.8399.0718893428860.5933136.280.8553320.136343100.137.9151101840363.5651.511680957.751449624.86182368.970.2828571.731278949.521293017.8741905463.518851.48583.6412721404.0912636.20878.86388762.896318.65418.80200124.38365018.05101696.1114156.543440309.1023044701768376.929.46428.6961986.202753.16106280.00000000158705.1111111120.341210430.4626.0106323.88235421.252.2416.5251.9965496354.330.6215.15918.98527885016.4633457816.32610.5058.343084531514.3826.7023422733.630732360091.05362441033.976908.11872.110.5939.62858.949.231466855.6606.71357.745.9441707592314.7799755.5445.5675.4565.4322.58698194.19743269.0102584.6076962.64286.27907.82453.73012.26587.9714520.5695088.3913744.847330.90714692.87846940899.941015.0217643135.743058.543686.05.80292.962206342014761944561288.5021811.15060448.361378.41932.34410.282124.541193.79555.233125913.5517.03011652.36352.474017338819763.472361352.441853.032120.1601963118.64587820423.500465403825.74317697798.43410098118.0224.2999.05396.4620.112062121.642082.119808.5243770.690.50686.2381.0429.54283141778.031946.5955534.270.11483378.128438.6072.53540.877403702.2268.73267.661309510816062.43311452930.10070.11370.05420.05810.05880.05870.04470.04460.04470.044687032.658726.057885.878.4764123.86723236991673.72266955.07745.10354.6591640722.7451.06138.7619.6231183438797.2420908.740.857186321100.637.4761101641024.6652.241796807.961446720.8181365.870.2928292.951262127.7118.4441932483.508861.03586.3712014924.1712644.37880.00392788.996302.15414.59199889.98364508.39102648.2814046.613444346.8923045157618351.129.50228.8671961.941201386.4626.0106423.94827965.622.2516.4652.5646216399.330.5922.00019.06527691023.1643520916.27610.4658.324344523814.5806.6853391933.631979374861.05355240673.425892.91859.010.62012.55358.6512.292466255.9276.71356.126.9371733022614.6775726.8285.5655.4435.4422.38353193.47176669.3273544.5627001.08287.16905.12460.13000.73585.2514592.3595149.2243754.067336.79214627.61246940789.840484.8212642823.643290.743044.65.83291.522266340514691936561286.2831787.26361072.161007.01948.85110.262124.232197.10536.25125113.6316.81891648.94852.044018008938957.852560487.041045.532129.5358973095.76250120383.394925404490.26163798328.0339899393.7024.2698.50697.7570.112761371.243516.836884.6444555.188.95786.8981.0029.40282043311.232857.2459273.900.11653449.435438.9172.95226.294406413.1468.64067.431312333790462.63011450430.10090.11350.05440.05770.05710.05700.04450.04460.04460.044786979.058881.857816.456.0874042.79049636993071.98275555.15831.08754.7701736465.5450.98739.4139.4058223450978.9433024.540.8584820.046329100.437.7541119840361.0653.311767421.971456349.79182363.090.2928472.821285133.001277018.1542014453.458874.14584.5712702276.0512826.51882.22392435.446207.71417.13199328.26364470.40102131.0914083.113456894.8323044538638320.729.47428.8301979.672725.61107358.00000000159066.8888888920.091222231.4226.4106223.75335185.432.2016.7849.6573456344.330.2014.61819.04828332616.4083471116.28910.4659.791643523214.4776.6933448633.630013377521.05361240844.205937.11878.010.7189.58158.529.263464555.8426.68358.005.9641716155214.7910155.5585.5595.4425.4522.09663493.38402767.2260924.6037062.00286.31886.32432.03033.84588.25OpenBenchmarking.org

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 0.10.0Test: Savina Reactors.IOpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83K6K9K12K15KSE +/- 282.10, N = 20SE +/- 149.07, N = 20SE +/- 345.76, N = 20SE +/- 596.06, N = 15SE +/- 173.05, N = 2014652.6114592.3614520.5715131.1014187.88
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Savina Reactors.IOpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83K6K9K12K15KMin: 12542.23 / Avg: 14652.61 / Max: 18696.52Min: 13748.61 / Avg: 14592.36 / Max: 16206.45Min: 12105.97 / Avg: 14520.57 / Max: 18723.17Min: 12772.07 / Avg: 15131.1 / Max: 21838.79Min: 12683.5 / Avg: 14187.88 / Max: 15484.7

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: In-Memory Database Shootoutpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.811002200330044005500SE +/- 53.29, N = 25SE +/- 48.80, N = 25SE +/- 59.42, N = 25SE +/- 42.32, N = 25SE +/- 42.42, N = 255136.645149.225088.395229.255098.66
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: In-Memory Database Shootoutpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89001800270036004500Min: 4581.46 / Avg: 5136.64 / Max: 5561.01Min: 4689.18 / Avg: 5149.22 / Max: 5614.06Min: 4431.91 / Avg: 5088.39 / Max: 5648.69Min: 4815.22 / Avg: 5229.25 / Max: 5512.97Min: 4676.55 / Avg: 5098.65 / Max: 5430.04

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark PageRankpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.88001600240032004000SE +/- 22.58, N = 5SE +/- 25.25, N = 25SE +/- 33.38, N = 25SE +/- 31.40, N = 25SE +/- 39.49, N = 213829.363754.073744.853683.323656.01
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark PageRankpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87001400210028003500Min: 3751.25 / Avg: 3829.36 / Max: 3882.42Min: 3262.24 / Avg: 3754.07 / Max: 3896.57Min: 3397.14 / Avg: 3744.85 / Max: 4027.28Min: 3246.11 / Avg: 3683.32 / Max: 3869.37Min: 3316.84 / Avg: 3656.01 / Max: 3982.26

Java Gradle Build

This test runs Java software project builds using the Gradle build system. It is intended to give developers an idea as to the build performance for development activities and build servers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterJava Gradle BuildGradle Build: Reactorpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.870140210280350SE +/- 4.65, N = 4SE +/- 0.85, N = 3SE +/- 5.30, N = 9SE +/- 5.33, N = 9SE +/- 4.35, N = 4333.73336.79330.91333.13318.95
OpenBenchmarking.orgSeconds, Fewer Is BetterJava Gradle BuildGradle Build: Reactorpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.860120180240300Min: 328.45 / Avg: 333.73 / Max: 347.64Min: 335.23 / Avg: 336.79 / Max: 338.14Min: 306.56 / Avg: 330.91 / Max: 357.82Min: 309.39 / Avg: 333.13 / Max: 361.58Min: 307.52 / Avg: 318.95 / Max: 328.57

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 0.10.0Test: Akka Unbalanced Cobwebbed Treepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83K6K9K12K15KSE +/- 189.63, N = 5SE +/- 175.16, N = 5SE +/- 115.45, N = 5SE +/- 123.71, N = 5SE +/- 66.42, N = 514932.2014627.6114692.8814532.6414829.73
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Akka Unbalanced Cobwebbed Treepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83K6K9K12K15KMin: 14431.13 / Avg: 14932.2 / Max: 15421.4Min: 13975.15 / Avg: 14627.61 / Max: 14917.74Min: 14423.16 / Avg: 14692.88 / Max: 15070.65Min: 14207.69 / Avg: 14532.64 / Max: 14905.52Min: 14649.4 / Avg: 14829.73 / Max: 15059.33

MariaDB

This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 256page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8100200300400500SE +/- 0.32, N = 3SE +/- 0.77, N = 3SE +/- 0.26, N = 3SE +/- 0.27, N = 3SE +/- 0.26, N = 34684694694704711. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 256page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.880160240320400Min: 467.73 / Avg: 468.24 / Max: 468.82Min: 467.73 / Avg: 468.61 / Max: 470.15Min: 468.38 / Avg: 468.75 / Max: 469.26Min: 469.7 / Avg: 470.07 / Max: 470.59Min: 470.81 / Avg: 471.25 / Max: 471.71. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

Memcached mcperf

This is a test of twmperf/mcperf with memcached, a distributed memory object caching system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Add - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89K18K27K36K45KSE +/- 35.29, N = 3SE +/- 474.28, N = 3SE +/- 149.13, N = 3SE +/- 127.76, N = 3SE +/- 182.57, N = 341210.940789.840899.939677.137421.61. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Add - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87K14K21K28K35KMin: 41163.5 / Avg: 41210.9 / Max: 41279.9Min: 39874.6 / Avg: 40789.83 / Max: 41463.3Min: 40715.6 / Avg: 40899.87 / Max: 41195.1Min: 39448.2 / Avg: 39677.13 / Max: 39889.9Min: 37066.5 / Avg: 37421.63 / Max: 37672.71. (CC) gcc options: -O2 -lm -rdynamic

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Set - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89K18K27K36K45KSE +/- 142.28, N = 3SE +/- 176.79, N = 3SE +/- 462.21, N = 3SE +/- 40.38, N = 3SE +/- 201.66, N = 341239.940484.841015.039836.537981.51. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Set - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87K14K21K28K35KMin: 41057.3 / Avg: 41239.9 / Max: 41520.2Min: 40142.3 / Avg: 40484.8 / Max: 40732.1Min: 40096.7 / Avg: 41015 / Max: 41566.1Min: 39785.5 / Avg: 39836.47 / Max: 39916.2Min: 37745.3 / Avg: 37981.47 / Max: 38382.71. (CC) gcc options: -O2 -lm -rdynamic

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: Eigenpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.85001000150020002500SE +/- 18.78, N = 3SE +/- 30.09, N = 3SE +/- 26.12, N = 3SE +/- 26.31, N = 3SE +/- 31.24, N = 4209821262176211420871. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: Eigenpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8400800120016002000Min: 2066 / Avg: 2097.67 / Max: 2131Min: 2092 / Avg: 2126 / Max: 2186Min: 2128 / Avg: 2175.67 / Max: 2218Min: 2067 / Avg: 2114 / Max: 2158Min: 2030 / Avg: 2086.5 / Max: 21681. (CXX) g++ options: -flto -pthread

Memcached mcperf

This is a test of twmperf/mcperf with memcached, a distributed memory object caching system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Append - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89K18K27K36K45KSE +/- 257.35, N = 3SE +/- 92.67, N = 3SE +/- 440.23, N = 3SE +/- 117.77, N = 3SE +/- 135.05, N = 342749.642823.643135.741622.640015.31. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Append - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87K14K21K28K35KMin: 42457.7 / Avg: 42749.63 / Max: 43262.7Min: 42699 / Avg: 42823.57 / Max: 43004.7Min: 42262.5 / Avg: 43135.73 / Max: 43669.8Min: 41432.2 / Avg: 41622.63 / Max: 41837.9Min: 39778.4 / Avg: 40015.27 / Max: 40246.11. (CC) gcc options: -O2 -lm -rdynamic

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Replace - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89K18K27K36K45KSE +/- 193.34, N = 3SE +/- 236.28, N = 3SE +/- 251.46, N = 3SE +/- 129.28, N = 3SE +/- 208.77, N = 343050.343290.743058.541885.239855.41. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Replace - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.88K16K24K32K40KMin: 42719.5 / Avg: 43050.27 / Max: 43389.1Min: 42958.3 / Avg: 43290.7 / Max: 43747.8Min: 42600.9 / Avg: 43058.47 / Max: 43468Min: 41664.4 / Avg: 41885.23 / Max: 42112.1Min: 39594.8 / Avg: 39855.37 / Max: 40268.21. (CC) gcc options: -O2 -lm -rdynamic

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Prepend - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89K18K27K36K45KSE +/- 209.95, N = 3SE +/- 144.50, N = 3SE +/- 200.88, N = 3SE +/- 41.21, N = 3SE +/- 66.44, N = 342968.443044.643686.041932.040102.31. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Prepend - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.88K16K24K32K40KMin: 42552.7 / Avg: 42968.4 / Max: 43227.5Min: 42814.2 / Avg: 43044.63 / Max: 43310.9Min: 43301.9 / Avg: 43686 / Max: 43980.1Min: 41850.6 / Avg: 41932.03 / Max: 41983.8Min: 39984.2 / Avg: 40102.3 / Max: 40214.11. (CC) gcc options: -O2 -lm -rdynamic

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81.31182.62363.93545.24726.559SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 35.775.835.805.755.76
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810Min: 5.69 / Avg: 5.77 / Max: 5.88Min: 5.82 / Avg: 5.83 / Max: 5.85Min: 5.72 / Avg: 5.8 / Max: 5.85Min: 5.73 / Avg: 5.75 / Max: 5.79Min: 5.74 / Avg: 5.76 / Max: 5.78

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 0.9Benchmark: vklBenchmarkpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.860120180240300SE +/- 0.50, N = 3SE +/- 0.60, N = 3SE +/- 0.18, N = 3SE +/- 0.85, N = 3SE +/- 0.51, N = 3292.17291.52292.96290.20292.28MIN: 1 / MAX: 1029MIN: 1 / MAX: 1035MIN: 1 / MAX: 1040MIN: 1 / MAX: 1034MIN: 1 / MAX: 1031
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.850100150200250Min: 291.17 / Avg: 292.17 / Max: 292.78Min: 290.39 / Avg: 291.52 / Max: 292.44Min: 292.61 / Avg: 292.96 / Max: 293.17Min: 288.5 / Avg: 290.2 / Max: 291.11Min: 291.61 / Avg: 292.28 / Max: 293.28

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: BLASpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.85001000150020002500SE +/- 21.11, N = 3SE +/- 18.19, N = 3SE +/- 15.06, N = 3SE +/- 24.90, N = 3SE +/- 16.05, N = 3225722662206225522481. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: BLASpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8400800120016002000Min: 2222 / Avg: 2257.33 / Max: 2295Min: 2234 / Avg: 2266 / Max: 2297Min: 2176 / Avg: 2205.67 / Max: 2225Min: 2207 / Avg: 2254.67 / Max: 2291Min: 2228 / Avg: 2248.33 / Max: 22801. (CXX) g++ options: -flto -pthread

AI Benchmark Alpha

AI Benchmark Alpha is a Python library for evaluating artificial intelligence (AI) performance on diverse hardware platforms and relies upon the TensorFlow machine learning library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI Scorepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8700140021002800350034173405342033253316

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training Scorepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83006009001200150014821469147614511456

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference Scorepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.840080012001600200019351936194418741860

MariaDB

This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 128page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8120240360480600SE +/- 0.37, N = 3SE +/- 0.91, N = 3SE +/- 0.38, N = 3SE +/- 0.43, N = 3SE +/- 0.28, N = 35655615615655671. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 128page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8100200300400500Min: 564.02 / Avg: 564.65 / Max: 565.29Min: 558.97 / Avg: 560.65 / Max: 562.11Min: 560.85 / Avg: 561.38 / Max: 562.11Min: 564.65 / Avg: 565.08 / Max: 565.93Min: 566.25 / Avg: 566.79 / Max: 567.211. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

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 10.0Time To Compilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.860120180240300SE +/- 2.44, N = 3SE +/- 4.57, N = 3SE +/- 3.81, N = 5SE +/- 3.09, N = 3SE +/- 0.81, N = 3288.04286.28288.50283.24282.64
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To Compilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.850100150200250Min: 284.8 / Avg: 288.04 / Max: 292.81Min: 279.47 / Avg: 286.28 / Max: 294.96Min: 275.56 / Avg: 288.5 / Max: 298.11Min: 277.26 / Avg: 283.24 / Max: 287.54Min: 281.54 / Avg: 282.64 / Max: 284.22

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 0.10.0Test: Genetic Algorithm Using Jenetics + Futurespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8400800120016002000SE +/- 11.35, N = 25SE +/- 11.35, N = 5SE +/- 13.30, N = 5SE +/- 20.78, N = 5SE +/- 19.79, N = 51840.381787.261811.151800.311823.49
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Genetic Algorithm Using Jenetics + Futurespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.830060090012001500Min: 1717.33 / Avg: 1840.37 / Max: 1984.6Min: 1763.16 / Avg: 1787.26 / Max: 1816.87Min: 1781.46 / Avg: 1811.15 / Max: 1849.07Min: 1739.9 / Avg: 1800.31 / Max: 1868.73Min: 1756.67 / Avg: 1823.49 / Max: 1865.73

Memcached mcperf

This is a test of twmperf/mcperf with memcached, a distributed memory object caching system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Delete - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.813K26K39K52K65KSE +/- 25.50, N = 3SE +/- 350.62, N = 3SE +/- 249.02, N = 3SE +/- 280.02, N = 3SE +/- 656.67, N = 361663.061072.160448.359868.959368.21. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Delete - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.811K22K33K44K55KMin: 61618.3 / Avg: 61662.97 / Max: 61706.6Min: 60417.3 / Avg: 61072.13 / Max: 61616.8Min: 60129.7 / Avg: 60448.27 / Max: 60939.1Min: 59371.6 / Avg: 59868.93 / Max: 60340.6Min: 58068.2 / Avg: 59368.17 / Max: 60180.11. (CC) gcc options: -O2 -lm -rdynamic

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Get - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.813K26K39K52K65KSE +/- 617.13, N = 3SE +/- 736.55, N = 3SE +/- 224.29, N = 3SE +/- 492.13, N = 3SE +/- 299.89, N = 361429.661007.061378.460759.658492.51. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Get - Connections: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.811K22K33K44K55KMin: 60388.4 / Avg: 61429.63 / Max: 62524.2Min: 59789.7 / Avg: 61007 / Max: 62334.1Min: 61078.8 / Avg: 61378.37 / Max: 61817.3Min: 59810.7 / Avg: 60759.63 / Max: 61460.4Min: 57905.1 / Avg: 58492.53 / Max: 58891.11. (CC) gcc options: -O2 -lm -rdynamic

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 0.10.0Test: Random Forestpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8400800120016002000SE +/- 12.57, N = 21SE +/- 16.96, N = 5SE +/- 22.29, N = 5SE +/- 20.68, N = 8SE +/- 9.85, N = 51932.101948.851932.341980.281959.97
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Random Forestpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.830060090012001500Min: 1770.46 / Avg: 1932.1 / Max: 2041.64Min: 1900.57 / Avg: 1948.85 / Max: 1997.67Min: 1874.27 / Avg: 1932.34 / Max: 2006.12Min: 1880.3 / Avg: 1980.28 / Max: 2064.92Min: 1928.35 / Avg: 1959.97 / Max: 1985.52

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: CPUpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 310.2510.2610.2810.4110.43
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: CPUpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215Min: 10.18 / Avg: 10.25 / Max: 10.32Min: 10.22 / Avg: 10.26 / Max: 10.28Min: 10.24 / Avg: 10.28 / Max: 10.32Min: 10.35 / Avg: 10.41 / Max: 10.5Min: 10.35 / Avg: 10.43 / Max: 10.5

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 0.10.0Test: Apache Spark ALSpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.85001000150020002500SE +/- 19.38, N = 5SE +/- 11.26, N = 5SE +/- 23.87, N = 7SE +/- 13.10, N = 5SE +/- 13.96, N = 252133.742124.232124.542108.752117.26
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark ALSpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8400800120016002000Min: 2093.24 / Avg: 2133.74 / Max: 2201.84Min: 2095.08 / Avg: 2124.23 / Max: 2155.35Min: 2075.46 / Avg: 2124.54 / Max: 2262.31Min: 2058.26 / Avg: 2108.75 / Max: 2127.57Min: 2053.87 / Avg: 2117.26 / Max: 2394.62

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Classroom - Compute: CPU-Onlypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.84080120160200SE +/- 0.95, N = 3SE +/- 0.54, N = 3SE +/- 0.14, N = 3SE +/- 0.43, N = 3SE +/- 0.38, N = 3197.25197.10193.79196.64197.15
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Classroom - Compute: CPU-Onlypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.84080120160200Min: 196.09 / Avg: 197.25 / Max: 199.13Min: 196.03 / Avg: 197.1 / Max: 197.71Min: 193.55 / Avg: 193.79 / Max: 194.03Min: 196.04 / Avg: 196.64 / Max: 197.48Min: 196.48 / Avg: 197.15 / Max: 197.78

CP2K Molecular Dynamics

CP2K is an open-source molecular dynamics software package focused on quantum chemistry and solid-state physics. This test profile currently makes use of the OpenMP implementation and using the Fayalite-FIST molecular dynamics run and measures the total time to complete. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 6.1Fayalite-FIST Datapage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8120240360480600555.00536.25555.23533.88537.09

MariaDB

This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 64page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.830060090012001500SE +/- 3.16, N = 3SE +/- 1.38, N = 3SE +/- 2.30, N = 3SE +/- 1.39, N = 3SE +/- 1.60, N = 3125612511259125612631. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 64page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82004006008001000Min: 1253.13 / Avg: 1256.3 / Max: 1262.63Min: 1248.44 / Avg: 1251.05 / Max: 1253.13Min: 1254.71 / Avg: 1258.93 / Max: 1262.63Min: 1253.13 / Avg: 1255.76 / Max: 1257.86Min: 1261.03 / Avg: 1262.63 / Max: 1265.821. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: CPUpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.848121620SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 313.2713.6313.5513.5713.48
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: CPUpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.848121620Min: 13.2 / Avg: 13.27 / Max: 13.33Min: 13.59 / Avg: 13.63 / Max: 13.67Min: 13.49 / Avg: 13.55 / Max: 13.6Min: 13.55 / Avg: 13.57 / Max: 13.61Min: 13.43 / Avg: 13.48 / Max: 13.55

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 3.1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.848121620SE +/- 0.05, N = 3SE +/- 0.15, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.17, N = 317.1816.8217.0317.0516.451. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.848121620Min: 17.07 / Avg: 17.18 / Max: 17.24Min: 16.6 / Avg: 16.82 / Max: 17.11Min: 17 / Avg: 17.03 / Max: 17.05Min: 16.97 / Avg: 17.05 / Max: 17.16Min: 16.13 / Avg: 16.45 / Max: 16.71. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

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 0.10.0Test: Scala Dottypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8400800120016002000SE +/- 12.98, N = 5SE +/- 5.12, N = 5SE +/- 5.99, N = 5SE +/- 8.56, N = 5SE +/- 3.92, N = 51648.201648.951652.361655.731649.87
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Scala Dottypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.830060090012001500Min: 1625.43 / Avg: 1648.2 / Max: 1687.34Min: 1634.33 / Avg: 1648.95 / Max: 1662.51Min: 1634.56 / Avg: 1652.36 / Max: 1670.54Min: 1639.44 / Avg: 1655.73 / Max: 1686.69Min: 1637.43 / Avg: 1649.87 / Max: 1661.01

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 0.11.07Test: CPU Cachepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81224364860SE +/- 0.83, N = 15SE +/- 0.84, N = 15SE +/- 0.84, N = 15SE +/- 0.87, N = 3SE +/- 0.84, N = 1554.0152.0452.4753.8751.951. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU Cachepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81122334455Min: 46.65 / Avg: 54.01 / Max: 60.31Min: 45.88 / Avg: 52.04 / Max: 57.24Min: 47.11 / Avg: 52.47 / Max: 58.44Min: 52.62 / Avg: 53.87 / Max: 55.55Min: 47.31 / Avg: 51.95 / Max: 57.241. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 2 - Workers Per Message Thread: 8page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8918273645SE +/- 0.47, N = 15SE +/- 0.72, N = 15SE +/- 1.17, N = 12SE +/- 0.53, N = 1538404039401. (CC) gcc options: -O2 -lpthread
OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 2 - Workers Per Message Thread: 8page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8816243240Min: 36 / Avg: 38.13 / Max: 42Min: 36 / Avg: 39.53 / Max: 46Min: 36 / Avg: 40 / Max: 50Min: 36 / Avg: 38.87 / Max: 431. (CC) gcc options: -O2 -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 3.11.4Test: Writespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.840K80K120K160K200KSE +/- 2398.64, N = 3SE +/- 1644.20, N = 10SE +/- 1812.57, N = 3SE +/- 2545.69, N = 3SE +/- 1589.70, N = 3179166180089173388184151176581
OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: Writespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.830K60K90K120K150KMin: 175471 / Avg: 179165.67 / Max: 183663Min: 175159 / Avg: 180089.1 / Max: 190478Min: 170945 / Avg: 173388 / Max: 176929Min: 179714 / Avg: 184151 / Max: 188532Min: 174610 / Avg: 176581 / Max: 179727

Apache Siege

This is a test of the Apache web server performance being facilitated by the Siege web serverb enchmark program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 250page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.813K26K39K52K65KSE +/- 236.51, N = 3SE +/- 129.13, N = 3SE +/- 106.42, N = 3SE +/- 28.55, N = 3SE +/- 1678.24, N = 1543478.3138957.8519763.4719657.2659490.651. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 250page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.810K20K30K40K50KMin: 43148.09 / Avg: 43478.31 / Max: 43936.73Min: 38699.69 / Avg: 38957.85 / Max: 39093.04Min: 19647.91 / Avg: 19763.47 / Max: 19976.03Min: 19618.61 / Avg: 19657.26 / Max: 19712.98Min: 40173.55 / Avg: 59490.65 / Max: 63694.271. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 2page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8612182430SE +/- 0.48, N = 15SE +/- 0.97, N = 15SE +/- 0.79, N = 1224252325251. (CC) gcc options: -O2 -lpthread
OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 2page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8612182430Min: 22 / Avg: 24.2 / Max: 29Min: 22 / Avg: 25.07 / Max: 36Min: 23 / Avg: 25.42 / Max: 321. (CC) gcc options: -O2 -lpthread

Memcached mcperf

This is a test of twmperf/mcperf with memcached, a distributed memory object caching system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Delete - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.813K26K39K52K65KSE +/- 562.95, N = 15SE +/- 710.11, N = 15SE +/- 706.32, N = 15SE +/- 661.72, N = 15SE +/- 733.36, N = 1559888.660487.061352.460717.258784.81. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Delete - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.811K22K33K44K55KMin: 56929.3 / Avg: 59888.63 / Max: 63552.1Min: 56788.8 / Avg: 60487 / Max: 65207.1Min: 58475.2 / Avg: 61352.41 / Max: 65732.6Min: 57081.3 / Avg: 60717.23 / Max: 65244.1Min: 54616.2 / Avg: 58784.84 / Max: 62107.81. (CC) gcc options: -O2 -lm -rdynamic

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Add - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89K18K27K36K45KSE +/- 478.98, N = 6SE +/- 460.43, N = 15SE +/- 456.01, N = 7SE +/- 342.85, N = 11SE +/- 373.15, N = 1541078.541045.541853.039749.937569.41. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Add - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87K14K21K28K35KMin: 39215.7 / Avg: 41078.5 / Max: 42041Min: 39006.5 / Avg: 41045.53 / Max: 44909.9Min: 39661.2 / Avg: 41853.01 / Max: 43312.2Min: 38355 / Avg: 39749.85 / Max: 41335Min: 36153.5 / Avg: 37569.44 / Max: 40123.41. (CC) gcc options: -O2 -lm -rdynamic

PostgreSQL pgbench

This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read Writepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87K14K21K28K35KSE +/- 88.82, N = 3SE +/- 197.83, N = 3SE +/- 52.94, N = 3SE +/- 140.24, N = 3SE +/- 126.41, N = 332511.1332129.5432120.1631955.1532192.641. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read Writepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.86K12K18K24K30KMin: 32335.76 / Avg: 32511.13 / Max: 32623.37Min: 31748.15 / Avg: 32129.54 / Max: 32411.46Min: 32046.86 / Avg: 32120.16 / Max: 32222.97Min: 31675.24 / Avg: 31955.15 / Max: 32110.73Min: 32038.64 / Avg: 32192.64 / Max: 32443.281. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Single Thread - Mode: Read Writepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87001400210028003500SE +/- 10.63, N = 3SE +/- 24.96, N = 3SE +/- 12.54, N = 3SE +/- 22.86, N = 3SE +/- 16.49, N = 33098.473095.763118.653064.153117.381. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Single Thread - Mode: Read Writepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.85001000150020002500Min: 3083.23 / Avg: 3098.47 / Max: 3118.93Min: 3051.56 / Avg: 3095.76 / Max: 3137.97Min: 3098.17 / Avg: 3118.65 / Max: 3141.42Min: 3019.94 / Avg: 3064.15 / Max: 3096.33Min: 3084.65 / Avg: 3117.38 / Max: 3137.211. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Single Thread - Mode: Read Onlypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.84K8K12K16K20KSE +/- 87.60, N = 3SE +/- 141.35, N = 3SE +/- 128.84, N = 3SE +/- 61.10, N = 3SE +/- 244.73, N = 320461.5820383.3920423.5020409.5920934.701. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Single Thread - Mode: Read Onlypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.84K8K12K16K20KMin: 20326.76 / Avg: 20461.58 / Max: 20625.89Min: 20155.17 / Avg: 20383.39 / Max: 20641.98Min: 20220.42 / Avg: 20423.5 / Max: 20662.39Min: 20297.99 / Avg: 20409.59 / Max: 20508.5Min: 20474.3 / Avg: 20934.7 / Max: 21308.761. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read Onlypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.890K180K270K360K450KSE +/- 151.42, N = 3SE +/- 602.67, N = 3SE +/- 85.70, N = 3SE +/- 993.29, N = 3SE +/- 136.76, N = 3405279.02404490.26403825.74403854.03408399.061. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read Onlypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.870K140K210K280K350KMin: 404990.41 / Avg: 405279.02 / Max: 405502.79Min: 403339.63 / Avg: 404490.26 / Max: 405376.49Min: 403737.56 / Avg: 403825.74 / Max: 403997.12Min: 402217.5 / Avg: 403854.03 / Max: 405647.57Min: 408218.3 / Avg: 408399.06 / Max: 408667.221. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -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: NASNet Mobilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820K40K60K80K100KSE +/- 131.50, N = 3SE +/- 345.79, N = 3SE +/- 215.31, N = 3SE +/- 813.90, N = 15SE +/- 201.80, N = 397724.298328.097798.498874.397790.3
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet Mobilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820K40K60K80K100KMin: 97469.1 / Avg: 97724.23 / Max: 97907.1Min: 97685 / Avg: 98328.03 / Max: 98870Min: 97569.6 / Avg: 97798.37 / Max: 98228.7Min: 97201.8 / Avg: 98874.33 / Max: 109689Min: 97400.7 / Avg: 97790.27 / Max: 98076.4

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 2 - Workers Per Message Thread: 6page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8816243240SE +/- 0.32, N = 15SE +/- 0.33, N = 3SE +/- 0.46, N = 1533333434351. (CC) gcc options: -O2 -lpthread
OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 2 - Workers Per Message Thread: 6page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8714212835Min: 32 / Avg: 33.33 / Max: 36Min: 33 / Avg: 33.33 / Max: 34Min: 31 / Avg: 33.8 / Max: 371. (CC) gcc options: -O2 -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 0.11.07Test: Context Switchingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82M4M6M8M10MSE +/- 86006.24, N = 15SE +/- 162599.66, N = 3SE +/- 106510.87, N = 15SE +/- 139140.74, N = 3SE +/- 83653.88, N = 1410228760.939899393.7010098118.0210013372.5610450619.331. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Context Switchingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82M4M6M8M10MMin: 9505318.6 / Avg: 10228760.93 / Max: 10706359.36Min: 9662360.45 / Avg: 9899393.7 / Max: 10210724.68Min: 9302946.95 / Avg: 10098118.02 / Max: 10850197.43Min: 9870031.22 / Avg: 10013372.56 / Max: 10291611.34Min: 9685432.94 / Avg: 10450619.33 / Max: 10806709.631. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8612182430SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.19, N = 3SE +/- 0.21, N = 3SE +/- 0.15, N = 323.9224.2624.2924.0024.21
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8612182430Min: 23.83 / Avg: 23.92 / Max: 24.04Min: 24.22 / Avg: 24.26 / Max: 24.3Min: 24.1 / Avg: 24.29 / Max: 24.67Min: 23.63 / Avg: 24 / Max: 24.35Min: 24.02 / Avg: 24.21 / Max: 24.5

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 LavaMDpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820406080100SE +/- 0.20, N = 3SE +/- 1.14, N = 3SE +/- 0.70, N = 3SE +/- 1.72, N = 3SE +/- 1.48, N = 397.6398.5199.0599.1598.371. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820406080100Min: 97.23 / Avg: 97.63 / Max: 97.88Min: 97.08 / Avg: 98.51 / Max: 100.77Min: 97.97 / Avg: 99.05 / Max: 100.35Min: 97.16 / Avg: 99.15 / Max: 102.57Min: 96.07 / Avg: 98.37 / Max: 101.121. (CXX) g++ options: -O2 -lOpenCL

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3Dpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820406080100SE +/- 1.41, N = 3SE +/- 0.02, N = 3SE +/- 0.59, N = 3SE +/- 0.20, N = 3SE +/- 0.63, N = 398.5897.7696.4697.4897.241. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3Dpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820406080100Min: 95.87 / Avg: 98.58 / Max: 100.58Min: 97.73 / Avg: 97.76 / Max: 97.78Min: 95.8 / Avg: 96.46 / Max: 97.64Min: 97.17 / Avg: 97.48 / Max: 97.87Min: 95.98 / Avg: 97.24 / Max: 97.871. (CXX) g++ options: -O2 -lOpenCL

pmbench

Pmbench is a Linux paging and virtual memory benchmark. This test profile will report the average page latency of the system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 2 - Read-Write Ratio: 50%page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.0270.0540.0810.1080.135SE +/- 0.0000, N = 3SE +/- 0.0010, N = 11SE +/- 0.0000, N = 3SE +/- 0.0001, N = 3SE +/- 0.0015, N = 40.11130.11270.11200.12000.11011. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 2 - Read-Write Ratio: 50%page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812345Min: 0.11 / Avg: 0.11 / Max: 0.11Min: 0.11 / Avg: 0.11 / Max: 0.12Min: 0.11 / Avg: 0.11 / Max: 0.11Min: 0.12 / Avg: 0.12 / Max: 0.12Min: 0.11 / Avg: 0.11 / Max: 0.111. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

Memcached mcperf

This is a test of twmperf/mcperf with memcached, a distributed memory object caching system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Get - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.813K26K39K52K65KSE +/- 571.32, N = 15SE +/- 577.62, N = 15SE +/- 664.31, N = 15SE +/- 550.61, N = 3SE +/- 634.23, N = 1561061.461371.262121.658072.359073.31. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Get - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.811K22K33K44K55KMin: 57701.4 / Avg: 61061.44 / Max: 65269.3Min: 58179.9 / Avg: 61371.22 / Max: 64830.7Min: 58428.3 / Avg: 62121.64 / Max: 65382.6Min: 57499.1 / Avg: 58072.3 / Max: 59173.2Min: 56174.2 / Avg: 59073.29 / Max: 63610.71. (CC) gcc options: -O2 -lm -rdynamic

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Replace - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89K18K27K36K45KSE +/- 457.84, N = 15SE +/- 411.52, N = 10SE +/- 484.12, N = 3SE +/- 560.74, N = 4SE +/- 347.73, N = 1543038.143516.842082.140974.739296.61. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Replace - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.88K16K24K32K40KMin: 41483.2 / Avg: 43038.06 / Max: 47073.9Min: 42228.8 / Avg: 43516.82 / Max: 45650.6Min: 41163.8 / Avg: 42082.07 / Max: 42807.1Min: 40021.5 / Avg: 40974.73 / Max: 42586.4Min: 37628.4 / Avg: 39296.59 / Max: 41799.51. (CC) gcc options: -O2 -lm -rdynamic

Apache Siege

This is a test of the Apache web server performance being facilitated by the Siege web serverb enchmark program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 200page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812K24K36K48K60KSE +/- 53.10, N = 3SE +/- 52.26, N = 3SE +/- 139.50, N = 3SE +/- 74.75, N = 3SE +/- 927.04, N = 1337615.3536884.6419808.5219552.8257546.341. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 200page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.810K20K30K40K50KMin: 37523.45 / Avg: 37615.35 / Max: 37707.39Min: 36784.99 / Avg: 36884.64 / Max: 36961.75Min: 19602.08 / Avg: 19808.52 / Max: 20074.28Min: 19459.04 / Avg: 19552.82 / Max: 19700.55Min: 46587.47 / Avg: 57546.34 / Max: 59154.091. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

Memcached mcperf

This is a test of twmperf/mcperf with memcached, a distributed memory object caching system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Prepend - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.810K20K30K40K50KSE +/- 427.88, N = 9SE +/- 761.33, N = 3SE +/- 373.90, N = 15SE +/- 633.01, N = 4SE +/- 394.48, N = 1544164.844555.143770.642450.539907.81. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Prepend - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.88K16K24K32K40KMin: 41373.9 / Avg: 44164.79 / Max: 45528Min: 43226.9 / Avg: 44555.07 / Max: 45864Min: 41155.7 / Avg: 43770.59 / Max: 45683.2Min: 40815 / Avg: 42450.48 / Max: 43904.7Min: 37981.9 / Avg: 39907.83 / Max: 42324.41. (CC) gcc options: -O2 -lm -rdynamic

YafaRay

YafaRay is an open-source physically based montecarlo ray-tracing engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample Scenepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820406080100SE +/- 0.12, N = 3SE +/- 0.51, N = 3SE +/- 1.08, N = 3SE +/- 0.89, N = 3SE +/- 0.69, N = 389.0988.9690.5190.1889.041. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample Scenepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820406080100Min: 88.85 / Avg: 89.09 / Max: 89.25Min: 87.99 / Avg: 88.96 / Max: 89.74Min: 88.4 / Avg: 90.51 / Max: 91.99Min: 88.66 / Avg: 90.18 / Max: 91.76Min: 88.02 / Avg: 89.04 / Max: 90.361. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Fishy Cat - Compute: CPU-Onlypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820406080100SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.29, N = 3SE +/- 0.18, N = 386.4386.8986.2386.9886.35
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Fishy Cat - Compute: CPU-Onlypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81632486480Min: 86.31 / Avg: 86.43 / Max: 86.6Min: 86.67 / Avg: 86.89 / Max: 87.03Min: 86.07 / Avg: 86.23 / Max: 86.42Min: 86.56 / Avg: 86.98 / Max: 87.54Min: 86.01 / Avg: 86.35 / Max: 86.64

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Exhaustivepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820406080100SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 381.1281.0081.0481.1280.991. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Exhaustivepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81530456075Min: 80.91 / Avg: 81.12 / Max: 81.31Min: 80.81 / Avg: 81 / Max: 81.12Min: 80.9 / Avg: 81.04 / Max: 81.14Min: 80.93 / Avg: 81.12 / Max: 81.27Min: 80.82 / Avg: 80.99 / Max: 81.081. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8714212835SE +/- 0.27, N = 3SE +/- 0.27, N = 3SE +/- 0.45, N = 3SE +/- 0.04, N = 3SE +/- 0.25, N = 329.6229.4029.5429.6729.57
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8714212835Min: 29.09 / Avg: 29.62 / Max: 29.97Min: 28.88 / Avg: 29.4 / Max: 29.78Min: 28.91 / Avg: 29.54 / Max: 30.42Min: 29.62 / Avg: 29.67 / Max: 29.74Min: 29.32 / Avg: 29.57 / Max: 30.08

MariaDB

This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 32page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.86001200180024003000SE +/- 2.01, N = 4SE +/- 2.65, N = 3SE +/- 2.00, N = 4SE +/- 4.69, N = 3SE +/- 2.73, N = 3283928202831284928601. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 32page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.85001000150020002500Min: 2832.86 / Avg: 2838.9 / Max: 2840.91Min: 2816.9 / Avg: 2819.55 / Max: 2824.86Min: 2824.86 / Avg: 2830.86 / Max: 2832.86Min: 2840.91 / Avg: 2849.02 / Max: 2857.14Min: 2857.14 / Avg: 2859.87 / Max: 2865.331. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

Memcached mcperf

This is a test of twmperf/mcperf with memcached, a distributed memory object caching system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Append - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89K18K27K36K45KSE +/- 500.81, N = 5SE +/- 463.31, N = 15SE +/- 606.62, N = 3SE +/- 362.05, N = 15SE +/- 650.04, N = 343064.443311.241778.041729.039856.01. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Append - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.88K16K24K32K40KMin: 41805.5 / Avg: 43064.36 / Max: 44657.3Min: 41142.4 / Avg: 43311.23 / Max: 46137.4Min: 40564.8 / Avg: 41778.03 / Max: 42389.4Min: 40057.6 / Avg: 41728.97 / Max: 43952.3Min: 38573.2 / Avg: 39856.03 / Max: 40680.21. (CC) gcc options: -O2 -lm -rdynamic

NGINX Benchmark

This is a test of ab, which is the Apache Benchmark program running against nginx. This test profile measures how many requests per second a given system can sustain when carrying out 2,000,000 requests with 500 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.9.9Static Web Page Servingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87K14K21K28K35KSE +/- 366.35, N = 6SE +/- 122.35, N = 3SE +/- 447.57, N = 4SE +/- 304.93, N = 3SE +/- 538.68, N = 332336.8132857.2431946.5932458.4433656.471. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.9.9Static Web Page Servingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.86K12K18K24K30KMin: 31127.53 / Avg: 32336.81 / Max: 33365.07Min: 32613.94 / Avg: 32857.24 / Max: 33001.57Min: 31197.78 / Avg: 31946.59 / Max: 33192.16Min: 32074.64 / Avg: 32458.44 / Max: 33060.8Min: 32735.2 / Avg: 33656.47 / Max: 34600.81. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native

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 0.11.07Test: Forkingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.814K28K42K56K70KSE +/- 365.75, N = 3SE +/- 483.59, N = 15SE +/- 241.68, N = 3SE +/- 727.53, N = 15SE +/- 703.73, N = 359757.7059273.9055534.2757705.5764896.911. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Forkingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.811K22K33K44K55KMin: 59061.71 / Avg: 59757.7 / Max: 60300.69Min: 55962.72 / Avg: 59273.9 / Max: 61152.67Min: 55133.35 / Avg: 55534.27 / Max: 55968.55Min: 50235.25 / Avg: 57705.57 / Max: 60649.48Min: 63837.8 / Avg: 64896.91 / Max: 66229.231. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

pmbench

Pmbench is a Linux paging and virtual memory benchmark. This test profile will report the average page latency of the system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 4 - Read-Write Ratio: 50%page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.02660.05320.07980.10640.133SE +/- 0.0018, N = 3SE +/- 0.0013, N = 7SE +/- 0.0007, N = 3SE +/- 0.0010, N = 3SE +/- 0.0006, N = 30.11500.11650.11480.11370.11831. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 4 - Read-Write Ratio: 50%page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812345Min: 0.11 / Avg: 0.12 / Max: 0.12Min: 0.11 / Avg: 0.12 / Max: 0.12Min: 0.11 / Avg: 0.11 / Max: 0.12Min: 0.11 / Avg: 0.11 / Max: 0.12Min: 0.12 / Avg: 0.12 / Max: 0.121. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

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 0.10.0Test: Twitter HTTP Requestspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87001400210028003500SE +/- 33.67, N = 5SE +/- 26.67, N = 5SE +/- 11.75, N = 5SE +/- 29.45, N = 5SE +/- 17.46, N = 53427.623449.443378.133405.963384.02
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Twitter HTTP Requestspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.86001200180024003000Min: 3306.84 / Avg: 3427.62 / Max: 3494.39Min: 3383.14 / Avg: 3449.43 / Max: 3513.21Min: 3336.44 / Avg: 3378.13 / Max: 3401.06Min: 3331.37 / Avg: 3405.96 / Max: 3483.32Min: 3353.32 / Avg: 3384.02 / Max: 3448

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 6page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81020304050SE +/- 0.63, N = 4SE +/- 0.59, N = 15SE +/- 0.33, N = 342434341431. (CC) gcc options: -O2 -lpthread
OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 6page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8918273645Min: 41 / Avg: 42.75 / Max: 44Min: 39 / Avg: 42.6 / Max: 47Min: 42 / Avg: 42.67 / Max: 431. (CC) gcc options: -O2 -lpthread

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_startuppage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 38.598.918.608.797.82
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startuppage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215Min: 8.57 / Avg: 8.59 / Max: 8.63Min: 8.91 / Avg: 8.91 / Max: 8.92Min: 8.58 / Avg: 8.6 / Max: 8.61Min: 8.75 / Avg: 8.79 / Max: 8.84Min: 7.81 / Avg: 7.82 / Max: 7.83

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 1,000page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81632486480SE +/- 0.86, N = 3SE +/- 0.63, N = 3SE +/- 0.14, N = 3SE +/- 0.58, N = 3SE +/- 0.30, N = 372.5172.9572.5472.1772.591. (CC) gcc options: -O2 -ldl -lz -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81428425670Min: 71.45 / Avg: 72.51 / Max: 74.22Min: 72.03 / Avg: 72.95 / Max: 74.17Min: 72.26 / Avg: 72.53 / Max: 72.67Min: 71.57 / Avg: 72.17 / Max: 73.32Min: 72.14 / Avg: 72.59 / Max: 73.161. (CC) gcc options: -O2 -ldl -lz -lpthread

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: Processpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8918273645SE +/- 0.10, N = 3SE +/- 0.26, N = 15SE +/- 0.07, N = 3SE +/- 0.32, N = 15SE +/- 0.08, N = 325.7426.2940.8827.2127.271. (CC) gcc options: -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: Processpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8918273645Min: 25.57 / Avg: 25.74 / Max: 25.93Min: 25.48 / Avg: 26.29 / Max: 28.83Min: 40.78 / Avg: 40.88 / Max: 41.01Min: 26.13 / Avg: 27.21 / Max: 29.54Min: 27.11 / Avg: 27.27 / Max: 27.371. (CC) gcc options: -lpthread

KeyDB

A benchmark of KeyDB as a multi-threaded fork of the Redis server. The KeyDB benchmark is conducted using memtier-benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 5.3.1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.890K180K270K360K450KSE +/- 489.23, N = 3SE +/- 2144.78, N = 3SE +/- 863.36, N = 3SE +/- 1167.53, N = 3SE +/- 2172.59, N = 3408020.54406413.14403702.22407410.68407304.601. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 5.3.1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.870K140K210K280K350KMin: 407278.62 / Avg: 408020.54 / Max: 408943.94Min: 402513.86 / Avg: 406413.14 / Max: 409910.99Min: 401997.43 / Avg: 403702.22 / Max: 404792.15Min: 405971.11 / Avg: 407410.68 / Max: 409722.66Min: 403066.82 / Avg: 407304.6 / Max: 410254.991. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre

Build2

This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.12Time To Compilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81530456075SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 368.8568.6468.7367.8168.01
OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.12Time To Compilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81326395265Min: 68.68 / Avg: 68.85 / Max: 69.01Min: 68.54 / Avg: 68.64 / Max: 68.81Min: 68.59 / Avg: 68.73 / Max: 68.98Min: 67.72 / Avg: 67.81 / Max: 67.89Min: 67.87 / Avg: 68.01 / Max: 68.11

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: BMW27 - Compute: CPU-Onlypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81530456075SE +/- 0.28, N = 3SE +/- 0.12, N = 3SE +/- 0.45, N = 3SE +/- 0.40, N = 3SE +/- 0.30, N = 367.0067.4367.6667.2867.01
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: BMW27 - Compute: CPU-Onlypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81326395265Min: 66.52 / Avg: 67 / Max: 67.5Min: 67.24 / Avg: 67.43 / Max: 67.64Min: 67 / Avg: 67.66 / Max: 68.53Min: 66.82 / Avg: 67.28 / Max: 68.07Min: 66.66 / Avg: 67.01 / Max: 67.62

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 V4page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8300K600K900K1200K1500KSE +/- 2748.33, N = 3SE +/- 838.93, N = 3SE +/- 2105.36, N = 3SE +/- 3706.10, N = 3SE +/- 2207.16, N = 313094131312333130951013155131310057
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8200K400K600K800K1000KMin: 1306660 / Avg: 1309413.33 / Max: 1314910Min: 1310800 / Avg: 1312333.33 / Max: 1313690Min: 1307150 / Avg: 1309510 / Max: 1313710Min: 1309730 / Avg: 1315513.33 / Max: 1322420Min: 1306630 / Avg: 1310056.67 / Max: 1314180

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 Testpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82K4K6K8K10KSE +/- 101.17, N = 15SE +/- 120.51, N = 15SE +/- 99.95, N = 15SE +/- 102.14, N = 15SE +/- 96.52, N = 15799379048160838086081. Nodejs v10.19.0
OpenBenchmarking.orgRequests Per Second, More Is BetterNode.js Express HTTP Load Testpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.815003000450060007500Min: 7529 / Avg: 7992.73 / Max: 8856Min: 7248 / Avg: 7903.8 / Max: 8871Min: 7649 / Avg: 8160 / Max: 8852Min: 7970 / Avg: 8379.8 / Max: 9395Min: 8245 / Avg: 8608.07 / Max: 93531. Nodejs v10.19.0

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 0page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81428425670SE +/- 0.09, N = 3SE +/- 0.30, N = 3SE +/- 0.17, N = 3SE +/- 0.13, N = 3SE +/- 0.17, N = 362.2862.6362.4362.0862.571. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 0page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81224364860Min: 62.14 / Avg: 62.28 / Max: 62.45Min: 62.32 / Avg: 62.63 / Max: 63.23Min: 62.12 / Avg: 62.43 / Max: 62.72Min: 61.86 / Avg: 62.08 / Max: 62.32Min: 62.28 / Avg: 62.57 / Max: 62.871. (CXX) g++ options: -O3 -fPIC

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 V2page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8200K400K600K800K1000KSE +/- 2079.65, N = 3SE +/- 1899.60, N = 3SE +/- 1428.94, N = 3SE +/- 2220.12, N = 3SE +/- 1754.01, N = 311481901145043114529311469901146897
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8200K400K600K800K1000KMin: 1144430 / Avg: 1148190 / Max: 1151610Min: 1141310 / Avg: 1145043.33 / Max: 1147520Min: 1142700 / Avg: 1145293.33 / Max: 1147630Min: 1142550 / Avg: 1146990 / Max: 1149250Min: 1143940 / Avg: 1146896.67 / Max: 1150010

pmbench

Pmbench is a Linux paging and virtual memory benchmark. This test profile will report the average page latency of the system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 1 - Read-Write Ratio: 50%page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.02270.04540.06810.09080.1135SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0002, N = 30.10090.10090.10070.10070.10101. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 1 - Read-Write Ratio: 50%page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812345Min: 0.1 / Avg: 0.1 / Max: 0.1Min: 0.1 / Avg: 0.1 / Max: 0.1Min: 0.1 / Avg: 0.1 / Max: 0.1Min: 0.1 / Avg: 0.1 / Max: 0.1Min: 0.1 / Avg: 0.1 / Max: 0.11. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 8 - Read-Write Ratio: 50%page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.0260.0520.0780.1040.13SE +/- 0.0002, N = 3SE +/- 0.0003, N = 3SE +/- 0.0003, N = 3SE +/- 0.0003, N = 3SE +/- 0.0004, N = 30.11350.11350.11370.11560.11291. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 8 - Read-Write Ratio: 50%page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812345Min: 0.11 / Avg: 0.11 / Max: 0.11Min: 0.11 / Avg: 0.11 / Max: 0.11Min: 0.11 / Avg: 0.11 / Max: 0.11Min: 0.12 / Avg: 0.12 / Max: 0.12Min: 0.11 / Avg: 0.11 / Max: 0.111. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 1 - Read-Write Ratio: 100% Writespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.01220.02440.03660.04880.061SE +/- 0.0001, N = 3SE +/- 0.0000, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0000, N = 30.05440.05440.05420.05430.05441. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 1 - Read-Write Ratio: 100% Writespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812345Min: 0.05 / Avg: 0.05 / Max: 0.05Min: 0.05 / Avg: 0.05 / Max: 0.05Min: 0.05 / Avg: 0.05 / Max: 0.05Min: 0.05 / Avg: 0.05 / Max: 0.05Min: 0.05 / Avg: 0.05 / Max: 0.051. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 2 - Read-Write Ratio: 100% Writespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.01310.02620.03930.05240.0655SE +/- 0.0001, N = 3SE +/- 0.0003, N = 3SE +/- 0.0000, N = 3SE +/- 0.0001, N = 3SE +/- 0.0002, N = 30.05820.05770.05810.05770.05821. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 2 - Read-Write Ratio: 100% Writespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812345Min: 0.06 / Avg: 0.06 / Max: 0.06Min: 0.06 / Avg: 0.06 / Max: 0.06Min: 0.06 / Avg: 0.06 / Max: 0.06Min: 0.06 / Avg: 0.06 / Max: 0.06Min: 0.06 / Avg: 0.06 / Max: 0.061. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 4 - Read-Write Ratio: 100% Writespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.01350.0270.04050.0540.0675SE +/- 0.0006, N = 3SE +/- 0.0002, N = 3SE +/- 0.0005, N = 3SE +/- 0.0002, N = 3SE +/- 0.0000, N = 30.05850.05710.05880.05900.05991. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 4 - Read-Write Ratio: 100% Writespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812345Min: 0.06 / Avg: 0.06 / Max: 0.06Min: 0.06 / Avg: 0.06 / Max: 0.06Min: 0.06 / Avg: 0.06 / Max: 0.06Min: 0.06 / Avg: 0.06 / Max: 0.06Min: 0.06 / Avg: 0.06 / Max: 0.061. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 8 - Read-Write Ratio: 100% Writespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.01320.02640.03960.05280.066SE +/- 0.0000, N = 3SE +/- 0.0000, N = 3SE +/- 0.0000, N = 3SE +/- 0.0002, N = 3SE +/- 0.0001, N = 30.05770.05700.05870.05860.05861. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 8 - Read-Write Ratio: 100% Writespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812345Min: 0.06 / Avg: 0.06 / Max: 0.06Min: 0.06 / Avg: 0.06 / Max: 0.06Min: 0.06 / Avg: 0.06 / Max: 0.06Min: 0.06 / Avg: 0.06 / Max: 0.06Min: 0.06 / Avg: 0.06 / Max: 0.061. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 1 - Read-Write Ratio: 100% Readspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.01010.02020.03030.04040.0505SE +/- 0.0001, N = 3SE +/- 0.0000, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 30.04460.04450.04470.04460.04461. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 1 - Read-Write Ratio: 100% Readspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812345Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.041. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 2 - Read-Write Ratio: 100% Readspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.010.020.030.040.05SE +/- 0.0000, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 30.04460.04460.04460.04460.04451. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 2 - Read-Write Ratio: 100% Readspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812345Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.041. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 8 - Read-Write Ratio: 100% Readspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.01010.02020.03030.04040.0505SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0000, N = 3SE +/- 0.0000, N = 30.04470.04460.04470.04470.04471. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 8 - Read-Write Ratio: 100% Readspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812345Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.041. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 4 - Read-Write Ratio: 100% Readspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.01010.02020.03030.04040.0505SE +/- 0.0000, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0000, N = 30.04480.04470.04460.04460.04451. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 4 - Read-Write Ratio: 100% Readspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812345Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.04Min: 0.04 / Avg: 0.04 / Max: 0.041. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

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: SqueezeNetpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820K40K60K80K100KSE +/- 186.84, N = 3SE +/- 109.20, N = 3SE +/- 130.69, N = 3SE +/- 123.22, N = 3SE +/- 91.50, N = 387178.386979.087032.687232.286930.6
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.815K30K45K60K75KMin: 86856.9 / Avg: 87178.33 / Max: 87504.1Min: 86809.1 / Avg: 86979.03 / Max: 87182.8Min: 86811.2 / Avg: 87032.57 / Max: 87263.6Min: 86988.6 / Avg: 87232.23 / Max: 87386.2Min: 86748.3 / Avg: 86930.57 / Max: 87035.9

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quantpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.813K26K39K52K65KSE +/- 138.55, N = 3SE +/- 270.03, N = 3SE +/- 36.08, N = 3SE +/- 162.01, N = 3SE +/- 130.06, N = 358486.758881.858726.058870.858686.1
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quantpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.810K20K30K40K50KMin: 58227.2 / Avg: 58486.7 / Max: 58700.6Min: 58342.6 / Avg: 58881.83 / Max: 59177.3Min: 58655.8 / Avg: 58726.03 / Max: 58775.5Min: 58556.5 / Avg: 58870.8 / Max: 59096.2Min: 58526.4 / Avg: 58686.13 / Max: 58943.8

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Floatpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812K24K36K48K60KSE +/- 252.59, N = 3SE +/- 92.04, N = 3SE +/- 116.85, N = 3SE +/- 116.29, N = 3SE +/- 166.77, N = 357928.857816.457885.858012.257927.7
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Floatpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.810K20K30K40K50KMin: 57448.3 / Avg: 57928.83 / Max: 58304.1Min: 57643.6 / Avg: 57816.37 / Max: 57957.8Min: 57676.6 / Avg: 57885.83 / Max: 58080.6Min: 57844 / Avg: 58012.17 / Max: 58235.4Min: 57691.6 / Avg: 57927.73 / Max: 58249.8

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 32 - Type: Processpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820406080100SE +/- 0.33, N = 3SE +/- 0.03, N = 3SE +/- 0.29, N = 3SE +/- 0.04, N = 3SE +/- 0.63, N = 355.7556.0978.4856.6951.591. (CC) gcc options: -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 32 - Type: Processpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81530456075Min: 55.1 / Avg: 55.75 / Max: 56.17Min: 56.05 / Avg: 56.09 / Max: 56.16Min: 78.04 / Avg: 78.48 / Max: 79.04Min: 56.61 / Avg: 56.69 / Max: 56.75Min: 50.54 / Avg: 51.59 / Max: 52.731. (CC) gcc options: -lpthread

Himeno Benchmark

The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solverpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89001800270036004500SE +/- 52.57, N = 3SE +/- 44.32, N = 3SE +/- 28.50, N = 3SE +/- 8.08, N = 3SE +/- 54.03, N = 34198.944042.794123.874084.744126.671. (CC) gcc options: -O3 -mavx2
OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solverpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87001400210028003500Min: 4109.92 / Avg: 4198.94 / Max: 4291.89Min: 3954.25 / Avg: 4042.79 / Max: 4090.52Min: 4070.84 / Avg: 4123.87 / Max: 4168.5Min: 4074.74 / Avg: 4084.74 / Max: 4100.73Min: 4019.97 / Avg: 4126.67 / Max: 4194.881. (CC) gcc options: -O3 -mavx2

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 8page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8918273645SE +/- 0.51, N = 5SE +/- 0.40, N = 6SE +/- 0.34, N = 10SE +/- 0.50, N = 438363637381. (CC) gcc options: -O2 -lpthread
OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 8page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8816243240Min: 37 / Avg: 38.4 / Max: 40Min: 35 / Avg: 36.17 / Max: 37Min: 35 / Avg: 36.5 / Max: 38Min: 37 / Avg: 37.5 / Max: 391. (CC) gcc options: -O2 -lpthread

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 Secondpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8200K400K600K800K1000KSE +/- 2135.32, N = 3SE +/- 2139.47, N = 3SE +/- 1048.27, N = 3SE +/- 646.60, N = 3SE +/- 1904.47, N = 3993508.76993071.98991673.72993262.70999077.151. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Secondpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8200K400K600K800K1000KMin: 989238.17 / Avg: 993508.76 / Max: 995663.42Min: 990903.81 / Avg: 993071.98 / Max: 997350.79Min: 990577.9 / Avg: 991673.72 / Max: 993769.53Min: 992248.06 / Avg: 993262.7 / Max: 994464.41Min: 995276.33 / Avg: 999077.15 / Max: 1001192.831. (CC) gcc options: -O2 -lrt" -lrt

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 Commandspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81224364860SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 355.1755.1655.0854.9955.081. git version 2.25.1
OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git Commandspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81122334455Min: 55.02 / Avg: 55.17 / Max: 55.39Min: 55.07 / Avg: 55.16 / Max: 55.24Min: 55.06 / Avg: 55.08 / Max: 55.1Min: 54.84 / Avg: 54.99 / Max: 55.16Min: 55.04 / Avg: 55.08 / Max: 55.111. git version 2.25.1

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: Threadpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81020304050SE +/- 0.20, N = 3SE +/- 0.15, N = 3SE +/- 0.08, N = 3SE +/- 0.29, N = 13SE +/- 0.09, N = 331.0731.0945.1030.8530.171. (CC) gcc options: -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: Threadpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8918273645Min: 30.77 / Avg: 31.07 / Max: 31.45Min: 30.8 / Avg: 31.09 / Max: 31.32Min: 44.99 / Avg: 45.1 / Max: 45.26Min: 27.56 / Avg: 30.85 / Max: 31.61Min: 30.04 / Avg: 30.17 / Max: 30.341. (CC) gcc options: -lpthread

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 Leukocytepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81224364860SE +/- 0.41, N = 3SE +/- 0.22, N = 3SE +/- 0.25, N = 3SE +/- 0.70, N = 3SE +/- 0.38, N = 354.4054.7754.6653.4754.571. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Leukocytepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81122334455Min: 53.93 / Avg: 54.4 / Max: 55.21Min: 54.48 / Avg: 54.77 / Max: 55.19Min: 54.19 / Avg: 54.66 / Max: 55.05Min: 52.6 / Avg: 53.47 / Max: 54.85Min: 54.03 / Avg: 54.57 / Max: 55.311. (CXX) g++ options: -O2 -lOpenCL

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SADDpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8400K800K1200K1600K2000KSE +/- 40404.79, N = 15SE +/- 51151.69, N = 15SE +/- 41328.15, N = 15SE +/- 24124.88, N = 14SE +/- 51091.22, N = 151622387.051736465.541640722.741620429.831817867.401. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SADDpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8300K600K900K1200K1500KMin: 1490313 / Avg: 1622387.05 / Max: 1930501.88Min: 1552795 / Avg: 1736465.54 / Max: 2016129.12Min: 1492537.25 / Avg: 1640722.74 / Max: 2028397.62Min: 1574803.12 / Avg: 1620429.83 / Max: 1930501.88Min: 1499250.38 / Avg: 1817867.4 / Max: 2053388.121. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

RawTherapee

RawTherapee is a cross-platform, open-source multi-threaded RAW image processing program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark Timepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81224364860SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 350.6250.9951.0650.5450.971. RawTherapee, version 5.8, command line.
OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark Timepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81020304050Min: 50.6 / Avg: 50.62 / Max: 50.66Min: 50.86 / Avg: 50.99 / Max: 51.06Min: 50.91 / Avg: 51.06 / Max: 51.15Min: 50.48 / Avg: 50.54 / Max: 50.64Min: 50.88 / Avg: 50.97 / Max: 51.081. RawTherapee, version 5.8, command line.

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To Compilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8918273645SE +/- 0.45, N = 6SE +/- 0.55, N = 3SE +/- 0.52, N = 5SE +/- 0.58, N = 3SE +/- 0.59, N = 338.8439.4138.7638.7138.63
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To Compilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8816243240Min: 37.44 / Avg: 38.84 / Max: 40.7Min: 38.84 / Avg: 39.41 / Max: 40.52Min: 37.39 / Avg: 38.76 / Max: 40.56Min: 38.13 / Avg: 38.71 / Max: 39.86Min: 38.03 / Avg: 38.63 / Max: 39.81

perf-bench

OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memcpy 1MBpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215SE +/- 0.033265, N = 3SE +/- 0.073161, N = 3SE +/- 0.136400, N = 3SE +/- 0.130104, N = 3SE +/- 0.074362, N = 159.0718899.4058229.6231189.2325739.2265241. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memcpy 1MBpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215Min: 9.02 / Avg: 9.07 / Max: 9.13Min: 9.26 / Avg: 9.41 / Max: 9.49Min: 9.39 / Avg: 9.62 / Max: 9.86Min: 8.99 / Avg: 9.23 / Max: 9.43Min: 8.89 / Avg: 9.23 / Max: 9.831. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma

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 0.11.07Test: Glibc C String Functionspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8700K1400K2100K2800K3500KSE +/- 17198.37, N = 3SE +/- 22410.29, N = 3SE +/- 22519.92, N = 3SE +/- 22183.62, N = 3SE +/- 63869.43, N = 123428860.593450978.943438797.243436106.843354956.811. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc C String Functionspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8600K1200K1800K2400K3000KMin: 3397730.49 / Avg: 3428860.59 / Max: 3457096.07Min: 3407207.03 / Avg: 3450978.94 / Max: 3481212.2Min: 3394525.53 / Avg: 3438797.24 / Max: 3468106.07Min: 3391778.84 / Avg: 3436106.84 / Max: 3459886.25Min: 2667606.99 / Avg: 3354956.81 / Max: 3501755.781. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Apache Siege

This is a test of the Apache web server performance being facilitated by the Siege web serverb enchmark program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 100page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87K14K21K28K35KSE +/- 169.95, N = 3SE +/- 224.80, N = 3SE +/- 279.76, N = 5SE +/- 289.78, N = 4SE +/- 84.95, N = 333136.2833024.5420908.7420975.0333610.111. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 100page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.86K12K18K24K30KMin: 32808.4 / Avg: 33136.28 / Max: 33377.84Min: 32583.9 / Avg: 33024.54 / Max: 33322.23Min: 20462.45 / Avg: 20908.74 / Max: 22002.2Min: 20487.6 / Avg: 20975.03 / Max: 21805.49Min: 33444.82 / Avg: 33610.11 / Max: 33726.811. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

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 Atomspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.19320.38640.57960.77280.966SE +/- 0.00039, N = 3SE +/- 0.00128, N = 3SE +/- 0.00072, N = 3SE +/- 0.00077, N = 3SE +/- 0.00110, N = 30.855330.858480.857180.857900.85800
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atomspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810Min: 0.85 / Avg: 0.86 / Max: 0.86Min: 0.86 / Avg: 0.86 / Max: 0.86Min: 0.86 / Avg: 0.86 / Max: 0.86Min: 0.86 / Avg: 0.86 / Max: 0.86Min: 0.86 / Avg: 0.86 / Max: 0.86

Ethr

Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and different measurements. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 1page_lock_unfairness 1000PLU 1Linux 5.9-rc4Linux 5.8510152025SE +/- 0.23, N = 3SE +/- 0.19, N = 9SE +/- 0.21, N = 3SE +/- 0.05, N = 320.1320.0421.0420.93MIN: 9.38 / MAX: 25.43MIN: 9.18 / MAX: 25.2MIN: 9.51 / MAX: 25.7MIN: 9.43 / MAX: 27.34
OpenBenchmarking.orgMicroseconds, Fewer Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 1page_lock_unfairness 1000PLU 1Linux 5.9-rc4Linux 5.8510152025Min: 19.78 / Avg: 20.13 / Max: 20.55Min: 18.78 / Avg: 20.04 / Max: 20.62Min: 20.63 / Avg: 21.04 / Max: 21.29Min: 20.86 / Avg: 20.93 / Max: 21.02

MariaDB

This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.814002800420056007000SE +/- 13.44, N = 3SE +/- 23.13, N = 3SE +/- 7.96, N = 5SE +/- 13.27, N = 3SE +/- 13.79, N = 3634363296321631664381. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 16page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.811002200330044005500Min: 6329.11 / Avg: 6342.55 / Max: 6369.43Min: 6289.31 / Avg: 6329.28 / Max: 6369.43Min: 6289.31 / Avg: 6321.15 / Max: 6329.11Min: 6289.31 / Avg: 6315.85 / Max: 6329.11Min: 6410.26 / Avg: 6437.83 / Max: 6451.611. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 19page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820406080100SE +/- 0.28, N = 3SE +/- 0.26, N = 3SE +/- 0.32, N = 3SE +/- 0.35, N = 3SE +/- 0.17, N = 3100.1100.4100.6102.4100.91. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 19page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820406080100Min: 99.5 / Avg: 100.07 / Max: 100.4Min: 99.9 / Avg: 100.4 / Max: 100.8Min: 100 / Avg: 100.63 / Max: 101Min: 101.9 / Avg: 102.43 / Max: 103.1Min: 100.6 / Avg: 100.9 / Max: 101.21. (CC) gcc options: -O3 -pthread -lz -llzma

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 2page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8918273645SE +/- 0.11, N = 3SE +/- 0.15, N = 3SE +/- 0.09, N = 3SE +/- 0.28, N = 3SE +/- 0.06, N = 337.9237.7537.4837.9037.761. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 2page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8816243240Min: 37.8 / Avg: 37.92 / Max: 38.14Min: 37.53 / Avg: 37.75 / Max: 38.03Min: 37.34 / Avg: 37.48 / Max: 37.65Min: 37.55 / Avg: 37.9 / Max: 38.46Min: 37.65 / Avg: 37.76 / Max: 37.861. (CXX) g++ options: -O3 -fPIC

perf-bench

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Epoll Waitpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82K4K6K8K10KSE +/- 182.47, N = 3SE +/- 180.33, N = 3SE +/- 147.05, N = 5SE +/- 146.72, N = 4SE +/- 92.15, N = 311018111981101610720111381. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Epoll Waitpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82K4K6K8K10KMin: 10658 / Avg: 11017.67 / Max: 11251Min: 10837 / Avg: 11197.67 / Max: 11379Min: 10624 / Avg: 11016.4 / Max: 11513Min: 10421 / Avg: 10719.75 / Max: 11121Min: 11037 / Avg: 11138 / Max: 113221. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma

Memcached mcperf

This is a test of twmperf/mcperf with memcached, a distributed memory object caching system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Set - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89K18K27K36K45KSE +/- 302.77, N = 3SE +/- 487.76, N = 6SE +/- 324.37, N = 3SE +/- 373.15, N = 3SE +/- 472.77, N = 340363.540361.041024.639138.538084.21. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.6.0Method: Set - Connections: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87K14K21K28K35KMin: 39808.9 / Avg: 40363.53 / Max: 40851.3Min: 38998.9 / Avg: 40361.03 / Max: 41877.1Min: 40382.5 / Avg: 41024.63 / Max: 41425.7Min: 38466.1 / Avg: 39138.5 / Max: 39755.1Min: 37394.8 / Avg: 38084.17 / Max: 38989.31. (CC) gcc options: -O2 -lm -rdynamic

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPUpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8140280420560700SE +/- 2.02, N = 3SE +/- 0.75, N = 3SE +/- 1.64, N = 3SE +/- 2.66, N = 3SE +/- 1.83, N = 3651.51653.31652.24654.03648.79
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPUpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8120240360480600Min: 647.65 / Avg: 651.51 / Max: 654.5Min: 652.05 / Avg: 653.31 / Max: 654.65Min: 649.41 / Avg: 652.24 / Max: 655.1Min: 649.08 / Avg: 654.03 / Max: 658.18Min: 645.61 / Avg: 648.79 / Max: 651.94

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: GETpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8400K800K1200K1600K2000KSE +/- 15418.77, N = 3SE +/- 17678.98, N = 15SE +/- 51885.64, N = 15SE +/- 15363.36, N = 3SE +/- 50914.96, N = 151680957.751767421.971796807.961768092.331996950.611. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: GETpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8300K600K900K1200K1500KMin: 1650165 / Avg: 1680957.75 / Max: 1697792.88Min: 1686340.62 / Avg: 1767421.97 / Max: 1984127Min: 1650165 / Avg: 1796807.96 / Max: 2288329.5Min: 1742160.25 / Avg: 1768092.33 / Max: 1795332.25Min: 1715265.88 / Avg: 1996950.61 / Max: 2320185.751. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SETpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8300K600K900K1200K1500KSE +/- 28971.66, N = 15SE +/- 23258.57, N = 3SE +/- 13133.17, N = 3SE +/- 19194.77, N = 14SE +/- 36931.54, N = 151449624.861456349.791446720.801444961.841600412.631. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SETpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8300K600K900K1200K1500KMin: 1373626.38 / Avg: 1449624.86 / Max: 1686340.62Min: 1414427.12 / Avg: 1456349.79 / Max: 1494768.25Min: 1420454.5 / Avg: 1446720.83 / Max: 1459854Min: 1377410.5 / Avg: 1444961.84 / Max: 1669449.12Min: 1396648 / Avg: 1600412.63 / Max: 1779359.51. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

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: regex_compilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.84080120160200SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3182182181183181
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8306090120150Min: 181 / Avg: 181.67 / Max: 182Min: 180 / Avg: 180.67 / Max: 181Min: 181 / Avg: 181.33 / Max: 182

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 0.11.07Test: Glibc Qsort Data Sortingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.880160240320400SE +/- 1.82, N = 3SE +/- 4.80, N = 5SE +/- 4.69, N = 4SE +/- 1.24, N = 3SE +/- 1.76, N = 3368.97363.09365.87369.27365.521. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc Qsort Data Sortingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.870140210280350Min: 367.03 / Avg: 368.97 / Max: 372.6Min: 345.77 / Avg: 363.09 / Max: 374.2Min: 351.83 / Avg: 365.87 / Max: 371.23Min: 367.53 / Avg: 369.27 / Max: 371.67Min: 362 / Avg: 365.52 / Max: 367.331. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

AOM AV1

This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 0 Two-Passpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.06750.1350.20250.270.3375SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.280.290.290.300.291. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 0 Two-Passpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.812345Min: 0.28 / Avg: 0.28 / Max: 0.29Min: 0.28 / Avg: 0.29 / Max: 0.29Min: 0.29 / Avg: 0.29 / Max: 0.29Min: 0.29 / Avg: 0.3 / Max: 0.3Min: 0.28 / Avg: 0.29 / Max: 0.291. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Apache Benchmark

This is a test of ab, which is the Apache benchmark program. This test profile measures how many requests per second a given system can sustain when carrying out 1,000,000 requests with 100 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page Servingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.86K12K18K24K30KSE +/- 176.90, N = 3SE +/- 149.23, N = 3SE +/- 61.67, N = 3SE +/- 30.81, N = 3SE +/- 222.22, N = 328571.7328472.8228292.9528386.7329495.141. (CC) gcc options: -shared -fPIC -O2 -pthread
OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page Servingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.85K10K15K20K25KMin: 28265.22 / Avg: 28571.73 / Max: 28878.02Min: 28242.86 / Avg: 28472.82 / Max: 28752.56Min: 28227.23 / Avg: 28292.95 / Max: 28416.19Min: 28340.91 / Avg: 28386.73 / Max: 28445.32Min: 29255.52 / Avg: 29495.14 / Max: 29939.111. (CC) gcc options: -shared -fPIC -O2 -pthread

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPOPpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8300K600K900K1200K1500KSE +/- 27438.74, N = 15SE +/- 14630.31, N = 3SE +/- 18865.48, N = 3SE +/- 25786.36, N = 15SE +/- 34105.93, N = 121278949.521285133.001262127.711332716.881420279.271. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPOPpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8200K400K600K800K1000KMin: 1186239.62 / Avg: 1278949.52 / Max: 1494768.25Min: 1256281.38 / Avg: 1285133 / Max: 1303780.88Min: 1230012.25 / Avg: 1262127.71 / Max: 1295336.75Min: 1234567.88 / Avg: 1332716.88 / Max: 1510574Min: 1223990.25 / Avg: 1420279.27 / Max: 1543209.881. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Ethr

Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and different measurements. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgConnections/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 1page_lock_unfairness 1000PLU 1Linux 5.9-rc4Linux 5.83K6K9K12K15KSE +/- 222.71, N = 3SE +/- 170.10, N = 3SE +/- 142.09, N = 7SE +/- 184.78, N = 312930127701269712963
OpenBenchmarking.orgConnections/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 1page_lock_unfairness 1000PLU 1Linux 5.9-rc4Linux 5.82K4K6K8K10KMin: 12490 / Avg: 12930 / Max: 13210Min: 12590 / Avg: 12770 / Max: 13110Min: 12100 / Avg: 12697.14 / Max: 13330Min: 12640 / Avg: 12963.33 / Max: 13280

AOM AV1

This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 Realtimepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8510152025SE +/- 0.22, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 317.8718.1518.4418.6918.321. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 Realtimepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8510152025Min: 17.61 / Avg: 17.87 / Max: 18.32Min: 18.03 / Avg: 18.15 / Max: 18.32Min: 18.3 / Avg: 18.44 / Max: 18.6Min: 18.64 / Avg: 18.69 / Max: 18.73Min: 18.18 / Avg: 18.32 / Max: 18.521. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Node.js Octane Benchmark

A Node.js version of the JavaScript Octane Benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNode.js Octane Benchmarkpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89K18K27K36K45KSE +/- 140.01, N = 3SE +/- 109.14, N = 3SE +/- 143.18, N = 3SE +/- 97.84, N = 3SE +/- 51.52, N = 341905420144193241798418161. Nodejs v10.19.0
OpenBenchmarking.orgScore, More Is BetterNode.js Octane Benchmarkpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87K14K21K28K35KMin: 41662 / Avg: 41905 / Max: 42147Min: 41810 / Avg: 42014.33 / Max: 42183Min: 41740 / Avg: 41932 / Max: 42212Min: 41610 / Avg: 41798 / Max: 41939Min: 41754 / Avg: 41815.67 / Max: 419181. Nodejs v10.19.0

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 4page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8112233445546454846461. (CC) gcc options: -O2 -lpthread

AOM AV1

This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 Two-Passpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.7921.5842.3763.1683.96SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 33.513.453.503.523.501. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 Two-Passpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810Min: 3.5 / Avg: 3.51 / Max: 3.52Min: 3.41 / Avg: 3.45 / Max: 3.49Min: 3.49 / Avg: 3.5 / Max: 3.52Min: 3.5 / Avg: 3.52 / Max: 3.54Min: 3.46 / Avg: 3.5 / Max: 3.531. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -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 0.11.07Test: CPU Stresspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82K4K6K8K10KSE +/- 11.33, N = 3SE +/- 1.98, N = 3SE +/- 19.72, N = 3SE +/- 9.65, N = 3SE +/- 5.81, N = 38851.488874.148861.038853.558898.871. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU Stresspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.815003000450060007500Min: 8830.48 / Avg: 8851.48 / Max: 8869.34Min: 8871.08 / Avg: 8874.14 / Max: 8877.85Min: 8840.78 / Avg: 8861.03 / Max: 8900.46Min: 8842.14 / Avg: 8853.55 / Max: 8872.73Min: 8887.25 / Avg: 8898.87 / Max: 8904.931. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: NUMApage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8130260390520650SE +/- 4.26, N = 3SE +/- 5.63, N = 3SE +/- 3.74, N = 3SE +/- 3.08, N = 3SE +/- 3.25, N = 3583.64584.57586.37578.19579.321. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: NUMApage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8100200300400500Min: 577.04 / Avg: 583.64 / Max: 591.61Min: 574.37 / Avg: 584.57 / Max: 593.8Min: 582.49 / Avg: 586.37 / Max: 593.84Min: 574.8 / Avg: 578.19 / Max: 584.35Min: 572.87 / Avg: 579.32 / Max: 583.181. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: System V Message Passingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83M6M9M12M15MSE +/- 194715.85, N = 3SE +/- 91399.87, N = 3SE +/- 27346.09, N = 3SE +/- 76200.04, N = 3SE +/- 177055.98, N = 312721404.0912702276.0512014924.1712519608.1413824575.941. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: System V Message Passingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82M4M6M8M10MMin: 12339181.24 / Avg: 12721404.09 / Max: 12977106.98Min: 12560754.41 / Avg: 12702276.05 / Max: 12873239.31Min: 11977690.23 / Avg: 12014924.17 / Max: 12068234.82Min: 12442358.55 / Avg: 12519608.14 / Max: 12672003.39Min: 13511662.24 / Avg: 13824575.94 / Max: 14124595.381. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Memory Copyingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83K6K9K12K15KSE +/- 147.12, N = 3SE +/- 56.43, N = 3SE +/- 191.65, N = 3SE +/- 37.14, N = 3SE +/- 51.45, N = 312636.2012826.5112644.3712488.1012739.561. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Memory Copyingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82K4K6K8K10KMin: 12362.32 / Avg: 12636.2 / Max: 12866.26Min: 12718.6 / Avg: 12826.51 / Max: 12909.08Min: 12389.59 / Avg: 12644.37 / Max: 13019.76Min: 12413.94 / Avg: 12488.1 / Max: 12529.02Min: 12639.9 / Avg: 12739.56 / Max: 12811.551. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MEMFDpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82004006008001000SE +/- 0.98, N = 3SE +/- 0.68, N = 3SE +/- 0.78, N = 3SE +/- 0.77, N = 3SE +/- 0.64, N = 3878.86882.22880.00825.00748.431. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MEMFDpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8150300450600750Min: 877.8 / Avg: 878.86 / Max: 880.82Min: 880.99 / Avg: 882.22 / Max: 883.33Min: 878.93 / Avg: 880 / Max: 881.53Min: 823.58 / Avg: 825 / Max: 826.23Min: 747.59 / Avg: 748.43 / Max: 749.681. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SENDFILEpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.880K160K240K320K400KSE +/- 1456.46, N = 3SE +/- 1604.55, N = 3SE +/- 460.98, N = 3SE +/- 1479.69, N = 3SE +/- 432.99, N = 3388762.89392435.44392788.99387421.39385334.221. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SENDFILEpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.870K140K210K280K350KMin: 387179.56 / Avg: 388762.89 / Max: 391672.01Min: 390205.6 / Avg: 392435.44 / Max: 395549Min: 392253.35 / Avg: 392788.99 / Max: 393706.67Min: 384979.95 / Avg: 387421.39 / Max: 390090.54Min: 384481 / Avg: 385334.22 / Max: 385889.11. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Cryptopage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.814002800420056007000SE +/- 1.54, N = 3SE +/- 8.74, N = 3SE +/- 8.71, N = 3SE +/- 6.01, N = 3SE +/- 5.80, N = 36318.656207.716302.156306.146317.761. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Cryptopage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.811002200330044005500Min: 6315.88 / Avg: 6318.65 / Max: 6321.21Min: 6190.44 / Avg: 6207.71 / Max: 6218.65Min: 6290.26 / Avg: 6302.15 / Max: 6319.12Min: 6294.4 / Avg: 6306.14 / Max: 6314.23Min: 6311.06 / Avg: 6317.76 / Max: 6329.321. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MMAPpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.890180270360450SE +/- 0.48, N = 3SE +/- 0.97, N = 3SE +/- 2.50, N = 3SE +/- 1.41, N = 3SE +/- 0.57, N = 3418.80417.13414.59410.72350.331. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MMAPpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.870140210280350Min: 418.01 / Avg: 418.8 / Max: 419.67Min: 416.01 / Avg: 417.13 / Max: 419.07Min: 409.6 / Avg: 414.59 / Max: 417.38Min: 408.08 / Avg: 410.72 / Max: 412.88Min: 349.18 / Avg: 350.33 / Max: 350.921. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Vector Mathpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.840K80K120K160K200KSE +/- 63.85, N = 3SE +/- 199.26, N = 3SE +/- 128.46, N = 3SE +/- 46.71, N = 3SE +/- 272.80, N = 3200124.38199328.26199889.98199819.54200464.431. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Vector Mathpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.830K60K90K120K150KMin: 199997.64 / Avg: 200124.38 / Max: 200201.23Min: 199004.86 / Avg: 199328.26 / Max: 199691.63Min: 199712.44 / Avg: 199889.98 / Max: 200139.58Min: 199743.28 / Avg: 199819.54 / Max: 199904.39Min: 199995.39 / Avg: 200464.43 / Max: 200940.331. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Atomicpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.880K160K240K320K400KSE +/- 1136.17, N = 3SE +/- 1635.29, N = 3SE +/- 1074.46, N = 3SE +/- 807.54, N = 3SE +/- 1680.39, N = 3365018.05364470.40364508.39365322.27365355.881. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Atomicpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.860K120K180K240K300KMin: 363315.12 / Avg: 365018.05 / Max: 367172.46Min: 361983.5 / Avg: 364470.4 / Max: 367553.42Min: 362987.66 / Avg: 364508.39 / Max: 366583.65Min: 364007.92 / Avg: 365322.27 / Max: 366792.31Min: 362067.37 / Avg: 365355.88 / Max: 367600.461. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Matrix Mathpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820K40K60K80K100KSE +/- 511.37, N = 3SE +/- 59.60, N = 3SE +/- 230.76, N = 3SE +/- 628.54, N = 3SE +/- 133.87, N = 3101696.11102131.09102648.28101892.21101825.561. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Matrix Mathpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820K40K60K80K100KMin: 100725.82 / Avg: 101696.11 / Max: 102461.24Min: 102054.51 / Avg: 102131.09 / Max: 102248.49Min: 102189.58 / Avg: 102648.28 / Max: 102921.72Min: 100635.13 / Avg: 101892.21 / Max: 102524.66Min: 101688.84 / Avg: 101825.56 / Max: 102093.281. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Socket Activitypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83K6K9K12K15KSE +/- 37.95, N = 3SE +/- 14.52, N = 3SE +/- 97.80, N = 3SE +/- 22.48, N = 3SE +/- 23.38, N = 314156.5414083.1114046.6113647.4013570.301. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Socket Activitypage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82K4K6K8K10KMin: 14116.78 / Avg: 14156.54 / Max: 14232.42Min: 14061.21 / Avg: 14083.11 / Max: 14110.58Min: 13851.55 / Avg: 14046.61 / Max: 14156.73Min: 13611.84 / Avg: 13647.4 / Max: 13689Min: 13523.7 / Avg: 13570.27 / Max: 13597.31. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Semaphorespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8700K1400K2100K2800K3500KSE +/- 15785.55, N = 3SE +/- 23322.63, N = 3SE +/- 4213.27, N = 3SE +/- 16327.08, N = 3SE +/- 7301.99, N = 33440309.103456894.833444346.893456386.403487114.641. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Semaphorespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8600K1200K1800K2400K3000KMin: 3417259.96 / Avg: 3440309.1 / Max: 3470517.98Min: 3419200.27 / Avg: 3456894.83 / Max: 3499536.55Min: 3437201.64 / Avg: 3444346.89 / Max: 3451787.85Min: 3429453.53 / Avg: 3456386.4 / Max: 3485843.01Min: 3474153.87 / Avg: 3487114.64 / Max: 3499423.481. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

perf-bench

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex Lock-Pipage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.850100150200250SE +/- 0.33, N = 3SE +/- 1.15, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 32302302302302271. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex Lock-Pipage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.84080120160200Min: 230 / Avg: 230.33 / Max: 231Min: 228 / Avg: 230 / Max: 232Min: 229 / Avg: 230.33 / Max: 231Min: 229 / Avg: 230 / Max: 2311. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex Hashpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81000K2000K3000K4000K5000KSE +/- 20875.45, N = 3SE +/- 27103.92, N = 3SE +/- 5830.32, N = 3SE +/- 31420.68, N = 3SE +/- 12029.79, N = 3447017644538634515761448121944894841. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Futex Hashpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8800K1600K2400K3200K4000KMin: 4429891 / Avg: 4470175.67 / Max: 4499816Min: 4400478 / Avg: 4453863 / Max: 4488704Min: 4505048 / Avg: 4515761.33 / Max: 4525105Min: 4424050 / Avg: 4481219 / Max: 4532399Min: 4465826 / Avg: 4489484.33 / Max: 45051031. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 3page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82K4K6K8K10KSE +/- 37.99, N = 3SE +/- 55.65, N = 3SE +/- 30.77, N = 3SE +/- 12.19, N = 3SE +/- 49.48, N = 38376.98320.78351.18384.58361.71. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 3page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.815003000450060007500Min: 8314.7 / Avg: 8376.9 / Max: 8445.8Min: 8253.2 / Avg: 8320.7 / Max: 8431.1Min: 8312.3 / Avg: 8351.13 / Max: 8411.9Min: 8366.7 / Avg: 8384.47 / Max: 8407.8Min: 8277.8 / Avg: 8361.67 / Max: 8449.11. (CC) gcc options: -O3 -pthread -lz -llzma

librsvg

RSVG/librsvg is an SVG vector graphics library. This test profile times how long it takes to complete various operations by rsvg-convert. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterlibrsvgOperation: SVG Files To PNGpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8714212835SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 329.4629.4729.5029.4829.261. rsvg-convert version 2.48.7
OpenBenchmarking.orgSeconds, Fewer Is BetterlibrsvgOperation: SVG Files To PNGpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8714212835Min: 29.43 / Avg: 29.46 / Max: 29.51Min: 29.42 / Avg: 29.47 / Max: 29.5Min: 29.49 / Avg: 29.5 / Max: 29.52Min: 29.46 / Avg: 29.48 / Max: 29.5Min: 29.21 / Avg: 29.26 / Max: 29.311. rsvg-convert version 2.48.7

Tesseract OCR

Tesseract-OCR is the open-source optical character recognition (OCR) engine for the conversion of text within images to raw text output. This test profile relies upon a system-supplied Tesseract installation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.1.1Time To OCR 7 Imagespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8714212835SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.13, N = 3SE +/- 0.19, N = 328.7028.8328.8728.7428.86
OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.1.1Time To OCR 7 Imagespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8612182430Min: 28.65 / Avg: 28.7 / Max: 28.74Min: 28.67 / Avg: 28.83 / Max: 28.98Min: 28.71 / Avg: 28.87 / Max: 28.99Min: 28.51 / Avg: 28.74 / Max: 28.97Min: 28.55 / Avg: 28.86 / Max: 29.21

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Compilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8400800120016002000SE +/- 26.44, N = 3SE +/- 24.29, N = 3SE +/- 3.21, N = 3SE +/- 20.22, N = 8SE +/- 22.26, N = 61986.201979.671961.941949.981988.91
OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Compilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.830060090012001500Min: 1934.18 / Avg: 1986.2 / Max: 2020.41Min: 1944.99 / Avg: 1979.67 / Max: 2026.48Min: 1956.43 / Avg: 1961.94 / Max: 1967.55Min: 1906.86 / Avg: 1949.98 / Max: 2075.8Min: 1944.99 / Avg: 1988.91 / Max: 2094.76

Ethr

Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and different measurements. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbits/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 16page_lock_unfairness 1000PLU 1Linux 5.9-rc4Linux 5.86001200180024003000SE +/- 17.11, N = 3SE +/- 9.43, N = 3SE +/- 14.09, N = 3SE +/- 6.73, N = 32753.162725.612758.072736.14MIN: 2630 / MAX: 2860MIN: 2630 / MAX: 2820MIN: 2640 / MAX: 2840MIN: 2660 / MAX: 2850
OpenBenchmarking.orgMbits/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 16page_lock_unfairness 1000PLU 1Linux 5.9-rc4Linux 5.85001000150020002500Min: 2731.05 / Avg: 2753.16 / Max: 2786.84Min: 2708.95 / Avg: 2725.61 / Max: 2741.58Min: 2730 / Avg: 2758.07 / Max: 2774.21Min: 2727.89 / Avg: 2736.14 / Max: 2749.47

OpenBenchmarking.orgMbits/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 16page_lock_unfairness 1000PLU 1Linux 5.9-rc4Linux 5.820K40K60K80K100KSE +/- 400.52, N = 3SE +/- 258.48, N = 3SE +/- 381.35, N = 3SE +/- 247.15, N = 3106280.00107358.00100940.67100755.11MIN: 105090 / MAX: 107540MIN: 106400 / MAX: 108600MIN: 99560 / MAX: 102240MIN: 99490 / MAX: 102530
OpenBenchmarking.orgMbits/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 16page_lock_unfairness 1000PLU 1Linux 5.9-rc4Linux 5.820K40K60K80K100KMin: 105565.33 / Avg: 106280 / Max: 106950.67Min: 106954 / Avg: 107358 / Max: 107839.33Min: 100313.33 / Avg: 100940.67 / Max: 101630Min: 100275.33 / Avg: 100755.11 / Max: 101098

OpenBenchmarking.orgMbits/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 16page_lock_unfairness 1000PLU 1Linux 5.9-rc4Linux 5.830K60K90K120K150KSE +/- 949.28, N = 3SE +/- 1489.80, N = 3SE +/- 681.49, N = 3SE +/- 1299.83, N = 3158705.11159066.89157893.78157569.11MIN: 150140 / MAX: 163510MIN: 150040 / MAX: 164830MIN: 153130 / MAX: 163030MIN: 149340 / MAX: 165470
OpenBenchmarking.orgMbits/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 16page_lock_unfairness 1000PLU 1Linux 5.9-rc4Linux 5.830K60K90K120K150KMin: 157411.33 / Avg: 158705.11 / Max: 160555.33Min: 157013.33 / Avg: 159066.89 / Max: 161963.33Min: 156565.33 / Avg: 157893.78 / Max: 158822Min: 155064 / Avg: 157569.11 / Max: 159423.33

OpenBenchmarking.orgMicroseconds, Fewer Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 16page_lock_unfairness 1000PLU 1Linux 5.9-rc4Linux 5.8510152025SE +/- 0.18, N = 3SE +/- 0.09, N = 3SE +/- 0.24, N = 3SE +/- 0.02, N = 320.3420.0920.9420.96MIN: 9.31 / MAX: 24.96MIN: 9.01 / MAX: 25.15MIN: 9.25 / MAX: 26.59MIN: 9.43 / MAX: 27.14
OpenBenchmarking.orgMicroseconds, Fewer Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 16page_lock_unfairness 1000PLU 1Linux 5.9-rc4Linux 5.8510152025Min: 20.08 / Avg: 20.34 / Max: 20.69Min: 19.91 / Avg: 20.09 / Max: 20.18Min: 20.59 / Avg: 20.94 / Max: 21.39Min: 20.92 / Avg: 20.96 / Max: 20.98

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPUSHpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8300K600K900K1200K1500KSE +/- 17095.74, N = 14SE +/- 12035.11, N = 3SE +/- 16082.36, N = 3SE +/- 7930.62, N = 3SE +/- 25884.34, N = 121210430.461222231.421201386.461218625.211353713.401. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPUSHpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8200K400K600K800K1000KMin: 1152073.75 / Avg: 1210430.46 / Max: 1412429.38Min: 1204819.25 / Avg: 1222231.42 / Max: 1245330Min: 1180637.5 / Avg: 1201386.46 / Max: 1233045.62Min: 1203369.5 / Avg: 1218625.21 / Max: 1230012.25Min: 1197604.88 / Avg: 1353713.4 / Max: 14598541. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

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: json_loadspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8612182430SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 326.026.426.026.226.3
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8612182430Min: 25.9 / Avg: 25.97 / Max: 26Min: 26.4 / Avg: 26.4 / Max: 26.4Min: 25.9 / Avg: 25.97 / Max: 26Min: 26.2 / Avg: 26.23 / Max: 26.3Min: 26.3 / Avg: 26.3 / Max: 26.3

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 Timespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82004006008001000SE +/- 1.45, N = 3SE +/- 1.53, N = 3SE +/- 2.52, N = 3SE +/- 1.33, N = 310631062106410681062
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test Timespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82004006008001000Min: 1061 / Avg: 1063.33 / Max: 1066Min: 1059 / Avg: 1062 / Max: 1064Min: 1061 / Avg: 1064 / Max: 1069Min: 1059 / Avg: 1061.67 / Max: 1063

Timed Apache Compilation

This test times how long it takes to build the Apache HTTPD web server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To Compilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8612182430SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 323.8823.7523.9523.3023.05
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To Compilepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8612182430Min: 23.86 / Avg: 23.88 / Max: 23.9Min: 23.73 / Avg: 23.75 / Max: 23.79Min: 23.85 / Avg: 23.95 / Max: 24.03Min: 23.24 / Avg: 23.3 / Max: 23.38Min: 22.99 / Avg: 23.05 / Max: 23.11

Apache Siege

This is a test of the Apache web server performance being facilitated by the Siege web serverb enchmark program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 50page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.88K16K24K32K40KSE +/- 193.59, N = 3SE +/- 517.53, N = 3SE +/- 140.31, N = 3SE +/- 253.47, N = 9SE +/- 299.97, N = 335421.2535185.4327965.6226919.6636228.061. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 50page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.86K12K18K24K30KMin: 35038.54 / Avg: 35421.25 / Max: 35663.34Min: 34153 / Avg: 35185.43 / Max: 35765.38Min: 27731.56 / Avg: 27965.62 / Max: 28216.71Min: 26315.79 / Avg: 26919.66 / Max: 28328.61Min: 35842.29 / Avg: 36228.06 / Max: 36818.851. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

AOM AV1

This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 4 Two-Passpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.50851.0171.52552.0342.5425SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 32.242.202.252.262.261. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 4 Two-Passpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810Min: 2.22 / Avg: 2.24 / Max: 2.26Min: 2.18 / Avg: 2.2 / Max: 2.23Min: 2.25 / Avg: 2.25 / Max: 2.25Min: 2.25 / Avg: 2.26 / Max: 2.28Min: 2.26 / Avg: 2.26 / Max: 2.261. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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 1.2.0Scene: Memorialpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8510152025SE +/- 0.11, N = 3SE +/- 0.14, N = 15SE +/- 0.00, N = 3SE +/- 0.21, N = 3SE +/- 0.15, N = 316.5216.7816.4618.2818.43
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.2.0Scene: Memorialpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8510152025Min: 16.36 / Avg: 16.52 / Max: 16.72Min: 16.36 / Avg: 16.78 / Max: 17.8Min: 16.46 / Avg: 16.46 / Max: 16.46Min: 17.96 / Avg: 18.28 / Max: 18.69Min: 18.23 / Avg: 18.43 / Max: 18.71

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Processespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81224364860SE +/- 0.53, N = 15SE +/- 0.35, N = 15SE +/- 0.50, N = 15SE +/- 0.50, N = 3SE +/- 0.37, N = 1552.0049.6652.5649.7543.671. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Processespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81122334455Min: 49.82 / Avg: 52 / Max: 54.98Min: 48.12 / Avg: 49.66 / Max: 53.97Min: 50.67 / Avg: 52.56 / Max: 56.44Min: 48.83 / Avg: 49.75 / Max: 50.54Min: 41.73 / Avg: 43.67 / Max: 46.481. (CC) gcc options: -lm

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performancepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.814002800420056007000SE +/- 12.55, N = 3SE +/- 6.79, N = 3SE +/- 5.17, N = 3SE +/- 4.91, N = 3SE +/- 3.84, N = 36354.36344.36399.36339.16339.11. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performancepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.811002200330044005500Min: 6339 / Avg: 6354.33 / Max: 6379.2Min: 6335.6 / Avg: 6344.33 / Max: 6357.7Min: 6392.7 / Avg: 6399.3 / Max: 6409.5Min: 6331.7 / Avg: 6339.13 / Max: 6348.4Min: 6333 / Avg: 6339.13 / Max: 6346.21. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

AOM AV1

This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 8 Realtimepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8714212835SE +/- 0.41, N = 3SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.20, N = 3SE +/- 0.32, N = 330.6230.2030.5932.2631.231. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 8 Realtimepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8714212835Min: 30.16 / Avg: 30.62 / Max: 31.45Min: 29.98 / Avg: 30.2 / Max: 30.52Min: 30.31 / Avg: 30.59 / Max: 30.77Min: 31.85 / Avg: 32.26 / Max: 32.49Min: 30.63 / Avg: 31.23 / Max: 31.71. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 8 - Type: Processpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8510152025SE +/- 0.21, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.17, N = 6SE +/- 0.05, N = 315.1614.6222.0015.0213.081. (CC) gcc options: -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 8 - Type: Processpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8510152025Min: 14.74 / Avg: 15.16 / Max: 15.43Min: 14.55 / Avg: 14.62 / Max: 14.67Min: 21.87 / Avg: 22 / Max: 22.07Min: 14.65 / Avg: 15.02 / Max: 15.63Min: 13.01 / Avg: 13.08 / Max: 13.181. (CC) gcc options: -lpthread

OCRMyPDF

OCRMyPDF is an optical character recognition (OCR) text layer to scanned PDF files, producing new PDFs with the text now selectable/searchable/copy-paste capable. OCRMyPDF leverages the Tesseract OCR engine and is written in Python. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 9.6.0+dfsgProcessing 60 Page PDF Documentpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8510152025SE +/- 0.06, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 318.9919.0519.0718.8818.95
OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 9.6.0+dfsgProcessing 60 Page PDF Documentpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8510152025Min: 18.89 / Avg: 18.99 / Max: 19.1Min: 18.92 / Avg: 19.05 / Max: 19.26Min: 19.01 / Avg: 19.07 / Max: 19.13Min: 18.79 / Avg: 18.88 / Max: 18.94Min: 18.84 / Avg: 18.95 / Max: 19.02

perf-bench

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Sched Pipepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.860K120K180K240K300KSE +/- 1818.33, N = 3SE +/- 613.65, N = 3SE +/- 1696.64, N = 3SE +/- 101.60, N = 3SE +/- 1191.59, N = 32788502833262769102812652761161. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Sched Pipepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.850K100K150K200K250KMin: 275214 / Avg: 278849.67 / Max: 280741Min: 282129 / Avg: 283325.67 / Max: 284160Min: 273648 / Avg: 276910.33 / Max: 279350Min: 281118 / Avg: 281265 / Max: 281460Min: 273785 / Avg: 276116 / Max: 2777111. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 8 - Type: Threadpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8612182430SE +/- 0.19, N = 3SE +/- 0.19, N = 3SE +/- 0.27, N = 3SE +/- 0.15, N = 3SE +/- 0.13, N = 316.4616.4123.1616.5214.761. (CC) gcc options: -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 8 - Type: Threadpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8510152025Min: 16.1 / Avg: 16.46 / Max: 16.74Min: 16.1 / Avg: 16.41 / Max: 16.75Min: 22.62 / Avg: 23.16 / Max: 23.47Min: 16.25 / Avg: 16.52 / Max: 16.77Min: 14.56 / Avg: 14.76 / Max: 15.021. (CC) gcc options: -lpthread

iPerf

iPerf is a network bandwidth throughput testing software. This test profile is used for automated testing of an iperf client and requires you have access to an iperf server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 20page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.88K16K24K32K40KSE +/- 61.55, N = 3SE +/- 139.08, N = 3SE +/- 398.64, N = 7SE +/- 505.96, N = 4SE +/- 159.38, N = 33457834711352093461735608
OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 20page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.86K12K18K24K30KMin: 34461 / Avg: 34577.67 / Max: 34670Min: 34435 / Avg: 34711 / Max: 34879Min: 33641 / Avg: 35209 / Max: 36312Min: 33180 / Avg: 34616.75 / Max: 35351Min: 35298 / Avg: 35607.67 / Max: 35828

Nebular Empirical Analysis Tool

NEAT is the Nebular Empirical Analysis Tool for empirical analysis of ionised nebulae, with uncertainty propagation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNebular Empirical Analysis Tool 2020-02-29page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.848121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 316.3316.2916.2816.2816.281. (F9X) gfortran options: -cpp -ffree-line-length-0 -Jsource/ -fopenmp -O3 -fno-backtrace
OpenBenchmarking.orgSeconds, Fewer Is BetterNebular Empirical Analysis Tool 2020-02-29page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.848121620Min: 16.31 / Avg: 16.33 / Max: 16.34Min: 16.27 / Avg: 16.29 / Max: 16.3Min: 16.23 / Avg: 16.28 / Max: 16.35Min: 16.27 / Avg: 16.28 / Max: 16.29Min: 16.25 / Avg: 16.28 / Max: 16.31. (F9X) gfortran options: -cpp -ffree-line-length-0 -Jsource/ -fopenmp -O3 -fno-backtrace

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Thoroughpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 310.5010.4610.4610.4810.451. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Thoroughpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215Min: 10.47 / Avg: 10.5 / Max: 10.55Min: 10.45 / Avg: 10.46 / Max: 10.46Min: 10.45 / Avg: 10.46 / Max: 10.47Min: 10.46 / Avg: 10.48 / Max: 10.49Min: 10.44 / Avg: 10.45 / Max: 10.461. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

perf-bench

OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memset 1MBpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81326395265SE +/- 0.51, N = 3SE +/- 1.00, N = 3SE +/- 0.83, N = 4SE +/- 0.97, N = 3SE +/- 0.55, N = 1558.3459.7958.3258.6459.131. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
OpenBenchmarking.orgGB/sec, More Is Betterperf-benchBenchmark: Memset 1MBpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81224364860Min: 57.61 / Avg: 58.34 / Max: 59.33Min: 58.53 / Avg: 59.79 / Max: 61.77Min: 56.8 / Avg: 58.32 / Max: 60.03Min: 57.41 / Avg: 58.64 / Max: 60.55Min: 56.62 / Avg: 59.13 / Max: 65.131. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma

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: Tradebeanspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.811002200330044005500SE +/- 18.65, N = 4SE +/- 25.44, N = 4SE +/- 30.29, N = 4SE +/- 18.92, N = 4SE +/- 38.95, N = 453155232523853025210
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Tradebeanspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89001800270036004500Min: 5272 / Avg: 5314.75 / Max: 5347Min: 5175 / Avg: 5231.5 / Max: 5297Min: 5200 / Avg: 5237.75 / Max: 5328Min: 5265 / Avg: 5301.5 / Max: 5349Min: 5095 / Avg: 5209.5 / Max: 5266

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 Streamclusterpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.848121620SE +/- 0.20, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 314.3814.4814.5814.3614.581. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Streamclusterpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.848121620Min: 14.07 / Avg: 14.38 / Max: 14.75Min: 14.34 / Avg: 14.48 / Max: 14.7Min: 14.44 / Avg: 14.58 / Max: 14.77Min: 14.15 / Avg: 14.36 / Max: 14.54Min: 14.46 / Avg: 14.58 / Max: 14.731. (CXX) g++ options: -O2 -lOpenCL

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080ppage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810SE +/- 0.037, N = 3SE +/- 0.015, N = 3SE +/- 0.019, N = 3SE +/- 0.061, N = 3SE +/- 0.021, N = 36.7026.6936.6856.7316.6801. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080ppage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215Min: 6.64 / Avg: 6.7 / Max: 6.77Min: 6.67 / Avg: 6.69 / Max: 6.72Min: 6.65 / Avg: 6.69 / Max: 6.71Min: 6.66 / Avg: 6.73 / Max: 6.85Min: 6.64 / Avg: 6.68 / Max: 6.71. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

iPerf

iPerf is a network bandwidth throughput testing software. This test profile is used for automated testing of an iperf client and requires you have access to an iperf server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 32page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.88K16K24K32K40KSE +/- 178.67, N = 3SE +/- 133.98, N = 3SE +/- 438.88, N = 4SE +/- 500.64, N = 3SE +/- 302.11, N = 33422734486339193439835056
OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 32page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.86K12K18K24K30KMin: 33986 / Avg: 34227 / Max: 34576Min: 34279 / Avg: 34486.33 / Max: 34737Min: 32801 / Avg: 33919 / Max: 34621Min: 33424 / Avg: 34398 / Max: 35086Min: 34615 / Avg: 35055.67 / Max: 35634

OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 32page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8816243240SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 333.633.633.633.633.6
OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 32page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8714212835Min: 33.6 / Avg: 33.6 / Max: 33.6Min: 33.6 / Avg: 33.6 / Max: 33.6Min: 33.6 / Avg: 33.6 / Max: 33.6Min: 33.6 / Avg: 33.6 / Max: 33.6Min: 33.6 / Avg: 33.6 / Max: 33.6

OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 32page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87K14K21K28K35KSE +/- 131.15, N = 3SE +/- 50.29, N = 3SE +/- 16.23, N = 3SE +/- 80.71, N = 3SE +/- 227.51, N = 33073230013319793182130959
OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 32page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.86K12K18K24K30KMin: 30474 / Avg: 30731.67 / Max: 30903Min: 29939 / Avg: 30013 / Max: 30109Min: 31947 / Avg: 31979.33 / Max: 31998Min: 31687 / Avg: 31821.33 / Max: 31966Min: 30650 / Avg: 30959.33 / Max: 31403

OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.88K16K24K32K40KSE +/- 213.51, N = 3SE +/- 281.37, N = 3SE +/- 236.58, N = 3SE +/- 403.01, N = 3SE +/- 322.08, N = 33600937752374863770137121
OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87K14K21K28K35KMin: 35678 / Avg: 36008.67 / Max: 36408Min: 37276 / Avg: 37752.33 / Max: 38250Min: 37103 / Avg: 37485.67 / Max: 37918Min: 36960 / Avg: 37701.33 / Max: 38346Min: 36524 / Avg: 37121 / Max: 37629

OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.23630.47260.70890.94521.1815SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.051.051.051.051.05
OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810Min: 1.05 / Avg: 1.05 / Max: 1.05Min: 1.05 / Avg: 1.05 / Max: 1.05Min: 1.05 / Avg: 1.05 / Max: 1.05Min: 1.05 / Avg: 1.05 / Max: 1.05Min: 1.05 / Avg: 1.05 / Max: 1.05

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: Tradesoappage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.88001600240032004000SE +/- 49.71, N = 4SE +/- 20.28, N = 4SE +/- 20.92, N = 4SE +/- 28.76, N = 4SE +/- 36.61, N = 436243612355236773617
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Tradesoappage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.86001200180024003000Min: 3511 / Avg: 3624 / Max: 3711Min: 3557 / Avg: 3612.25 / Max: 3654Min: 3499 / Avg: 3552 / Max: 3586Min: 3615 / Avg: 3677.25 / Max: 3753Min: 3523 / Avg: 3617.25 / Max: 3696

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.89001800270036004500SE +/- 50.00, N = 4SE +/- 30.30, N = 4SE +/- 33.33, N = 4SE +/- 36.52, N = 4SE +/- 50.79, N = 541034084406740984138
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87001400210028003500Min: 4010 / Avg: 4102.75 / Max: 4242Min: 4005 / Avg: 4083.5 / Max: 4152Min: 3986 / Avg: 4067 / Max: 4138Min: 4011 / Avg: 4097.75 / Max: 4172Min: 4008 / Avg: 4138.2 / Max: 4302

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 1 - Type: Threadpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.80.94611.89222.83833.78444.7305SE +/- 0.122, N = 12SE +/- 0.023, N = 3SE +/- 0.056, N = 3SE +/- 0.073, N = 15SE +/- 0.078, N = 153.9764.2053.4253.8943.2391. (CC) gcc options: -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 1 - Type: Threadpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810Min: 2.72 / Avg: 3.98 / Max: 4.45Min: 4.18 / Avg: 4.21 / Max: 4.25Min: 3.33 / Avg: 3.43 / Max: 3.53Min: 2.99 / Avg: 3.89 / Max: 4.22Min: 2.51 / Avg: 3.24 / Max: 3.621. (CC) gcc options: -lpthread

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 4000 Files, 32 Sub Dirs, 1MB Sizepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82004006008001000SE +/- 1.50, N = 3SE +/- 10.84, N = 15SE +/- 1.05, N = 3SE +/- 2.74, N = 3SE +/- 7.53, N = 13908.1937.1892.9886.9916.01. (CC) gcc options: -static
OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 4000 Files, 32 Sub Dirs, 1MB Sizepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8160320480640800Min: 905.1 / Avg: 908.1 / Max: 909.8Min: 877.6 / Avg: 937.13 / Max: 994.9Min: 890.8 / Avg: 892.9 / Max: 894.1Min: 884 / Avg: 886.93 / Max: 892.4Min: 892.5 / Avg: 916.02 / Max: 9891. (CC) gcc options: -static

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 5000 Files, 1MB Size, 4 Threadspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8400800120016002000SE +/- 12.08, N = 3SE +/- 4.99, N = 3SE +/- 1.94, N = 3SE +/- 8.13, N = 3SE +/- 3.48, N = 31872.11878.01859.01869.81875.51. (CC) gcc options: -static
OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 5000 Files, 1MB Size, 4 Threadspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.830060090012001500Min: 1859.2 / Avg: 1872.07 / Max: 1896.2Min: 1872.5 / Avg: 1878.03 / Max: 1888Min: 1856.8 / Avg: 1859.03 / Max: 1862.9Min: 1855.2 / Avg: 1869.77 / Max: 1883.3Min: 1868.5 / Avg: 1875.47 / Max: 1879.11. (CC) gcc options: -static

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 CFD Solverpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 310.5910.7210.6210.6010.641. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD Solverpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215Min: 10.56 / Avg: 10.59 / Max: 10.65Min: 10.61 / Avg: 10.72 / Max: 10.82Min: 10.6 / Avg: 10.62 / Max: 10.65Min: 10.55 / Avg: 10.6 / Max: 10.67Min: 10.57 / Avg: 10.64 / Max: 10.721. (CXX) g++ options: -O2 -lOpenCL

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 4 - Type: Threadpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215SE +/- 0.133, N = 4SE +/- 0.125, N = 3SE +/- 0.026, N = 3SE +/- 0.130, N = 3SE +/- 0.040, N = 39.6289.58112.5539.5507.9251. (CC) gcc options: -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 4 - Type: Threadpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.848121620Min: 9.23 / Avg: 9.63 / Max: 9.81Min: 9.33 / Avg: 9.58 / Max: 9.72Min: 12.51 / Avg: 12.55 / Max: 12.6Min: 9.32 / Avg: 9.55 / Max: 9.77Min: 7.85 / Avg: 7.92 / Max: 7.981. (CC) gcc options: -lpthread

x265

This is a simple test of the x265 encoder run on the CPU with a sample 1080p video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.1.2H.265 1080p Video Encodingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81428425670SE +/- 0.05, N = 3SE +/- 0.21, N = 3SE +/- 0.02, N = 3SE +/- 0.29, N = 3SE +/- 0.12, N = 358.9458.5258.6560.6759.991. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.1.2H.265 1080p Video Encodingpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81224364860Min: 58.86 / Avg: 58.94 / Max: 59.03Min: 58.3 / Avg: 58.52 / Max: 58.94Min: 58.61 / Avg: 58.65 / Max: 58.68Min: 60.11 / Avg: 60.67 / Max: 61.08Min: 59.82 / Avg: 59.99 / Max: 60.211. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 4 - Type: Processpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215SE +/- 0.081, N = 3SE +/- 0.052, N = 3SE +/- 0.066, N = 3SE +/- 0.011, N = 3SE +/- 0.034, N = 39.2319.26312.2929.2526.4341. (CC) gcc options: -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 4 - Type: Processpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.848121620Min: 9.08 / Avg: 9.23 / Max: 9.36Min: 9.16 / Avg: 9.26 / Max: 9.34Min: 12.16 / Avg: 12.29 / Max: 12.38Min: 9.24 / Avg: 9.25 / Max: 9.27Min: 6.38 / Avg: 6.43 / Max: 6.51. (CC) gcc options: -lpthread

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: Jythonpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.810002000300040005000SE +/- 16.08, N = 4SE +/- 17.10, N = 4SE +/- 10.36, N = 4SE +/- 8.24, N = 4SE +/- 20.14, N = 446684645466246244698
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Jythonpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.88001600240032004000Min: 4635 / Avg: 4667.5 / Max: 4706Min: 4626 / Avg: 4644.75 / Max: 4696Min: 4635 / Avg: 4662.25 / Max: 4682Min: 4603 / Avg: 4623.75 / Max: 4637Min: 4640 / Avg: 4697.5 / Max: 4734

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080ppage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81326395265SE +/- 0.16, N = 3SE +/- 0.26, N = 3SE +/- 0.23, N = 3SE +/- 0.09, N = 3SE +/- 0.26, N = 355.6655.8455.9356.6856.061. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080ppage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81122334455Min: 55.42 / Avg: 55.66 / Max: 55.97Min: 55.33 / Avg: 55.84 / Max: 56.17Min: 55.67 / Avg: 55.93 / Max: 56.38Min: 56.51 / Avg: 56.68 / Max: 56.83Min: 55.55 / Avg: 56.06 / Max: 56.421. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Mediumpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 36.716.686.716.716.711. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Mediumpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215Min: 6.7 / Avg: 6.71 / Max: 6.72Min: 6.66 / Avg: 6.68 / Max: 6.69Min: 6.7 / Avg: 6.71 / Max: 6.72Min: 6.67 / Avg: 6.71 / Max: 6.73Min: 6.69 / Avg: 6.71 / Max: 6.741. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

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 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080ppage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.880160240320400SE +/- 12.49, N = 12SE +/- 12.48, N = 12SE +/- 12.36, N = 12SE +/- 1.50, N = 3SE +/- 2.40, N = 3357.74358.00356.12369.70365.291. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080ppage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.870140210280350Min: 220.51 / Avg: 357.74 / Max: 374.77Min: 220.99 / Avg: 358 / Max: 374.77Min: 220.51 / Avg: 356.12 / Max: 373.6Min: 367.87 / Avg: 369.7 / Max: 372.67Min: 361.88 / Avg: 365.29 / Max: 369.911. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 2 - Type: Threadpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810SE +/- 0.031, N = 3SE +/- 0.048, N = 3SE +/- 0.017, N = 3SE +/- 0.046, N = 3SE +/- 0.053, N = 35.9445.9646.9375.9514.6701. (CC) gcc options: -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 2 - Type: Threadpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215Min: 5.89 / Avg: 5.94 / Max: 6Min: 5.91 / Avg: 5.96 / Max: 6.06Min: 6.91 / Avg: 6.94 / Max: 6.97Min: 5.9 / Avg: 5.95 / Max: 6.04Min: 4.57 / Avg: 4.67 / Max: 4.741. (CC) gcc options: -lpthread

perf-bench

OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Syscall Basicpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.84M8M12M16M20MSE +/- 173424.65, N = 3SE +/- 40252.20, N = 3SE +/- 14576.49, N = 3SE +/- 34882.47, N = 3SE +/- 10970.47, N = 317075923171615521733022617262967172380581. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
OpenBenchmarking.orgops/sec, More Is Betterperf-benchBenchmark: Syscall Basicpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83M6M9M12M15MMin: 16833478 / Avg: 17075922.67 / Max: 17411956Min: 17087868 / Avg: 17161552.33 / Max: 17226478Min: 17306161 / Avg: 17330225.67 / Max: 17356509Min: 17227772 / Avg: 17262967 / Max: 17332731Min: 17216175 / Avg: 17238058.33 / Max: 172503761. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Filespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.848121620SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 314.7814.7914.6814.8814.731. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Filespage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.848121620Min: 14.74 / Avg: 14.78 / Max: 14.82Min: 14.78 / Avg: 14.79 / Max: 14.81Min: 14.66 / Avg: 14.68 / Max: 14.69Min: 14.84 / Avg: 14.88 / Max: 14.96Min: 14.71 / Avg: 14.73 / Max: 14.761. (CC) gcc options: -lm

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 2 - Type: Processpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810SE +/- 0.006, N = 3SE +/- 0.058, N = 3SE +/- 0.020, N = 3SE +/- 0.056, N = 3SE +/- 0.014, N = 35.5445.5586.8285.5584.3211. (CC) gcc options: -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 2 - Type: Processpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.83691215Min: 5.53 / Avg: 5.54 / Max: 5.55Min: 5.47 / Avg: 5.56 / Max: 5.67Min: 6.8 / Avg: 6.83 / Max: 6.87Min: 5.5 / Avg: 5.56 / Max: 5.67Min: 4.3 / Avg: 4.32 / Max: 4.351. (CC) gcc options: -lpthread

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 8page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81.25912.51823.77735.03646.2955SE +/- 0.017, N = 3SE +/- 0.005, N = 3SE +/- 0.012, N = 3SE +/- 0.014, N = 3SE +/- 0.021, N = 35.5675.5595.5655.5485.5961. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 8page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810Min: 5.54 / Avg: 5.57 / Max: 5.6Min: 5.55 / Avg: 5.56 / Max: 5.57Min: 5.55 / Avg: 5.57 / Max: 5.59Min: 5.52 / Avg: 5.55 / Max: 5.57Min: 5.56 / Avg: 5.6 / Max: 5.631. (CXX) g++ options: -O3 -fPIC

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 10page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81.22762.45523.68284.91046.138SE +/- 0.015, N = 3SE +/- 0.021, N = 3SE +/- 0.013, N = 3SE +/- 0.015, N = 3SE +/- 0.021, N = 35.4565.4425.4435.4135.4561. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 10page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810Min: 5.43 / Avg: 5.46 / Max: 5.48Min: 5.41 / Avg: 5.44 / Max: 5.48Min: 5.43 / Avg: 5.44 / Max: 5.47Min: 5.39 / Avg: 5.41 / Max: 5.44Min: 5.43 / Avg: 5.46 / Max: 5.51. (CXX) g++ options: -O3 -fPIC

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Fastpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81.22632.45263.67894.90526.1315SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 35.435.455.445.425.421. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Fastpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810Min: 5.42 / Avg: 5.43 / Max: 5.44Min: 5.43 / Avg: 5.45 / Max: 5.47Min: 5.43 / Avg: 5.44 / Max: 5.45Min: 5.39 / Avg: 5.42 / Max: 5.45Min: 5.41 / Avg: 5.42 / Max: 5.441. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Threadspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8510152025SE +/- 0.13, N = 3SE +/- 0.23, N = 3SE +/- 0.32, N = 3SE +/- 0.12, N = 3SE +/- 0.30, N = 422.5922.1022.3822.4521.001. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Threadspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8510152025Min: 22.41 / Avg: 22.59 / Max: 22.83Min: 21.66 / Avg: 22.1 / Max: 22.44Min: 21.96 / Avg: 22.38 / Max: 23.01Min: 22.24 / Avg: 22.45 / Max: 22.67Min: 20.52 / Avg: 21 / Max: 21.881. (CC) gcc options: -lm

OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory Allocationspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820406080100SE +/- 0.18, N = 3SE +/- 0.13, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 3SE +/- 0.04, N = 394.2093.3893.47104.05102.891. (CC) gcc options: -lm
OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory Allocationspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.820406080100Min: 93.85 / Avg: 94.2 / Max: 94.38Min: 93.19 / Avg: 93.38 / Max: 93.63Min: 93.42 / Avg: 93.47 / Max: 93.58Min: 103.82 / Avg: 104.05 / Max: 104.21Min: 102.81 / Avg: 102.89 / Max: 102.951. (CC) gcc options: -lm

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Launch Programspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81530456075SE +/- 0.50, N = 3SE +/- 0.17, N = 3SE +/- 0.74, N = 3SE +/- 0.35, N = 3SE +/- 0.75, N = 369.0167.2369.3368.9062.321. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Launch Programspage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81326395265Min: 68.48 / Avg: 69.01 / Max: 70Min: 66.95 / Avg: 67.23 / Max: 67.54Min: 68.08 / Avg: 69.33 / Max: 70.65Min: 68.28 / Avg: 68.9 / Max: 69.5Min: 60.87 / Avg: 62.32 / Max: 63.371. (CC) gcc options: -lm

SQLite

This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.30.1Threads / Copies: 8page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.81.03932.07863.11794.15725.1965SE +/- 0.013, N = 3SE +/- 0.036, N = 3SE +/- 0.031, N = 3SE +/- 0.006, N = 3SE +/- 0.007, N = 34.6074.6034.5624.6194.6161. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.30.1Threads / Copies: 8page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8246810Min: 4.59 / Avg: 4.61 / Max: 4.63Min: 4.53 / Avg: 4.6 / Max: 4.65Min: 4.5 / Avg: 4.56 / Max: 4.6Min: 4.61 / Avg: 4.62 / Max: 4.63Min: 4.61 / Avg: 4.62 / Max: 4.631. (CC) gcc options: -O2 -lz -lm -ldl -lpthread

Apache Siege

This is a test of the Apache web server performance being facilitated by the Siege web serverb enchmark program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82K4K6K8K10KSE +/- 84.93, N = 3SE +/- 79.71, N = 7SE +/- 68.13, N = 13SE +/- 93.15, N = 3SE +/- 160.13, N = 156962.647062.007001.086789.897912.291. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 1page_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.814002800420056007000Min: 6802.72 / Avg: 6962.64 / Max: 7092.2Min: 6666.67 / Avg: 7062 / Max: 7246.38Min: 6451.61 / Avg: 7001.08 / Max: 7462.69Min: 6622.52 / Avg: 6789.89 / Max: 6944.44Min: 7092.2 / Avg: 7912.29 / Max: 9259.261. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

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 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080ppage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.860120180240300SE +/- 0.97, N = 3SE +/- 2.77, N = 3SE +/- 2.18, N = 3SE +/- 1.50, N = 3SE +/- 2.84, N = 3286.27286.31287.16285.77285.091. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080ppage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.850100150200250Min: 285.04 / Avg: 286.27 / Max: 288.18Min: 281.69 / Avg: 286.31 / Max: 291.26Min: 283.42 / Avg: 287.16 / Max: 290.98Min: 283.02 / Avg: 285.77 / Max: 288.18Min: 281.03 / Avg: 285.09 / Max: 290.561. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Sizepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.82004006008001000SE +/- 7.49, N = 3SE +/- 11.34, N = 3SE +/- 13.92, N = 3SE +/- 11.44, N = 3SE +/- 3.81, N = 3907.8886.3905.1898.4900.71. (CC) gcc options: -static
OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Sizepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8160320480640800Min: 893.8 / Avg: 907.8 / Max: 919.4Min: 865.9 / Avg: 886.27 / Max: 905.1Min: 877.5 / Avg: 905.1 / Max: 922Min: 878.9 / Avg: 898.37 / Max: 918.5Min: 893.1 / Avg: 900.67 / Max: 905.21. (CC) gcc options: -static

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Size, No Sync/FSyncpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.85001000150020002500SE +/- 6.11, N = 3SE +/- 8.70, N = 3SE +/- 2.44, N = 3SE +/- 12.61, N = 3SE +/- 3.80, N = 32453.72432.02460.12442.32490.71. (CC) gcc options: -static
OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Size, No Sync/FSyncpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8400800120016002000Min: 2446.4 / Avg: 2453.67 / Max: 2465.8Min: 2414.7 / Avg: 2432 / Max: 2442.3Min: 2455.2 / Avg: 2460.07 / Max: 2462.9Min: 2417.1 / Avg: 2442.27 / Max: 2456.2Min: 2486 / Avg: 2490.67 / Max: 2498.21. (CC) gcc options: -static

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled Treepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.87001400210028003500SE +/- 0.00, N = 3SE +/- 10.79, N = 3SE +/- 10.44, N = 3SE +/- 10.79, N = 3SE +/- 10.79, N = 33012.263033.843000.733023.053023.05
OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled Treepage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.85001000150020002500Min: 3012.26 / Avg: 3012.26 / Max: 3012.26Min: 3012.26 / Avg: 3033.84 / Max: 3044.63Min: 2979.89 / Avg: 3000.73 / Max: 3012.26Min: 3012.26 / Avg: 3023.05 / Max: 3044.63Min: 3012.26 / Avg: 3023.05 / Max: 3044.63

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial Createpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8130260390520650SE +/- 2.09, N = 3SE +/- 4.28, N = 3SE +/- 1.85, N = 3SE +/- 2.19, N = 3SE +/- 3.10, N = 3587.97588.25585.25585.65603.17
OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial Createpage_lock_unfairness 1000PLU 1PLU 0Linux 5.9-rc4Linux 5.8110220330440550Min: 583.78 / Avg: 587.97 / Max: 590.18Min: 581.63 / Avg: 588.25 / Max: 596.27Min: 582.04 / Avg: 585.25 / Max: 588.44Min: 583.14 / Avg: 585.65 / Max: 590.02Min: 597.28 / Avg: 603.17 / Max: 607.78

200 Results Shown

Renaissance:
  Savina Reactors.IO
  In-Memory Database Shootout
  Apache Spark PageRank
Java Gradle Build
Renaissance
MariaDB
Memcached mcperf:
  Add - 16
  Set - 16
LeelaChessZero
Memcached mcperf:
  Append - 16
  Replace - 16
  Prepend - 16
PlaidML
OpenVKL
LeelaChessZero
AI Benchmark Alpha:
  Device AI Score
  Device Training Score
  Device Inference Score
MariaDB
Timed LLVM Compilation
Renaissance
Memcached mcperf:
  Delete - 16
  Get - 16
Renaissance
PlaidML
Renaissance
Blender
CP2K Molecular Dynamics
MariaDB
PlaidML
High Performance Conjugate Gradient
Renaissance
Stress-NG
Schbench
Apache Cassandra
Apache Siege
Schbench
Memcached mcperf:
  Delete - 1
  Add - 1
PostgreSQL pgbench:
  Buffer Test - Normal Load - Read Write
  Buffer Test - Single Thread - Read Write
  Buffer Test - Single Thread - Read Only
  Buffer Test - Normal Load - Read Only
TensorFlow Lite
Schbench
Stress-NG
PlaidML
Rodinia:
  OpenMP LavaMD
  OpenMP HotSpot3D
pmbench
Memcached mcperf:
  Get - 1
  Replace - 1
Apache Siege
Memcached mcperf
YafaRay
Blender
ASTC Encoder
PlaidML
MariaDB
Memcached mcperf
NGINX Benchmark
Stress-NG
pmbench
Renaissance
Schbench
PyPerformance
SQLite Speedtest
Hackbench
KeyDB
Build2
Blender
TensorFlow Lite
Node.js Express HTTP Load Test
libavif avifenc
TensorFlow Lite
pmbench:
  1 - 50%
  8 - 50%
  1 - 100% Writes
  2 - 100% Writes
  4 - 100% Writes
  8 - 100% Writes
  1 - 100% Reads
  2 - 100% Reads
  8 - 100% Reads
  4 - 100% Reads
TensorFlow Lite:
  SqueezeNet
  Mobilenet Quant
  Mobilenet Float
Hackbench
Himeno Benchmark
Schbench
Coremark
Git
Hackbench
Rodinia
Redis
RawTherapee
Timed Linux Kernel Compilation
perf-bench
Stress-NG
Apache Siege
NAMD
Ethr
MariaDB
Zstd Compression
libavif avifenc
perf-bench
Memcached mcperf
PlaidML
Redis:
  GET
  SET
PyPerformance
Stress-NG
AOM AV1
Apache Benchmark
Redis
Ethr
AOM AV1
Node.js Octane Benchmark
Schbench
AOM AV1
Stress-NG:
  CPU Stress
  NUMA
  System V Message Passing
  Memory Copying
  MEMFD
  SENDFILE
  Crypto
  MMAP
  Vector Math
  Atomic
  Matrix Math
  Socket Activity
  Semaphores
perf-bench:
  Futex Lock-Pi
  Futex Hash
Zstd Compression
librsvg
Tesseract OCR
Compile Bench
Ethr:
  HTTP - Bandwidth - 16
  UDP - Bandwidth - 16
  TCP - Bandwidth - 16
  TCP - Latency - 16
Redis
PyPerformance
PyBench
Timed Apache Compilation
Apache Siege
AOM AV1
Intel Open Image Denoise
OSBench
OpenSSL
AOM AV1
Hackbench
OCRMyPDF
perf-bench
Hackbench
iPerf
Nebular Empirical Analysis Tool
ASTC Encoder
perf-bench
DaCapo Benchmark
Rodinia
SVT-AV1
iPerf:
  5201 - 10 Seconds - TCP - 32
  5201 - 10 Seconds - UDP - 32
  5201 - 10 Seconds - UDP - 1000Mbit Objective - 32
  5201 - 10 Seconds - TCP - 1
  5201 - 10 Seconds - UDP - 1
DaCapo Benchmark:
  Tradesoap
  H2
Hackbench
FS-Mark:
  4000 Files, 32 Sub Dirs, 1MB Size
  5000 Files, 1MB Size, 4 Threads
Rodinia
Hackbench
x265
Hackbench
DaCapo Benchmark
SVT-AV1
ASTC Encoder
SVT-VP9
Hackbench
perf-bench
OSBench
Hackbench
libavif avifenc:
  8
  10
ASTC Encoder
OSBench:
  Create Threads
  Memory Allocations
  Launch Programs
SQLite
Apache Siege
SVT-VP9
FS-Mark:
  1000 Files, 1MB Size
  1000 Files, 1MB Size, No Sync/FSync
Compile Bench:
  Read Compiled Tree
  Initial Create

Linux 5.9-rc4

Processor: AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash Disk, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel I350

OS: Ubuntu 20.04, Kernel: 5.9.0-rc4-pts (x86_64) 20200910, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x830101c
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.2
Security Notes: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 10 September 2020 18:15 by user phoronix.

Linux 5.8

Processor: AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash Disk, Graphics: ASPEED, Audio: AMD Starship/Matisse, Network: 2 x Intel I350

OS: Ubuntu 20.04, Kernel: 5.8.0-pts (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x830101c
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.2
Security Notes: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 13 September 2020 06:29 by user phoronix.

page_lock_unfairness 1000

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x830101c
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.2
Security Notes: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 14 September 2020 15:58 by user phoronix.

PLU 0

Processor: AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash Disk, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel I350

OS: Ubuntu 20.04, Kernel: 5.9.0-rc5-14sep-patch (x86_64) 20200914, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x830101c
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.2
Security Notes: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 15 September 2020 09:38 by user phoronix.

PLU 1

Processor: AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash Disk, Graphics: ASPEED, Audio: AMD Starship/Matisse, Network: 2 x Intel I350

OS: Ubuntu 20.04, Kernel: 5.9.0-rc5-14sep-patch (x86_64) 20200914, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x830101c
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.2
Security Notes: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 16 September 2020 06:08 by user phoronix.