5220R 2P Ubuntu EO 2020

2 x Intel Xeon Gold 5220R testing with a TYAN S7106 (V2.01.B40 BIOS) and llvmpipe 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 2012214-HA-5220R2PUB13
Jump To Table - Results

View

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

Limit displaying results to tests within:

Audio Encoding 4 Tests
Bioinformatics 2 Tests
Timed Code Compilation 3 Tests
C/C++ Compiler Tests 5 Tests
CPU Massive 6 Tests
Creator Workloads 6 Tests
Encoding 4 Tests
HPC - High Performance Computing 4 Tests
Machine Learning 2 Tests
Multi-Core 5 Tests
Programmer / Developer System Benchmarks 6 Tests
Scientific Computing 2 Tests
Server 4 Tests
Server CPU Tests 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
1
December 21 2020
  4 Hours, 34 Minutes
2
December 21 2020
  3 Hours, 47 Minutes
3
December 21 2020
  3 Hours, 3 Minutes
Invert Hiding All Results Option
  3 Hours, 48 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):


5220R 2P Ubuntu EO 2020ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen Resolution1232 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads)TYAN S7106 (V2.01.B40 BIOS)Intel Sky Lake-E DMI3 Registers94GB500GB Samsung SSD 860llvmpipeVE2282 x Intel I210 + 2 x QLogic cLOM8214 1/10GbEUbuntu 20.045.9.0-050900rc6-generic (x86_64) 20200920GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.83.3 Mesa 20.0.4 (LLVM 9.0.1 256 bits)GCC 9.3.0ext41920x1080OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/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- Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5003003Security Details- itlb_multihit: KVM: Mitigation of VMX disabled + 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: Mitigation of TSX disabled

123Result OverviewPhoronix Test Suite100%102%104%105%107%oneDNNApache SiegeSQLite SpeedtestNCNNCLOMPNode.js V8 Web Tooling BenchmarkTimed MAFFT AlignmentMonkey Audio EncodingCoremarkTimed HMMer SearchTimed Clash CompilationsimdjsonTimed FFmpeg CompilationTimed Eigen CompilationBuild2Opus Codec EncodingOgg Audio EncodingWavPack Audio Encoding

5220R 2P Ubuntu EO 2020simdjson: Kostyasimdjson: LargeRandsimdjson: PartialTweetssimdjson: DistinctUserIDcoremark: CoreMark Size 666 - Iterations Per Secondnode-web-tooling: clomp: Static OMP Speedupapache-siege: 10apache-siege: 50apache-siege: 100apache-siege: 200apache-siege: 250apache-siege: 500brl-cad: VGR Performance Metriconednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: IP Shapes 1D - bf16bf16bf16 - CPUonednn: IP Shapes 3D - bf16bf16bf16 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mhmmer: Pfam Database Searchmafft: Multiple Sequence Alignment - LSU RNAbuild-clash: Time To Compilebuild-ffmpeg: Time To Compilebuild2: Time To Compilebuild-eigen: Time To Compileencode-ape: WAV To APEencode-ogg: WAV To Oggencode-opus: WAV To Opus Encodesqlite-speedtest: Timed Time - Size 1,000encode-wavpack: WAV To WavPack1230.560.390.560.581096383.89092110.253221723.4133348.7135458.4351905.5945610.3451574.652531041.813623.924791.345031.255375.6923314.358697.470372.284872.735947.059180.5625190.6948781443.59819.4571457.166.411387.658609.50819818.4300.5528511941.01818.4080.3481591.4664522.9110.129.269.209.3012.144.8020.5840.2813.8610.0426.9632.2623.4366.18224.32511.843482.02730.58979.00385.76013.08223.21610.18366.08316.7850.560.390.570.581088921.69768810.2831.821708.1033392.8436786.9844343.8446010.1348209.461.810943.853281.362781.272845.687733.698647.470632.281412.739447.062780.5622480.6952541951.91828.0631430.866.416367.666169.53901826.7850.5538131431.41817.9200.3414761.4585423.1510.199.088.829.4612.564.8520.4839.9713.679.8028.4034.0624.2568.47223.76111.728485.10230.59778.85886.01613.00923.20210.17865.29716.7790.560.390.560.581093129.50814510.3731.521771.5333656.6635464.3541854.1844492.5646008.381.813333.892961.343851.248185.685003.668377.476172.275242.739416.976010.5614080.6947241434.19822.7421446.436.429897.653649.53508821.6430.5572421458.06832.7590.3471511.4559623.1610.299.269.089.6112.684.8321.1040.8114.1210.8326.7732.4323.9467.53225.08611.859484.60030.50578.80285.77713.11223.17110.20164.79216.808OpenBenchmarking.org

simdjson

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

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: Kostya1230.1260.2520.3780.5040.63SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.560.560.561. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: Kostya123246810Min: 0.56 / Avg: 0.56 / Max: 0.56Min: 0.56 / Avg: 0.56 / Max: 0.56Min: 0.56 / Avg: 0.56 / Max: 0.561. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: LargeRandom1230.08780.17560.26340.35120.439SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.390.390.391. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: LargeRandom12312345Min: 0.39 / Avg: 0.39 / Max: 0.39Min: 0.39 / Avg: 0.39 / Max: 0.39Min: 0.39 / Avg: 0.39 / Max: 0.391. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: PartialTweets1230.12830.25660.38490.51320.6415SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.560.570.561. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: PartialTweets123246810Min: 0.56 / Avg: 0.56 / Max: 0.57Min: 0.56 / Avg: 0.57 / Max: 0.57Min: 0.56 / Avg: 0.56 / Max: 0.561. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: DistinctUserID1230.13050.2610.39150.5220.6525SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.580.580.581. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: DistinctUserID123246810Min: 0.58 / Avg: 0.58 / Max: 0.58Min: 0.58 / Avg: 0.58 / Max: 0.58Min: 0.58 / Avg: 0.58 / Max: 0.581. (CXX) g++ options: -O3 -pthread

Coremark

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

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Second123200K400K600K800K1000KSE +/- 8504.83, N = 3SE +/- 5763.94, N = 3SE +/- 6644.33, N = 31096383.891088921.701093129.511. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Second123200K400K600K800K1000KMin: 1081649.52 / Avg: 1096383.89 / Max: 1111111.11Min: 1078530.5 / Avg: 1088921.7 / Max: 1098440.06Min: 1079905.51 / Avg: 1093129.51 / Max: 1100875.351. (CC) gcc options: -O2 -lrt" -lrt

Node.js V8 Web Tooling Benchmark

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

OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling Benchmark1233691215SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 310.2510.2810.371. Nodejs v10.19.0
OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling Benchmark1233691215Min: 10.15 / Avg: 10.25 / Max: 10.34Min: 10.22 / Avg: 10.28 / Max: 10.38Min: 10.34 / Avg: 10.37 / Max: 10.41. Nodejs v10.19.0

CLOMP

CLOMP is the C version of the Livermore OpenMP benchmark developed to measure OpenMP overheads and other performance impacts due to threading in order to influence future system designs. This particular test profile configuration is currently set to look at the OpenMP static schedule speed-up across all available CPU cores using the recommended test configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 1.2Static OMP Speedup123714212835SE +/- 0.09, N = 3SE +/- 0.09, N = 332.031.831.51. (CC) gcc options: -fopenmp -O3 -lm
OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 1.2Static OMP Speedup123714212835Min: 31.7 / Avg: 31.83 / Max: 32Min: 31.3 / Avg: 31.47 / Max: 31.61. (CC) gcc options: -fopenmp -O3 -lm

Apache Siege

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

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 101235K10K15K20K25KSE +/- 15.72, N = 3SE +/- 68.54, N = 3SE +/- 96.00, N = 321723.4121708.1021771.531. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 101234K8K12K16K20KMin: 21691.97 / Avg: 21723.41 / Max: 21739.13Min: 21598.27 / Avg: 21708.1 / Max: 21834.06Min: 21598.27 / Avg: 21771.53 / Max: 21929.821. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 501237K14K21K28K35KSE +/- 96.11, N = 3SE +/- 48.81, N = 3SE +/- 171.37, N = 333348.7133392.8433656.661. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 501236K12K18K24K30KMin: 33156.5 / Avg: 33348.71 / Max: 33444.82Min: 33333.33 / Avg: 33392.84 / Max: 33489.62Min: 33422.46 / Avg: 33656.66 / Max: 33990.481. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 1001238K16K24K32K40KSE +/- 423.42, N = 3SE +/- 279.56, N = 3SE +/- 243.60, N = 335458.4336786.9835464.351. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 1001236K12K18K24K30KMin: 34940.6 / Avg: 35458.43 / Max: 36297.64Min: 36337.21 / Avg: 36786.98 / Max: 37299.52Min: 35026.27 / Avg: 35464.35 / Max: 35868.011. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 20012311K22K33K44K55KSE +/- 1707.01, N = 12SE +/- 560.13, N = 3SE +/- 391.74, N = 351905.5944343.8441854.181. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 2001239K18K27K36K45KMin: 40048.06 / Avg: 51905.59 / Max: 56481.22Min: 43224.55 / Avg: 44343.84 / Max: 44943.82Min: 41169.2 / Avg: 41854.18 / Max: 42526.051. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 25012310K20K30K40K50KSE +/- 582.76, N = 3SE +/- 456.56, N = 3SE +/- 270.33, N = 345610.3446010.1344492.561. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 2501238K16K24K32K40KMin: 44634.89 / Avg: 45610.34 / Max: 46650.5Min: 45101.93 / Avg: 46010.13 / Max: 46546.27Min: 43967.64 / Avg: 44492.56 / Max: 44867.191. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 50012311K22K33K44K55KSE +/- 846.89, N = 12SE +/- 667.57, N = 4SE +/- 317.59, N = 351574.6548209.4646008.381. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 5001239K18K27K36K45KMin: 45789.19 / Avg: 51574.65 / Max: 54347.83Min: 46465.02 / Avg: 48209.46 / Max: 49342.11Min: 45373.66 / Avg: 46008.38 / Max: 46346.781. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

BRL-CAD

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

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.30.8VGR Performance Metric150K100K150K200K250K2531041. (CXX) g++ options: -std=c++11 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lXi -lGLU -lGL -lGLdispatch -lX11 -lXext -lXrender -lpthread -ldl -luuid -lm

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 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU1230.40810.81621.22431.63242.0405SE +/- 0.00667, N = 3SE +/- 0.00137, N = 3SE +/- 0.00350, N = 31.813621.810941.81333MIN: 1.72MIN: 1.7MIN: 1.721. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU123246810Min: 1.8 / Avg: 1.81 / Max: 1.82Min: 1.81 / Avg: 1.81 / Max: 1.81Min: 1.81 / Avg: 1.81 / Max: 1.821. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU1230.88311.76622.64933.53244.4155SE +/- 0.01612, N = 3SE +/- 0.00730, N = 3SE +/- 0.00503, N = 33.924793.853283.89296MIN: 3.84MIN: 3.79MIN: 3.821. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU123246810Min: 3.9 / Avg: 3.92 / Max: 3.95Min: 3.84 / Avg: 3.85 / Max: 3.87Min: 3.89 / Avg: 3.89 / Max: 3.91. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU1230.30660.61320.91981.22641.533SE +/- 0.01667, N = 5SE +/- 0.01651, N = 6SE +/- 0.01635, N = 51.345031.362781.34385MIN: 1.21MIN: 1.23MIN: 1.211. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU123246810Min: 1.32 / Avg: 1.35 / Max: 1.41Min: 1.32 / Avg: 1.36 / Max: 1.43Min: 1.3 / Avg: 1.34 / Max: 1.41. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU1230.28640.57280.85921.14561.432SE +/- 0.01721, N = 3SE +/- 0.00361, N = 3SE +/- 0.01312, N = 31.255371.272841.24818MIN: 1.13MIN: 1.14MIN: 1.151. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU123246810Min: 1.23 / Avg: 1.26 / Max: 1.29Min: 1.27 / Avg: 1.27 / Max: 1.28Min: 1.23 / Avg: 1.25 / Max: 1.271. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU1231.28082.56163.84245.12326.404SE +/- 0.00373, N = 3SE +/- 0.00725, N = 3SE +/- 0.01035, N = 35.692335.687735.68500MIN: 5.51MIN: 5.53MIN: 5.521. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU123246810Min: 5.69 / Avg: 5.69 / Max: 5.7Min: 5.68 / Avg: 5.69 / Max: 5.7Min: 5.67 / Avg: 5.69 / Max: 5.711. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU12348121620SE +/- 5.73224, N = 12SE +/- 0.08058, N = 15SE +/- 0.08350, N = 1514.358693.698643.66837MIN: 2.72MIN: 2.71MIN: 2.71. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU12348121620Min: 3.18 / Avg: 14.36 / Max: 57.7Min: 3.1 / Avg: 3.7 / Max: 4.19Min: 3.13 / Avg: 3.67 / Max: 4.151. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU123246810SE +/- 0.01532, N = 3SE +/- 0.01810, N = 3SE +/- 0.01439, N = 37.470377.470637.47617MIN: 7.37MIN: 7.38MIN: 3.131. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU1233691215Min: 7.45 / Avg: 7.47 / Max: 7.5Min: 7.45 / Avg: 7.47 / Max: 7.51Min: 7.45 / Avg: 7.48 / Max: 7.51. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU1230.51411.02821.54232.05642.5705SE +/- 0.00407, N = 3SE +/- 0.00102, N = 3SE +/- 0.00603, N = 32.284872.281412.27524MIN: 2.21MIN: 2.21MIN: 2.211. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU123246810Min: 2.28 / Avg: 2.28 / Max: 2.29Min: 2.28 / Avg: 2.28 / Max: 2.28Min: 2.26 / Avg: 2.28 / Max: 2.281. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU1230.61641.23281.84922.46563.082SE +/- 0.00436, N = 3SE +/- 0.00953, N = 3SE +/- 0.00193, N = 32.735942.739442.73941MIN: 2.69MIN: 2.69MIN: 2.691. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU123246810Min: 2.73 / Avg: 2.74 / Max: 2.74Min: 2.72 / Avg: 2.74 / Max: 2.76Min: 2.74 / Avg: 2.74 / Max: 2.741. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU123246810SE +/- 0.01330, N = 3SE +/- 0.01028, N = 3SE +/- 0.09282, N = 37.059187.062786.97601MIN: 6.97MIN: 6.97MIN: 2.51. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU1233691215Min: 7.04 / Avg: 7.06 / Max: 7.09Min: 7.05 / Avg: 7.06 / Max: 7.08Min: 6.79 / Avg: 6.98 / Max: 7.091. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU1230.12660.25320.37980.50640.633SE +/- 0.001025, N = 3SE +/- 0.000242, N = 3SE +/- 0.000912, N = 30.5625190.5622480.561408MIN: 0.54MIN: 0.54MIN: 0.531. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU123246810Min: 0.56 / Avg: 0.56 / Max: 0.56Min: 0.56 / Avg: 0.56 / Max: 0.56Min: 0.56 / Avg: 0.56 / Max: 0.561. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU1230.15640.31280.46920.62560.782SE +/- 0.001664, N = 3SE +/- 0.000340, N = 3SE +/- 0.001534, N = 30.6948780.6952540.694724MIN: 0.68MIN: 0.68MIN: 0.681. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU123246810Min: 0.69 / Avg: 0.69 / Max: 0.7Min: 0.69 / Avg: 0.7 / Max: 0.7Min: 0.69 / Avg: 0.69 / Max: 0.71. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU123400800120016002000SE +/- 10.07, N = 3SE +/- 463.22, N = 15SE +/- 2.21, N = 31443.591951.911434.19MIN: 1421.98MIN: 1412.46MIN: 1424.291. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU12330060090012001500Min: 1431.3 / Avg: 1443.59 / Max: 1463.55Min: 1428.93 / Avg: 1951.91 / Max: 8424.46Min: 1430.14 / Avg: 1434.19 / Max: 1437.731. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU1232004006008001000SE +/- 4.25, N = 3SE +/- 8.38, N = 8SE +/- 5.98, N = 3819.46828.06822.74MIN: 809.53MIN: 800.64MIN: 803.831. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU123150300450600750Min: 814.91 / Avg: 819.46 / Max: 827.96Min: 814.81 / Avg: 828.06 / Max: 882.61Min: 815.5 / Avg: 822.74 / Max: 834.621. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU12330060090012001500SE +/- 13.34, N = 3SE +/- 5.02, N = 3SE +/- 8.18, N = 31457.161430.861446.43MIN: 1424.17MIN: 1416.66MIN: 1408.271. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU12330060090012001500Min: 1430.84 / Avg: 1457.16 / Max: 1474.14Min: 1422.86 / Avg: 1430.86 / Max: 1440.12Min: 1431.11 / Avg: 1446.43 / Max: 1459.051. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU123246810SE +/- 0.01793, N = 3SE +/- 0.00690, N = 3SE +/- 0.01957, N = 36.411386.416366.42989MIN: 6.3MIN: 6.31MIN: 6.31. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU1233691215Min: 6.38 / Avg: 6.41 / Max: 6.43Min: 6.4 / Avg: 6.42 / Max: 6.42Min: 6.4 / Avg: 6.43 / Max: 6.471. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU123246810SE +/- 0.00487, N = 3SE +/- 0.01236, N = 3SE +/- 0.00837, N = 37.658607.666167.65364MIN: 7.54MIN: 7.54MIN: 7.531. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU1233691215Min: 7.65 / Avg: 7.66 / Max: 7.67Min: 7.65 / Avg: 7.67 / Max: 7.69Min: 7.64 / Avg: 7.65 / Max: 7.671. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU1233691215SE +/- 0.00202, N = 3SE +/- 0.02942, N = 3SE +/- 0.02255, N = 39.508199.539019.53508MIN: 9.41MIN: 9.4MIN: 9.411. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU1233691215Min: 9.5 / Avg: 9.51 / Max: 9.51Min: 9.5 / Avg: 9.54 / Max: 9.6Min: 9.51 / Avg: 9.54 / Max: 9.581. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU1232004006008001000SE +/- 1.82, N = 3SE +/- 9.62, N = 3SE +/- 3.85, N = 3818.43826.79821.64MIN: 805.26MIN: 799.56MIN: 810.141. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU123150300450600750Min: 814.98 / Avg: 818.43 / Max: 821.17Min: 816.83 / Avg: 826.79 / Max: 846.02Min: 815.4 / Avg: 821.64 / Max: 828.671. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU1230.12540.25080.37620.50160.627SE +/- 0.001999, N = 3SE +/- 0.001779, N = 3SE +/- 0.001173, N = 30.5528510.5538130.557242MIN: 0.53MIN: 0.53MIN: 0.531. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU123246810Min: 0.55 / Avg: 0.55 / Max: 0.56Min: 0.55 / Avg: 0.55 / Max: 0.56Min: 0.56 / Avg: 0.56 / Max: 0.561. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU123400800120016002000SE +/- 387.00, N = 15SE +/- 11.16, N = 3SE +/- 21.58, N = 31941.011431.411458.06MIN: 1403.8MIN: 1405.72MIN: 14121. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU12330060090012001500Min: 1414.94 / Avg: 1941.01 / Max: 7183.34Min: 1415.83 / Avg: 1431.41 / Max: 1453.05Min: 1435.17 / Avg: 1458.06 / Max: 1501.191. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU1232004006008001000SE +/- 0.70, N = 3SE +/- 1.69, N = 3SE +/- 8.52, N = 3818.41817.92832.76MIN: 811.75MIN: 807.14MIN: 800.411. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU123150300450600750Min: 817.02 / Avg: 818.41 / Max: 819.14Min: 815.4 / Avg: 817.92 / Max: 821.13Min: 820.18 / Avg: 832.76 / Max: 849.011. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU1230.07830.15660.23490.31320.3915SE +/- 0.004840, N = 4SE +/- 0.002266, N = 3SE +/- 0.003928, N = 30.3481590.3414760.347151MIN: 0.31MIN: 0.31MIN: 0.311. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU12312345Min: 0.34 / Avg: 0.35 / Max: 0.36Min: 0.34 / Avg: 0.34 / Max: 0.35Min: 0.34 / Avg: 0.35 / Max: 0.351. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU1230.330.660.991.321.65SE +/- 0.00352, N = 3SE +/- 0.00103, N = 3SE +/- 0.00357, N = 31.466451.458541.45596MIN: 1.41MIN: 1.42MIN: 1.421. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU123246810Min: 1.46 / Avg: 1.47 / Max: 1.47Min: 1.46 / Avg: 1.46 / Max: 1.46Min: 1.45 / Avg: 1.46 / Max: 1.461. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenet123612182430SE +/- 0.29, N = 5SE +/- 0.30, N = 4SE +/- 0.31, N = 322.9123.1523.16MIN: 22.04 / MAX: 24.82MIN: 22.12 / MAX: 25.31MIN: 22.45 / MAX: 26.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenet123510152025Min: 22.28 / Avg: 22.91 / Max: 23.99Min: 22.36 / Avg: 23.15 / Max: 23.77Min: 22.68 / Avg: 23.16 / Max: 23.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v21233691215SE +/- 0.21, N = 5SE +/- 0.19, N = 4SE +/- 0.15, N = 310.1210.1910.29MIN: 9.37 / MAX: 25.56MIN: 9.48 / MAX: 31.67MIN: 9.67 / MAX: 32.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v21233691215Min: 9.52 / Avg: 10.12 / Max: 10.79Min: 9.82 / Avg: 10.19 / Max: 10.53Min: 9.99 / Avg: 10.29 / Max: 10.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v31233691215SE +/- 0.21, N = 5SE +/- 0.18, N = 4SE +/- 0.07, N = 39.269.089.26MIN: 8.45 / MAX: 39.85MIN: 8.43 / MAX: 40.21MIN: 8.89 / MAX: 12.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v31233691215Min: 8.73 / Avg: 9.26 / Max: 10.01Min: 8.7 / Avg: 9.08 / Max: 9.39Min: 9.18 / Avg: 9.26 / Max: 9.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v21233691215SE +/- 0.20, N = 5SE +/- 0.12, N = 4SE +/- 0.04, N = 39.208.829.08MIN: 8.56 / MAX: 10.92MIN: 8.54 / MAX: 10.49MIN: 8.94 / MAX: 10.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v21233691215Min: 8.64 / Avg: 9.2 / Max: 9.8Min: 8.6 / Avg: 8.82 / Max: 9.04Min: 9.01 / Avg: 9.08 / Max: 9.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnet1233691215SE +/- 0.12, N = 5SE +/- 0.17, N = 4SE +/- 0.10, N = 39.309.469.61MIN: 8.78 / MAX: 10.96MIN: 8.8 / MAX: 33.29MIN: 9.15 / MAX: 55.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnet1233691215Min: 8.87 / Avg: 9.3 / Max: 9.64Min: 9.12 / Avg: 9.46 / Max: 9.78Min: 9.41 / Avg: 9.61 / Max: 9.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b01233691215SE +/- 0.27, N = 5SE +/- 0.11, N = 4SE +/- 0.23, N = 312.1412.5612.68MIN: 11.27 / MAX: 34.46MIN: 11.5 / MAX: 42.38MIN: 11.81 / MAX: 54.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b012348121620Min: 11.5 / Avg: 12.14 / Max: 12.82Min: 12.35 / Avg: 12.56 / Max: 12.86Min: 12.24 / Avg: 12.68 / Max: 12.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazeface1231.09132.18263.27394.36525.4565SE +/- 0.06, N = 5SE +/- 0.01, N = 4SE +/- 0.06, N = 34.804.854.83MIN: 4.56 / MAX: 6.42MIN: 4.76 / MAX: 5.32MIN: 4.65 / MAX: 5.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazeface123246810Min: 4.66 / Avg: 4.8 / Max: 4.94Min: 4.83 / Avg: 4.85 / Max: 4.88Min: 4.72 / Avg: 4.83 / Max: 4.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenet123510152025SE +/- 0.45, N = 5SE +/- 0.18, N = 4SE +/- 0.20, N = 320.5820.4821.10MIN: 19.51 / MAX: 58.18MIN: 19.94 / MAX: 21.74MIN: 20.64 / MAX: 39.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenet123510152025Min: 19.67 / Avg: 20.58 / Max: 22.07Min: 20.16 / Avg: 20.48 / Max: 20.92Min: 20.89 / Avg: 21.1 / Max: 21.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg16123918273645SE +/- 0.64, N = 5SE +/- 0.52, N = 4SE +/- 0.82, N = 340.2839.9740.81MIN: 38.75 / MAX: 86.53MIN: 38.61 / MAX: 110.54MIN: 38.92 / MAX: 82.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg16123816243240Min: 39.04 / Avg: 40.28 / Max: 42.52Min: 39.25 / Avg: 39.97 / Max: 41.52Min: 39.17 / Avg: 40.81 / Max: 41.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet1812348121620SE +/- 0.31, N = 5SE +/- 0.08, N = 4SE +/- 0.20, N = 313.8613.6714.12MIN: 13.25 / MAX: 25.23MIN: 13.41 / MAX: 15.51MIN: 13.65 / MAX: 14.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet1812348121620Min: 13.34 / Avg: 13.86 / Max: 15.01Min: 13.49 / Avg: 13.67 / Max: 13.82Min: 13.73 / Avg: 14.12 / Max: 14.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnet1233691215SE +/- 0.34, N = 5SE +/- 0.21, N = 4SE +/- 0.06, N = 310.049.8010.83MIN: 9.32 / MAX: 35.37MIN: 8.83 / MAX: 49.27MIN: 10.67 / MAX: 13.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnet1233691215Min: 9.41 / Avg: 10.04 / Max: 10.97Min: 9.44 / Avg: 9.8 / Max: 10.29Min: 10.73 / Avg: 10.83 / Max: 10.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet50123714212835SE +/- 0.16, N = 5SE +/- 0.59, N = 4SE +/- 0.30, N = 326.9628.4026.77MIN: 25.86 / MAX: 79.69MIN: 26.69 / MAX: 109.07MIN: 24.83 / MAX: 63.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet50123612182430Min: 26.45 / Avg: 26.96 / Max: 27.38Min: 26.88 / Avg: 28.4 / Max: 29.78Min: 26.23 / Avg: 26.77 / Max: 27.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tiny123816243240SE +/- 0.89, N = 5SE +/- 1.23, N = 4SE +/- 0.98, N = 332.2634.0632.43MIN: 29.84 / MAX: 67.93MIN: 30.11 / MAX: 67.85MIN: 30.29 / MAX: 76.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tiny123714212835Min: 31.21 / Avg: 32.26 / Max: 35.8Min: 32.05 / Avg: 34.06 / Max: 37.49Min: 30.48 / Avg: 32.43 / Max: 33.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssd123612182430SE +/- 0.31, N = 5SE +/- 0.83, N = 4SE +/- 0.30, N = 323.4324.2523.94MIN: 22.42 / MAX: 104.2MIN: 22.74 / MAX: 27.15MIN: 23.29 / MAX: 59.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssd123612182430Min: 22.54 / Avg: 23.43 / Max: 24.29Min: 22.96 / Avg: 24.25 / Max: 26.66Min: 23.44 / Avg: 23.94 / Max: 24.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400m1231530456075SE +/- 1.00, N = 5SE +/- 0.15, N = 4SE +/- 1.92, N = 366.1868.4767.53MIN: 62.2 / MAX: 92.33MIN: 66.73 / MAX: 90.49MIN: 63.08 / MAX: 89.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400m1231326395265Min: 64.09 / Avg: 66.18 / Max: 68.79Min: 68.22 / Avg: 68.47 / Max: 68.9Min: 63.7 / Avg: 67.53 / Max: 69.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Timed HMMer Search

This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database Search12350100150200250SE +/- 0.76, N = 3SE +/- 0.25, N = 3SE +/- 0.59, N = 3224.33223.76225.091. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database Search1234080120160200Min: 222.83 / Avg: 224.33 / Max: 225.29Min: 223.28 / Avg: 223.76 / Max: 224.07Min: 223.94 / Avg: 225.09 / Max: 225.931. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

Timed MAFFT Alignment

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNA1233691215SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 311.8411.7311.861. (CC) gcc options: -std=c99 -O3 -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNA1233691215Min: 11.73 / Avg: 11.84 / Max: 11.97Min: 11.67 / Avg: 11.73 / Max: 11.8Min: 11.75 / Avg: 11.86 / Max: 12.071. (CC) gcc options: -std=c99 -O3 -lm -lpthread

Timed Clash Compilation

Build the clash-lang Haskell to VHDL/Verilog/SystemVerilog compiler with GHC 8.10.1 Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Clash CompilationTime To Compile123100200300400500SE +/- 0.24, N = 3SE +/- 2.07, N = 3SE +/- 0.20, N = 3482.03485.10484.60
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Clash CompilationTime To Compile12390180270360450Min: 481.59 / Avg: 482.03 / Max: 482.42Min: 482.63 / Avg: 485.1 / Max: 489.21Min: 484.28 / Avg: 484.6 / Max: 484.98

Timed FFmpeg Compilation

This test times how long it takes to build the FFmpeg multimedia library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.2.2Time To Compile123714212835SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 330.5930.6030.51
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.2.2Time To Compile123714212835Min: 30.47 / Avg: 30.59 / Max: 30.78Min: 30.44 / Avg: 30.6 / Max: 30.81Min: 30.44 / Avg: 30.51 / Max: 30.55

Build2

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To Compile12320406080100SE +/- 0.52, N = 3SE +/- 0.49, N = 3SE +/- 0.25, N = 379.0078.8678.80
OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To Compile1231530456075Min: 78.39 / Avg: 79 / Max: 80.03Min: 77.91 / Avg: 78.86 / Max: 79.54Min: 78.49 / Avg: 78.8 / Max: 79.29

Timed Eigen Compilation

This test times how long it takes to build all Eigen examples. The Eigen examples are compiled serially. Eigen is a C++ template library for linear algebra. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.3.9Time To Compile12320406080100SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.14, N = 385.7686.0285.78
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.3.9Time To Compile1231632486480Min: 85.62 / Avg: 85.76 / Max: 85.87Min: 85.89 / Avg: 86.02 / Max: 86.19Min: 85.56 / Avg: 85.78 / Max: 86.04

Monkey Audio Encoding

This test times how long it takes to encode a sample WAV file to Monkey's Audio APE format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMonkey Audio Encoding 3.99.6WAV To APE1233691215SE +/- 0.04, N = 5SE +/- 0.02, N = 5SE +/- 0.04, N = 513.0813.0113.111. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt
OpenBenchmarking.orgSeconds, Fewer Is BetterMonkey Audio Encoding 3.99.6WAV To APE12348121620Min: 13.01 / Avg: 13.08 / Max: 13.19Min: 12.96 / Avg: 13.01 / Max: 13.1Min: 12.98 / Avg: 13.11 / Max: 13.231. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt

Ogg Audio Encoding

This test times how long it takes to encode a sample WAV file to Ogg format using the reference Xiph.org tools/libraries. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Audio Encoding 1.3.4WAV To Ogg123612182430SE +/- 0.11, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 323.2223.2023.171. (CC) gcc options: -O2 -ffast-math -fsigned-char
OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Audio Encoding 1.3.4WAV To Ogg123510152025Min: 23.11 / Avg: 23.22 / Max: 23.43Min: 23.11 / Avg: 23.2 / Max: 23.38Min: 23.09 / Avg: 23.17 / Max: 23.221. (CC) gcc options: -O2 -ffast-math -fsigned-char

Opus Codec Encoding

Opus is an open audio codec. Opus is a lossy audio compression format designed primarily for interactive real-time applications over the Internet. This test uses Opus-Tools and measures the time required to encode a WAV file to Opus. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus Encode1233691215SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.04, N = 510.1810.1810.201. (CXX) g++ options: -fvisibility=hidden -logg -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus Encode1233691215Min: 10.17 / Avg: 10.18 / Max: 10.2Min: 10.16 / Avg: 10.18 / Max: 10.19Min: 10.15 / Avg: 10.2 / Max: 10.341. (CXX) g++ options: -fvisibility=hidden -logg -lm

SQLite Speedtest

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

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,0001231530456075SE +/- 0.09, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 366.0865.3064.791. (CC) gcc options: -O2 -ldl -lz -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,0001231326395265Min: 65.89 / Avg: 66.08 / Max: 66.18Min: 65.1 / Avg: 65.3 / Max: 65.54Min: 64.56 / Avg: 64.79 / Max: 64.931. (CC) gcc options: -O2 -ldl -lz -lpthread

WavPack Audio Encoding

This test times how long it takes to encode a sample WAV file to WavPack format with very high quality settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPack12348121620SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.02, N = 516.7916.7816.811. (CXX) g++ options: -rdynamic
OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPack12348121620Min: 16.75 / Avg: 16.79 / Max: 16.81Min: 16.74 / Avg: 16.78 / Max: 16.81Min: 16.77 / Avg: 16.81 / Max: 16.91. (CXX) g++ options: -rdynamic

64 Results Shown

simdjson:
  Kostya
  LargeRand
  PartialTweets
  DistinctUserID
Coremark
Node.js V8 Web Tooling Benchmark
CLOMP
Apache Siege:
  10
  50
  100
  200
  250
  500
BRL-CAD
oneDNN:
  IP Shapes 1D - f32 - CPU
  IP Shapes 3D - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
  IP Shapes 1D - bf16bf16bf16 - CPU
  IP Shapes 3D - bf16bf16bf16 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
  Deconvolution Batch shapes_1d - f32 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
  Convolution Batch Shapes Auto - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
  Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPU
NCNN:
  CPU - mobilenet
  CPU-v2-v2 - mobilenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU - shufflenet-v2
  CPU - mnasnet
  CPU - efficientnet-b0
  CPU - blazeface
  CPU - googlenet
  CPU - vgg16
  CPU - resnet18
  CPU - alexnet
  CPU - resnet50
  CPU - yolov4-tiny
  CPU - squeezenet_ssd
  CPU - regnety_400m
Timed HMMer Search
Timed MAFFT Alignment
Timed Clash Compilation
Timed FFmpeg Compilation
Build2
Timed Eigen Compilation
Monkey Audio Encoding
Ogg Audio Encoding
Opus Codec Encoding
SQLite Speedtest
WavPack Audio Encoding