xeon-platinum-8380-2p-smoke-run

2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on Ubuntu 20.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2105012-IB-XEONPLATI04
Jump To Table - Results

View

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

Limit displaying results to tests within:

AV1 2 Tests
Timed Code Compilation 6 Tests
C/C++ Compiler Tests 6 Tests
CPU Massive 11 Tests
Creator Workloads 13 Tests
Cryptography 3 Tests
Encoding 4 Tests
Game Development 5 Tests
HPC - High Performance Computing 4 Tests
Imaging 2 Tests
Machine Learning 2 Tests
Molecular Dynamics 2 Tests
Multi-Core 16 Tests
NVIDIA GPU Compute 3 Tests
OpenMPI Tests 2 Tests
Programmer / Developer System Benchmarks 6 Tests
Python Tests 5 Tests
Renderers 2 Tests
Scientific Computing 2 Tests
Software Defined Radio 4 Tests
Server CPU Tests 11 Tests
Single-Threaded 3 Tests
Texture Compression 4 Tests
Video Encoding 4 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
r1
April 28 2021
  1 Day, 1 Minute
r1a
April 29 2021
  11 Hours, 50 Minutes
r2
April 29 2021
  1 Minute
r2a
April 29 2021
  1 Hour, 9 Minutes
r2b
April 29 2021
  18 Hours, 2 Minutes
r3
April 30 2021
  17 Hours, 57 Minutes
r4
April 30 2021
  17 Hours, 55 Minutes
r5
May 01 2021
  46 Minutes
Invert Hiding All Results Option
  11 Hours, 28 Minutes

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


xeon-platinum-8380-2p-smoke-run ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen Resolutionr1r1ar2r2ar2br3r4r52 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads)Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS)Intel Device 099816 x 32 GB DDR4-3200MT/s Hynix HMA84GR7CJR4N-XN2 x 7682GB INTEL SSDPF2KX076TZ + 2 x 800GB INTEL SSDPF21Q800GB + 3841GB Micron_9300_MTFDHAL3T8TDP + 960GB INTEL SSDSC2KG96ASPEEDVE2282 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFPUbuntu 20.045.11.0-051100-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8GCC 9.3.0ext41920x10801024x768OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/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 Processor Details- r1: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270- r1a: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270- r2: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270- r2a: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270- r2b: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270- r3: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270- r4: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270- r5: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270Python Details- Python 2.7.18 + Python 3.8.5Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

xeon-platinum-8380-2p-smoke-run hammerdb-mariadb: 128 - 250hammerdb-mariadb: 128 - 250hammerdb-mariadb: 128 - 500hammerdb-mariadb: 128 - 500hammerdb-mariadb: 64 - 250hammerdb-mariadb: 64 - 250hammerdb-mariadb: 32 - 250hammerdb-mariadb: 32 - 250hammerdb-mariadb: 16 - 500hammerdb-mariadb: 16 - 500hammerdb-mariadb: 32 - 500hammerdb-mariadb: 32 - 500mysqlslap: 256mysqlslap: 512mysqlslap: 128hammerdb-mariadb: 64 - 500hammerdb-mariadb: 64 - 500incompact3d: X3D-benchmarking input.i3dgnuradio: Hilbert Transformgnuradio: FM Deemphasis Filtergnuradio: IIR Filtergnuradio: FIR Filtergnuradio: Signal Source (Cosine)gnuradio: Five Back to Back FIR Filtersmysqlslap: 64aom-av1: Speed 4 Two-Pass - Bosphorus 4Kcp2k: Fayalite-FISThammerdb-mariadb: 16 - 250hammerdb-mariadb: 16 - 250luaradio: Complex Phaseluaradio: Hilbert Transformluaradio: FM Deemphasis Filterluaradio: Five Back to Back FIR Filtershammerdb-mariadb: 8 - 250hammerdb-mariadb: 8 - 250hammerdb-mariadb: 8 - 500hammerdb-mariadb: 8 - 500aom-av1: Speed 6 Two-Pass - Bosphorus 4Kmnn: inception-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224mnn: resnet-v2-50mnn: SqueezeNetV1.0mysqlslap: 1securemark: SecureMark-TLSaom-av1: Speed 0 Two-Pass - Bosphorus 4Kmysqlslap: 32build-llvm: Unix Makefilesaom-av1: Speed 4 Two-Pass - Bosphorus 1080pluxcorerender: Orange Juice - CPUmysqlslap: 16build-erlang: Time To Compileluxcorerender: DLSC - CPUintel-mlc: Max Bandwidth - Stream-Triad Likeintel-mlc: Max Bandwidth - 1:1 Reads-Writesintel-mlc: Max Bandwidth - 2:1 Reads-Writesintel-mlc: Max Bandwidth - 3:1 Reads-Writesintel-mlc: Max Bandwidth - All Readsmysqlslap: 8build-llvm: Ninjaaom-av1: Speed 6 Realtime - Bosphorus 4Konednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUmysqlslap: 4aom-av1: Speed 8 Realtime - Bosphorus 4Kgmpbench: Total Timeblender: Barbershop - CPU-Onlybuild-nodejs: Time To Compileviennacl: CPU BLAS - dGEMM-TTviennacl: CPU BLAS - dGEMM-TNviennacl: CPU BLAS - dGEMM-NTviennacl: CPU BLAS - dGEMM-NNviennacl: CPU BLAS - dGEMV-Tviennacl: CPU BLAS - dGEMV-Nviennacl: CPU BLAS - dDOTviennacl: CPU BLAS - dAXPYviennacl: CPU BLAS - dCOPYviennacl: CPU BLAS - sDOTviennacl: CPU BLAS - sAXPYviennacl: CPU BLAS - sCOPYxmrig: Monero - 1Maom-av1: Speed 6 Two-Pass - Bosphorus 1080pbuild-linux-kernel: Time To Compilesysbench: CPUblender: Pabellon Barcelona - CPU-Onlybuild-wasmer: Time To Compileonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUaom-av1: Speed 9 Realtime - Bosphorus 4Kblender: Classroom - CPU-Onlytoktx: UASTC 4 + Zstd Compression 19onednn: Deconvolution Batch shapes_1d - f32 - CPUluxcorerender: Danish Mood - CPUluxcorerender: LuxCore Benchmark - CPUavifenc: 0aom-av1: Speed 0 Two-Pass - Bosphorus 1080pluxcorerender: Rainbow Colors and Prism - CPUaom-av1: Speed 6 Realtime - Bosphorus 1080pblender: Fishy Cat - CPU-Onlyonednn: IP Shapes 1D - bf16bf16bf16 - CPUvosk: stockfish: Total Timeavifenc: 6, Losslesssrslte: PHY_DL_Testsrslte: PHY_DL_Testavifenc: 6srslte: OFDM_Testsysbench: RAM / Memoryavifenc: 2botan: AES-256 - Decryptbotan: AES-256basis: ETC1Sbasis: UASTC Level 0avifenc: 10, Losslessaom-av1: Speed 9 Realtime - Bosphorus 1080pblender: BMW27 - CPU-Onlybotan: ChaCha20Poly1305 - Decryptbotan: ChaCha20Poly1305botan: Blowfish - Decryptbotan: Blowfishbotan: Twofish - Decryptbotan: Twofishbotan: CAST-256 - Decryptbotan: CAST-256botan: KASUMI - Decryptbotan: KASUMItoybrot: TBBxmrig: Wownero - 1Mintel-mlc: Peak Injection Bandwidth - Stream-Triad Likeintel-mlc: Peak Injection Bandwidth - 1:1 Reads-Writesintel-mlc: Peak Injection Bandwidth - 2:1 Reads-Writesintel-mlc: Peak Injection Bandwidth - 3:1 Reads-Writesintel-mlc: Peak Injection Bandwidth - All Readsonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUhelsing: 14 digittjbench: Decompression Throughputastcenc: Thoroughastcenc: Exhaustiveavifenc: 10astcenc: Mediumbuild-mesa: Time To Compileonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUsvt-hevc: 1 - Bosphorus 1080paom-av1: Speed 8 Realtime - Bosphorus 1080pliquid-dsp: 160 - 256 - 57liquid-dsp: 128 - 256 - 57liquid-dsp: 64 - 256 - 57liquid-dsp: 32 - 256 - 57liquid-dsp: 16 - 256 - 57liquid-dsp: 8 - 256 - 57liquid-dsp: 4 - 256 - 57liquid-dsp: 2 - 256 - 57liquid-dsp: 1 - 256 - 57toktx: Zstd Compression 19basis: UASTC Level 3onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUsvt-vp9: VMAF Optimized - Bosphorus 1080ptoktx: UASTC 3onednn: IP Shapes 3D - f32 - CPUintel-mlc: Idle Latencyonednn: IP Shapes 1D - f32 - CPUbasis: UASTC Level 2incompact3d: input.i3d 193 Cells Per Directiontoktx: UASTC 3 + Zstd Compression 19onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUincompact3d: input.i3d 129 Cells Per Directiontoktx: Zstd Compression 9onednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUtoybrot: C++ Tasksdraco: Church Facadeonednn: IP Shapes 3D - bf16bf16bf16 - CPUdraco: Liontoybrot: OpenMPtoybrot: C++ Threadssvt-vp9: Visual Quality Optimized - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080ponednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUsvt-hevc: 10 - Bosphorus 1080psvt-hevc: 7 - Bosphorus 1080pr1r1ar2r2ar2br3r4r516780955415173288571901913976327920925469054195258644772084196881819468464298313.920451459.3734.0610.6603.02183.51024.319291363757546.880.3410.01094.829008295768285984943797.37225412216.32314.36114.5509.70325766.94439496.74459455.38426148.96357285.28145.71715.09804.39229.204642.1101.10176.376.075.673.571972.372010588436201003183419299.524.38262.160801.409792.8311.21594447.971445.144445.51933.077.494677.427.8457.97517.042.9613535.91818164481932.11376.9183.413.24712030000031.5395663.0555669.7008.852619.458623.494363.255363.038292.736289.126116.074115.97274.32077.287685048051.5324377.2442422.3459038.6425933.7356476.20.3383270.21511577.872161.6346195.47720.9523.530260.39828236.913144800000341593333332671333331735100000885320000441953333217643333110713333577920000.239989386.291.2480935.10.91856811.35860220.2109190.5930422.743709963.572470.86416478791.8004673187018327.87401.291.109910.8778152.07944499.23290.671732285724218876162311311.960785459.1727.4609.5604.82175.31015.24.17548.280.3409.61094.57.552253660.19215.7606.8914.26113.8009.61325184.58441408.09456629.89424612.62358364.56145.55015.19793.36328.994642.8100.44677.277.476.872.331963.637139233527737050419452.021.2524.36061.930804.323791.9271.22278447.308446.936447.43632.517.500597.558.0457.7100.5113.3428.662.9685735.00918626355231.62477.3184.213.32812013333331.4795663.6125670.8098.812125.25619.538623.198363.326363.615292.374288.852116.069115.97074.28877.310696450166.1323924.2442843.2456260.3424096.6358385.50.3416630.21364378.159156.9690165.50520.3793.543670.39558837.34103.9231620666673352733333326370000017368000008902733330.240122393.461.2526733.00.91227911.27271140.2107280.5956612.738590963.576620.86321477241.7988173086980329.53408.241.122240.8791372.08532493.51288.9967.51374.663325260.41442460.05456545.88424818.83358456.09323826.9442144.2456408.6424077.3358269.732.5160166192307.622108357.4645.8498.2470.01684.4111.24032.01458.778.2370.1804.53.2253.0733.2134.07848.7327.17433362253430.14885226.4403.3014.281264191.7469.27325409.99441732.77459226.53425997.22357774.431413148.4845.97791.695161412.034524.5110.02110.93054.762.359.861.9389.962.3447.65507.1422.234947469119311.17.4527.997214210.8388.5771.928808.289789.8361.23796446.389447.287447.70114.3071.7856.66028.40235.735.8464.9710.3213.4210.3946.383.0046436.42418155421838.39575.0181.616.06512073333312510.5638.3725662.7635606.96734.23711.25110.28243.2629.56612.438615.806363.196362.926292.396288.562116.080114.66374.27576.286698449908.3324209.8440454.7459309.8425925.6357742.90.3418930.21680678.33160.2625599.290716.36216.6567.188721.5753.531210.40340927.8036.2031318666673400066667322743333316993333338628900004281000002132033331101733335623033319.78117.1630.243026182.265.6641.253130.94362413.97911.561715810.0110.2103240.6021223.022819923.4703.642320.874080805070011.81774612674127149164.32182.171.118740.8699782.11712234.51158.16189386.390001408.0621.0487.4502.01723.9580.54042.05458.278.2370.3662.83.2034582252910.15887226.1993.3613.891262192.2459.24325218.50440939.22457141.24424925.84358268.001420147.1635.97793.916158011.944504.5111.79061.766.968.966.464764.3713.471024.2913532862113520652.97.3828.01871.130796.689793.0801.24508450.648447.144446.91714.0628.18155.655.9265.9600.3316.4710.393.0092935.58118921449938.59076.1181.616.61512083333338.3135662.3425593.36610.08843.42612.149616.501363.314359.452292.827286.180115.723114.51774.30976.407700349813.4324227.4449554.1457190.5424904.5358463.70.3419550.21658678.079159.1870386.59721.3693.562240.40687728.2236.063143300000341100000032327000001704500000865410000432170000215343333111510000571976670.243308185.531.2417667.60.93694114.59829650.2183490.6023143.565927743.640330.87496880481.8433974397203164.51181.521.145780.9018232.10841234.39157.83389.698280373.8622.0487.7515.61619.2487.92.10452.778.4368.0706.13.2352.2273.3624.10048.0417.1702227470.14224.2903.3613.94193.8399.25325314.62440315.41458790.96425848.09357925.98146.9096.00811.94112.104525.7109.96111.67363.767.672.470.864770.27651158936535855116720574.67.4328.094214241.3488.6870.758792.296792.0491.24116446.536448.906447.95814.7372.2956.77028.46135.685.8765.8880.3314.7910.5446.733.0090735.50318601326138.50778.3183.716.21112066666712553.4437.7965650.1395611.99534.42011.22610.20842.3729.69615.975619.638363.279359.573292.610286.004116.070114.64674.29276.403701649937.3324112.8446396.0458941.9425822.1358110.50.3402430.21508578.539159.2377529.309116.37296.7467.147221.3133.547830.40291928.0136.3531402666673398800000324566666716975000008600466674320133332167733331094300005525166720.08217.1850.242450184.075.5621.2422267.80.94071414.15914.657748910.0290.2179410.6020383.572781533.6973.643190.876227803770821.81913617074297141162.21179.131.118110.8754212.10837233.96156.26325312.30440205.22458756.46425467.51357550.82324234.5448800.1458830.6425508.1357722.768.1OpenBenchmarking.org

HammerDB - MariaDB

This is a MariaDB MySQL database server benchmark making use of the HammerDB benchmarking / load testing tool. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 128 - Warehouses: 250r140K80K120K160K200KSE +/- 2616.54, N = 91678091. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgNew Orders Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 128 - Warehouses: 250r112K24K36K48K60KSE +/- 857.30, N = 9554151. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgTransactions Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 128 - Warehouses: 500r1ar140K80K120K160K200KSE +/- 1389.03, N = 9SE +/- 2691.06, N = 91732281732881. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgNew Orders Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 128 - Warehouses: 500r1r1a12K24K36K48K60KSE +/- 891.59, N = 9SE +/- 484.29, N = 957190572421. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgTransactions Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 64 - Warehouses: 250r140K80K120K160K200KSE +/- 2831.11, N = 91913971. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgNew Orders Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 64 - Warehouses: 250r114K28K42K56K70KSE +/- 937.55, N = 9632791. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgTransactions Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 32 - Warehouses: 250r140K80K120K160K200KSE +/- 3390.81, N = 92092541. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgNew Orders Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 32 - Warehouses: 250r115K30K45K60K75KSE +/- 1078.76, N = 9690541. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgTransactions Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 16 - Warehouses: 500r140K80K120K160K200KSE +/- 3159.46, N = 91952581. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgNew Orders Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 16 - Warehouses: 500r114K28K42K56K70KSE +/- 1031.07, N = 9644771. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgTransactions Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 32 - Warehouses: 500r140K80K120K160K200KSE +/- 2885.40, N = 92084191. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgNew Orders Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 32 - Warehouses: 500r115K30K45K60K75KSE +/- 921.11, N = 9688181. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 256r2b4080120160200SE +/- 0.22, N = 31601. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 512r2b4080120160200SE +/- 0.87, N = 31661. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 128r3r2b4080120160200SE +/- 0.35, N = 3SE +/- 0.65, N = 31891921. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lsnappy -ldl -lz -lrt

HammerDB - MariaDB

This is a MariaDB MySQL database server benchmark making use of the HammerDB benchmarking / load testing tool. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 64 - Warehouses: 500r1ar140K80K120K160K200KSE +/- 2084.32, N = 9SE +/- 2149.33, N = 31887611946841. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgNew Orders Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 64 - Warehouses: 500r1ar114K28K42K56K70KSE +/- 730.55, N = 9SE +/- 620.04, N = 362311642981. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dr4r3r1r1ar2b80160240320400SE +/- 3.91, N = 9SE +/- 4.39, N = 9SE +/- 0.46, N = 3SE +/- 0.12, N = 3SE +/- 2.73, N = 9389.70386.39313.92311.96307.621. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

GNU Radio

GNU Radio is a free software development toolkit providing signal processing blocks to implement software-defined radios (SDR) and signal processing systems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Hilbert Transformr2br4r3r1ar1100200300400500SE +/- 47.90, N = 3SE +/- 24.71, N = 9SE +/- 17.46, N = 9SE +/- 1.66, N = 3SE +/- 2.02, N = 3357.4373.8408.0459.1459.31. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FM Deemphasis Filterr3r4r2br1ar1160320480640800SE +/- 31.57, N = 9SE +/- 32.02, N = 9SE +/- 53.33, N = 3SE +/- 1.04, N = 3SE +/- 1.94, N = 3621.0622.0645.8727.4734.01. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: IIR Filterr3r4r2br1ar1130260390520650SE +/- 26.49, N = 9SE +/- 25.67, N = 9SE +/- 45.07, N = 3SE +/- 0.46, N = 3SE +/- 0.38, N = 3487.4487.7498.2609.5610.61. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FIR Filterr2br3r4r1r1a130260390520650SE +/- 44.41, N = 3SE +/- 16.19, N = 9SE +/- 11.25, N = 9SE +/- 1.45, N = 3SE +/- 0.20, N = 3470.0502.0515.6603.0604.81. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Signal Source (Cosine)r4r2br3r1ar15001000150020002500SE +/- 82.03, N = 9SE +/- 168.17, N = 3SE +/- 72.44, N = 9SE +/- 2.24, N = 3SE +/- 0.93, N = 31619.21684.41723.92175.32183.51. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Five Back to Back FIR Filtersr2br4r3r1ar12004006008001000SE +/- 1.12, N = 3SE +/- 48.36, N = 9SE +/- 39.63, N = 9SE +/- 2.30, N = 3SE +/- 2.54, N = 3111.2487.9580.51015.21024.31. 3.8.1.0

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 64r2br390180270360450SE +/- 0.62, N = 3SE +/- 0.16, N = 34034041. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lsnappy -ldl -lz -lrt

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4Kr2br3r4r1a0.93831.87662.81493.75324.6915SE +/- 0.03, N = 3SE +/- 0.02, N = 9SE +/- 0.01, N = 3SE +/- 0.03, N = 32.012.052.104.171. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

CP2K Molecular Dynamics

CP2K is an open-source molecular dynamics software package focused on quantum chemistry and solid-state physics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 8.1Input: Fayalite-FISTr2a300600900120015001374.66

HammerDB - MariaDB

This is a MariaDB MySQL database server benchmark making use of the HammerDB benchmarking / load testing tool. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 16 - Warehouses: 250r140K80K120K160K200KSE +/- 2649.02, N = 31929131. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgNew Orders Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 16 - Warehouses: 250r114K28K42K56K70KSE +/- 880.35, N = 3637571. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

LuaRadio

LuaRadio is a lightweight software-defined radio (SDR) framework built atop LuaJIT. LuaRadio provides a suite of source, sink, and processing blocks, with a simple API for defining flow graphs, running flow graphs, creating blocks, and creating data types. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Complex Phaser4r3r2br1r1a120240360480600SE +/- 4.50, N = 6SE +/- 4.31, N = 6SE +/- 3.61, N = 9SE +/- 0.25, N = 3SE +/- 0.71, N = 3452.7458.2458.7546.8548.2

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Hilbert Transformr2br3r4r1r1a20406080100SE +/- 0.41, N = 9SE +/- 0.47, N = 6SE +/- 0.61, N = 6SE +/- 0.00, N = 3SE +/- 0.00, N = 378.278.278.480.380.3

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: FM Deemphasis Filterr4r2br3r1ar190180270360450SE +/- 1.19, N = 6SE +/- 5.30, N = 9SE +/- 4.83, N = 6SE +/- 1.40, N = 3SE +/- 0.21, N = 3368.0370.1370.3409.6410.0

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Five Back to Back FIR Filtersr3r4r2br1ar12004006008001000SE +/- 74.31, N = 6SE +/- 73.21, N = 6SE +/- 22.87, N = 9SE +/- 0.62, N = 3SE +/- 2.24, N = 3662.8706.1804.51094.51094.8

HammerDB - MariaDB

This is a MariaDB MySQL database server benchmark making use of the HammerDB benchmarking / load testing tool. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 8 - Warehouses: 250r160K120K180K240K300KSE +/- 2006.72, N = 32900821. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgNew Orders Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 8 - Warehouses: 250r120K40K60K80K100KSE +/- 675.05, N = 3957681. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgTransactions Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 8 - Warehouses: 500r160K120K180K240K300KSE +/- 2338.98, N = 32859841. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

OpenBenchmarking.orgNew Orders Per Minute, More Is BetterHammerDB - MariaDB 10.5.9Virtual Users: 8 - Warehouses: 500r120K40K60K80K100KSE +/- 693.36, N = 3943791. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lbz2 -lsnappy -ldl -lz -lrt

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4Kr3r2br4r1r1a246810SE +/- 0.04, N = 3SE +/- 0.03, N = 9SE +/- 0.03, N = 5SE +/- 0.09, N = 15SE +/- 0.06, N = 33.203.223.237.377.551. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Mobile Neural Network

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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: inception-v3r2br41224364860SE +/- 1.54, N = 3SE +/- 0.75, N = 1253.0752.23MIN: 49.59 / MAX: 69.62MIN: 47.47 / MAX: 94.691. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: mobilenet-v1-1.0r4r2b0.75651.5132.26953.0263.7825SE +/- 0.021, N = 12SE +/- 0.089, N = 33.3623.213MIN: 2.98 / MAX: 6.66MIN: 2.8 / MAX: 6.71. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: MobileNetV2_224r4r2b0.92251.8452.76753.694.6125SE +/- 0.135, N = 12SE +/- 0.333, N = 34.1004.078MIN: 2.97 / MAX: 12.98MIN: 2.9 / MAX: 13.171. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: resnet-v2-50r2br41122334455SE +/- 2.59, N = 3SE +/- 1.07, N = 1248.7348.04MIN: 43.19 / MAX: 69.59MIN: 42.13 / MAX: 145.21. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: SqueezeNetV1.0r2br4246810SE +/- 0.002, N = 3SE +/- 0.078, N = 127.1747.170MIN: 6.95 / MAX: 7.88MIN: 6.38 / MAX: 9.971. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 1r2br37001400210028003500SE +/- 73.97, N = 15SE +/- 61.33, N = 12333634581. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lsnappy -ldl -lz -lrt

SecureMark

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

OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSr4r3r2br1ar150K100K150K200K250KSE +/- 2769.20, N = 3SE +/- 267.95, N = 3SE +/- 84.15, N = 3SE +/- 236.12, N = 3SE +/- 234.37, N = 32227472252912253432253662254121. (CC) gcc options: -pedantic -O3

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4Kr2br4r3r1a0.04280.08560.12840.17120.214SE +/- 0.00, N = 12SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 50.140.140.150.191. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 32r2br32004006008001000SE +/- 0.26, N = 3SE +/- 1.83, N = 38858871. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lsnappy -ldl -lz -lrt

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Unix Makefilesr2br3r4r1r1a50100150200250SE +/- 0.77, N = 3SE +/- 1.24, N = 3SE +/- 0.43, N = 3SE +/- 0.91, N = 3SE +/- 0.80, N = 3226.44226.20224.29216.32215.76

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080pr2br3r4r1a246810SE +/- 0.03, N = 3SE +/- 0.04, N = 5SE +/- 0.01, N = 3SE +/- 0.02, N = 33.303.363.366.891. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: CPUr3r4r1ar2br148121620SE +/- 0.12, N = 15SE +/- 0.13, N = 15SE +/- 0.21, N = 3SE +/- 0.18, N = 3SE +/- 0.13, N = 313.8913.9414.2614.2814.36MIN: 11.08 / MAX: 17.77MIN: 11.06 / MAX: 17.84MIN: 11.6 / MAX: 19.3MIN: 11.93 / MAX: 17.73MIN: 11.58 / MAX: 19.44

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 16r3r2b30060090012001500SE +/- 3.49, N = 3SE +/- 1.85, N = 3126212641. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lsnappy -ldl -lz -lrt

Timed Erlang/OTP Compilation

This test times how long it takes to compile Erlang/OTP. Erlang is a programming language and run-time for massively scalable soft real-time systems with high availability requirements. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Erlang/OTP Compilation 23.2Time To Compiler4r3r2br1r1a4080120160200SE +/- 1.56, N = 3SE +/- 0.31, N = 3SE +/- 1.08, N = 3SE +/- 0.18, N = 3SE +/- 0.37, N = 3193.84192.25191.75114.55113.80

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: CPUr3r4r2br1ar13691215SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 15SE +/- 0.09, N = 15SE +/- 0.09, N = 39.249.259.279.619.70MIN: 8.74 / MAX: 11.37MIN: 8.59 / MAX: 11.4MIN: 8.31 / MAX: 11.98MIN: 8 / MAX: 12.27MIN: 8.98 / MAX: 12.22

Intel Memory Latency Checker

Intel Memory Latency Checker (MLC) is a binary-only system memory bandwidth and latency benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - Stream-Triad Liker1ar3r2ar5r4r2br170K140K210K280K350KSE +/- 11.61, N = 3SE +/- 50.80, N = 3SE +/- 53.08, N = 3SE +/- 22.58, N = 3SE +/- 7.71, N = 3SE +/- 50.20, N = 3SE +/- 25.05, N = 3325184.58325218.50325260.41325312.30325314.62325409.99325766.94

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - 1:1 Reads-Writesr1r5r4r3r1ar2br2a90K180K270K360K450KSE +/- 821.19, N = 3SE +/- 1051.98, N = 3SE +/- 2322.32, N = 3SE +/- 276.68, N = 3SE +/- 1093.30, N = 3SE +/- 3117.58, N = 3SE +/- 1844.14, N = 3439496.74440205.22440315.41440939.22441408.09441732.77442460.05

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - 2:1 Reads-Writesr2ar1ar3r5r4r2br1100K200K300K400K500KSE +/- 54.98, N = 3SE +/- 129.26, N = 3SE +/- 89.89, N = 3SE +/- 53.22, N = 3SE +/- 8.60, N = 3SE +/- 51.02, N = 3SE +/- 33.49, N = 3456545.88456629.89457141.24458756.46458790.96459226.53459455.38

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - 3:1 Reads-Writesr1ar2ar3r5r4r2br190K180K270K360K450KSE +/- 465.24, N = 3SE +/- 392.90, N = 3SE +/- 109.66, N = 3SE +/- 133.64, N = 3SE +/- 67.02, N = 3SE +/- 71.38, N = 3SE +/- 105.41, N = 3424612.62424818.83424925.84425467.51425848.09425997.22426148.96

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Max Bandwidth - All Readsr1r5r2br4r3r1ar2a80K160K240K320K400KSE +/- 67.01, N = 3SE +/- 46.23, N = 3SE +/- 83.63, N = 3SE +/- 83.70, N = 3SE +/- 59.61, N = 3SE +/- 142.76, N = 3SE +/- 107.35, N = 3357285.28357550.82357774.43357925.98358268.00358364.56358456.09

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 8r2br330060090012001500SE +/- 10.97, N = 3SE +/- 3.56, N = 3141314201. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lsnappy -ldl -lz -lrt

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Ninjar2br3r4r1r1a306090120150SE +/- 1.12, N = 3SE +/- 0.32, N = 3SE +/- 0.56, N = 3SE +/- 0.52, N = 3SE +/- 0.75, N = 3148.48147.16146.91145.72145.55

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4Kr2br3r4r1r1a48121620SE +/- 0.06, N = 3SE +/- 0.07, N = 12SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 35.975.976.0015.0915.191. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUr4r1r3r1ar2b2004006008001000SE +/- 16.86, N = 14SE +/- 7.01, N = 3SE +/- 0.83, N = 3SE +/- 1.56, N = 3SE +/- 0.61, N = 3811.94804.39793.92793.36791.70MIN: 761.61MIN: 763.49MIN: 769MIN: 765.14MIN: 769.611. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 4r3r2b30060090012001500SE +/- 7.20, N = 3SE +/- 16.07, N = 3158016141. (CXX) g++ options: -fPIC -pie -fstack-protector -O2 -shared -lpthread -lsnappy -ldl -lz -lrt

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4Kr3r2br4r1ar1714212835SE +/- 0.12, N = 15SE +/- 0.08, N = 15SE +/- 0.17, N = 3SE +/- 0.29, N = 5SE +/- 0.19, N = 311.9412.0312.1028.9929.201. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

GNU GMP GMPbench

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

OpenBenchmarking.orgGMPbench Score, More Is BetterGNU GMP GMPbench 6.2.1Total Timer3r2br4r1r1a100020003000400050004504.54524.54525.74642.14642.81. (CC) gcc options: -O3 -fomit-frame-pointer -lm

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-Onlyr2br420406080100SE +/- 0.18, N = 3SE +/- 0.59, N = 3110.02109.96

Timed Node.js Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To Compiler3r4r2br1r1a306090120150SE +/- 0.68, N = 3SE +/- 0.78, N = 3SE +/- 0.50, N = 3SE +/- 0.27, N = 3SE +/- 0.29, N = 3111.79111.67110.93101.10100.45

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TTr2br3r4r1r1a20406080100SE +/- 1.75, N = 15SE +/- 2.33, N = 15SE +/- 2.94, N = 15SE +/- 1.45, N = 13SE +/- 0.90, N = 354.761.763.776.377.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TNr2br3r4r1r1a20406080100SE +/- 2.02, N = 15SE +/- 1.88, N = 15SE +/- 2.43, N = 14SE +/- 1.67, N = 13SE +/- 0.69, N = 362.366.967.676.077.41. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NTr2br3r4r1r1a20406080100SE +/- 1.14, N = 15SE +/- 1.99, N = 15SE +/- 1.98, N = 15SE +/- 1.88, N = 13SE +/- 1.01, N = 359.868.972.475.676.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NNr2br3r4r1ar11632486480SE +/- 2.06, N = 15SE +/- 2.18, N = 15SE +/- 1.95, N = 15SE +/- 3.11, N = 3SE +/- 1.42, N = 1461.966.470.872.373.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-Tr1ar2br3r4r1160320480640800SE +/- 5.04, N = 3SE +/- 27.49, N = 15SE +/- 2.02, N = 15SE +/- 3.20, N = 15SE +/- 2.46, N = 13319.0389.9647.0647.0719.01. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-Nr2br1ar3r4r11632486480SE +/- 3.75, N = 15SE +/- 2.90, N = 3SE +/- 3.93, N = 15SE +/- 0.25, N = 15SE +/- 0.36, N = 1462.363.664.370.272.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOTr1ar2br3r1r4160320480640800SE +/- 34.44, N = 3SE +/- 34.40, N = 14SE +/- 50.57, N = 15SE +/- 6.43, N = 14SE +/- 2.76, N = 15371.00447.65713.47720.00765.001. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPYr1ar2br3r1r42004006008001000SE +/- 23.02, N = 3SE +/- 40.80, N = 15SE +/- 82.34, N = 15SE +/- 20.63, N = 14SE +/- 5.62, N = 15392.0507.11024.21058.01158.01. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPYr1ar2br1r3r42004006008001000SE +/- 29.90, N = 3SE +/- 35.11, N = 15SE +/- 25.47, N = 14SE +/- 26.97, N = 15SE +/- 9.73, N = 15335.0422.2843.0913.0936.01. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOTr1ar2br3r4r1130260390520650SE +/- 11.67, N = 3SE +/- 5.60, N = 15SE +/- 2.55, N = 15SE +/- 2.45, N = 15SE +/- 2.34, N = 142773495325356201. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPYr1ar2br4r3r12004006008001000SE +/- 15.25, N = 3SE +/- 10.36, N = 15SE +/- 11.35, N = 15SE +/- 8.11, N = 15SE +/- 6.62, N = 1437047485586210031. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPYr1ar2br3r4r1400800120016002000SE +/- 4.10, N = 3SE +/- 22.07, N = 15SE +/- 51.32, N = 15SE +/- 54.62, N = 15SE +/- 16.63, N = 145046911135116718341. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1Mr1r2br1ar4r34K8K12K16K20KSE +/- 23.28, N = 3SE +/- 151.73, N = 3SE +/- 20.55, N = 3SE +/- 243.31, N = 15SE +/- 245.77, N = 319299.519311.119452.020574.620652.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080pr3r4r2br1a510152025SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.17, N = 37.387.437.4521.251. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Timed Linux Kernel Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To Compiler4r3r2br1r1a714212835SE +/- 0.37, N = 14SE +/- 0.41, N = 14SE +/- 0.32, N = 14SE +/- 0.30, N = 4SE +/- 0.28, N = 428.0928.0228.0024.3824.36

Sysbench

This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPUr2br450K100K150K200K250KSE +/- 247.29, N = 3SE +/- 269.51, N = 3214210.83214241.341. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CPU-Onlyr4r2b20406080100SE +/- 0.28, N = 3SE +/- 0.08, N = 388.6888.57

Timed Wasmer Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 1.0.2Time To Compiler2br3r4r1r1a1632486480SE +/- 0.42, N = 3SE +/- 0.66, N = 7SE +/- 0.51, N = 3SE +/- 0.22, N = 3SE +/- 0.62, N = 371.9371.1370.7662.1661.931. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUr2br1ar1r3r42004006008001000SE +/- 9.76, N = 3SE +/- 4.49, N = 3SE +/- 7.46, N = 3SE +/- 1.09, N = 3SE +/- 2.67, N = 3808.29804.32801.41796.69792.30MIN: 767.97MIN: 765.37MIN: 767.38MIN: 771.28MIN: 763.961. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUr3r1r4r1ar2b2004006008001000SE +/- 2.18, N = 3SE +/- 2.07, N = 3SE +/- 1.96, N = 3SE +/- 3.65, N = 3SE +/- 1.48, N = 3793.08792.83792.05791.93789.84MIN: 768.2MIN: 763.76MIN: 765.9MIN: 765.01MIN: 767.031. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUr3r4r2br1ar10.28010.56020.84031.12041.4005SE +/- 0.01066, N = 15SE +/- 0.00891, N = 15SE +/- 0.01174, N = 15SE +/- 0.01126, N = 15SE +/- 0.01080, N = 151.245081.241161.237961.222781.21594MIN: 0.89MIN: 0.85MIN: 0.87MIN: 0.85MIN: 0.841. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUr3r1r1ar4r2b100200300400500SE +/- 2.40, N = 3SE +/- 0.58, N = 3SE +/- 0.90, N = 3SE +/- 1.10, N = 3SE +/- 0.78, N = 3450.65447.97447.31446.54446.39MIN: 432.96MIN: 433.22MIN: 432.33MIN: 429.71MIN: 432.041. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUr4r2br3r1ar1100200300400500SE +/- 3.51, N = 3SE +/- 0.65, N = 3SE +/- 1.24, N = 3SE +/- 1.79, N = 3SE +/- 0.58, N = 3448.91447.29447.14446.94445.14MIN: 431.33MIN: 433.06MIN: 432.42MIN: 430.47MIN: 431.521. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUr4r2br1ar3r1100200300400500SE +/- 2.63, N = 3SE +/- 1.13, N = 3SE +/- 2.18, N = 3SE +/- 0.04, N = 3SE +/- 0.85, N = 3447.96447.70447.44446.92445.52MIN: 429.99MIN: 433.04MIN: 429.4MIN: 433.64MIN: 431.181. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4Kr3r2br4r1ar1816243240SE +/- 0.18, N = 4SE +/- 0.15, N = 15SE +/- 0.08, N = 3SE +/- 0.28, N = 3SE +/- 0.28, N = 314.0614.3014.7332.5133.071. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-Onlyr4r2b1632486480SE +/- 0.13, N = 3SE +/- 0.08, N = 372.2971.78

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 4 + Zstd Compression 19r4r2b1326395265SE +/- 0.74, N = 3SE +/- 0.68, N = 456.7756.66

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUr4r2br3r1ar1714212835SE +/- 0.38629, N = 12SE +/- 0.31773, N = 13SE +/- 0.30585, N = 15SE +/- 0.01835, N = 3SE +/- 0.02080, N = 328.4613028.4023028.181507.500597.49467MIN: 14.76MIN: 14.66MIN: 14.34MIN: 6.91MIN: 6.981. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: CPUr3r4r2br1r1a246810SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 35.655.685.737.427.55MIN: 1.24 / MAX: 7.63MIN: 1.26 / MAX: 7.6MIN: 1.3 / MAX: 7.65MIN: 3.2 / MAX: 8.74MIN: 3.28 / MAX: 8.86

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: CPUr2br4r3r1r1a246810SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 35.845.875.927.848.04MIN: 1.16 / MAX: 7.97MIN: 1.15 / MAX: 7.95MIN: 1.15 / MAX: 7.98MIN: 3.44 / MAX: 9.2MIN: 3.51 / MAX: 9.33

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 0r3r4r2br1r1a1530456075SE +/- 0.20, N = 3SE +/- 0.68, N = 3SE +/- 0.22, N = 3SE +/- 0.21, N = 3SE +/- 0.24, N = 365.9665.8964.9757.9857.711. (CXX) g++ options: -O3 -fPIC -lm

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080pr2br3r4r1a0.11480.22960.34440.45920.574SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.320.330.330.511. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: CPUr1ar2br4r3r148121620SE +/- 0.47, N = 15SE +/- 0.87, N = 13SE +/- 0.79, N = 12SE +/- 1.13, N = 12SE +/- 1.05, N = 1513.3413.4214.7916.4717.04MIN: 10.32 / MAX: 17.45MIN: 8.28 / MAX: 21.15MIN: 9.85 / MAX: 20.95MIN: 10.39 / MAX: 21.43MIN: 11.27 / MAX: 22.05

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080pr2br3r4r1a714212835SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 310.3910.3910.5428.661. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CPU-Onlyr4r2b1122334455SE +/- 0.25, N = 3SE +/- 0.15, N = 346.7346.38

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUr3r4r2br1ar10.67711.35422.03132.70843.3855SE +/- 0.02478, N = 14SE +/- 0.02449, N = 14SE +/- 0.02287, N = 13SE +/- 0.00276, N = 3SE +/- 0.00128, N = 33.009293.009073.004642.968572.96135MIN: 2.84MIN: 2.84MIN: 2.84MIN: 2.84MIN: 2.841. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

VOSK Speech Recognition Toolkit

VOSK is an open-source offline speech recognition API/toolkit. VOSK supports speech recognition in 17 languages and has a variety of models available and interfaces for different programming languages. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterVOSK Speech Recognition Toolkit 0.3.21r2br1r3r4r1a816243240SE +/- 0.43, N = 3SE +/- 0.32, N = 3SE +/- 0.43, N = 3SE +/- 0.32, N = 3SE +/- 0.29, N = 836.4235.9235.5835.5035.01

Stockfish

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

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total Timer2br1r4r1ar340M80M120M160M200MSE +/- 1982639.48, N = 3SE +/- 1585265.68, N = 15SE +/- 2183262.34, N = 4SE +/- 2404481.41, N = 3SE +/- 1924842.52, N = 31815542181816448191860132611862635521892144991. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6, Losslessr3r4r2br1r1a918273645SE +/- 0.35, N = 3SE +/- 0.36, N = 6SE +/- 0.24, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 338.5938.5138.4032.1131.621. (CXX) g++ options: -O3 -fPIC -lm

srsLTE

srsLTE is an open-source LTE software radio suite created by Software Radio Systems (SRS). srsLTE can be used for building your own software defined (SDR) LTE mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgUE Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_Testr2br3r1r1ar420406080100SE +/- 0.38, N = 3SE +/- 1.14, N = 3SE +/- 0.76, N = 3SE +/- 1.16, N = 3SE +/- 0.62, N = 375.076.176.977.378.31. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_Testr2br3r1r4r1a4080120160200SE +/- 1.23, N = 3SE +/- 2.42, N = 3SE +/- 1.15, N = 3SE +/- 0.58, N = 3SE +/- 0.36, N = 3181.6181.6183.4183.7184.21. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6r3r4r2br1ar148121620SE +/- 0.13, N = 15SE +/- 0.12, N = 15SE +/- 0.23, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 316.6216.2116.0713.3313.251. (CXX) g++ options: -O3 -fPIC -lm

srsLTE

srsLTE is an open-source LTE software radio suite created by Software Radio Systems (SRS). srsLTE can be used for building your own software defined (SDR) LTE mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSamples / Second, More Is BettersrsLTE 20.10.1Test: OFDM_Testr1ar1r4r2br330M60M90M120M150MSE +/- 240370.09, N = 3SE +/- 611010.09, N = 3SE +/- 233333.33, N = 3SE +/- 366666.67, N = 3SE +/- 600925.21, N = 31201333331203000001206666671207333331208333331. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -mavx512f -mavx512cd -mavx512bw -mavx512dq -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f

Sysbench

This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSysbench 1.0.20Test: RAM / Memoryr2br43K6K9K12K15KSE +/- 125.16, N = 15SE +/- 118.72, N = 1512510.5612553.441. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 2r2br3r4r1r1a918273645SE +/- 0.40, N = 3SE +/- 0.20, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 338.3738.3137.8031.5431.481. (CXX) g++ options: -O3 -fPIC -lm

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256 - Decryptr4r3r2br1r1a12002400360048006000SE +/- 12.66, N = 3SE +/- 1.10, N = 3SE +/- 0.94, N = 3SE +/- 1.20, N = 3SE +/- 0.12, N = 35650.145662.345662.765663.065663.611. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256r3r2br4r1r1a12002400360048006000SE +/- 42.23, N = 3SE +/- 55.60, N = 3SE +/- 51.03, N = 3SE +/- 0.92, N = 3SE +/- 0.28, N = 35593.375606.975612.005669.705670.811. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: ETC1Sr4r2b816243240SE +/- 0.42, N = 3SE +/- 0.21, N = 334.4234.241. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 0r2br43691215SE +/- 0.08, N = 15SE +/- 0.08, N = 311.2511.231. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10, Losslessr2br4r3r1r1a3691215SE +/- 0.154, N = 15SE +/- 0.157, N = 15SE +/- 0.130, N = 15SE +/- 0.036, N = 3SE +/- 0.016, N = 310.28210.20810.0888.8528.8121. (CXX) g++ options: -O3 -fPIC -lm

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080pr4r2br3r1a306090120150SE +/- 0.28, N = 3SE +/- 0.49, N = 3SE +/- 0.31, N = 15SE +/- 0.82, N = 1542.3743.2643.42125.251. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-Onlyr4r2b714212835SE +/- 0.32, N = 3SE +/- 0.08, N = 329.6929.56

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - Decryptr3r2br4r1r1a130260390520650SE +/- 3.74, N = 3SE +/- 3.49, N = 3SE +/- 2.81, N = 3SE +/- 0.40, N = 3SE +/- 0.57, N = 3612.15612.44615.98619.46619.541. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305r2br3r4r1ar1130260390520650SE +/- 3.48, N = 3SE +/- 3.19, N = 3SE +/- 2.98, N = 3SE +/- 0.17, N = 3SE +/- 0.03, N = 3615.81616.50619.64623.20623.491. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish - Decryptr2br1r4r3r1a80160240320400SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3363.20363.26363.28363.31363.331. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfishr3r4r2br1r1a80160240320400SE +/- 3.73, N = 3SE +/- 3.51, N = 3SE +/- 0.11, N = 3SE +/- 0.56, N = 3SE +/- 0.05, N = 3359.45359.57362.93363.04363.621. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish - Decryptr1ar2br4r1r360120180240300SE +/- 0.11, N = 3SE +/- 0.12, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 3SE +/- 0.06, N = 3292.37292.40292.61292.74292.831. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofishr4r3r2br1ar160120180240300SE +/- 2.83, N = 3SE +/- 2.66, N = 3SE +/- 0.11, N = 3SE +/- 0.14, N = 3SE +/- 0.14, N = 3286.00286.18288.56288.85289.131. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256 - Decryptr3r1ar4r1r2b306090120150SE +/- 0.35, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3115.72116.07116.07116.07116.081. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256r3r4r2br1ar1306090120150SE +/- 1.33, N = 3SE +/- 1.17, N = 3SE +/- 1.15, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3114.52114.65114.66115.97115.971. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI - Decryptr2br1ar4r3r120406080100SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 374.2874.2974.2974.3174.321. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMIr2br4r3r1r1a20406080100SE +/- 1.01, N = 3SE +/- 0.87, N = 3SE +/- 0.77, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 376.2976.4076.4177.2977.311. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: TBBr4r3r2br1ar115003000450060007500SE +/- 81.70, N = 15SE +/- 69.20, N = 15SE +/- 73.83, N = 15SE +/- 80.68, N = 3SE +/- 59.06, N = 15701670036984696468501. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1Mr1r3r2br4r1a11K22K33K44K55KSE +/- 425.40, N = 7SE +/- 358.18, N = 3SE +/- 238.38, N = 3SE +/- 235.04, N = 3SE +/- 588.34, N = 348051.549813.449908.349937.350166.11. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Intel Memory Latency Checker

Intel Memory Latency Checker (MLC) is a binary-only system memory bandwidth and latency benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - Stream-Triad Liker2ar1ar4r2br3r5r170K140K210K280K350KSE +/- 34.05, N = 3SE +/- 38.10, N = 3SE +/- 60.42, N = 3SE +/- 12.95, N = 3SE +/- 32.03, N = 3SE +/- 55.81, N = 3SE +/- 177.93, N = 3323826.9323924.2324112.8324209.8324227.4324234.5324377.2

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - 1:1 Reads-Writesr2br2ar1r1ar4r5r3100K200K300K400K500KSE +/- 314.54, N = 3SE +/- 212.40, N = 3SE +/- 1187.16, N = 3SE +/- 148.63, N = 3SE +/- 1601.80, N = 3SE +/- 847.23, N = 3SE +/- 138.13, N = 3440454.7442144.2442422.3442843.2446396.0448800.1449554.1

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - 2:1 Reads-Writesr1ar2ar3r5r4r1r2b100K200K300K400K500KSE +/- 130.28, N = 3SE +/- 115.55, N = 3SE +/- 73.04, N = 3SE +/- 12.06, N = 3SE +/- 36.24, N = 3SE +/- 274.15, N = 3SE +/- 64.32, N = 3456260.3456408.6457190.5458830.6458941.9459038.6459309.8

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - 3:1 Reads-Writesr2ar1ar3r5r4r2br190K180K270K360K450KSE +/- 236.99, N = 3SE +/- 94.95, N = 3SE +/- 88.34, N = 3SE +/- 23.30, N = 3SE +/- 23.30, N = 3SE +/- 25.04, N = 3SE +/- 163.24, N = 3424077.3424096.6424904.5425508.1425822.1425925.6425933.7

OpenBenchmarking.orgMB/s, More Is BetterIntel Memory Latency CheckerTest: Peak Injection Bandwidth - All Readsr1r5r2br4r2ar1ar380K160K240K320K400KSE +/- 709.43, N = 3SE +/- 23.85, N = 3SE +/- 14.54, N = 3SE +/- 26.62, N = 3SE +/- 37.47, N = 3SE +/- 14.58, N = 3SE +/- 24.95, N = 3356476.2357722.7357742.9358110.5358269.7358385.5358463.7

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUr3r2br1ar4r10.07690.15380.23070.30760.3845SE +/- 0.003372, N = 6SE +/- 0.003448, N = 5SE +/- 0.002562, N = 3SE +/- 0.004121, N = 3SE +/- 0.000853, N = 30.3419550.3418930.3416630.3402430.338327MIN: 0.31MIN: 0.3MIN: 0.31MIN: 0.3MIN: 0.31. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUr2br3r1r4r1a0.04880.09760.14640.19520.244SE +/- 0.001893, N = 8SE +/- 0.002019, N = 7SE +/- 0.000867, N = 3SE +/- 0.001544, N = 12SE +/- 0.000781, N = 30.2168060.2165860.2151150.2150850.213643MIN: 0.19MIN: 0.19MIN: 0.19MIN: 0.19MIN: 0.191. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Helsing

Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digitr4r2br1ar3r12040608010078.5478.3378.1678.0877.871. (CC) gcc options: -O2 -pthread -lcrypto

libjpeg-turbo tjbench

tjbench is a JPEG decompression/compression benchmark that is part of libjpeg-turbo, a JPEG image codec library optimized for SIMD instructions on modern CPU architectures. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.1.0Test: Decompression Throughputr1ar3r4r2br14080120160200SE +/- 0.39, N = 3SE +/- 1.04, N = 3SE +/- 0.47, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 3156.97159.19159.24160.26161.631. (CC) gcc options: -O3 -rdynamic

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Thoroughr4r2b3691215SE +/- 0.0879, N = 7SE +/- 0.0796, N = 89.30919.29071. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Exhaustiver4r2b48121620SE +/- 0.02, N = 3SE +/- 0.00, N = 316.3716.361. (CXX) g++ options: -O3 -flto -pthread

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10r4r2br3r1ar1246810SE +/- 0.130, N = 15SE +/- 0.116, N = 15SE +/- 0.145, N = 15SE +/- 0.014, N = 3SE +/- 0.038, N = 36.7466.6566.5975.5055.4771. (CXX) g++ options: -O3 -fPIC -lm

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Mediumr2br4246810SE +/- 0.0906, N = 15SE +/- 0.0290, N = 37.18877.14721. (CXX) g++ options: -O3 -flto -pthread

Timed Mesa Compilation

This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To Compiler2br3r4r1r1a510152025SE +/- 0.04, N = 3SE +/- 0.15, N = 3SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.12, N = 321.5821.3721.3120.9520.38

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUr3r4r1ar2br10.80151.6032.40453.2064.0075SE +/- 0.01280, N = 3SE +/- 0.00650, N = 3SE +/- 0.00732, N = 3SE +/- 0.00854, N = 3SE +/- 0.00193, N = 33.562243.547833.543673.531213.53026MIN: 3.39MIN: 3.37MIN: 3.38MIN: 3.37MIN: 3.381. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUr3r2br4r1r1a0.09150.1830.27450.3660.4575SE +/- 0.003204, N = 10SE +/- 0.004259, N = 4SE +/- 0.002415, N = 14SE +/- 0.001135, N = 3SE +/- 0.001124, N = 30.4068770.4034090.4029190.3982820.395588MIN: 0.37MIN: 0.36MIN: 0.36MIN: 0.37MIN: 0.361. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pr2br4r3r1r1a918273645SE +/- 0.09, N = 3SE +/- 0.31, N = 3SE +/- 0.14, N = 3SE +/- 0.29, N = 3SE +/- 0.24, N = 327.8028.0128.2236.9137.341. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080pr3r2br4r1a20406080100SE +/- 0.26, N = 3SE +/- 0.19, N = 3SE +/- 0.27, N = 3SE +/- 1.01, N = 1536.0636.2036.35103.921. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 160 - Buffer Length: 256 - Filter Length: 57r2br4r3r1r1a700M1400M2100M2800M3500MSE +/- 14685858.66, N = 3SE +/- 16411005.79, N = 3SE +/- 14901789.60, N = 3SE +/- 17047384.94, N = 3SE +/- 2062630.47, N = 3313186666731402666673143300000314480000031620666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 128 - Buffer Length: 256 - Filter Length: 57r1ar4r2br3r1700M1400M2100M2800M3500MSE +/- 38975091.76, N = 3SE +/- 16537936.19, N = 3SE +/- 14312737.14, N = 3SE +/- 6896617.53, N = 3SE +/- 8088331.79, N = 3335273333333988000003400066667341100000034159333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 57r2br3r4r1ar1700M1400M2100M2800M3500MSE +/- 17049079.48, N = 3SE +/- 14893734.70, N = 3SE +/- 12876378.03, N = 3SE +/- 2150193.79, N = 3SE +/- 5206513.02, N = 3322743333332327000003245666667326370000032671333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 32 - Buffer Length: 256 - Filter Length: 57r4r2br3r1r1a400M800M1200M1600M2000MSE +/- 6582552.70, N = 3SE +/- 10121648.97, N = 3SE +/- 3951371.07, N = 3SE +/- 2515949.13, N = 3169750000016993333331704500000173510000017368000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57r4r2br3r1r1a200M400M600M800M1000MSE +/- 10609570.10, N = 3SE +/- 3620722.76, N = 3SE +/- 859903.10, N = 3SE +/- 691953.76, N = 3SE +/- 669162.00, N = 38600466678628900008654100008853200008902733331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 57r2br4r3r190M180M270M360M450MSE +/- 2458908.97, N = 3SE +/- 2739929.03, N = 3SE +/- 1240739.03, N = 3SE +/- 422150.58, N = 34281000004320133334321700004419533331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 57r2br3r4r150M100M150M200M250MSE +/- 824809.74, N = 3SE +/- 1663583.82, N = 3SE +/- 1956802.95, N = 3SE +/- 1090112.12, N = 32132033332153433332167733332176433331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 57r4r2br1r320M40M60M80M100MSE +/- 132035.35, N = 3SE +/- 907677.13, N = 3SE +/- 729984.78, N = 3SE +/- 430348.70, N = 31094300001101733331107133331115100001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 1 - Buffer Length: 256 - Filter Length: 57r4r2br3r112M24M36M48M60MSE +/- 534784.17, N = 3SE +/- 613156.95, N = 3SE +/- 550708.74, N = 3SE +/- 173700.89, N = 3552516675623033357197667577920001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 19r4r2b510152025SE +/- 0.20, N = 3SE +/- 0.22, N = 320.0819.78

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 3r4r2b48121620SE +/- 0.01, N = 3SE +/- 0.02, N = 317.1917.161. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUr3r2br4r1ar10.05470.10940.16410.21880.2735SE +/- 0.002507, N = 5SE +/- 0.003187, N = 3SE +/- 0.002245, N = 7SE +/- 0.000662, N = 3SE +/- 0.000856, N = 30.2433080.2430260.2424500.2401220.239989MIN: 0.22MIN: 0.22MIN: 0.22MIN: 0.23MIN: 0.221. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pr2br4r3r1r1a90180270360450SE +/- 4.05, N = 12SE +/- 0.65, N = 3SE +/- 1.57, N = 3SE +/- 15.40, N = 12SE +/- 16.03, N = 12182.26184.07185.53386.29393.461. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3r2br41.27442.54883.82325.09766.372SE +/- 0.053, N = 15SE +/- 0.008, N = 35.6645.562

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUr2br1ar1r4r30.2820.5640.8461.1281.41SE +/- 0.00964, N = 3SE +/- 0.01592, N = 15SE +/- 0.00180, N = 3SE +/- 0.01282, N = 3SE +/- 0.01211, N = 31.253131.252671.248091.242221.24176MIN: 1.2MIN: 1.19MIN: 1.2MIN: 1.19MIN: 1.181. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Intel Memory Latency Checker

Intel Memory Latency Checker (MLC) is a binary-only system memory bandwidth and latency benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns, Fewer Is BetterIntel Memory Latency CheckerTest: Idle Latencyr5r4r3r2r1r1ar2a1530456075SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.39, N = 3SE +/- 0.28, N = 868.167.867.667.535.133.032.5

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUr2br4r3r1r1a0.21230.42460.63690.84921.0615SE +/- 0.011253, N = 3SE +/- 0.008450, N = 3SE +/- 0.007264, N = 3SE +/- 0.002101, N = 3SE +/- 0.002111, N = 30.9436240.9407140.9369410.9185680.912279MIN: 0.86MIN: 0.86MIN: 0.85MIN: 0.85MIN: 0.861. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 2r4r2b48121620SE +/- 0.15, N = 3SE +/- 0.18, N = 314.1613.981. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per Directionr4r3r2br1r1a48121620SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 314.6614.6011.5611.3611.271. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3 + Zstd Compression 19r4r2b3691215SE +/- 0.11, N = 5SE +/- 0.06, N = 310.0310.01

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUr3r4r1r1ar2b0.04910.09820.14730.19640.2455SE +/- 0.003384, N = 15SE +/- 0.004970, N = 15SE +/- 0.002205, N = 15SE +/- 0.001109, N = 3SE +/- 0.004449, N = 150.2183490.2179410.2109190.2107280.210324MIN: 0.19MIN: 0.19MIN: 0.19MIN: 0.2MIN: 0.181. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPUr3r2br4r1ar10.13550.2710.40650.5420.6775SE +/- 0.004400, N = 3SE +/- 0.004180, N = 3SE +/- 0.003648, N = 3SE +/- 0.000780, N = 3SE +/- 0.001703, N = 30.6023140.6021220.6020380.5956610.593042MIN: 0.56MIN: 0.56MIN: 0.56MIN: 0.56MIN: 0.561. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per Directionr4r3r2br1r1a0.80391.60782.41173.21564.0195SE +/- 0.02850005, N = 15SE +/- 0.03072276, N = 15SE +/- 0.02799890, N = 3SE +/- 0.00774937, N = 3SE +/- 0.01532048, N = 33.572781533.565927743.022819922.743709962.738590961. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 9r4r2b0.83181.66362.49543.32724.159SE +/- 0.064, N = 15SE +/- 0.003, N = 33.6973.470

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUr4r2br3r1ar10.81971.63942.45913.27884.0985SE +/- 0.05617, N = 14SE +/- 0.05421, N = 14SE +/- 0.05675, N = 14SE +/- 0.00795, N = 3SE +/- 0.00924, N = 33.643193.642323.640333.576623.57247MIN: 3.5MIN: 3.51MIN: 3.47MIN: 3.5MIN: 3.531. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUr4r3r2br1r1a0.19720.39440.59160.78880.986SE +/- 0.007461, N = 14SE +/- 0.007890, N = 14SE +/- 0.008361, N = 14SE +/- 0.002419, N = 3SE +/- 0.002055, N = 30.8762270.8749680.8740800.8641640.863214MIN: 0.84MIN: 0.84MIN: 0.83MIN: 0.84MIN: 0.841. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ Tasksr2br3r4r1r1a2K4K6K8K10KSE +/- 102.03, N = 3SE +/- 93.55, N = 4SE +/- 85.46, N = 4SE +/- 43.45, N = 3SE +/- 80.44, N = 4805080488037787977241. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

Google Draco

Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.4.1Model: Church Facader4r2b15003000450060007500SE +/- 3.33, N = 3SE +/- 20.01, N = 3708270011. (CXX) g++ options: -O3

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUr3r4r2br1r1a0.41480.82961.24441.65922.074SE +/- 0.02043, N = 3SE +/- 0.00968, N = 3SE +/- 0.01382, N = 3SE +/- 0.00580, N = 3SE +/- 0.00121, N = 31.843391.819131.817741.800461.79881MIN: 1.67MIN: 1.68MIN: 1.69MIN: 1.68MIN: 1.691. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Google Draco

Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.4.1Model: Lionr4r2b13002600390052006500SE +/- 21.15, N = 3SE +/- 25.21, N = 3617061261. (CXX) g++ options: -O3

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: OpenMPr3r4r2br1r1a16003200480064008000SE +/- 85.45, N = 4SE +/- 91.12, N = 4SE +/- 101.59, N = 3SE +/- 5.13, N = 3SE +/- 0.88, N = 3743974297412731873081. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ Threadsr3r2br4r1r1a15003000450060007500SE +/- 98.76, N = 3SE +/- 89.67, N = 3SE +/- 76.94, N = 4SE +/- 49.12, N = 3SE +/- 29.96, N = 3720371497141701869801. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pr4r2br3r1r1a70140210280350SE +/- 1.59, N = 3SE +/- 1.13, N = 3SE +/- 1.63, N = 3SE +/- 1.20, N = 3SE +/- 1.10, N = 3162.21164.32164.51327.87329.531. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pr4r3r2br1r1a90180270360450SE +/- 0.47, N = 3SE +/- 2.25, N = 3SE +/- 0.90, N = 3SE +/- 1.44, N = 3SE +/- 0.66, N = 3179.13181.52182.17401.29408.241. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUr3r1ar2br4r10.25780.51560.77341.03121.289SE +/- 0.00975, N = 3SE +/- 0.00124, N = 3SE +/- 0.00330, N = 3SE +/- 0.01182, N = 3SE +/- 0.00274, N = 31.145781.122241.118741.118111.10991MIN: 1.04MIN: 1.02MIN: 1.02MIN: 1.02MIN: 1.021. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUr3r1ar1r4r2b0.20290.40580.60870.81161.0145SE +/- 0.006631, N = 3SE +/- 0.003986, N = 3SE +/- 0.006225, N = 3SE +/- 0.005244, N = 3SE +/- 0.004902, N = 30.9018230.8791370.8778150.8754210.869978MIN: 0.84MIN: 0.83MIN: 0.82MIN: 0.82MIN: 0.821. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUr2br3r4r1ar10.47640.95281.42921.90562.382SE +/- 0.01980, N = 3SE +/- 0.01943, N = 3SE +/- 0.01801, N = 3SE +/- 0.00168, N = 3SE +/- 0.00138, N = 32.117122.108412.108372.085322.07944MIN: 2.03MIN: 2.03MIN: 2.03MIN: 2.03MIN: 2.031. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pr4r3r2br1ar1110220330440550SE +/- 1.14, N = 3SE +/- 1.80, N = 10SE +/- 2.64, N = 4SE +/- 4.78, N = 3SE +/- 3.80, N = 3233.96234.39234.51493.51499.231. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pr4r3r2br1ar160120180240300SE +/- 1.22, N = 3SE +/- 1.64, N = 3SE +/- 1.76, N = 5SE +/- 1.37, N = 3SE +/- 1.68, N = 3156.26157.83158.16288.99290.671. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

188 Results Shown

HammerDB - MariaDB:
  128 - 250:
    Transactions Per Minute
    New Orders Per Minute
  128 - 500:
    Transactions Per Minute
    New Orders Per Minute
  64 - 250:
    Transactions Per Minute
    New Orders Per Minute
  32 - 250:
    Transactions Per Minute
    New Orders Per Minute
  16 - 500:
    Transactions Per Minute
    New Orders Per Minute
  32 - 500:
    Transactions Per Minute
    New Orders Per Minute
MariaDB:
  256
  512
  128
HammerDB - MariaDB:
  64 - 500:
    Transactions Per Minute
    New Orders Per Minute
Xcompact3d Incompact3d
GNU Radio:
  Hilbert Transform
  FM Deemphasis Filter
  IIR Filter
  FIR Filter
  Signal Source (Cosine)
  Five Back to Back FIR Filters
MariaDB
AOM AV1
CP2K Molecular Dynamics
HammerDB - MariaDB:
  16 - 250:
    Transactions Per Minute
    New Orders Per Minute
LuaRadio:
  Complex Phase
  Hilbert Transform
  FM Deemphasis Filter
  Five Back to Back FIR Filters
HammerDB - MariaDB:
  8 - 250:
    Transactions Per Minute
    New Orders Per Minute
  8 - 500:
    Transactions Per Minute
    New Orders Per Minute
AOM AV1
Mobile Neural Network:
  inception-v3
  mobilenet-v1-1.0
  MobileNetV2_224
  resnet-v2-50
  SqueezeNetV1.0
MariaDB
SecureMark
AOM AV1
MariaDB
Timed LLVM Compilation
AOM AV1
LuxCoreRender
MariaDB
Timed Erlang/OTP Compilation
LuxCoreRender
Intel Memory Latency Checker:
  Max Bandwidth - Stream-Triad Like
  Max Bandwidth - 1:1 Reads-Writes
  Max Bandwidth - 2:1 Reads-Writes
  Max Bandwidth - 3:1 Reads-Writes
  Max Bandwidth - All Reads
MariaDB
Timed LLVM Compilation
AOM AV1
oneDNN
MariaDB
AOM AV1
GNU GMP GMPbench
Blender
Timed Node.js Compilation
ViennaCL:
  CPU BLAS - dGEMM-TT
  CPU BLAS - dGEMM-TN
  CPU BLAS - dGEMM-NT
  CPU BLAS - dGEMM-NN
  CPU BLAS - dGEMV-T
  CPU BLAS - dGEMV-N
  CPU BLAS - dDOT
  CPU BLAS - dAXPY
  CPU BLAS - dCOPY
  CPU BLAS - sDOT
  CPU BLAS - sAXPY
  CPU BLAS - sCOPY
Xmrig
AOM AV1
Timed Linux Kernel Compilation
Sysbench
Blender
Timed Wasmer Compilation
oneDNN:
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
AOM AV1
Blender
KTX-Software toktx
oneDNN
LuxCoreRender:
  Danish Mood - CPU
  LuxCore Benchmark - CPU
libavif avifenc
AOM AV1
LuxCoreRender
AOM AV1
Blender
oneDNN
VOSK Speech Recognition Toolkit
Stockfish
libavif avifenc
srsLTE:
  PHY_DL_Test:
    UE Mb/s
    eNb Mb/s
libavif avifenc
srsLTE
Sysbench
libavif avifenc
Botan:
  AES-256 - Decrypt
  AES-256
Basis Universal:
  ETC1S
  UASTC Level 0
libavif avifenc
AOM AV1
Blender
Botan:
  ChaCha20Poly1305 - Decrypt
  ChaCha20Poly1305
  Blowfish - Decrypt
  Blowfish
  Twofish - Decrypt
  Twofish
  CAST-256 - Decrypt
  CAST-256
  KASUMI - Decrypt
  KASUMI
toyBrot Fractal Generator
Xmrig
Intel Memory Latency Checker:
  Peak Injection Bandwidth - Stream-Triad Like
  Peak Injection Bandwidth - 1:1 Reads-Writes
  Peak Injection Bandwidth - 2:1 Reads-Writes
  Peak Injection Bandwidth - 3:1 Reads-Writes
  Peak Injection Bandwidth - All Reads
oneDNN:
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
Helsing
libjpeg-turbo tjbench
ASTC Encoder:
  Thorough
  Exhaustive
libavif avifenc
ASTC Encoder
Timed Mesa Compilation
oneDNN:
  Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU
  IP Shapes 3D - u8s8f32 - CPU
SVT-HEVC
AOM AV1
Liquid-DSP:
  160 - 256 - 57
  128 - 256 - 57
  64 - 256 - 57
  32 - 256 - 57
  16 - 256 - 57
  8 - 256 - 57
  4 - 256 - 57
  2 - 256 - 57
  1 - 256 - 57
KTX-Software toktx
Basis Universal
oneDNN
SVT-VP9
KTX-Software toktx
oneDNN
Intel Memory Latency Checker
oneDNN
Basis Universal
Xcompact3d Incompact3d
KTX-Software toktx
oneDNN:
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPU
Xcompact3d Incompact3d
KTX-Software toktx
oneDNN:
  Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
toyBrot Fractal Generator
Google Draco
oneDNN
Google Draco
toyBrot Fractal Generator:
  OpenMP
  C++ Threads
SVT-VP9:
  Visual Quality Optimized - Bosphorus 1080p
  PSNR/SSIM Optimized - Bosphorus 1080p
oneDNN:
  Convolution Batch Shapes Auto - f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Convolution Batch Shapes Auto - bf16bf16bf16 - CPU
SVT-HEVC:
  10 - Bosphorus 1080p
  7 - Bosphorus 1080p