Linux 5.11 Ryzen 9 5950X

Benchmarks 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 2012195-HA-LINUX511R08
Jump To Table - Results

View

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

Limit displaying results to tests within:

Timed Code Compilation 4 Tests
C/C++ Compiler Tests 13 Tests
CPU Massive 16 Tests
Creator Workloads 6 Tests
Database Test Suite 6 Tests
Disk Test Suite 2 Tests
Encoding 2 Tests
Fortran Tests 2 Tests
Game Development 2 Tests
HPC - High Performance Computing 11 Tests
Common Kernel Benchmarks 5 Tests
Machine Learning 6 Tests
Molecular Dynamics 3 Tests
MPI Benchmarks 3 Tests
Multi-Core 16 Tests
NVIDIA GPU Compute 2 Tests
Intel oneAPI 3 Tests
OpenMPI Tests 3 Tests
Programmer / Developer System Benchmarks 9 Tests
Python 3 Tests
Scientific Computing 4 Tests
Server 8 Tests
Server CPU Tests 11 Tests
Single-Threaded 2 Tests
Video Encoding 2 Tests
Common Workstation Benchmarks 2 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 5.10.1
December 18 2020
  10 Hours, 34 Minutes
Linux 5.11 18Dec
December 18 2020
  7 Hours, 14 Minutes
Invert Hiding All Results Option
  8 Hours, 54 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 5.10.1

Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3003 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 2000GB Corsair Force MP600 + 2000GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 20.04, Kernel: 5.10.1-051001-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 21.0.0-devel (git-e6a6620 2020-12-17 focal-oibaf-ppa) (LLVM 11.0.0), Vulkan: 1.2.145, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160

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=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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 / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa201009
Java Notes: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.04)
Python Notes: Python 2.7.18 + Python 3.8.5
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 5.11 18Dec

OS: Ubuntu 20.04, Kernel: 5.10.0-051000daily20201218-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 21.0.0-devel (git-e6a6620 2020-12-17 focal-oibaf-ppa) (LLVM 11.0.0), Vulkan: 1.2.145, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160

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=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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 / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa201009
Python Notes: Python 2.7.18 + Python 3.8.5
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 5.11 Ryzen 9 5950XOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3003 BIOS)AMD Starship/Matisse16GB2000GB Corsair Force MP600 + 2000GBAMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz)AMD Navi 10 HDMI AudioASUS MG28URealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 20.045.10.1-051001-generic (x86_64)5.10.0-051000daily20201218-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.6 Mesa 21.0.0-devel (git-e6a6620 2020-12-17 focal-oibaf-ppa) (LLVM 11.0.0)1.2.145GCC 9.3.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelsDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionLinux 5.11 Ryzen 9 5950X BenchmarksSystem Logs- --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=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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 / Block Size: 4096- Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa201009- Linux 5.10.1: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.04)- Python 2.7.18 + Python 3.8.5- 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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Linux 5.10.1 vs. Linux 5.11 18Dec ComparisonPhoronix Test SuiteBaseline+73.9%+73.9%+147.8%+147.8%+221.7%+221.7%295.4%295.1%73.7%73.7%63.9%63.9%27.7%17.6%15.1%11.1%11%7.7%7.4%7%6.2%3.6%3.4%3.4%3.2%3.2%3.1%2.9%2.9%2.7%2.6%2.6%2.6%2.5%2.3%Rand Write - IO_uring - No - Yes - 4KBRand Write - IO_uring - No - Yes - 4KB100 - 50 - Read Write - Average Latency74.6%Rand Write - IO_uring - No - No - 4KBRand Write - IO_uring - No - No - 4KB100 - 50 - Read Write68.8%Seq Write - IO_uring - No - Yes - 4KBSeq Write - IO_uring - No - Yes - 4KBS.V.M.PKostyaSENDFILERand Write - IO_uring - Yes - No - 4KBRand Write - IO_uring - Yes - No - 4KBSeq Read - IO_uring - No - No - 4KB9.9%Seq Read - IO_uring - No - No - 4KB9.8%PartialTweets1 - 1 - Read Only - Average Latency1 - 1 - Read Only100 - 1 - Read Write - Average Latency6.3%DistinctUserIDSeq Write - IO_uring - Yes - Yes - 4KB5.5%100 - 1 - Read Write5.5%Seq Write - IO_uring - Yes - Yes - 4KB5.5%Seq Write - IO_uring - No - No - 4KB4.8%Seq Write - IO_uring - No - No - 4KB4.8%Semaphores3.9%Initial Create3.7%100 - 1 - Read OnlySeq Read - IO_uring - Yes - No - 4KBSeq Read - IO_uring - Yes - No - 4KBForking3.4%NUMAscikit_ica100 - 1 - Read Only - Average LatencySeq Read - IO_uring - Yes - Yes - 4KBSeq Read - IO_uring - Yes - Yes - 4KBCPU-v2-v2 - mobilenet-v2Rand Write - IO_uring - Yes - Yes - 4KBRand Read - IO_uring - No - Yes - 4KBRand Read - IO_uring - No - Yes - 4KBRand Write - IO_uring - Yes - Yes - 4KBContext Switching2.3%CPU - googlenetSeq Read - IO_uring - No - Yes - 4KB2.2%Seq Read - IO_uring - No - Yes - 4KB2.2%M.S.A - LSU RNA2%Flexible IO TesterFlexible IO TesterPostgreSQL pgbenchFlexible IO TesterFlexible IO TesterPostgreSQL pgbenchFlexible IO TesterFlexible IO TesterStress-NGsimdjsonStress-NGFlexible IO TesterFlexible IO TesterFlexible IO TesterFlexible IO TestersimdjsonPostgreSQL pgbenchPostgreSQL pgbenchPostgreSQL pgbenchsimdjsonFlexible IO TesterPostgreSQL pgbenchFlexible IO TesterFlexible IO TesterFlexible IO TesterStress-NGCompile BenchPostgreSQL pgbenchFlexible IO TesterFlexible IO TesterStress-NGStress-NGMlpack BenchmarkPostgreSQL pgbenchFlexible IO TesterFlexible IO TesterNCNNFlexible IO TesterFlexible IO TesterFlexible IO TesterFlexible IO TesterStress-NGNCNNFlexible IO TesterFlexible IO TesterTimed MAFFT AlignmentLinux 5.10.1Linux 5.11 18Dec

Linux 5.11 Ryzen 9 5950Xstress-ng: System V Message Passingstress-ng: SENDFILEfio: Seq Read - IO_uring - No - No - 4KB - Default Test Directoryfio: Seq Read - IO_uring - No - No - 4KB - Default Test Directoryfio: Seq Write - IO_uring - Yes - Yes - 4KB - Default Test Directoryfio: Seq Write - IO_uring - Yes - Yes - 4KB - Default Test Directoryfio: Seq Write - IO_uring - No - No - 4KB - Default Test Directoryfio: Seq Write - IO_uring - No - No - 4KB - Default Test Directorystress-ng: Semaphorescompilebench: Initial Createpgbench: 100 - 1 - Read Onlyfio: Seq Read - IO_uring - Yes - No - 4KB - Default Test Directoryfio: Seq Read - IO_uring - Yes - No - 4KB - Default Test Directorystress-ng: Forkingstress-ng: NUMAmlpack: scikit_icapgbench: 100 - 1 - Read Only - Average Latencyfio: Seq Read - IO_uring - Yes - Yes - 4KB - Default Test Directoryfio: Seq Read - IO_uring - Yes - Yes - 4KB - Default Test Directoryncnn: CPU-v2-v2 - mobilenet-v2fio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directorystress-ng: Context Switchingncnn: CPU - googlenetfio: Seq Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Seq Read - IO_uring - No - Yes - 4KB - Default Test Directorymafft: Multiple Sequence Alignment - LSU RNAsimdjson: LargeRandcouchdb: 100 - 1000 - 24ncnn: CPU - blazefacencnn: CPU - yolov4-tinybuild-llvm: Time To Compileinfluxdb: 1024 - 10000 - 2,5000,1 - 10000namd: ATPase Simulation - 327,506 Atomsopenvino: Person Detection 0106 FP32 - CPUpybench: Total For Average Test Timesncnn: CPU - mobilenetopenvino: Person Detection 0106 FP32 - CPUncnn: CPU-v3-v3 - mobilenet-v3stress-ng: Glibc C String Functionsinfluxdb: 64 - 10000 - 2,5000,1 - 10000stress-ng: Mallocpgbench: 1 - 1 - Read Writestress-ng: CPU Cachepgbench: 1 - 50 - Read Writencnn: CPU - resnet50pgbench: 1 - 50 - Read Write - Average Latencypgbench: 100 - 50 - Read Onlypgbench: 1 - 1 - Read Write - Average Latencyncnn: CPU - squeezenet_ssdpgbench: 1 - 50 - Read Onlynumpy: x265: Bosphorus 1080popenvkl: vklBenchmarkStructuredVolumecompilebench: Compilepgbench: 100 - 50 - Read Only - Average Latencyleveldb: Seq Fillmlpack: scikit_qdaleveldb: Rand Fillleveldb: Rand Fillstress-ng: Glibc Qsort Data Sortingbuild-gdb: Time To Compilebrl-cad: VGR Performance Metrictnn: CPU - SqueezeNet v1.1leveldb: Seq Fillsqlite-speedtest: Timed Time - Size 1,000ncnn: CPU - efficientnet-b0openvino: Person Detection 0106 FP16 - CPUbuild2: Time To Compilejohn-the-ripper: MD5keydb: ncnn: CPU - regnety_400mstockfish: Total Timencnn: CPU - vgg16tensorflow-lite: SqueezeNetoidn: Memorialstress-ng: MMAPgromacs: Water Benchmarkinfluxdb: 4 - 10000 - 2,5000,1 - 10000fio: Rand Read - IO_uring - Yes - No - 4KB - Default Test Directorystress-ng: Atomictensorflow-lite: NASNet Mobilenode-web-tooling: fio: Rand Read - IO_uring - Yes - No - 4KB - Default Test Directorytensorflow-lite: Mobilenet Floatstress-ng: Memory Copyingopenvino: Age Gender Recognition Retail 0013 FP16 - CPUsvt-av1: Enc Mode 8 - 1080pncnn: CPU - resnet18tensorflow-lite: Mobilenet Quantx265: Bosphorus 4Kopenvkl: vklBenchmarkmlpack: scikit_linearridgeregressionlammps: Rhodopsin Proteintnn: CPU - MobileNet v2tensorflow-lite: Inception ResNet V2fio: Seq Write - IO_uring - Yes - No - 4KB - Default Test Directoryblosc: blosclzopenvino: Person Detection 0106 FP16 - CPUfio: Seq Write - IO_uring - Yes - No - 4KB - Default Test Directoryopenvino: Face Detection 0106 FP32 - CPUleveldb: Overwritestress-ng: Cryptostress-ng: Vector Mathstress-ng: MEMFDfio: Rand Read - IO_uring - No - No - 4KB - Default Test Directorytensorflow-lite: Inception V4fio: Rand Read - IO_uring - No - No - 4KB - Default Test Directoryleveldb: Overwriteleveldb: Seek Randopenvino: Face Detection 0106 FP32 - CPUopenvino: Face Detection 0106 FP16 - CPUncnn: CPU - mnasnetmlpack: scikit_svmbuild-linux-kernel: Time To Compileleveldb: Rand Readleveldb: Fill Syncstress-ng: Socket Activityfio: Rand Read - IO_uring - Yes - Yes - 4KB - Default Test Directorysvt-av1: Enc Mode 4 - 1080phpcg: openvino: Age Gender Recognition Retail 0013 FP32 - CPUleveldb: Hot Readjohn-the-ripper: Blowfishcompilebench: Read Compiled Treestress-ng: Matrix Mathopenvino: Face Detection 0106 FP16 - CPUstress-ng: CPU Stressleveldb: Rand Deleteopenvino: Age Gender Recognition Retail 0013 FP32 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUctx-clock: Context Switch Timencnn: CPU - alexnetncnn: CPU - shufflenet-v2pgbench: 1 - 50 - Read Only - Average Latencyfio: Rand Read - IO_uring - Yes - Yes - 4KB - Default Test Directoryleveldb: Fill Syncpgbench: 100 - 50 - Read Write - Average Latencypgbench: 100 - 50 - Read Writepgbench: 100 - 1 - Read Write - Average Latencypgbench: 100 - 1 - Read Writepgbench: 1 - 1 - Read Only - Average Latencypgbench: 1 - 1 - Read Onlysimdjson: DistinctUserIDsimdjson: PartialTweetssimdjson: Kostyafio: Seq Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Seq Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - Yes - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - Yes - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - Yes - No - 4KB - Default Test Directoryfio: Rand Write - IO_uring - Yes - No - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - No - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - No - 4KB - Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec15135767.53354797.873435331342110428233381933331992410026.03773.2730674528333206595063.90427.0251.920.03354200021174.5517714533338768343.9113.4812723255337.2790.5971.1841.8621.76361.1092216419.31.088703153.7671712.482.504.242533146.812197660.1251404923.52129036.00150725.4433.1954639570.77514.70634683531.1683.5587177472.8378382855.430.10832.761.7933.1106.774257.3579.738261410214.017108.38742.9375.493107.2572.0272199667805277.9518.094307986758.0995305.614.60506.001.3131999403.71596194151.5310495016.1340866762929.01456.9413759.2650.42314.6968289.327.66288.692.2212.332229.9641219143101413991.32.532596002094.4533.14818.36172105.661418.7446300013542371809107.04818.8353.793.824.0716.3945.58013.7391928.56011815.774060006.0784.2270213482.0413.609379074508.3075646.902072.0711798.24102.0260.580.5713611.304.470.07815871.81.950256550.84411850.029347510.970.910.685009581957254933995231867906208000813469247183319331994.01408513.233126671222104626766778166730532319076.40745.7431767546556213591964.25440.7250.330.03255766721784.4318174650008568472.1313.1812453186677.4220.6072.3621.8322.10366.6552248367.91.074333113.8270812.632.534.192504693.062222530.6254222859.97130436.39152325.7132.8474688000.76714.55641163536.5382.7488014355.2792792882.590.10732.462.3632.8107.680255.2279.093263535212.336109.23142.6105.453084.8272.5312215000799825.0818.214336404157.7194780.714.52503.281.3202009772.41588195117.9610443216.2140666762622.91464.0513826.3150.66814.6267966.627.53290.002.2312.278228.9591214260101014046.72.542586672101.8233.04832.91172622.661422.9346166713504001804107.34118.8853.783.834.0816.4345.68513.7691924.66911835.884066676.0864.2324113499.0013.592379484512.1375670.942072.4011799.29102.0290.580.5713611.304.470.07815871.83.404151970.89711230.027371751.030.980.8082100032072613331021257667100682233332128150003184OpenBenchmarking.org

Stress-NG

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

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: System V Message PassingLinux 5.10.1Linux 5.11 18Dec4M8M12M16M20MSE +/- 14913.24, N = 3SE +/- 147807.54, N = 315135767.5319331994.011. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: System V Message PassingLinux 5.10.1Linux 5.11 18Dec3M6M9M12M15MMin: 15114789.02 / Avg: 15135767.53 / Max: 15164618.17Min: 19050473.35 / Avg: 19331994.01 / Max: 19550861.951. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SENDFILELinux 5.10.1Linux 5.11 18Dec90K180K270K360K450KSE +/- 394.84, N = 3SE +/- 244.43, N = 3354797.87408513.231. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SENDFILELinux 5.10.1Linux 5.11 18Dec70K140K210K280K350KMin: 354344.73 / Avg: 354797.87 / Max: 355584.52Min: 408073.7 / Avg: 408513.23 / Max: 408918.331. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec70K140K210K280K350KSE +/- 4054.24, N = 15SE +/- 3756.48, N = 33435333126671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec60K120K180K240K300KMin: 315000 / Avg: 343533.33 / Max: 368000Min: 306000 / Avg: 312666.67 / Max: 3190001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec30060090012001500SE +/- 15.95, N = 15SE +/- 14.45, N = 3134212221. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec2004006008001000Min: 1231 / Avg: 1342.13 / Max: 1437Min: 1196 / Avg: 1221.67 / Max: 12461. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec2004006008001000SE +/- 9.24, N = 3SE +/- 0.67, N = 3110410461. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec2004006008001000Min: 1088 / Avg: 1103.67 / Max: 1120Min: 1045 / Avg: 1045.67 / Max: 10471. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec60K120K180K240K300KSE +/- 2603.42, N = 3SE +/- 333.33, N = 32823332676671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec50K100K150K200K250KMin: 278000 / Avg: 282333.33 / Max: 287000Min: 267000 / Avg: 267666.67 / Max: 2680001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec200K400K600K800K1000KSE +/- 11893.04, N = 3SE +/- 4807.40, N = 38193337816671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec140K280K420K560K700KMin: 796000 / Avg: 819333.33 / Max: 835000Min: 775000 / Avg: 781666.67 / Max: 7910001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec7001400210028003500SE +/- 46.59, N = 3SE +/- 17.80, N = 3319930531. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec6001200180024003000Min: 3108 / Avg: 3199.33 / Max: 3261Min: 3029 / Avg: 3053.33 / Max: 30881. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -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: SemaphoresLinux 5.10.1Linux 5.11 18Dec500K1000K1500K2000K2500KSE +/- 1518.78, N = 3SE +/- 33704.45, N = 32410026.032319076.401. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SemaphoresLinux 5.10.1Linux 5.11 18Dec400K800K1200K1600K2000KMin: 2407422.05 / Avg: 2410026.03 / Max: 2412682.46Min: 2252365.27 / Avg: 2319076.4 / Max: 2360809.831. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

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: Initial CreateLinux 5.10.1Linux 5.11 18Dec170340510680850SE +/- 11.93, N = 3SE +/- 15.56, N = 3773.27745.74
OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial CreateLinux 5.10.1Linux 5.11 18Dec140280420560700Min: 750.27 / Avg: 773.27 / Max: 790.28Min: 715.96 / Avg: 745.74 / Max: 768.44

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 1 - Mode: Read OnlyLinux 5.10.1Linux 5.11 18Dec7K14K21K28K35KSE +/- 419.20, N = 4SE +/- 258.23, N = 330674317671. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 1 - Mode: Read OnlyLinux 5.10.1Linux 5.11 18Dec6K12K18K24K30KMin: 29686.49 / Avg: 30673.6 / Max: 31717.84Min: 31450.09 / Avg: 31767.5 / Max: 32279.031. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec120K240K360K480K600KSE +/- 5811.87, N = 3SE +/- 5145.42, N = 95283335465561. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec90K180K270K360K450KMin: 519000 / Avg: 528333.33 / Max: 539000Min: 521000 / Avg: 546555.56 / Max: 5640001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec5001000150020002500SE +/- 22.94, N = 3SE +/- 20.01, N = 9206521351. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec400800120016002000Min: 2028 / Avg: 2065 / Max: 2107Min: 2037 / Avg: 2135 / Max: 22051. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -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: ForkingLinux 5.10.1Linux 5.11 18Dec20K40K60K80K100KSE +/- 1088.48, N = 3SE +/- 1279.57, N = 495063.9091964.251. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: ForkingLinux 5.10.1Linux 5.11 18Dec16K32K48K64K80KMin: 92899.22 / Avg: 95063.9 / Max: 96346.18Min: 90142.49 / Avg: 91964.25 / Max: 95636.31. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: NUMALinux 5.10.1Linux 5.11 18Dec100200300400500SE +/- 0.70, N = 3SE +/- 3.16, N = 3427.02440.721. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: NUMALinux 5.10.1Linux 5.11 18Dec80160240320400Min: 426.1 / Avg: 427.02 / Max: 428.4Min: 435.39 / Avg: 440.72 / Max: 446.321. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaLinux 5.10.1Linux 5.11 18Dec1224364860SE +/- 0.62, N = 3SE +/- 0.71, N = 351.9250.33
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaLinux 5.10.1Linux 5.11 18Dec1020304050Min: 51.26 / Avg: 51.92 / Max: 53.15Min: 49.6 / Avg: 50.33 / Max: 51.74

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 1 - Mode: Read Only - Average LatencyLinux 5.10.1Linux 5.11 18Dec0.00740.01480.02220.02960.037SE +/- 0.000, N = 4SE +/- 0.000, N = 30.0330.0321. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 1 - Mode: Read Only - Average LatencyLinux 5.10.1Linux 5.11 18Dec12345Min: 0.03 / Avg: 0.03 / Max: 0.03Min: 0.03 / Avg: 0.03 / Max: 0.031. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec120K240K360K480K600KSE +/- 1527.53, N = 3SE +/- 2905.93, N = 35420005576671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec100K200K300K400K500KMin: 540000 / Avg: 542000 / Max: 545000Min: 553000 / Avg: 557666.67 / Max: 5630001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec5001000150020002500SE +/- 5.36, N = 3SE +/- 11.36, N = 3211721781. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec400800120016002000Min: 2111 / Avg: 2117.33 / Max: 2128Min: 2160 / Avg: 2178 / Max: 21991. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v2Linux 5.10.1Linux 5.11 18Dec1.02382.04763.07144.09525.119SE +/- 0.05, N = 15SE +/- 0.02, N = 54.554.43MIN: 4.25 / MAX: 6.32MIN: 4.24 / MAX: 4.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v2Linux 5.10.1Linux 5.11 18Dec246810Min: 4.4 / Avg: 4.55 / Max: 5.1Min: 4.39 / Avg: 4.43 / Max: 4.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec400800120016002000SE +/- 26.43, N = 3SE +/- 9.94, N = 3177118171. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec30060090012001500Min: 1718 / Avg: 1770.67 / Max: 1801Min: 1805 / Avg: 1817.33 / Max: 18371. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec100K200K300K400K500KSE +/- 6691.62, N = 3SE +/- 2516.61, N = 34533334650001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec80K160K240K320K400KMin: 440000 / Avg: 453333.33 / Max: 461000Min: 462000 / Avg: 465000 / Max: 4700001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -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: Context SwitchingLinux 5.10.1Linux 5.11 18Dec2M4M6M8M10MSE +/- 115453.96, N = 3SE +/- 50631.93, N = 38768343.918568472.131. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Context SwitchingLinux 5.10.1Linux 5.11 18Dec1.5M3M4.5M6M7.5MMin: 8537612.57 / Avg: 8768343.91 / Max: 8891528.65Min: 8470803.05 / Avg: 8568472.13 / Max: 8640465.71. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenetLinux 5.10.1Linux 5.11 18Dec3691215SE +/- 0.20, N = 15SE +/- 0.35, N = 513.4813.18MIN: 12.49 / MAX: 51.88MIN: 12.27 / MAX: 15.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenetLinux 5.10.1Linux 5.11 18Dec48121620Min: 12.85 / Avg: 13.48 / Max: 15.05Min: 12.57 / Avg: 13.18 / Max: 14.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec30060090012001500SE +/- 11.88, N = 15SE +/- 17.46, N = 3127212451. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec2004006008001000Min: 1160 / Avg: 1271.6 / Max: 1322Min: 1219 / Avg: 1244.67 / Max: 12781. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec70K140K210K280K350KSE +/- 3017.20, N = 15SE +/- 4409.59, N = 33255333186671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec60K120K180K240K300KMin: 297000 / Avg: 325533.33 / Max: 338000Min: 312000 / Avg: 318666.67 / Max: 3270001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Timed MAFFT Alignment

This test performs an alignment of 100 pyruvate decarboxylase sequences. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNALinux 5.10.1Linux 5.11 18Dec246810SE +/- 0.120, N = 3SE +/- 0.058, N = 37.2797.4221. (CC) gcc options: -std=c99 -O3 -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNALinux 5.10.1Linux 5.11 18Dec3691215Min: 7.09 / Avg: 7.28 / Max: 7.5Min: 7.36 / Avg: 7.42 / Max: 7.541. (CC) gcc options: -std=c99 -O3 -lm -lpthread

simdjson

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

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: LargeRandomLinux 5.10.1Linux 5.11 18Dec0.1350.270.4050.540.675SE +/- 0.01, N = 3SE +/- 0.01, N = 30.590.601. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: LargeRandomLinux 5.10.1Linux 5.11 18Dec246810Min: 0.58 / Avg: 0.59 / Max: 0.6Min: 0.59 / Avg: 0.6 / Max: 0.611. (CXX) g++ options: -O3 -pthread

Apache CouchDB

This is a bulk insertion benchmark of Apache CouchDB. CouchDB is a document-oriented NoSQL database implemented in Erlang. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.1.1Bulk Size: 100 - Inserts: 1000 - Rounds: 24Linux 5.10.1Linux 5.11 18Dec1632486480SE +/- 0.73, N = 8SE +/- 0.16, N = 371.1872.361. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lerl_interface -lei -fPIC -MMD
OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.1.1Bulk Size: 100 - Inserts: 1000 - Rounds: 24Linux 5.10.1Linux 5.11 18Dec1428425670Min: 68.78 / Avg: 71.18 / Max: 74.95Min: 72.1 / Avg: 72.36 / Max: 72.661. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lerl_interface -lei -fPIC -MMD

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazefaceLinux 5.10.1Linux 5.11 18Dec0.41850.8371.25551.6742.0925SE +/- 0.02, N = 15SE +/- 0.02, N = 51.861.83MIN: 1.76 / MAX: 3.8MIN: 1.78 / MAX: 1.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazefaceLinux 5.10.1Linux 5.11 18Dec246810Min: 1.78 / Avg: 1.86 / Max: 2Min: 1.79 / Avg: 1.83 / Max: 1.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tinyLinux 5.10.1Linux 5.11 18Dec510152025SE +/- 0.24, N = 15SE +/- 0.52, N = 521.7622.10MIN: 20.6 / MAX: 31.18MIN: 20.41 / MAX: 24.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tinyLinux 5.10.1Linux 5.11 18Dec510152025Min: 20.83 / Avg: 21.76 / Max: 23.13Min: 20.62 / Avg: 22.1 / Max: 23.21. (CXX) g++ options: -O3 -rdynamic -lgomp -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 10.0Time To CompileLinux 5.10.1Linux 5.11 18Dec80160240320400SE +/- 4.30, N = 3SE +/- 0.74, N = 3361.11366.66
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To CompileLinux 5.10.1Linux 5.11 18Dec70140210280350Min: 356 / Avg: 361.11 / Max: 369.66Min: 365.32 / Avg: 366.65 / Max: 367.86

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Linux 5.10.1Linux 5.11 18Dec500K1000K1500K2000K2500KSE +/- 4243.37, N = 3SE +/- 7136.81, N = 32216419.32248367.9
OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Linux 5.10.1Linux 5.11 18Dec400K800K1200K1600K2000KMin: 2208870.4 / Avg: 2216419.3 / Max: 2223552.2Min: 2237797.4 / Avg: 2248367.9 / Max: 2261959.8

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 AtomsLinux 5.10.1Linux 5.11 18Dec0.2450.490.7350.981.225SE +/- 0.00499, N = 3SE +/- 0.00161, N = 31.088701.07433
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsLinux 5.10.1Linux 5.11 18Dec246810Min: 1.08 / Avg: 1.09 / Max: 1.1Min: 1.07 / Avg: 1.07 / Max: 1.08

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP32 - Device: CPULinux 5.10.1Linux 5.11 18Dec7001400210028003500SE +/- 32.67, N = 3SE +/- 20.64, N = 33153.763113.821. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP32 - Device: CPULinux 5.10.1Linux 5.11 18Dec5001000150020002500Min: 3113.67 / Avg: 3153.76 / Max: 3218.48Min: 3087.89 / Avg: 3113.82 / Max: 3154.61. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread

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 TimesLinux 5.10.1Linux 5.11 18Dec150300450600750SE +/- 3.84, N = 3SE +/- 3.93, N = 3717708
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesLinux 5.10.1Linux 5.11 18Dec130260390520650Min: 709 / Avg: 716.67 / Max: 721Min: 703 / Avg: 708.33 / Max: 716

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenetLinux 5.10.1Linux 5.11 18Dec3691215SE +/- 0.14, N = 15SE +/- 0.15, N = 512.4812.63MIN: 11.84 / MAX: 14.29MIN: 11.95 / MAX: 14.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenetLinux 5.10.1Linux 5.11 18Dec48121620Min: 11.99 / Avg: 12.48 / Max: 13.63Min: 12.18 / Avg: 12.63 / Max: 131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP32 - Device: CPULinux 5.10.1Linux 5.11 18Dec0.56931.13861.70792.27722.8465SE +/- 0.02, N = 3SE +/- 0.02, N = 32.502.531. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP32 - Device: CPULinux 5.10.1Linux 5.11 18Dec246810Min: 2.47 / Avg: 2.5 / Max: 2.53Min: 2.5 / Avg: 2.53 / Max: 2.551. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v3Linux 5.10.1Linux 5.11 18Dec0.9541.9082.8623.8164.77SE +/- 0.04, N = 15SE +/- 0.05, N = 54.244.19MIN: 4.06 / MAX: 12.53MIN: 4.06 / MAX: 4.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v3Linux 5.10.1Linux 5.11 18Dec246810Min: 4.09 / Avg: 4.24 / Max: 4.58Min: 4.1 / Avg: 4.19 / Max: 4.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

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

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc C String FunctionsLinux 5.10.1Linux 5.11 18Dec500K1000K1500K2000K2500KSE +/- 15556.35, N = 3SE +/- 18910.24, N = 32533146.812504693.061. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc C String FunctionsLinux 5.10.1Linux 5.11 18Dec400K800K1200K1600K2000KMin: 2502506.67 / Avg: 2533146.81 / Max: 2553145.21Min: 2476574.61 / Avg: 2504693.06 / Max: 2540656.761. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Linux 5.10.1Linux 5.11 18Dec500K1000K1500K2000K2500KSE +/- 2178.27, N = 3SE +/- 15034.71, N = 32197660.12222530.6
OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Linux 5.10.1Linux 5.11 18Dec400K800K1200K1600K2000KMin: 2194762.7 / Avg: 2197660.07 / Max: 2201926.3Min: 2202516 / Avg: 2222530.57 / Max: 2251972.1

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: MallocLinux 5.10.1Linux 5.11 18Dec50M100M150M200M250MSE +/- 309200.46, N = 3SE +/- 320519.10, N = 3251404923.52254222859.971. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MallocLinux 5.10.1Linux 5.11 18Dec40M80M120M160M200MMin: 250811126.31 / Avg: 251404923.52 / Max: 251851382.93Min: 253647966.58 / Avg: 254222859.97 / Max: 254755909.331. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read WriteLinux 5.10.1Linux 5.11 18Dec30060090012001500SE +/- 3.95, N = 3SE +/- 9.15, N = 3129013041. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read WriteLinux 5.10.1Linux 5.11 18Dec2004006008001000Min: 1283.04 / Avg: 1290.47 / Max: 1296.5Min: 1293.83 / Avg: 1303.91 / Max: 1322.181. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

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 CacheLinux 5.10.1Linux 5.11 18Dec816243240SE +/- 0.43, N = 15SE +/- 0.40, N = 336.0036.391. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU CacheLinux 5.10.1Linux 5.11 18Dec816243240Min: 31.46 / Avg: 36 / Max: 38.39Min: 35.92 / Avg: 36.39 / Max: 37.191. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read WriteLinux 5.10.1Linux 5.11 18Dec30060090012001500SE +/- 4.99, N = 3SE +/- 3.57, N = 3150715231. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read WriteLinux 5.10.1Linux 5.11 18Dec30060090012001500Min: 1498.91 / Avg: 1506.58 / Max: 1515.94Min: 1515.92 / Avg: 1522.56 / Max: 1528.131. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet50Linux 5.10.1Linux 5.11 18Dec612182430SE +/- 0.21, N = 15SE +/- 0.44, N = 525.4425.71MIN: 24.27 / MAX: 51.41MIN: 23.9 / MAX: 37.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet50Linux 5.10.1Linux 5.11 18Dec612182430Min: 24.54 / Avg: 25.44 / Max: 26.93Min: 24.18 / Avg: 25.71 / Max: 26.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average LatencyLinux 5.10.1Linux 5.11 18Dec816243240SE +/- 0.11, N = 3SE +/- 0.08, N = 333.2032.851. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average LatencyLinux 5.10.1Linux 5.11 18Dec714212835Min: 32.99 / Avg: 33.2 / Max: 33.36Min: 32.73 / Avg: 32.85 / Max: 32.991. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read OnlyLinux 5.10.1Linux 5.11 18Dec100K200K300K400K500KSE +/- 686.02, N = 3SE +/- 3049.90, N = 34639574688001. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read OnlyLinux 5.10.1Linux 5.11 18Dec80K160K240K320K400KMin: 463011.01 / Avg: 463956.54 / Max: 465290.34Min: 462752.21 / Avg: 468800.05 / Max: 472511.971. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average LatencyLinux 5.10.1Linux 5.11 18Dec0.17440.34880.52320.69760.872SE +/- 0.002, N = 3SE +/- 0.006, N = 30.7750.7671. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average LatencyLinux 5.10.1Linux 5.11 18Dec246810Min: 0.77 / Avg: 0.77 / Max: 0.78Min: 0.76 / Avg: 0.77 / Max: 0.771. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssdLinux 5.10.1Linux 5.11 18Dec48121620SE +/- 0.08, N = 15SE +/- 0.19, N = 514.7014.55MIN: 14.06 / MAX: 18.35MIN: 13.85 / MAX: 21.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssdLinux 5.10.1Linux 5.11 18Dec48121620Min: 14.3 / Avg: 14.7 / Max: 15.42Min: 14.03 / Avg: 14.55 / Max: 15.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read OnlyLinux 5.10.1Linux 5.11 18Dec140K280K420K560K700KSE +/- 2541.94, N = 3SE +/- 3004.95, N = 36346836411631. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read OnlyLinux 5.10.1Linux 5.11 18Dec110K220K330K440K550KMin: 629600.66 / Avg: 634683.15 / Max: 637327Min: 635219.22 / Avg: 641162.98 / Max: 644904.891. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkLinux 5.10.1Linux 5.11 18Dec120240360480600SE +/- 6.43, N = 3SE +/- 3.18, N = 3531.16536.53
OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkLinux 5.10.1Linux 5.11 18Dec90180270360450Min: 523.8 / Avg: 531.16 / Max: 543.97Min: 530.73 / Avg: 536.53 / Max: 541.69

x265

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

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pLinux 5.10.1Linux 5.11 18Dec20406080100SE +/- 0.19, N = 3SE +/- 0.19, N = 383.5582.741. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pLinux 5.10.1Linux 5.11 18Dec1632486480Min: 83.18 / Avg: 83.55 / Max: 83.79Min: 82.4 / Avg: 82.74 / Max: 83.051. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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: vklBenchmarkStructuredVolumeLinux 5.10.1Linux 5.11 18Dec20M40M60M80M100MSE +/- 273590.10, N = 3SE +/- 630189.49, N = 387177472.8488014355.28MIN: 1356984 / MAX: 708220656MIN: 1339647 / MAX: 703034496
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkStructuredVolumeLinux 5.10.1Linux 5.11 18Dec15M30M45M60M75MMin: 86645077.16 / Avg: 87177472.84 / Max: 87553081.62Min: 87375932.59 / Avg: 88014355.28 / Max: 89274698.24

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: CompileLinux 5.10.1Linux 5.11 18Dec6001200180024003000SE +/- 25.53, N = 3SE +/- 32.14, N = 32855.432882.59
OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: CompileLinux 5.10.1Linux 5.11 18Dec5001000150020002500Min: 2804.79 / Avg: 2855.43 / Max: 2886.42Min: 2825.62 / Avg: 2882.59 / Max: 2936.86

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average LatencyLinux 5.10.1Linux 5.11 18Dec0.02430.04860.07290.09720.1215SE +/- 0.000, N = 3SE +/- 0.001, N = 30.1080.1071. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average LatencyLinux 5.10.1Linux 5.11 18Dec12345Min: 0.11 / Avg: 0.11 / Max: 0.11Min: 0.11 / Avg: 0.11 / Max: 0.111. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

LevelDB

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

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential FillLinux 5.10.1Linux 5.11 18Dec816243240SE +/- 0.03, N = 3SE +/- 0.06, N = 332.732.41. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential FillLinux 5.10.1Linux 5.11 18Dec714212835Min: 32.6 / Avg: 32.67 / Max: 32.7Min: 32.3 / Avg: 32.4 / Max: 32.51. (CXX) g++ options: -O3 -lsnappy -lpthread

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaLinux 5.10.1Linux 5.11 18Dec1428425670SE +/- 0.17, N = 3SE +/- 0.29, N = 361.7962.36
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaLinux 5.10.1Linux 5.11 18Dec1224364860Min: 61.57 / Avg: 61.79 / Max: 62.12Min: 61.88 / Avg: 62.36 / Max: 62.89

LevelDB

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

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random FillLinux 5.10.1Linux 5.11 18Dec816243240SE +/- 0.03, N = 3SE +/- 0.03, N = 333.132.81. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random FillLinux 5.10.1Linux 5.11 18Dec714212835Min: 33.1 / Avg: 33.13 / Max: 33.2Min: 32.8 / Avg: 32.83 / Max: 32.91. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random FillLinux 5.10.1Linux 5.11 18Dec20406080100SE +/- 0.13, N = 3SE +/- 0.08, N = 3106.77107.681. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random FillLinux 5.10.1Linux 5.11 18Dec20406080100Min: 106.51 / Avg: 106.77 / Max: 106.96Min: 107.53 / Avg: 107.68 / Max: 107.761. (CXX) g++ options: -O3 -lsnappy -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: Glibc Qsort Data SortingLinux 5.10.1Linux 5.11 18Dec60120180240300SE +/- 0.45, N = 3SE +/- 1.18, N = 3257.35255.221. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc Qsort Data SortingLinux 5.10.1Linux 5.11 18Dec50100150200250Min: 256.47 / Avg: 257.35 / Max: 257.97Min: 252.87 / Avg: 255.22 / Max: 256.471. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Timed GDB GNU Debugger Compilation

This test times how long it takes to build the GNU Debugger (GDB) in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompileLinux 5.10.1Linux 5.11 18Dec20406080100SE +/- 0.34, N = 3SE +/- 0.17, N = 379.7479.09
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompileLinux 5.10.1Linux 5.11 18Dec1530456075Min: 79.4 / Avg: 79.74 / Max: 80.42Min: 78.89 / Avg: 79.09 / Max: 79.42

BRL-CAD

BRL-CAD 7.28.0 is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.30.8VGR Performance MetricLinux 5.10.1Linux 5.11 18Dec60K120K180K240K300K2614102635351. (CXX) g++ options: -std=c++11 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lXi -lGLU -lGL -lGLdispatch -lX11 -lXext -lXrender -lpthread -ldl -luuid -lm

TNN

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

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1Linux 5.10.1Linux 5.11 18Dec50100150200250SE +/- 0.70, N = 3SE +/- 0.76, N = 3214.02212.34MIN: 212.52 / MAX: 218.18MIN: 210.71 / MAX: 213.281. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1Linux 5.10.1Linux 5.11 18Dec4080120160200Min: 212.63 / Avg: 214.02 / Max: 214.86Min: 210.82 / Avg: 212.34 / Max: 213.151. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

LevelDB

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

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential FillLinux 5.10.1Linux 5.11 18Dec20406080100SE +/- 0.10, N = 3SE +/- 0.12, N = 3108.39109.231. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential FillLinux 5.10.1Linux 5.11 18Dec20406080100Min: 108.23 / Avg: 108.39 / Max: 108.58Min: 109.05 / Avg: 109.23 / Max: 109.461. (CXX) g++ options: -O3 -lsnappy -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 1,000Linux 5.10.1Linux 5.11 18Dec1020304050SE +/- 0.16, N = 3SE +/- 0.40, N = 342.9442.611. (CC) gcc options: -O2 -ldl -lz -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Linux 5.10.1Linux 5.11 18Dec918273645Min: 42.75 / Avg: 42.94 / Max: 43.26Min: 42.05 / Avg: 42.61 / Max: 43.381. (CC) gcc options: -O2 -ldl -lz -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b0Linux 5.10.1Linux 5.11 18Dec1.23532.47063.70594.94126.1765SE +/- 0.05, N = 15SE +/- 0.07, N = 55.495.45MIN: 5.24 / MAX: 16.26MIN: 5.23 / MAX: 5.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b0Linux 5.10.1Linux 5.11 18Dec246810Min: 5.31 / Avg: 5.49 / Max: 6.05Min: 5.29 / Avg: 5.45 / Max: 5.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP16 - Device: CPULinux 5.10.1Linux 5.11 18Dec7001400210028003500SE +/- 7.02, N = 3SE +/- 6.12, N = 33107.253084.821. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP16 - Device: CPULinux 5.10.1Linux 5.11 18Dec5001000150020002500Min: 3096.66 / Avg: 3107.25 / Max: 3120.54Min: 3072.69 / Avg: 3084.82 / Max: 3092.241. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread

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 0.13Time To CompileLinux 5.10.1Linux 5.11 18Dec1632486480SE +/- 0.01, N = 3SE +/- 0.20, N = 372.0372.53
OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To CompileLinux 5.10.1Linux 5.11 18Dec1428425670Min: 72.01 / Avg: 72.03 / Max: 72.04Min: 72.23 / Avg: 72.53 / Max: 72.91

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: MD5Linux 5.10.1Linux 5.11 18Dec500K1000K1500K2000K2500KSE +/- 13691.04, N = 3SE +/- 14294.52, N = 3219966722150001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: MD5Linux 5.10.1Linux 5.11 18Dec400K800K1200K1600K2000KMin: 2178000 / Avg: 2199666.67 / Max: 2225000Min: 2187000 / Avg: 2215000 / Max: 22340001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

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 6.0.16Linux 5.10.1Linux 5.11 18Dec200K400K600K800K1000KSE +/- 1125.85, N = 3SE +/- 1063.75, N = 3805277.95799825.081. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.0.16Linux 5.10.1Linux 5.11 18Dec140K280K420K560K700KMin: 803475.47 / Avg: 805277.95 / Max: 807347.9Min: 798363.99 / Avg: 799825.08 / Max: 801894.891. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400mLinux 5.10.1Linux 5.11 18Dec48121620SE +/- 0.05, N = 15SE +/- 0.19, N = 518.0918.21MIN: 17.66 / MAX: 40.13MIN: 17.64 / MAX: 20.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400mLinux 5.10.1Linux 5.11 18Dec510152025Min: 17.85 / Avg: 18.09 / Max: 18.62Min: 17.8 / Avg: 18.21 / Max: 18.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 12Total TimeLinux 5.10.1Linux 5.11 18Dec9M18M27M36M45MSE +/- 665245.18, N = 3SE +/- 154284.94, N = 343079867433640411. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver
OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 12Total TimeLinux 5.10.1Linux 5.11 18Dec8M16M24M32M40MMin: 41823675 / Avg: 43079867.33 / Max: 44087620Min: 43203604 / Avg: 43364041 / Max: 436725281. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg16Linux 5.10.1Linux 5.11 18Dec1326395265SE +/- 0.07, N = 15SE +/- 0.26, N = 558.0957.71MIN: 56.73 / MAX: 97.23MIN: 55.68 / MAX: 68.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg16Linux 5.10.1Linux 5.11 18Dec1122334455Min: 57.57 / Avg: 58.09 / Max: 58.49Min: 56.69 / Avg: 57.71 / Max: 58.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetLinux 5.10.1Linux 5.11 18Dec20K40K60K80K100KSE +/- 103.88, N = 3SE +/- 65.14, N = 395305.694780.7
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetLinux 5.10.1Linux 5.11 18Dec17K34K51K68K85KMin: 95097.8 / Avg: 95305.57 / Max: 95410.2Min: 94651.9 / Avg: 94780.7 / Max: 94862.1

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: MemorialLinux 5.10.1Linux 5.11 18Dec48121620SE +/- 0.03, N = 3SE +/- 0.02, N = 314.6014.52
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.2.0Scene: MemorialLinux 5.10.1Linux 5.11 18Dec48121620Min: 14.55 / Avg: 14.6 / Max: 14.65Min: 14.49 / Avg: 14.52 / Max: 14.57

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: MMAPLinux 5.10.1Linux 5.11 18Dec110220330440550SE +/- 1.37, N = 3SE +/- 0.94, N = 3506.00503.281. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MMAPLinux 5.10.1Linux 5.11 18Dec90180270360450Min: 503.58 / Avg: 506 / Max: 508.31Min: 501.72 / Avg: 503.28 / Max: 504.981. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) 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 2020.3Water BenchmarkLinux 5.10.1Linux 5.11 18Dec0.2970.5940.8911.1881.485SE +/- 0.001, N = 3SE +/- 0.002, N = 31.3131.3201. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water BenchmarkLinux 5.10.1Linux 5.11 18Dec246810Min: 1.31 / Avg: 1.31 / Max: 1.31Min: 1.32 / Avg: 1.32 / Max: 1.321. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Linux 5.10.1Linux 5.11 18Dec400K800K1200K1600K2000KSE +/- 3846.90, N = 3SE +/- 3387.13, N = 31999403.72009772.4
OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Linux 5.10.1Linux 5.11 18Dec300K600K900K1200K1500KMin: 1992586.2 / Avg: 1999403.7 / Max: 2005900.7Min: 2005271.1 / Avg: 2009772.4 / Max: 2016407.3

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec30060090012001500SE +/- 7.54, N = 3SE +/- 5.29, N = 3159615881. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec30060090012001500Min: 1582 / Avg: 1595.67 / Max: 1608Min: 1580 / Avg: 1588 / Max: 15981. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -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: AtomicLinux 5.10.1Linux 5.11 18Dec40K80K120K160K200KSE +/- 270.00, N = 3SE +/- 521.63, N = 3194151.53195117.961. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: AtomicLinux 5.10.1Linux 5.11 18Dec30K60K90K120K150KMin: 193615.85 / Avg: 194151.53 / Max: 194478.34Min: 194237.54 / Avg: 195117.96 / Max: 196042.861. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

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 MobileLinux 5.10.1Linux 5.11 18Dec20K40K60K80K100KSE +/- 206.07, N = 3SE +/- 126.83, N = 3104950104432
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileLinux 5.10.1Linux 5.11 18Dec20K40K60K80K100KMin: 104694 / Avg: 104950.33 / Max: 105358Min: 104279 / Avg: 104432.33 / Max: 104684

Node.js V8 Web Tooling Benchmark

Running the V8 project's Web-Tooling-Benchmark under Node.js. The Web-Tooling-Benchmark stresses JavaScript-related workloads common to web developers like Babel and TypeScript and Babylon. This test profile can test the system's JavaScript performance with Node.js. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkLinux 5.10.1Linux 5.11 18Dec48121620SE +/- 0.14, N = 3SE +/- 0.15, N = 316.1316.211. Nodejs v10.19.0
OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkLinux 5.10.1Linux 5.11 18Dec48121620Min: 15.9 / Avg: 16.13 / Max: 16.37Min: 15.93 / Avg: 16.21 / Max: 16.441. Nodejs v10.19.0

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec90K180K270K360K450KSE +/- 2027.59, N = 3SE +/- 1201.85, N = 34086674066671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec70K140K210K280K350KMin: 405000 / Avg: 408666.67 / Max: 412000Min: 405000 / Avg: 406666.67 / Max: 4090001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatLinux 5.10.1Linux 5.11 18Dec13K26K39K52K65KSE +/- 14.42, N = 3SE +/- 64.77, N = 362929.062622.9
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatLinux 5.10.1Linux 5.11 18Dec11K22K33K44K55KMin: 62904.6 / Avg: 62929 / Max: 62954.5Min: 62495.2 / Avg: 62622.93 / Max: 62705.5

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 0.11.07Test: Memory CopyingLinux 5.10.1Linux 5.11 18Dec30060090012001500SE +/- 2.10, N = 3SE +/- 5.28, N = 31456.941464.051. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Memory CopyingLinux 5.10.1Linux 5.11 18Dec30060090012001500Min: 1452.87 / Avg: 1456.94 / Max: 1459.87Min: 1455.61 / Avg: 1464.05 / Max: 1473.781. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPULinux 5.10.1Linux 5.11 18Dec3K6K9K12K15KSE +/- 6.24, N = 3SE +/- 13.22, N = 313759.2613826.311. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPULinux 5.10.1Linux 5.11 18Dec2K4K6K8K10KMin: 13751.67 / Avg: 13759.26 / Max: 13771.64Min: 13811.02 / Avg: 13826.31 / Max: 13852.641. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread

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: 1080pLinux 5.10.1Linux 5.11 18Dec1122334455SE +/- 0.26, N = 3SE +/- 0.15, N = 350.4250.671. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pLinux 5.10.1Linux 5.11 18Dec1020304050Min: 50.1 / Avg: 50.42 / Max: 50.94Min: 50.47 / Avg: 50.67 / Max: 50.961. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet18Linux 5.10.1Linux 5.11 18Dec48121620SE +/- 0.09, N = 15SE +/- 0.19, N = 514.6914.62MIN: 14.3 / MAX: 26.71MIN: 14.22 / MAX: 16.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet18Linux 5.10.1Linux 5.11 18Dec48121620Min: 14.39 / Avg: 14.69 / Max: 15.34Min: 14.32 / Avg: 14.62 / Max: 15.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantLinux 5.10.1Linux 5.11 18Dec15K30K45K60K75KSE +/- 47.73, N = 3SE +/- 27.18, N = 368289.367966.6
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantLinux 5.10.1Linux 5.11 18Dec12K24K36K48K60KMin: 68204.8 / Avg: 68289.27 / Max: 68370Min: 67913.7 / Avg: 67966.6 / Max: 68003.9

x265

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

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KLinux 5.10.1Linux 5.11 18Dec714212835SE +/- 0.06, N = 3SE +/- 0.12, N = 327.6627.531. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KLinux 5.10.1Linux 5.11 18Dec612182430Min: 27.56 / Avg: 27.66 / Max: 27.78Min: 27.29 / Avg: 27.53 / Max: 27.661. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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: vklBenchmarkLinux 5.10.1Linux 5.11 18Dec60120180240300SE +/- 0.53, N = 3SE +/- 1.04, N = 3288.69290.00MIN: 1 / MAX: 1113MIN: 1 / MAX: 1123
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkLinux 5.10.1Linux 5.11 18Dec50100150200250Min: 288.17 / Avg: 288.69 / Max: 289.75Min: 288.25 / Avg: 290 / Max: 291.83

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionLinux 5.10.1Linux 5.11 18Dec0.50181.00361.50542.00722.509SE +/- 0.00, N = 3SE +/- 0.01, N = 32.222.23
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionLinux 5.10.1Linux 5.11 18Dec246810Min: 2.22 / Avg: 2.22 / Max: 2.23Min: 2.21 / Avg: 2.23 / Max: 2.25

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin ProteinLinux 5.10.1Linux 5.11 18Dec3691215SE +/- 0.15, N = 15SE +/- 0.17, N = 312.3312.281. (CXX) g++ options: -O3 -pthread -lm
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin ProteinLinux 5.10.1Linux 5.11 18Dec48121620Min: 11.11 / Avg: 12.33 / Max: 12.86Min: 11.95 / Avg: 12.28 / Max: 12.521. (CXX) g++ options: -O3 -pthread -lm

TNN

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

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2Linux 5.10.1Linux 5.11 18Dec50100150200250SE +/- 1.69, N = 3SE +/- 1.36, N = 3229.96228.96MIN: 226.02 / MAX: 260.61MIN: 224.93 / MAX: 250.011. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2Linux 5.10.1Linux 5.11 18Dec4080120160200Min: 226.59 / Avg: 229.96 / Max: 231.87Min: 227.46 / Avg: 228.96 / Max: 231.671. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

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 V2Linux 5.10.1Linux 5.11 18Dec300K600K900K1200K1500KSE +/- 781.91, N = 3SE +/- 980.00, N = 312191431214260
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Linux 5.10.1Linux 5.11 18Dec200K400K600K800K1000KMin: 1217690 / Avg: 1219143.33 / Max: 1220370Min: 1212440 / Avg: 1214260 / Max: 1215800

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec2004006008001000SE +/- 15.40, N = 15SE +/- 17.29, N = 3101410101. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec2004006008001000Min: 893 / Avg: 1014 / Max: 1102Min: 977 / Avg: 1010.33 / Max: 10351. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

C-Blosc

A simple, compressed, fast and persistent data store library for C. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.0 Beta 5Compressor: blosclzLinux 5.10.1Linux 5.11 18Dec3K6K9K12K15KSE +/- 27.03, N = 3SE +/- 13.94, N = 313991.314046.71. (CXX) g++ options: -rdynamic
OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.0 Beta 5Compressor: blosclzLinux 5.10.1Linux 5.11 18Dec2K4K6K8K10KMin: 13937.9 / Avg: 13991.3 / Max: 14025.3Min: 14022.5 / Avg: 14046.7 / Max: 14070.81. (CXX) g++ options: -rdynamic

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP16 - Device: CPULinux 5.10.1Linux 5.11 18Dec0.57151.1431.71452.2862.8575SE +/- 0.01, N = 3SE +/- 0.00, N = 32.532.541. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Person Detection 0106 FP16 - Device: CPULinux 5.10.1Linux 5.11 18Dec246810Min: 2.5 / Avg: 2.53 / Max: 2.55Min: 2.53 / Avg: 2.54 / Max: 2.541. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec60K120K180K240K300KSE +/- 3926.47, N = 15SE +/- 4484.54, N = 32596002586671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec40K80K120K160K200KMin: 229000 / Avg: 259600 / Max: 282000Min: 250000 / Avg: 258666.67 / Max: 2650001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP32 - Device: CPULinux 5.10.1Linux 5.11 18Dec5001000150020002500SE +/- 4.88, N = 3SE +/- 6.53, N = 32094.452101.821. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP32 - Device: CPULinux 5.10.1Linux 5.11 18Dec400800120016002000Min: 2086.38 / Avg: 2094.45 / Max: 2103.23Min: 2092.3 / Avg: 2101.82 / Max: 2114.321. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread

LevelDB

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

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: OverwriteLinux 5.10.1Linux 5.11 18Dec816243240SE +/- 0.03, N = 3SE +/- 0.09, N = 333.133.01. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: OverwriteLinux 5.10.1Linux 5.11 18Dec714212835Min: 33 / Avg: 33.07 / Max: 33.1Min: 32.8 / Avg: 32.97 / Max: 33.11. (CXX) g++ options: -O3 -lsnappy -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: CryptoLinux 5.10.1Linux 5.11 18Dec10002000300040005000SE +/- 11.66, N = 3SE +/- 7.32, N = 34818.364832.911. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CryptoLinux 5.10.1Linux 5.11 18Dec8001600240032004000Min: 4801.79 / Avg: 4818.36 / Max: 4840.85Min: 4821.74 / Avg: 4832.91 / Max: 4846.681. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Vector MathLinux 5.10.1Linux 5.11 18Dec40K80K120K160K200KSE +/- 207.23, N = 3SE +/- 170.14, N = 3172105.66172622.661. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Vector MathLinux 5.10.1Linux 5.11 18Dec30K60K90K120K150KMin: 171781.7 / Avg: 172105.66 / Max: 172491.53Min: 172362.82 / Avg: 172622.66 / Max: 172942.851. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MEMFDLinux 5.10.1Linux 5.11 18Dec30060090012001500SE +/- 1.12, N = 3SE +/- 0.56, N = 31418.741422.931. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MEMFDLinux 5.10.1Linux 5.11 18Dec2004006008001000Min: 1416.66 / Avg: 1418.74 / Max: 1420.49Min: 1421.85 / Avg: 1422.93 / Max: 1423.71. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec100K200K300K400K500KSE +/- 3511.88, N = 3SE +/- 1201.85, N = 34630004616671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec80K160K240K320K400KMin: 459000 / Avg: 463000 / Max: 470000Min: 460000 / Avg: 461666.67 / Max: 4640001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

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 V4Linux 5.10.1Linux 5.11 18Dec300K600K900K1200K1500KSE +/- 883.37, N = 3SE +/- 912.27, N = 313542371350400
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Linux 5.10.1Linux 5.11 18Dec200K400K600K800K1000KMin: 1352640 / Avg: 1354236.67 / Max: 1355690Min: 1348830 / Avg: 1350400 / Max: 1351990

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec400800120016002000SE +/- 13.86, N = 3SE +/- 4.37, N = 3180918041. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec30060090012001500Min: 1794 / Avg: 1809.33 / Max: 1837Min: 1799 / Avg: 1804.33 / Max: 18131. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

LevelDB

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

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: OverwriteLinux 5.10.1Linux 5.11 18Dec20406080100SE +/- 0.09, N = 3SE +/- 0.28, N = 3107.05107.341. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: OverwriteLinux 5.10.1Linux 5.11 18Dec20406080100Min: 106.93 / Avg: 107.05 / Max: 107.22Min: 107.02 / Avg: 107.34 / Max: 107.91. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomLinux 5.10.1Linux 5.11 18Dec510152025SE +/- 0.02, N = 3SE +/- 0.05, N = 318.8418.891. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomLinux 5.10.1Linux 5.11 18Dec510152025Min: 18.81 / Avg: 18.84 / Max: 18.87Min: 18.81 / Avg: 18.88 / Max: 18.991. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP32 - Device: CPULinux 5.10.1Linux 5.11 18Dec0.85281.70562.55843.41124.264SE +/- 0.01, N = 3SE +/- 0.01, N = 33.793.781. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP32 - Device: CPULinux 5.10.1Linux 5.11 18Dec246810Min: 3.77 / Avg: 3.79 / Max: 3.81Min: 3.76 / Avg: 3.78 / Max: 3.791. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP16 - Device: CPULinux 5.10.1Linux 5.11 18Dec0.86181.72362.58543.44724.309SE +/- 0.01, N = 3SE +/- 0.01, N = 33.823.831. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP16 - Device: CPULinux 5.10.1Linux 5.11 18Dec246810Min: 3.8 / Avg: 3.82 / Max: 3.84Min: 3.81 / Avg: 3.83 / Max: 3.851. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnetLinux 5.10.1Linux 5.11 18Dec0.9181.8362.7543.6724.59SE +/- 0.05, N = 15SE +/- 0.07, N = 54.074.08MIN: 3.83 / MAX: 6.64MIN: 3.83 / MAX: 4.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnetLinux 5.10.1Linux 5.11 18Dec246810Min: 3.92 / Avg: 4.07 / Max: 4.65Min: 3.92 / Avg: 4.08 / Max: 4.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmLinux 5.10.1Linux 5.11 18Dec48121620SE +/- 0.07, N = 3SE +/- 0.09, N = 316.3916.43
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmLinux 5.10.1Linux 5.11 18Dec48121620Min: 16.26 / Avg: 16.39 / Max: 16.48Min: 16.24 / Avg: 16.43 / Max: 16.54

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 CompileLinux 5.10.1Linux 5.11 18Dec1020304050SE +/- 0.44, N = 3SE +/- 0.42, N = 345.5845.69
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileLinux 5.10.1Linux 5.11 18Dec918273645Min: 45.09 / Avg: 45.58 / Max: 46.46Min: 45.23 / Avg: 45.69 / Max: 46.53

LevelDB

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

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random ReadLinux 5.10.1Linux 5.11 18Dec48121620SE +/- 0.06, N = 3SE +/- 0.03, N = 313.7413.771. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random ReadLinux 5.10.1Linux 5.11 18Dec48121620Min: 13.63 / Avg: 13.74 / Max: 13.83Min: 13.72 / Avg: 13.77 / Max: 13.811. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill SyncLinux 5.10.1Linux 5.11 18Dec400800120016002000SE +/- 9.10, N = 3SE +/- 7.05, N = 31928.561924.671. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill SyncLinux 5.10.1Linux 5.11 18Dec30060090012001500Min: 1916.13 / Avg: 1928.56 / Max: 1946.28Min: 1911.57 / Avg: 1924.67 / Max: 1935.761. (CXX) g++ options: -O3 -lsnappy -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: Socket ActivityLinux 5.10.1Linux 5.11 18Dec3K6K9K12K15KSE +/- 42.25, N = 3SE +/- 158.48, N = 311815.7711835.881. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Socket ActivityLinux 5.10.1Linux 5.11 18Dec2K4K6K8K10KMin: 11734.42 / Avg: 11815.77 / Max: 11876.25Min: 11519.25 / Avg: 11835.88 / Max: 12006.861. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec90K180K270K360K450KSE +/- 1000.00, N = 3SE +/- 666.67, N = 34060004066671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec70K140K210K280K350KMin: 404000 / Avg: 406000 / Max: 407000Min: 406000 / Avg: 406666.67 / Max: 4080001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

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: 1080pLinux 5.10.1Linux 5.11 18Dec246810SE +/- 0.013, N = 3SE +/- 0.016, N = 36.0786.0861. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pLinux 5.10.1Linux 5.11 18Dec246810Min: 6.05 / Avg: 6.08 / Max: 6.1Min: 6.06 / Avg: 6.09 / Max: 6.121. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

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 3.1Linux 5.10.1Linux 5.11 18Dec0.95231.90462.85693.80924.7615SE +/- 0.00409, N = 3SE +/- 0.00416, N = 34.227024.232411. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1Linux 5.10.1Linux 5.11 18Dec246810Min: 4.22 / Avg: 4.23 / Max: 4.23Min: 4.22 / Avg: 4.23 / Max: 4.241. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP32 - Device: CPULinux 5.10.1Linux 5.11 18Dec3K6K9K12K15KSE +/- 2.77, N = 3SE +/- 9.08, N = 313482.0413499.001. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP32 - Device: CPULinux 5.10.1Linux 5.11 18Dec2K4K6K8K10KMin: 13476.57 / Avg: 13482.04 / Max: 13485.55Min: 13483.65 / Avg: 13499 / Max: 13515.091. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread

LevelDB

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

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadLinux 5.10.1Linux 5.11 18Dec3691215SE +/- 0.11, N = 3SE +/- 0.08, N = 313.6113.591. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadLinux 5.10.1Linux 5.11 18Dec48121620Min: 13.4 / Avg: 13.61 / Max: 13.78Min: 13.48 / Avg: 13.59 / Max: 13.751. (CXX) g++ options: -O3 -lsnappy -lpthread

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: BlowfishLinux 5.10.1Linux 5.11 18Dec8K16K24K32K40KSE +/- 149.17, N = 3SE +/- 147.61, N = 337907379481. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: BlowfishLinux 5.10.1Linux 5.11 18Dec7K14K21K28K35KMin: 37680 / Avg: 37906.67 / Max: 38188Min: 37747 / Avg: 37948.33 / Max: 382361. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

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 TreeLinux 5.10.1Linux 5.11 18Dec10002000300040005000SE +/- 61.75, N = 3SE +/- 60.11, N = 34508.304512.13
OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled TreeLinux 5.10.1Linux 5.11 18Dec8001600240032004000Min: 4414.29 / Avg: 4508.3 / Max: 4624.66Min: 4397.95 / Avg: 4512.13 / Max: 4601.8

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: Matrix MathLinux 5.10.1Linux 5.11 18Dec16K32K48K64K80KSE +/- 65.04, N = 3SE +/- 285.69, N = 375646.9075670.941. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Matrix MathLinux 5.10.1Linux 5.11 18Dec13K26K39K52K65KMin: 75517.65 / Avg: 75646.9 / Max: 75724.27Min: 75193.3 / Avg: 75670.94 / Max: 76181.321. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP16 - Device: CPULinux 5.10.1Linux 5.11 18Dec400800120016002000SE +/- 5.63, N = 3SE +/- 5.12, N = 32072.072072.401. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Face Detection 0106 FP16 - Device: CPULinux 5.10.1Linux 5.11 18Dec400800120016002000Min: 2061.12 / Avg: 2072.07 / Max: 2079.79Min: 2062.39 / Avg: 2072.4 / Max: 2079.31. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -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 StressLinux 5.10.1Linux 5.11 18Dec3K6K9K12K15KSE +/- 52.37, N = 3SE +/- 138.45, N = 611798.2411799.291. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU StressLinux 5.10.1Linux 5.11 18Dec2K4K6K8K10KMin: 11698.5 / Avg: 11798.24 / Max: 11875.83Min: 11430.18 / Avg: 11799.29 / Max: 12409.591. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

LevelDB

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

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random DeleteLinux 5.10.1Linux 5.11 18Dec20406080100SE +/- 0.42, N = 3SE +/- 0.16, N = 3102.03102.031. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random DeleteLinux 5.10.1Linux 5.11 18Dec20406080100Min: 101.52 / Avg: 102.03 / Max: 102.87Min: 101.72 / Avg: 102.03 / Max: 102.251. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP32 - Device: CPULinux 5.10.1Linux 5.11 18Dec0.13050.2610.39150.5220.6525SE +/- 0.00, N = 3SE +/- 0.00, N = 30.580.581. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP32 - Device: CPULinux 5.10.1Linux 5.11 18Dec246810Min: 0.58 / Avg: 0.58 / Max: 0.58Min: 0.58 / Avg: 0.58 / Max: 0.581. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPULinux 5.10.1Linux 5.11 18Dec0.12830.25660.38490.51320.6415SE +/- 0.00, N = 3SE +/- 0.00, N = 30.570.571. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2021.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPULinux 5.10.1Linux 5.11 18Dec246810Min: 0.57 / Avg: 0.57 / Max: 0.57Min: 0.57 / Avg: 0.57 / Max: 0.571. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -pie -pthread -lpthread

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 TimeLinux 5.10.1Linux 5.11 18Dec306090120150136136

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnetLinux 5.10.1Linux 5.11 18Dec3691215SE +/- 0.11, N = 15SE +/- 0.17, N = 511.3011.30MIN: 10.81 / MAX: 25.05MIN: 10.78 / MAX: 18.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnetLinux 5.10.1Linux 5.11 18Dec3691215Min: 10.9 / Avg: 11.3 / Max: 12Min: 10.87 / Avg: 11.3 / Max: 11.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v2Linux 5.10.1Linux 5.11 18Dec1.00582.01163.01744.02325.029SE +/- 0.01, N = 14SE +/- 0.02, N = 54.474.47MIN: 4.36 / MAX: 14.76MIN: 4.36 / MAX: 4.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v2Linux 5.10.1Linux 5.11 18Dec246810Min: 4.42 / Avg: 4.47 / Max: 4.5Min: 4.43 / Avg: 4.47 / Max: 4.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average LatencyLinux 5.10.1Linux 5.11 18Dec0.01760.03520.05280.07040.088SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0780.0781. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average LatencyLinux 5.10.1Linux 5.11 18Dec12345Min: 0.08 / Avg: 0.08 / Max: 0.08Min: 0.08 / Avg: 0.08 / Max: 0.081. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec30060090012001500SE +/- 3.51, N = 3SE +/- 2.67, N = 3158715871. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec30060090012001500Min: 1580 / Avg: 1587 / Max: 1591Min: 1584 / Avg: 1586.67 / Max: 15921. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

LevelDB

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

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill SyncLinux 5.10.1Linux 5.11 18Dec0.4050.811.2151.622.025SE +/- 0.00, N = 3SE +/- 0.00, N = 31.81.81. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill SyncLinux 5.10.1Linux 5.11 18Dec246810Min: 1.8 / Avg: 1.8 / Max: 1.8Min: 1.8 / Avg: 1.8 / Max: 1.81. (CXX) g++ options: -O3 -lsnappy -lpthread

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average LatencyLinux 5.10.1Linux 5.11 18Dec0.76591.53182.29773.06363.8295SE +/- 0.030, N = 3SE +/- 0.164, N = 151.9503.4041. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average LatencyLinux 5.10.1Linux 5.11 18Dec246810Min: 1.91 / Avg: 1.95 / Max: 2.01Min: 2.39 / Avg: 3.4 / Max: 4.421. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read WriteLinux 5.10.1Linux 5.11 18Dec5K10K15K20K25KSE +/- 390.32, N = 3SE +/- 763.01, N = 1525655151971. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 50 - Mode: Read WriteLinux 5.10.1Linux 5.11 18Dec4K8K12K16K20KMin: 24880.78 / Avg: 25655.1 / Max: 26128.13Min: 11312.55 / Avg: 15196.62 / Max: 20933.671. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 1 - Mode: Read Write - Average LatencyLinux 5.10.1Linux 5.11 18Dec0.20180.40360.60540.80721.009SE +/- 0.006, N = 3SE +/- 0.026, N = 120.8440.8971. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 1 - Mode: Read Write - Average LatencyLinux 5.10.1Linux 5.11 18Dec246810Min: 0.84 / Avg: 0.84 / Max: 0.86Min: 0.83 / Avg: 0.9 / Max: 1.141. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 1 - Mode: Read WriteLinux 5.10.1Linux 5.11 18Dec30060090012001500SE +/- 7.93, N = 3SE +/- 27.64, N = 12118511231. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 1 - Mode: Read WriteLinux 5.10.1Linux 5.11 18Dec2004006008001000Min: 1169.65 / Avg: 1184.95 / Max: 1196.21Min: 875.31 / Avg: 1122.97 / Max: 1212.591. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average LatencyLinux 5.10.1Linux 5.11 18Dec0.00650.0130.01950.0260.0325SE +/- 0.001, N = 12SE +/- 0.000, N = 30.0290.0271. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average LatencyLinux 5.10.1Linux 5.11 18Dec12345Min: 0.03 / Avg: 0.03 / Max: 0.05Min: 0.03 / Avg: 0.03 / Max: 0.031. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read OnlyLinux 5.10.1Linux 5.11 18Dec8K16K24K32K40KSE +/- 1225.94, N = 12SE +/- 387.99, N = 334751371751. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read OnlyLinux 5.10.1Linux 5.11 18Dec6K12K18K24K30KMin: 22046.99 / Avg: 34751.34 / Max: 38661.27Min: 36465.39 / Avg: 37175.13 / Max: 37801.681. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

simdjson

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

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: DistinctUserIDLinux 5.10.1Linux 5.11 18Dec0.23180.46360.69540.92721.159SE +/- 0.02, N = 15SE +/- 0.01, N = 150.971.031. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: DistinctUserIDLinux 5.10.1Linux 5.11 18Dec246810Min: 0.9 / Avg: 0.97 / Max: 1.08Min: 0.9 / Avg: 1.03 / Max: 1.091. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: PartialTweetsLinux 5.10.1Linux 5.11 18Dec0.22050.4410.66150.8821.1025SE +/- 0.02, N = 15SE +/- 0.02, N = 150.910.981. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: PartialTweetsLinux 5.10.1Linux 5.11 18Dec246810Min: 0.87 / Avg: 0.91 / Max: 1.05Min: 0.87 / Avg: 0.98 / Max: 1.051. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: KostyaLinux 5.10.1Linux 5.11 18Dec0.180.360.540.720.9SE +/- 0.00, N = 3SE +/- 0.03, N = 150.680.801. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: KostyaLinux 5.10.1Linux 5.11 18Dec246810Min: 0.67 / Avg: 0.68 / Max: 0.68Min: 0.67 / Avg: 0.8 / Max: 0.951. (CXX) g++ options: -O3 -pthread

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec200K400K600K800K1000KSE +/- 80406.08, N = 12SE +/- 11532.56, N = 35009588210001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec140K280K420K560K700KMin: 98500 / Avg: 500958.33 / Max: 846000Min: 804000 / Avg: 821000 / Max: 8430001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec7001400210028003500SE +/- 313.98, N = 12SE +/- 45.08, N = 3195732071. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec6001200180024003000Min: 385 / Avg: 1956.58 / Max: 3304Min: 3141 / Avg: 3206.67 / Max: 32931. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec60K120K180K240K300KSE +/- 4080.69, N = 15SE +/- 2905.93, N = 32549332613331. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec50K100K150K200K250KMin: 221000 / Avg: 254933.33 / Max: 271000Min: 256000 / Avg: 261333.33 / Max: 2660001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec2004006008001000SE +/- 16.00, N = 15SE +/- 10.90, N = 399510211. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec2004006008001000Min: 861 / Avg: 995.27 / Max: 1057Min: 1000 / Avg: 1020.67 / Max: 10371. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec60K120K180K240K300KSE +/- 20787.44, N = 12SE +/- 1333.33, N = 32318672576671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec40K80K120K160K200KMin: 49400 / Avg: 231866.67 / Max: 277000Min: 255000 / Avg: 257666.67 / Max: 2590001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec2004006008001000SE +/- 81.17, N = 12SE +/- 5.03, N = 390610061. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec2004006008001000Min: 193 / Avg: 906.08 / Max: 1082Min: 996 / Avg: 1006 / Max: 10121. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec200K400K600K800K1000KSE +/- 6782.33, N = 12SE +/- 8647.41, N = 32080008223331. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec140K280K420K560K700KMin: 140000 / Avg: 208000 / Max: 224000Min: 810000 / Avg: 822333.33 / Max: 8390001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec7001400210028003500SE +/- 26.57, N = 12SE +/- 34.59, N = 381332121. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec6001200180024003000Min: 547 / Avg: 813.08 / Max: 877Min: 3163 / Avg: 3212.33 / Max: 32791. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec200K400K600K800K1000KSE +/- 71344.93, N = 15SE +/- 13012.81, N = 34692478150001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec140K280K420K560K700KMin: 72700 / Avg: 469246.67 / Max: 821000Min: 801000 / Avg: 815000 / Max: 8410001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec7001400210028003500SE +/- 278.77, N = 15SE +/- 51.36, N = 3183331841. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.10.1Linux 5.11 18Dec6001200180024003000Min: 284 / Avg: 1832.67 / Max: 3209Min: 3130 / Avg: 3184.33 / Max: 32871. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

156 Results Shown

Stress-NG:
  System V Message Passing
  SENDFILE
Flexible IO Tester:
  Seq Read - IO_uring - No - No - 4KB - Default Test Directory:
    IOPS
    MB/s
  Seq Write - IO_uring - Yes - Yes - 4KB - Default Test Directory:
    MB/s
    IOPS
  Seq Write - IO_uring - No - No - 4KB - Default Test Directory:
    IOPS
    MB/s
Stress-NG
Compile Bench
PostgreSQL pgbench
Flexible IO Tester:
  Seq Read - IO_uring - Yes - No - 4KB - Default Test Directory:
    IOPS
    MB/s
Stress-NG:
  Forking
  NUMA
Mlpack Benchmark
PostgreSQL pgbench
Flexible IO Tester:
  Seq Read - IO_uring - Yes - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
NCNN
Flexible IO Tester:
  Rand Read - IO_uring - No - Yes - 4KB - Default Test Directory:
    MB/s
    IOPS
Stress-NG
NCNN
Flexible IO Tester:
  Seq Read - IO_uring - No - Yes - 4KB - Default Test Directory:
    MB/s
    IOPS
Timed MAFFT Alignment
simdjson
Apache CouchDB
NCNN:
  CPU - blazeface
  CPU - yolov4-tiny
Timed LLVM Compilation
InfluxDB
NAMD
OpenVINO
PyBench
NCNN
OpenVINO
NCNN
Stress-NG
InfluxDB
Stress-NG
PostgreSQL pgbench
Stress-NG
PostgreSQL pgbench
NCNN
PostgreSQL pgbench:
  1 - 50 - Read Write - Average Latency
  100 - 50 - Read Only
  1 - 1 - Read Write - Average Latency
NCNN
PostgreSQL pgbench
Numpy Benchmark
x265
OpenVKL
Compile Bench
PostgreSQL pgbench
LevelDB
Mlpack Benchmark
LevelDB:
  Rand Fill:
    MB/s
    Microseconds Per Op
Stress-NG
Timed GDB GNU Debugger Compilation
BRL-CAD
TNN
LevelDB
SQLite Speedtest
NCNN
OpenVINO
Build2
John The Ripper
KeyDB
NCNN
Stockfish
NCNN
TensorFlow Lite
Intel Open Image Denoise
Stress-NG
GROMACS
InfluxDB
Flexible IO Tester
Stress-NG
TensorFlow Lite
Node.js V8 Web Tooling Benchmark
Flexible IO Tester
TensorFlow Lite
Stress-NG
OpenVINO
SVT-AV1
NCNN
TensorFlow Lite
x265
OpenVKL
Mlpack Benchmark
LAMMPS Molecular Dynamics Simulator
TNN
TensorFlow Lite
Flexible IO Tester
C-Blosc
OpenVINO
Flexible IO Tester
OpenVINO
LevelDB
Stress-NG:
  Crypto
  Vector Math
  MEMFD
Flexible IO Tester
TensorFlow Lite
Flexible IO Tester
LevelDB:
  Overwrite
  Seek Rand
OpenVINO:
  Face Detection 0106 FP32 - CPU
  Face Detection 0106 FP16 - CPU
NCNN
Mlpack Benchmark
Timed Linux Kernel Compilation
LevelDB:
  Rand Read
  Fill Sync
Stress-NG
Flexible IO Tester
SVT-AV1
High Performance Conjugate Gradient
OpenVINO
LevelDB
John The Ripper
Compile Bench
Stress-NG
OpenVINO
Stress-NG
LevelDB
OpenVINO:
  Age Gender Recognition Retail 0013 FP32 - CPU
  Age Gender Recognition Retail 0013 FP16 - CPU
ctx_clock
NCNN:
  CPU - alexnet
  CPU - shufflenet-v2
PostgreSQL pgbench
Flexible IO Tester
LevelDB
PostgreSQL pgbench:
  100 - 50 - Read Write - Average Latency
  100 - 50 - Read Write
  100 - 1 - Read Write - Average Latency
  100 - 1 - Read Write
  1 - 1 - Read Only - Average Latency
  1 - 1 - Read Only
simdjson:
  DistinctUserID
  PartialTweets
  Kostya
Flexible IO Tester:
  Seq Write - IO_uring - No - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
  Rand Write - IO_uring - Yes - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
  Rand Write - IO_uring - Yes - No - 4KB - Default Test Directory:
    IOPS
    MB/s
  Rand Write - IO_uring - No - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
  Rand Write - IO_uring - No - No - 4KB - Default Test Directory:
    IOPS
    MB/s

Linux 5.10.1

Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3003 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 2000GB Corsair Force MP600 + 2000GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 20.04, Kernel: 5.10.1-051001-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 21.0.0-devel (git-e6a6620 2020-12-17 focal-oibaf-ppa) (LLVM 11.0.0), Vulkan: 1.2.145, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160

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=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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 / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa201009
Java Notes: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.04)
Python Notes: Python 2.7.18 + Python 3.8.5
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 18 December 2020 13:48 by user pts.

Linux 5.11 18Dec

Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3003 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 2000GB Corsair Force MP600 + 2000GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 20.04, Kernel: 5.10.0-051000daily20201218-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 21.0.0-devel (git-e6a6620 2020-12-17 focal-oibaf-ppa) (LLVM 11.0.0), Vulkan: 1.2.145, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160

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=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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 / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa201009
Python Notes: Python 2.7.18 + Python 3.8.5
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 18 December 2020 20:17 by user phoronix.