Linux 5.5 Clang Kernel

GCC vs. Clang Linux 5.5 built kernels by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1912270-PTS-LINUX55C73
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
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Clang 9.0 Built
December 24 2019
  8 Hours, 58 Minutes
GCC 9.2 Built
December 25 2019
  6 Hours, 58 Minutes
Invert Behavior (Only Show Selected Data)
  7 Hours, 58 Minutes
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 5.5 Clang KernelOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (32 Cores / 64 Threads)ASUS ROG ZENITH II EXTREME (0601 BIOS)AMD Starship/Matisse64512MB1000GB Force MP600AMD Radeon VII 16GB (1802/1001MHz)AMD Vega 20 HDMI AudioASUS VP28UAquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 19.105.5.0-rc3-clang9phx (x86_64) 201912245.5.0-rc3-gcc9phx (x86_64) 20191224GNOME Shell 3.34.1X Server 1.20.5amdgpu 19.0.14.5 Mesa 19.2.1 (LLVM 9.0.0)GCC 9.2.1 20191008ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelsDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionLinux 5.5 Clang Kernel BenchmarksSystem Logs- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --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 - NONE / errors=remount-ro,relatime,rw- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025- GLAMOR- Python 2.7.17rc1 + Python 3.7.5- 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 STIBP: conditional RSB filling + tsx_async_abort: Not affected

Clang 9.0 Built vs. GCC 9.2 Built ComparisonPhoronix Test SuiteBaseline+4.3%+4.3%+8.6%+8.6%+12.9%+12.9%17%15.7%13.5%7.6%7.6%6.3%4.7%4.7%4%3.8%3.3%3.2%3%2.9%2.9%2.1%2.1%S.V.M.PForkingC.S.TWavelet Contour - 3840 x 2160Wavelet Contour - 3840 x 2160Buffer Test - Heavy Contention - Read Write7.4%Buffer Test - Normal Load - Read Write7.3%BLASTCP - Bandwidth - 646.1%SET5.8%4.F.3.S.D.1.S5.3%TCP - Connections/s - 645.3%Socket Activity4.9%Wavelet Volume - 3840 x 2160Wavelet Volume - 3840 x 2160Read4.4%3840 x 2160 - GL2 AntTweakBarContext Switching4%32 - Process3.5%CPUSeq FillWrite3.1%Rand FillRedis3840 x 2160O.S2.3%1920 x 1080 - Fullscreen - Ultimate - 8 - Cocoa TempleUDP - Bandwidth - 64Rand Read2%Stress-NGStress-NGctx_clockParaViewParaViewPostgreSQL pgbenchPostgreSQL pgbenchLeelaChessZeroEthrRedisFS-MarkEthrStress-NGParaViewParaViewBlogBenchGeeXLabStress-NGHackbenchebizzyDeepSpeechFacebook RocksDBBlogBenchFacebook RocksDBMemtier_benchmarkTesseractRodiniaSuperTuxKartEthrFacebook RocksDBClang 9.0 BuiltGCC 9.2 Built

Linux 5.5 Clang Kernelselenium: ARES-6 - Firefoxselenium: WebXPRT - Firefoxselenium: Basemark - Firefoxselenium: CanvasMark - Firefoxselenium: PSPDFKit WASM - Firefoxcompilebench: Compilecompilebench: Initial Createcompilebench: Read Compiled Treegeexlab: 3840 x 2160 - GL2 Hot Tunnel DNActx-clock: Context Switch Timegeexlab: 3840 x 2160 - GL2 Noise Animation Electrichackbench: 32 - Processgeexlab: 3840 x 2160 - GL3 Mesh Exploderstress-ng: Forkingstress-ng: Socket Activitygeexlab: 3840 x 2160 - GL2 Cell Shadinggeexlab: 3840 x 2160 - GL2 Tunnel Beautygeexlab: 3840 x 2160 - GL2 AntTweakBargeexlab: 3840 x 2160 - GL3 Vertex Poolsupertuxkart: 1920 x 1080 - Fullscreen - Ultimate - 8 - Cocoa Templesupertuxkart: 1920 x 1080 - Fullscreen - Ultimate - 8 - Candela Citystress-ng: Semaphoresstress-ng: Context Switchingstress-ng: System V Message Passingtesseract: 3840 x 2160dbench: 1dbench: 6gputest: Pixmark Volplosion - 3840 x 2160 - Fullscreenfs-mark: 1000 Files, 1MB Sizegputest: Triangle - 3840 x 2160 - Fullscreengputest: Pixmark Piano - 3840 x 2160 - Fullscreengputest: TessMark - 3840 x 2160 - Fullscreengputest: Furmark - 3840 x 2160 - Fullscreengputest: Plot3D - 3840 x 2160 - Fullscreengputest: GiMark - 3840 x 2160 - Fullscreenfs-mark: 4000 Files, 32 Sub Dirs, 1MB Sizefs-mark: 1000 Files, 1MB Size, No Sync/FSynchimeno: Poisson Pressure Solverlczero: BLASlczero: Randdeepspeech: CPUgromacs: Water Benchmarkparboil: OpenMP LBMparboil: OpenMP CUTCPparboil: OpenMP Stencilparboil: OpenMP MRI Griddingnpb: BT.Cnpb: CG.Cnpb: EP.Cnpb: EP.Dnpb: FT.Cnpb: IS.Dnpb: LU.Cnpb: MG.Cnpb: SP.Brodinia: OpenMP LavaMDrodinia: OpenMP CFD Solverrodinia: OpenMP Streamclusternamd: ATPase Simulation - 327,506 Atomsaskap: tConvolve MT - Griddingaskap: tConvolve MT - Degriddingaskap: tConvolve MPI - Griddingaskap: tConvolve MPI - Degriddingaskap: tConvolve OpenMP - Griddingaskap: tConvolve OpenMP - Degriddingethr: TCP - Latency - 1ethr: TCP - Latency - 64ethr: HTTP - Bandwidth - 1ethr: TCP - Bandwidth - 64ethr: UDP - Bandwidth - 64ethr: HTTP - Bandwidth - 64ethr: TCP - Connections/s - 1y-cruncher: Calculating 500M Pi Digitsethr: TCP - Connections/s - 64coremark: CoreMark Size 666 - Iterations Per Secondstockfish: Total Timecompress-7zip: Compress Speed Testbuild-llvm: Time To Compilecompress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19build-gcc: Time To Compilesvt-vp9: Visual Quality Optimized - Bosphorus 1080psvt-av1: Enc Mode 4 - 1080psvt-av1: Enc Mode 8 - 1080pblender: Pabellon Barcelona - CPU-Onlybuild2: Time To Compilelibreoffice: 20 Documents To PDFblogbench: Readblogbench: Writenginx: Static Web Page Servingapache: Static Web Page Servingmemtier-benchmark: Redisredis: GETredis: SETsqlite: 1sqlite: 8rocksdb: Rand Fillrocksdb: Rand Readrocksdb: Seq Fillrocksdb: Rand Fill Syncrocksdb: Read While Writingsqlite-speedtest: Timed Time - Size 1,000pgbench: Buffer Test - Normal Load - Read Onlypgbench: Buffer Test - Normal Load - Read Writepgbench: Buffer Test - Heavy Contention - Read Onlypgbench: Buffer Test - Heavy Contention - Read Writeebizzy: paraview: Many Spheres - 3840 x 2160paraview: Many Spheres - 3840 x 2160paraview: Wavelet Volume - 3840 x 2160paraview: Wavelet Volume - 3840 x 2160paraview: Wavelet Contour - 3840 x 2160paraview: Wavelet Contour - 3840 x 2160Clang 9.0 BuiltGCC 9.2 Built50.03259754.811488712972361.80719.323745.81135.71852686.934.0014039.184600.9822850.863982.0112.13096.36623.7192.180013220.1479843378876.6913430897.9116958863.51380.033488.8987351.1962549574.74128041000158095944957937887579.22926.54873.04404733.553910099957.871843.27042.7431270.9480774.78237258.26572674687.1210998.942901.352923.0734986.161491.4166925.3630893.3634591.638.0247.63514.6190.563792706.583888.142733.753927.576290.294590.6216.5816.551005.281167530.66666667144142.666666673924.167145889.407543851388240.87633996599235197116121.3538.525572.126353.118.34768.548151.3649.8506.85515416145491542955.8833679.093058231.032473763.421961726.7814.21040.8871108679181240810117388332747610899258.295751720.66189913491.875997765627.63315612792.714109257166444.014412.356117.591881.379168.141752.24350.52261741.211490713042364.34711.703729.09136.31632694.132.7693992.597847.8621782.553972.9112.83221.06634.4196.292150222.1423393378942.7612914746.0219840008.52391.12612565571.84098641005158466000958167894549.82967.54877.78399235.6640100269.056.048503.24942.6466250.9460994.85899258.27038374188.7011008.582923.712918.6935126.471483.6967155.4230970.8234456.008.0087.66014.9620.563232716.033882.232734.923931.196339.434590.6216.6416.451005.77157939.11111111147127.777777783898.750146439.395516521399094.27084996431209196548119.2318.535567.874351.328.43068.345152.4949.5196.85214771445328142916.5034134.453148364.332463546.221854760.0314.33240.3911142437177770388121104232546602674358.045745068.67716912575.119136758184.37995811909.996817248504843.924403.150123.081969.290180.871884.833OpenBenchmarking.org

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: ARES-6 - Browser: FirefoxClang 9.0 BuiltGCC 9.2 Built1122334455SE +/- 0.22, N = 3SE +/- 0.10, N = 350.0350.521. firefox 71.0

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: WebXPRT - Browser: FirefoxClang 9.0 BuiltGCC 9.2 Built60120180240300SE +/- 1.45, N = 3SE +/- 0.33, N = 32592611. firefox 71.0

OpenBenchmarking.orgOverall Score, More Is BetterSeleniumBenchmark: Basemark - Browser: FirefoxClang 9.0 BuiltGCC 9.2 Built160320480640800SE +/- 12.10, N = 12SE +/- 10.68, N = 4754.81741.211. firefox 71.0

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: CanvasMark - Browser: FirefoxClang 9.0 BuiltGCC 9.2 Built3K6K9K12K15KSE +/- 131.56, N = 12SE +/- 207.75, N = 1214887149071. firefox 71.0

OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: FirefoxClang 9.0 BuiltGCC 9.2 Built30060090012001500SE +/- 2.85, N = 3SE +/- 4.70, N = 3129713041. firefox 71.0

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: CompileClang 9.0 BuiltGCC 9.2 Built5001000150020002500SE +/- 27.97, N = 6SE +/- 9.36, N = 32361.802364.34

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial CreateClang 9.0 BuiltGCC 9.2 Built160320480640800SE +/- 7.65, N = 3SE +/- 3.94, N = 3719.32711.70

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled TreeClang 9.0 BuiltGCC 9.2 Built8001600240032004000SE +/- 16.72, N = 3SE +/- 16.72, N = 33745.813729.09

GeeXLab

GeeXLab is a cross-platform tool for 3D programming and demo creation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterGeeXLab 0.28.0Resolution: 3840 x 2160 - Test: GL2 Hot Tunnel DNAClang 9.0 BuiltGCC 9.2 Built306090120150SE +/- 0.21, N = 3SE +/- 0.09, N = 3135.7136.3

ctx_clock

Ctx_clock is a simple test program to measure the context switch time in clock cycles. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch TimeClang 9.0 BuiltGCC 9.2 Built4080120160200SE +/- 4.84, N = 15185163

GeeXLab

GeeXLab is a cross-platform tool for 3D programming and demo creation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterGeeXLab 0.28.0Resolution: 3840 x 2160 - Test: GL2 Noise Animation ElectricClang 9.0 BuiltGCC 9.2 Built6001200180024003000SE +/- 11.71, N = 3SE +/- 11.21, N = 32686.92694.1

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: 32 - Type: ProcessClang 9.0 BuiltGCC 9.2 Built816243240SE +/- 0.45, N = 15SE +/- 0.08, N = 334.0032.771. (CC) gcc options: -lpthread

GeeXLab

GeeXLab is a cross-platform tool for 3D programming and demo creation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterGeeXLab 0.28.0Resolution: 3840 x 2160 - Test: GL3 Mesh ExploderClang 9.0 BuiltGCC 9.2 Built9001800270036004500SE +/- 8.78, N = 3SE +/- 17.25, N = 34039.13992.5

Stress-NG

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

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: ForkingClang 9.0 BuiltGCC 9.2 Built20K40K60K80K100KSE +/- 1402.96, N = 3SE +/- 956.73, N = 1584600.9897847.861. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Socket ActivityClang 9.0 BuiltGCC 9.2 Built5K10K15K20K25KSE +/- 107.95, N = 3SE +/- 300.15, N = 322850.8621782.551. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

GeeXLab

GeeXLab is a cross-platform tool for 3D programming and demo creation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterGeeXLab 0.28.0Resolution: 3840 x 2160 - Test: GL2 Cell ShadingClang 9.0 BuiltGCC 9.2 Built9001800270036004500SE +/- 13.62, N = 3SE +/- 4.96, N = 33982.03972.9

OpenBenchmarking.orgFPS, More Is BetterGeeXLab 0.28.0Resolution: 3840 x 2160 - Test: GL2 Tunnel BeautyClang 9.0 BuiltGCC 9.2 Built306090120150SE +/- 0.12, N = 3SE +/- 0.00, N = 3112.1112.8

OpenBenchmarking.orgFPS, More Is BetterGeeXLab 0.28.0Resolution: 3840 x 2160 - Test: GL2 AntTweakBarClang 9.0 BuiltGCC 9.2 Built7001400210028003500SE +/- 24.71, N = 3SE +/- 15.36, N = 33096.33221.0

OpenBenchmarking.orgFPS, More Is BetterGeeXLab 0.28.0Resolution: 3840 x 2160 - Test: GL3 Vertex PoolClang 9.0 BuiltGCC 9.2 Built14002800420056007000SE +/- 11.23, N = 3SE +/- 26.21, N = 36623.76634.4

SuperTuxKart

This is a test of SuperTuxKart, an open-source racing game. The engine, Antarctica, is a highly modified version of Irrlicht and uses OpenGL 3.1+. Bullet is used for physics. Sound is provided by OpenAL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 0.9.3Resolution: 1920 x 1080 - Mode: Fullscreen - Graphics Effects: Ultimate - Karts: 8 - Scene: Cocoa TempleClang 9.0 BuiltGCC 9.2 Built4080120160200SE +/- 3.26, N = 3SE +/- 1.91, N = 3192.18196.29

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 0.9.3Resolution: 1920 x 1080 - Mode: Fullscreen - Graphics Effects: Ultimate - Karts: 8 - Scene: Candela CityClang 9.0 BuiltGCC 9.2 Built50100150200250SE +/- 3.00, N = 4SE +/- 1.47, N = 3220.15222.14

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 0.07.26Test: SemaphoresClang 9.0 BuiltGCC 9.2 Built700K1400K2100K2800K3500KSE +/- 17095.02, N = 3SE +/- 5354.29, N = 33378876.693378942.761. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Context SwitchingClang 9.0 BuiltGCC 9.2 Built3M6M9M12M15MSE +/- 32348.37, N = 3SE +/- 70573.25, N = 313430897.9112914746.021. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: System V Message PassingClang 9.0 BuiltGCC 9.2 Built4M8M12M16M20MSE +/- 80535.55, N = 3SE +/- 56140.92, N = 316958863.5119840008.521. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Tesseract

Tesseract is a fork of Cube 2 Sauerbraten with numerous graphics and game-play improvements. Tesseract has been in development since 2012 while its first release happened in May of 2014. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 3840 x 2160Clang 9.0 BuiltGCC 9.2 Built80160240320400SE +/- 1.72, N = 3SE +/- 2.93, N = 15380.03391.13

Dbench

Dbench is a benchmark designed by the Samba project as a free alternative to netbench, but dbench contains only file-system calls for testing the disk performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterDbench 4.0Client Count: 1Clang 9.0 Built20406080100SE +/- 0.27, N = 388.901. (CC) gcc options: -lpopt -O2

OpenBenchmarking.orgMB/s, More Is BetterDbench 4.0Client Count: 6Clang 9.0 Built80160240320400SE +/- 21.82, N = 8351.201. (CC) gcc options: -lpopt -O2

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Pixmark Volplosion - Resolution: 3840 x 2160 - Mode: FullscreenClang 9.0 BuiltGCC 9.2 Built6001200180024003000SE +/- 0.33, N = 325492565

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 SizeClang 9.0 BuiltGCC 9.2 Built120240360480600SE +/- 11.68, N = 12SE +/- 4.47, N = 15574.7571.81. (CC) gcc options: -static

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Triangle - Resolution: 3840 x 2160 - Mode: FullscreenClang 9.0 BuiltGCC 9.2 Built90K180K270K360K450KSE +/- 248.53, N = 3SE +/- 300.42, N = 3412804409864

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Pixmark Piano - Resolution: 3840 x 2160 - Mode: FullscreenClang 9.0 BuiltGCC 9.2 Built200400600800100010001005

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: TessMark - Resolution: 3840 x 2160 - Mode: FullscreenClang 9.0 BuiltGCC 9.2 Built3K6K9K12K15KSE +/- 41.93, N = 3SE +/- 15.71, N = 31580915846

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Furmark - Resolution: 3840 x 2160 - Mode: FullscreenClang 9.0 BuiltGCC 9.2 Built13002600390052006500SE +/- 68.61, N = 3SE +/- 53.69, N = 359446000

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Plot3D - Resolution: 3840 x 2160 - Mode: FullscreenClang 9.0 BuiltGCC 9.2 Built20K40K60K80K100KSE +/- 1.00, N = 39579395816

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: GiMark - Resolution: 3840 x 2160 - Mode: FullscreenClang 9.0 BuiltGCC 9.2 Built2K4K6K8K10KSE +/- 16.17, N = 3SE +/- 8.50, N = 378877894

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 SizeClang 9.0 BuiltGCC 9.2 Built130260390520650SE +/- 4.40, N = 3SE +/- 18.56, N = 15579.2549.81. (CC) gcc options: -static

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Size, No Sync/FSyncClang 9.0 BuiltGCC 9.2 Built6001200180024003000SE +/- 18.73, N = 3SE +/- 13.36, N = 32926.52967.51. (CC) gcc options: -static

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 SolverClang 9.0 BuiltGCC 9.2 Built10002000300040005000SE +/- 27.34, N = 3SE +/- 73.82, N = 34873.044877.781. (CC) gcc options: -O3 -mavx2

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 0.22.0Backend: BLASClang 9.0 BuiltGCC 9.2 Built816243240SE +/- 0.74, N = 15SE +/- 0.77, N = 1433.5535.661. (CXX) g++ options: -lpthread

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.22.0Backend: RandomClang 9.0 BuiltGCC 9.2 Built20K40K60K80K100KSE +/- 366.88, N = 3SE +/- 273.38, N = 3100999.0100269.01. (CXX) g++ options: -lpthread

DeepSpeech

Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUClang 9.0 BuiltGCC 9.2 Built1326395265SE +/- 0.52, N = 3SE +/- 0.26, N = 357.8756.05

GROMACS

The Gromacs molecular dynamics package testing on the CPU with the water_GMX50 data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2019.4Water BenchmarkClang 9.0 BuiltGCC 9.2 Built0.73581.47162.20742.94323.679SE +/- 0.003, N = 3SE +/- 0.001, N = 53.2703.2491. (CXX) g++ options: -mavx2 -mfma -std=c++11 -O3 -funroll-all-loops -pthread -lrt -lpthread -lm

Parboil

The Parboil Benchmarks from the IMPACT Research Group at University of Illinois are a set of throughput computing applications for looking at computing architecture and compilers. Parboil test-cases support OpenMP, OpenCL, and CUDA multi-processing environments. However, at this time the test profile is just making use of the OpenMP and OpenCL test workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP LBMClang 9.0 BuiltGCC 9.2 Built1020304050SE +/- 0.00, N = 3SE +/- 0.05, N = 342.7442.651. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPClang 9.0 BuiltGCC 9.2 Built0.21330.42660.63990.85321.0665SE +/- 0.007491, N = 3SE +/- 0.002941, N = 30.9480770.9460991. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP StencilClang 9.0 BuiltGCC 9.2 Built1.09332.18663.27994.37325.4665SE +/- 0.081857, N = 3SE +/- 0.037115, N = 34.7823724.8589921. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI GriddingClang 9.0 BuiltGCC 9.2 Built1326395265SE +/- 0.10, N = 3SE +/- 0.07, N = 358.2758.271. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CClang 9.0 BuiltGCC 9.2 Built16K32K48K64K80KSE +/- 382.78, N = 3SE +/- 197.41, N = 374687.1274188.701. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CClang 9.0 BuiltGCC 9.2 Built2K4K6K8K10KSE +/- 35.46, N = 3SE +/- 27.38, N = 310998.9411008.581. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CClang 9.0 BuiltGCC 9.2 Built6001200180024003000SE +/- 8.17, N = 3SE +/- 7.36, N = 32901.352923.711. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DClang 9.0 BuiltGCC 9.2 Built6001200180024003000SE +/- 4.40, N = 3SE +/- 4.31, N = 32923.072918.691. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CClang 9.0 BuiltGCC 9.2 Built8K16K24K32K40KSE +/- 100.06, N = 3SE +/- 9.63, N = 334986.1635126.471. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DClang 9.0 BuiltGCC 9.2 Built30060090012001500SE +/- 1.48, N = 3SE +/- 6.71, N = 31491.411483.691. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CClang 9.0 BuiltGCC 9.2 Built14K28K42K56K70KSE +/- 96.45, N = 3SE +/- 43.75, N = 366925.3667155.421. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CClang 9.0 BuiltGCC 9.2 Built7K14K21K28K35KSE +/- 58.07, N = 3SE +/- 23.30, N = 330893.3630970.821. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BClang 9.0 BuiltGCC 9.2 Built7K14K21K28K35KSE +/- 123.63, N = 3SE +/- 387.43, N = 334591.6334456.001. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

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 the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMDClang 9.0 BuiltGCC 9.2 Built246810SE +/- 0.015, N = 3SE +/- 0.012, N = 38.0248.0081. (CXX) g++ options: -O2 -lOpenCL

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD SolverClang 9.0 BuiltGCC 9.2 Built246810SE +/- 0.016, N = 3SE +/- 0.042, N = 37.6357.6601. (CXX) g++ options: -O2 -lOpenCL

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP StreamclusterClang 9.0 BuiltGCC 9.2 Built48121620SE +/- 0.03, N = 3SE +/- 0.23, N = 1514.6214.961. (CXX) g++ options: -O2 -lOpenCL

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 2.13b1ATPase Simulation - 327,506 AtomsClang 9.0 BuiltGCC 9.2 Built0.12690.25380.38070.50760.6345SE +/- 0.00059, N = 3SE +/- 0.00053, N = 120.563790.56323

ASKAP

This is a CUDA benchmark of ATNF's ASKAP Benchmark with currently using the tConvolveCuda sub-test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MT - GriddingClang 9.0 BuiltGCC 9.2 Built6001200180024003000SE +/- 6.94, N = 3SE +/- 2.00, N = 32706.582716.031. (CXX) g++ options: -lpthread

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MT - DegriddingClang 9.0 BuiltGCC 9.2 Built8001600240032004000SE +/- 3.13, N = 3SE +/- 1.18, N = 33888.143882.231. (CXX) g++ options: -lpthread

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MPI - GriddingClang 9.0 BuiltGCC 9.2 Built6001200180024003000SE +/- 1.63, N = 3SE +/- 0.77, N = 32733.752734.921. (CXX) g++ options: -lpthread

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MPI - DegriddingClang 9.0 BuiltGCC 9.2 Built8001600240032004000SE +/- 0.60, N = 3SE +/- 0.60, N = 33927.573931.191. (CXX) g++ options: -lpthread

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve OpenMP - GriddingClang 9.0 BuiltGCC 9.2 Built14002800420056007000SE +/- 49.14, N = 3SE +/- 0.00, N = 36290.296339.431. (CXX) g++ options: -lpthread

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve OpenMP - DegriddingClang 9.0 BuiltGCC 9.2 Built10002000300040005000SE +/- 0.00, N = 3SE +/- 0.00, N = 34590.624590.621. (CXX) g++ options: -lpthread

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: 1Clang 9.0 BuiltGCC 9.2 Built48121620SE +/- 0.21, N = 3SE +/- 0.14, N = 1516.5816.64MIN: 6.18 / MAX: 23.17MIN: 6.1 / MAX: 22.77

OpenBenchmarking.orgMicroseconds, Fewer Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 64Clang 9.0 BuiltGCC 9.2 Built48121620SE +/- 0.17, N = 15SE +/- 0.09, N = 316.5516.45MIN: 6.09 / MAX: 22.82MIN: 6.1 / MAX: 22.49

OpenBenchmarking.orgMbits/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 1Clang 9.0 BuiltGCC 9.2 Built2004006008001000SE +/- 4.45, N = 5SE +/- 4.89, N = 51005.281005.77MAX: 1050MAX: 1030

OpenBenchmarking.orgMbits/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 64Clang 9.0 BuiltGCC 9.2 Built40K80K120K160K200KSE +/- 365.04, N = 3SE +/- 619.26, N = 3167530.67157939.11MIN: 163270 / MAX: 171280MIN: 146710 / MAX: 169070

OpenBenchmarking.orgMbits/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 64Clang 9.0 BuiltGCC 9.2 Built30K60K90K120K150KSE +/- 246.51, N = 3SE +/- 99.90, N = 3144142.67147127.78MIN: 135600 / MAX: 150380MIN: 140720 / MAX: 154930

OpenBenchmarking.orgMbits/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 64Clang 9.0 BuiltGCC 9.2 Built8001600240032004000SE +/- 6.50, N = 3SE +/- 6.97, N = 33924.173898.75MIN: 3840 / MAX: 3990MIN: 3800 / MAX: 4040

OpenBenchmarking.orgConnections/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 1Clang 9.0 BuiltGCC 9.2 Built3K6K9K12K15KSE +/- 186.32, N = 5SE +/- 108.68, N = 31458814643

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.7.8.9503Calculating 500M Pi DigitsClang 9.0 BuiltGCC 9.2 Built3691215SE +/- 0.008, N = 3SE +/- 0.006, N = 39.4079.395

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: 64Clang 9.0 BuiltGCC 9.2 Built12K24K36K48K60KSE +/- 7200.68, N = 15SE +/- 3334.56, N = 155438551652

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 SecondClang 9.0 BuiltGCC 9.2 Built300K600K900K1200K1500KSE +/- 3017.38, N = 3SE +/- 2476.46, N = 31388240.881399094.271. (CC) gcc options: -O2 -lrt" -lrt

Stockfish

This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total TimeClang 9.0 BuiltGCC 9.2 Built20M40M60M80M100MSE +/- 1200577.83, N = 3SE +/- 760523.84, N = 396599235964312091. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto

7-Zip Compression

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

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestClang 9.0 BuiltGCC 9.2 Built40K80K120K160K200KSE +/- 783.13, N = 3SE +/- 358.51, N = 31971161965481. (CXX) g++ options: -pipe -lpthread

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 6.0.1Time To CompileClang 9.0 BuiltGCC 9.2 Built306090120150121.35119.23

Zstd Compression

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

OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19Clang 9.0 BuiltGCC 9.2 Built246810SE +/- 0.037, N = 3SE +/- 0.023, N = 38.5258.5351. (CC) gcc options: -O3 -pthread -lz -llzma

Timed GCC Compilation

This test times how long it takes to build the GNU Compiler Collection (GCC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 8.2Time To CompileClang 9.0 BuiltGCC 9.2 Built120240360480600SE +/- 0.60, N = 3SE +/- 0.45, N = 3572.13567.87

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 1080pClang 9.0 BuiltGCC 9.2 Built80160240320400SE +/- 2.69, N = 13SE +/- 4.28, N = 6353.11351.321. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm

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: 1080pClang 9.0 BuiltGCC 9.2 Built246810SE +/- 0.008, N = 3SE +/- 0.026, N = 38.3478.4301. (CXX) g++ options: -fPIE -fPIC -pie

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pClang 9.0 BuiltGCC 9.2 Built1530456075SE +/- 0.19, N = 3SE +/- 0.33, N = 368.5568.351. (CXX) g++ options: -fPIE -fPIC -pie

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 2.81Blend File: Pabellon Barcelona - Compute: CPU-OnlyClang 9.0 BuiltGCC 9.2 Built306090120150SE +/- 0.39, N = 3SE +/- 0.09, N = 3151.36152.49

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 CompileClang 9.0 BuiltGCC 9.2 Built1122334455SE +/- 0.04, N = 3SE +/- 0.12, N = 349.8549.52

LibreOffice

Various benchmarking operations with the LibreOffice open-source office suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterLibreOfficeTest: 20 Documents To PDFClang 9.0 BuiltGCC 9.2 Built246810SE +/- 0.055, N = 21SE +/- 0.047, N = 216.8556.8521. LibreOffice 6.3.3.2 30(Build:2)

BlogBench

BlogBench is designed to replicate the load of a real-world busy file server by stressing the file-system with multiple threads of random reads, writes, and rewrites. The behavior is mimicked of that of a blog by creating blogs with content and pictures, modifying blog posts, adding comments to these blogs, and then reading the content of the blogs. All of these blogs generated are created locally with fake content and pictures. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: ReadClang 9.0 BuiltGCC 9.2 Built300K600K900K1200K1500KSE +/- 23808.12, N = 3SE +/- 15836.11, N = 9154161414771441. (CC) gcc options: -O2 -pthread

OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: WriteClang 9.0 BuiltGCC 9.2 Built12K24K36K48K60KSE +/- 2302.33, N = 3SE +/- 3053.28, N = 354915532811. (CC) gcc options: -O2 -pthread

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 ServingClang 9.0 BuiltGCC 9.2 Built9K18K27K36K45KSE +/- 97.23, N = 3SE +/- 637.10, N = 342955.8842916.501. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native

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 ServingClang 9.0 BuiltGCC 9.2 Built7K14K21K28K35KSE +/- 51.61, N = 3SE +/- 78.79, N = 333679.0934134.451. (CC) gcc options: -shared -fPIC -O2 -pthread

Memtier_benchmark

Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool. This current test profile currently just stresses the Redis protocol and basic options exposed wotj a 1:1 Set/Get ratio, 30 pipeline, 100 clients per thread, and thread count equal to the number of CPU cores/threads present. Patches to extend the test are welcome as always. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemtier_benchmark 1.2.17Protocol: RedisClang 9.0 BuiltGCC 9.2 Built700K1400K2100K2800K3500KSE +/- 103739.94, N = 12SE +/- 87137.03, N = 153058231.033148364.331. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre

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: GETClang 9.0 BuiltGCC 9.2 Built500K1000K1500K2000K2500KSE +/- 58575.48, N = 15SE +/- 51991.94, N = 152473763.422463546.221. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SETClang 9.0 BuiltGCC 9.2 Built400K800K1200K1600K2000KSE +/- 29786.87, N = 15SE +/- 27467.28, N = 41961726.781854760.031. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

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: 1Clang 9.0 BuiltGCC 9.2 Built48121620SE +/- 0.01, N = 3SE +/- 0.02, N = 314.2114.331. (CC) gcc options: -O2 -lz -lm -ldl -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.30.1Threads / Copies: 8Clang 9.0 BuiltGCC 9.2 Built918273645SE +/- 0.42, N = 3SE +/- 0.66, N = 340.8940.391. (CC) gcc options: -O2 -lz -lm -ldl -lpthread

Facebook RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random FillClang 9.0 BuiltGCC 9.2 Built200K400K600K800K1000KSE +/- 2251.84, N = 3SE +/- 2820.50, N = 3110867911424371. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random ReadClang 9.0 BuiltGCC 9.2 Built40M80M120M160M200MSE +/- 1710859.72, N = 3SE +/- 416751.10, N = 31812408101777703881. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Sequential FillClang 9.0 BuiltGCC 9.2 Built300K600K900K1200K1500KSE +/- 3104.32, N = 3SE +/- 700.57, N = 3117388312110421. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Fill SyncClang 9.0 BuiltGCC 9.2 Built7K14K21K28K35KSE +/- 132.59, N = 3SE +/- 64.89, N = 332747325461. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Read While WritingClang 9.0 BuiltGCC 9.2 Built1.3M2.6M3.9M5.2M6.5MSE +/- 47939.98, N = 3SE +/- 28660.86, N = 3610899260267431. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

SQLite Speedtest

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

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Clang 9.0 BuiltGCC 9.2 Built1326395265SE +/- 0.13, N = 3SE +/- 0.09, N = 358.3058.051. (CC) gcc options: -O2 -ldl -lz -lpthread

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 OnlyClang 9.0 BuiltGCC 9.2 Built160K320K480K640K800KSE +/- 2243.06, N = 3SE +/- 2821.88, N = 3751720.66745068.681. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read WriteClang 9.0 BuiltGCC 9.2 Built3K6K9K12K15KSE +/- 1359.03, N = 15SE +/- 220.76, N = 1513491.8812575.121. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Heavy Contention - Mode: Read OnlyClang 9.0 BuiltGCC 9.2 Built160K320K480K640K800KSE +/- 2492.99, N = 3SE +/- 4310.08, N = 3765627.63758184.381. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Heavy Contention - Mode: Read WriteClang 9.0 BuiltGCC 9.2 Built3K6K9K12K15KSE +/- 412.77, N = 15SE +/- 202.28, N = 312792.7111910.001. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

ebizzy

This is a test of ebizzy, a program to generate workloads resembling web server workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.3Clang 9.0 BuiltGCC 9.2 Built600K1200K1800K2400K3000KSE +/- 22371.96, N = 3SE +/- 20852.68, N = 15257166424850481. (CC) gcc options: -pthread -lpthread -O3 -march=native

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Many Spheres - Resolution: 3840 x 2160Clang 9.0 BuiltGCC 9.2 Built1020304050SE +/- 0.41, N = 3SE +/- 0.32, N = 344.0143.92

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.4.1Test: Many Spheres - Resolution: 3840 x 2160Clang 9.0 BuiltGCC 9.2 Built9001800270036004500SE +/- 41.24, N = 3SE +/- 32.69, N = 34412.364403.15

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Wavelet Volume - Resolution: 3840 x 2160Clang 9.0 BuiltGCC 9.2 Built306090120150SE +/- 0.87, N = 3SE +/- 5.41, N = 12117.59123.08

OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.4.1Test: Wavelet Volume - Resolution: 3840 x 2160Clang 9.0 BuiltGCC 9.2 Built400800120016002000SE +/- 13.89, N = 3SE +/- 86.53, N = 121881.381969.29

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Wavelet Contour - Resolution: 3840 x 2160Clang 9.0 BuiltGCC 9.2 Built4080120160200SE +/- 1.32, N = 3SE +/- 3.11, N = 3168.14180.87

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.4.1Test: Wavelet Contour - Resolution: 3840 x 2160Clang 9.0 BuiltGCC 9.2 Built400800120016002000SE +/- 13.76, N = 3SE +/- 32.42, N = 31752.241884.83

112 Results Shown

Selenium:
  ARES-6 - Firefox
  WebXPRT - Firefox
  Basemark - Firefox
  CanvasMark - Firefox
  PSPDFKit WASM - Firefox
Compile Bench:
  Compile
  Initial Create
  Read Compiled Tree
GeeXLab
ctx_clock
GeeXLab
Hackbench
GeeXLab
Stress-NG:
  Forking
  Socket Activity
GeeXLab:
  3840 x 2160 - GL2 Cell Shading
  3840 x 2160 - GL2 Tunnel Beauty
  3840 x 2160 - GL2 AntTweakBar
  3840 x 2160 - GL3 Vertex Pool
SuperTuxKart:
  1920 x 1080 - Fullscreen - Ultimate - 8 - Cocoa Temple
  1920 x 1080 - Fullscreen - Ultimate - 8 - Candela City
Stress-NG:
  Semaphores
  Context Switching
  System V Message Passing
Tesseract
Dbench:
  1
  6
GpuTest
FS-Mark
GpuTest:
  Triangle - 3840 x 2160 - Fullscreen
  Pixmark Piano - 3840 x 2160 - Fullscreen
  TessMark - 3840 x 2160 - Fullscreen
  Furmark - 3840 x 2160 - Fullscreen
  Plot3D - 3840 x 2160 - Fullscreen
  GiMark - 3840 x 2160 - Fullscreen
FS-Mark:
  4000 Files, 32 Sub Dirs, 1MB Size
  1000 Files, 1MB Size, No Sync/FSync
Himeno Benchmark
LeelaChessZero:
  BLAS
  Rand
DeepSpeech
GROMACS
Parboil:
  OpenMP LBM
  OpenMP CUTCP
  OpenMP Stencil
  OpenMP MRI Gridding
NAS Parallel Benchmarks:
  BT.C
  CG.C
  EP.C
  EP.D
  FT.C
  IS.D
  LU.C
  MG.C
  SP.B
Rodinia:
  OpenMP LavaMD
  OpenMP CFD Solver
  OpenMP Streamcluster
NAMD
ASKAP:
  tConvolve MT - Gridding
  tConvolve MT - Degridding
  tConvolve MPI - Gridding
  tConvolve MPI - Degridding
  tConvolve OpenMP - Gridding
  tConvolve OpenMP - Degridding
Ethr:
  TCP - Latency - 1
  TCP - Latency - 64
  HTTP - Bandwidth - 1
  TCP - Bandwidth - 64
  UDP - Bandwidth - 64
  HTTP - Bandwidth - 64
  TCP - Connections/s - 1
Y-Cruncher
Ethr
Coremark
Stockfish
7-Zip Compression
Timed LLVM Compilation
Zstd Compression
Timed GCC Compilation
SVT-VP9
SVT-AV1:
  Enc Mode 4 - 1080p
  Enc Mode 8 - 1080p
Blender
Build2
LibreOffice
BlogBench:
  Read
  Write
NGINX Benchmark
Apache Benchmark
Memtier_benchmark
Redis:
  GET
  SET
SQLite:
  1
  8
Facebook RocksDB:
  Rand Fill
  Rand Read
  Seq Fill
  Rand Fill Sync
  Read While Writing
SQLite Speedtest
PostgreSQL pgbench:
  Buffer Test - Normal Load - Read Only
  Buffer Test - Normal Load - Read Write
  Buffer Test - Heavy Contention - Read Only
  Buffer Test - Heavy Contention - Read Write
ebizzy
ParaView:
  Many Spheres - 3840 x 2160:
    Frames / Sec
    MiPolys / Sec
  Wavelet Volume - 3840 x 2160:
    Frames / Sec
    MiVoxels / Sec
  Wavelet Contour - 3840 x 2160:
    Frames / Sec
    MiPolys / Sec