3800xt nn

AMD Ryzen 7 3800XT 8-Core testing with a MSI X370 XPOWER GAMING TITANIUM (MS-7A31) v1.0 (1.MS BIOS) and Sapphire AMD Radeon HD 4650 on Debian 10 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 2107097-IB-3800XTNN098
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:

HPC - High Performance Computing 3 Tests
Machine Learning 3 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
July 09
  5 Hours, 24 Minutes
2
July 09
  5 Hours, 16 Minutes
3
July 09
  3 Hours, 21 Minutes
Invert Hiding All Results Option
  4 Hours, 40 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):


3800xt nnProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDisplay ServerCompilerFile-SystemScreen Resolution123AMD Ryzen 7 3800XT 8-Core @ 3.90GHz (8 Cores / 16 Threads)MSI X370 XPOWER GAMING TITANIUM (MS-7A31) v1.0 (1.MS BIOS)AMD Starship/Matisse16GB128GB INTEL SSDPEKKW128G7Sapphire AMD Radeon HD 4650AMD RV710/730Intel I211Debian 104.19.0-17-amd64 (x86_64)X Server 1.20.4GCC 8.3.0ext41024x768OpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8701021 Java Details- OpenJDK Runtime Environment (build 11.0.11+9-post-Debian-1deb10u1)Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

123Result OverviewPhoronix Test Suite 10.6.1100%100%101%101%101%Mobile Neural NetworkTNNNCNNRenaissance

3800xt nnrenaissance: Scala Dottyrenaissance: Rand Forestrenaissance: ALS Movie Lensrenaissance: Apache Spark ALSrenaissance: Apache Spark Bayesrenaissance: Savina Reactors.IOrenaissance: Apache Spark PageRankrenaissance: Finagle HTTP Requestsrenaissance: In-Memory Database Shootoutrenaissance: Akka Unbalanced Cobwebbed Treerenaissance: Genetic Algorithm Using Jenetics + Futuresmnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3ncnn: 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_400mtnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.1123694.4680.27176.62052.51925.68181.23623.61729.83582.910511.51670.42.8614.30824.4096.7213.8223.19732.80717.205.414.594.314.297.241.8615.4865.3517.1013.5628.1126.9622.3210.542877.780247.98861.046219.772766.7683.97141.82027.51941.58109.33492.31742.23640.510514.21692.62.8614.34324.4146.7913.8983.22632.92417.135.404.594.324.267.221.8315.4366.6717.0813.4927.6427.1822.1910.192881.720248.41161.596217.468750.9672.27153.21977.41937.68110.23421.71736.43472.010574.61659.32.8564.29824.6886.7254.0653.19632.79517.395.424.594.304.277.231.8315.4565.8217.1014.0127.5726.9522.2910.182888.970249.55060.903225.877OpenBenchmarking.org

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Scala Dotty123170340510680850SE +/- 4.26, N = 3SE +/- 5.65, N = 3SE +/- 10.32, N = 15694.4766.7750.9MIN: 568.04 / MAX: 1528.4MIN: 563.93 / MAX: 1477.46MIN: 559.99 / MAX: 2958.83
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Scala Dotty123130260390520650Min: 688.95 / Avg: 694.41 / Max: 702.8Min: 757.41 / Avg: 766.72 / Max: 776.93Min: 686.32 / Avg: 750.89 / Max: 815.15

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Random Forest123150300450600750SE +/- 9.40, N = 3SE +/- 5.88, N = 3SE +/- 2.20, N = 3680.2683.9672.2MIN: 608.7 / MAX: 840.54MIN: 626.53 / MAX: 816.13MIN: 616.75 / MAX: 830.59
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Random Forest123120240360480600Min: 670.57 / Avg: 680.2 / Max: 699Min: 672.17 / Avg: 683.93 / Max: 690.2Min: 668.16 / Avg: 672.22 / Max: 675.72

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: ALS Movie Lens12315003000450060007500SE +/- 16.48, N = 3SE +/- 23.24, N = 3SE +/- 7.01, N = 37176.67141.87153.2MIN: 7154.04 / MAX: 7879.66MIN: 7102.96 / MAX: 7924.37MIN: 7139.38 / MAX: 7831.25
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: ALS Movie Lens12312002400360048006000Min: 7154.04 / Avg: 7176.62 / Max: 7208.7Min: 7102.96 / Avg: 7141.85 / Max: 7183.33Min: 7139.38 / Avg: 7153.22 / Max: 7162.1

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark ALS123400800120016002000SE +/- 5.11, N = 3SE +/- 6.47, N = 3SE +/- 23.56, N = 32052.52027.51977.4MIN: 1946.3 / MAX: 2244.61MIN: 1949.54 / MAX: 2258.66MIN: 1850.21 / MAX: 2122.46
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark ALS123400800120016002000Min: 2042.55 / Avg: 2052.46 / Max: 2059.56Min: 2014.87 / Avg: 2027.53 / Max: 2036.15Min: 1952.49 / Avg: 1977.41 / Max: 2024.51

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark Bayes123400800120016002000SE +/- 5.21, N = 3SE +/- 8.42, N = 3SE +/- 2.43, N = 31925.61941.51937.6MIN: 1469.38 / MAX: 1935.6MIN: 1474.04 / MAX: 1957.52MIN: 1469.32 / MAX: 1940.02
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark Bayes12330060090012001500Min: 1918 / Avg: 1925.63 / Max: 1935.6Min: 1929.04 / Avg: 1941.47 / Max: 1957.52Min: 1932.7 / Avg: 1937.55 / Max: 1940.02

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Savina Reactors.IO1232K4K6K8K10KSE +/- 90.50, N = 15SE +/- 107.95, N = 15SE +/- 113.52, N = 158181.28109.38110.2MIN: 7515.49 / MAX: 13584.35MIN: 7362.22 / MAX: 14764.62MIN: 7457.43 / MAX: 13392.01
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Savina Reactors.IO12314002800420056007000Min: 7515.49 / Avg: 8181.23 / Max: 8926.72Min: 7362.22 / Avg: 8109.28 / Max: 8895.3Min: 7457.43 / Avg: 8110.19 / Max: 8921.34

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark PageRank1238001600240032004000SE +/- 42.32, N = 3SE +/- 50.56, N = 3SE +/- 43.92, N = 153623.63492.33421.7MIN: 3204.77 / MAX: 3716.12MIN: 3104.55 / MAX: 3638.26MIN: 2764.62 / MAX: 3771.68
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark PageRank1236001200180024003000Min: 3542.51 / Avg: 3623.63 / Max: 3685.08Min: 3400.03 / Avg: 3492.34 / Max: 3574.23Min: 2962.7 / Avg: 3421.73 / Max: 3656.32

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Finagle HTTP Requests123400800120016002000SE +/- 3.61, N = 3SE +/- 4.82, N = 3SE +/- 11.72, N = 31729.81742.21736.4MIN: 1579.93 / MAX: 1789.42MIN: 1568.53 / MAX: 1823.17MIN: 1555.2 / MAX: 1904.32
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Finagle HTTP Requests12330060090012001500Min: 1723.74 / Avg: 1729.8 / Max: 1736.23Min: 1735.44 / Avg: 1742.24 / Max: 1751.56Min: 1713.51 / Avg: 1736.38 / Max: 1752.22

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: In-Memory Database Shootout1238001600240032004000SE +/- 28.02, N = 13SE +/- 45.53, N = 5SE +/- 43.56, N = 43582.93640.53472.0MIN: 3224.53 / MAX: 3897.38MIN: 3267.72 / MAX: 4627.58MIN: 3137.95 / MAX: 3858.73
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: In-Memory Database Shootout1236001200180024003000Min: 3489.27 / Avg: 3582.87 / Max: 3897.38Min: 3526.21 / Avg: 3640.46 / Max: 3785.58Min: 3367.65 / Avg: 3471.98 / Max: 3580.56

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Akka Unbalanced Cobwebbed Tree1232K4K6K8K10KSE +/- 95.45, N = 3SE +/- 22.31, N = 3SE +/- 97.37, N = 310511.510514.210574.6MIN: 8095.7 / MAX: 10698.04MIN: 8025.58 / MAX: 10557.75MIN: 8116.36 / MAX: 10766.94
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Akka Unbalanced Cobwebbed Tree1232K4K6K8K10KMin: 10383.16 / Avg: 10511.46 / Max: 10698.04Min: 10484.05 / Avg: 10514.17 / Max: 10557.75Min: 10451.86 / Avg: 10574.64 / Max: 10766.94

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Genetic Algorithm Using Jenetics + Futures123400800120016002000SE +/- 4.28, N = 3SE +/- 18.80, N = 3SE +/- 9.92, N = 31670.41692.61659.3MIN: 1627.7 / MAX: 1711.42MIN: 1624.36 / MAX: 1753.6MIN: 1612.96 / MAX: 1705.59
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Genetic Algorithm Using Jenetics + Futures12330060090012001500Min: 1664.08 / Avg: 1670.36 / Max: 1678.54Min: 1667.83 / Avg: 1692.57 / Max: 1729.46Min: 1644.32 / Avg: 1659.25 / Max: 1678.03

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 1.2Model: mobilenetV31230.64371.28741.93112.57483.2185SE +/- 0.044, N = 15SE +/- 0.031, N = 15SE +/- 0.005, N = 32.8612.8612.856MIN: 2.61 / MAX: 13.16MIN: 2.62 / MAX: 13.43MIN: 2.82 / MAX: 3.041. (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 1.2Model: mobilenetV3123246810Min: 2.73 / Avg: 2.86 / Max: 3.45Min: 2.65 / Avg: 2.86 / Max: 3.2Min: 2.85 / Avg: 2.86 / Max: 2.861. (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 1.2Model: squeezenetv1.11230.97721.95442.93163.90884.886SE +/- 0.030, N = 15SE +/- 0.057, N = 15SE +/- 0.020, N = 34.3084.3434.298MIN: 4.07 / MAX: 14.99MIN: 4.03 / MAX: 14.8MIN: 4.22 / MAX: 6.351. (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 1.2Model: squeezenetv1.1123246810Min: 4.11 / Avg: 4.31 / Max: 4.66Min: 4.07 / Avg: 4.34 / Max: 5.11Min: 4.27 / Avg: 4.3 / Max: 4.341. (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 1.2Model: resnet-v2-50123612182430SE +/- 0.13, N = 15SE +/- 0.10, N = 15SE +/- 0.51, N = 324.4124.4124.69MIN: 23.21 / MAX: 41.39MIN: 23.28 / MAX: 41.55MIN: 23.73 / MAX: 71.671. (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 1.2Model: resnet-v2-50123612182430Min: 23.55 / Avg: 24.41 / Max: 25.35Min: 23.83 / Avg: 24.41 / Max: 25.21Min: 23.91 / Avg: 24.69 / Max: 25.641. (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 1.2Model: SqueezeNetV1.0123246810SE +/- 0.059, N = 15SE +/- 0.072, N = 15SE +/- 0.081, N = 36.7216.7916.725MIN: 6.32 / MAX: 17.35MIN: 6.39 / MAX: 19.92MIN: 6.52 / MAX: 8.791. (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 1.2Model: SqueezeNetV1.01233691215Min: 6.37 / Avg: 6.72 / Max: 7.46Min: 6.43 / Avg: 6.79 / Max: 7.57Min: 6.58 / Avg: 6.72 / Max: 6.851. (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 1.2Model: MobileNetV2_2241230.91461.82922.74383.65844.573SE +/- 0.028, N = 15SE +/- 0.038, N = 15SE +/- 0.173, N = 33.8223.8984.065MIN: 3.57 / MAX: 4.34MIN: 3.65 / MAX: 14.74MIN: 3.82 / MAX: 13.81. (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 1.2Model: MobileNetV2_224123246810Min: 3.59 / Avg: 3.82 / Max: 3.97Min: 3.69 / Avg: 3.9 / Max: 4.36Min: 3.85 / Avg: 4.06 / Max: 4.411. (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 1.2Model: mobilenet-v1-1.01230.72591.45182.17772.90363.6295SE +/- 0.029, N = 15SE +/- 0.057, N = 14SE +/- 0.005, N = 33.1973.2263.196MIN: 2.98 / MAX: 13.17MIN: 3.03 / MAX: 13.31MIN: 3.16 / MAX: 3.61. (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 1.2Model: mobilenet-v1-1.0123246810Min: 3.01 / Avg: 3.2 / Max: 3.49Min: 3.05 / Avg: 3.23 / Max: 3.95Min: 3.19 / Avg: 3.2 / Max: 3.21. (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 1.2Model: inception-v3123816243240SE +/- 0.14, N = 15SE +/- 0.10, N = 15SE +/- 0.26, N = 332.8132.9232.80MIN: 31.66 / MAX: 55.39MIN: 31.72 / MAX: 54.26MIN: 32.33 / MAX: 541. (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 1.2Model: inception-v3123714212835Min: 31.82 / Avg: 32.81 / Max: 33.63Min: 32.51 / Avg: 32.92 / Max: 33.77Min: 32.51 / Avg: 32.79 / Max: 33.321. (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

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 20210525Target: CPU - Model: mobilenet12348121620SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.18, N = 317.2017.1317.39MIN: 16.61 / MAX: 18.04MIN: 15.97 / MAX: 21.27MIN: 16.67 / MAX: 22.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mobilenet12348121620Min: 17.06 / Avg: 17.2 / Max: 17.34Min: 16.99 / Avg: 17.13 / Max: 17.34Min: 17.09 / Avg: 17.39 / Max: 17.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v21231.21952.4393.65854.8786.0975SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 35.415.405.42MIN: 5.32 / MAX: 5.53MIN: 5.34 / MAX: 5.59MIN: 5.36 / MAX: 5.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v2123246810Min: 5.4 / Avg: 5.41 / Max: 5.42Min: 5.39 / Avg: 5.4 / Max: 5.42Min: 5.42 / Avg: 5.42 / Max: 5.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v31231.03282.06563.09844.13125.164SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 34.594.594.59MIN: 4.52 / MAX: 7.44MIN: 4.53 / MAX: 4.94MIN: 4.52 / MAX: 7.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v3123246810Min: 4.57 / Avg: 4.59 / Max: 4.62Min: 4.58 / Avg: 4.59 / Max: 4.59Min: 4.57 / Avg: 4.59 / Max: 4.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v21230.9721.9442.9163.8884.86SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 34.314.324.30MIN: 4.25 / MAX: 4.42MIN: 4.24 / MAX: 4.46MIN: 4.24 / MAX: 4.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v2123246810Min: 4.29 / Avg: 4.31 / Max: 4.32Min: 4.29 / Avg: 4.32 / Max: 4.35Min: 4.3 / Avg: 4.3 / Max: 4.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet1230.96531.93062.89593.86124.8265SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 34.294.264.27MIN: 4.22 / MAX: 4.53MIN: 4.21 / MAX: 4.42MIN: 4.22 / MAX: 4.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet123246810Min: 4.26 / Avg: 4.29 / Max: 4.35Min: 4.25 / Avg: 4.26 / Max: 4.27Min: 4.26 / Avg: 4.27 / Max: 4.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b0123246810SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 37.247.227.23MIN: 7.14 / MAX: 12.02MIN: 7.13 / MAX: 7.51MIN: 7.13 / MAX: 7.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b01233691215Min: 7.19 / Avg: 7.24 / Max: 7.31Min: 7.2 / Avg: 7.22 / Max: 7.23Min: 7.2 / Avg: 7.23 / Max: 7.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface1230.41850.8371.25551.6742.0925SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.861.831.83MIN: 1.81 / MAX: 4.44MIN: 1.81 / MAX: 1.89MIN: 1.8 / MAX: 2.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface123246810Min: 1.83 / Avg: 1.86 / Max: 1.92Min: 1.83 / Avg: 1.83 / Max: 1.83Min: 1.83 / Avg: 1.83 / Max: 1.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet12348121620SE +/- 0.11, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 315.4815.4315.45MIN: 15.24 / MAX: 15.96MIN: 15.28 / MAX: 17.42MIN: 15.3 / MAX: 15.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet12348121620Min: 15.36 / Avg: 15.48 / Max: 15.7Min: 15.4 / Avg: 15.43 / Max: 15.44Min: 15.43 / Avg: 15.45 / Max: 15.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg161231530456075SE +/- 0.69, N = 3SE +/- 0.10, N = 3SE +/- 0.63, N = 365.3566.6765.82MIN: 64.12 / MAX: 85.11MIN: 63.99 / MAX: 88.7MIN: 64.27 / MAX: 85.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg161231326395265Min: 64.5 / Avg: 65.35 / Max: 66.73Min: 66.47 / Avg: 66.67 / Max: 66.81Min: 64.97 / Avg: 65.82 / Max: 67.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet1812348121620SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 317.1017.0817.10MIN: 16.98 / MAX: 17.38MIN: 16.84 / MAX: 17.5MIN: 16.86 / MAX: 22.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet1812348121620Min: 17.07 / Avg: 17.1 / Max: 17.15Min: 16.95 / Avg: 17.08 / Max: 17.21Min: 16.99 / Avg: 17.1 / Max: 17.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet12348121620SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.38, N = 313.5613.4914.01MIN: 13.39 / MAX: 13.79MIN: 13.31 / MAX: 13.73MIN: 13.5 / MAX: 25.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet12348121620Min: 13.5 / Avg: 13.56 / Max: 13.61Min: 13.43 / Avg: 13.49 / Max: 13.53Min: 13.63 / Avg: 14.01 / Max: 14.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet50123714212835SE +/- 0.58, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 328.1127.6427.57MIN: 27.3 / MAX: 61.91MIN: 27.42 / MAX: 27.99MIN: 27.29 / MAX: 30.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet50123612182430Min: 27.43 / Avg: 28.11 / Max: 29.26Min: 27.59 / Avg: 27.64 / Max: 27.68Min: 27.47 / Avg: 27.57 / Max: 27.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny123612182430SE +/- 0.05, N = 3SE +/- 0.41, N = 3SE +/- 0.03, N = 326.9627.1826.95MIN: 26.7 / MAX: 29.67MIN: 26.55 / MAX: 40.87MIN: 26.74 / MAX: 27.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny123612182430Min: 26.86 / Avg: 26.96 / Max: 27.04Min: 26.73 / Avg: 27.18 / Max: 28Min: 26.89 / Avg: 26.95 / Max: 26.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd123510152025SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 322.3222.1922.29MIN: 22.02 / MAX: 26.98MIN: 21.93 / MAX: 23.3MIN: 21.96 / MAX: 22.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd123510152025Min: 22.25 / Avg: 22.32 / Max: 22.38Min: 22.08 / Avg: 22.19 / Max: 22.25Min: 22.17 / Avg: 22.29 / Max: 22.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m1233691215SE +/- 0.37, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 310.5410.1910.18MIN: 10.08 / MAX: 33.92MIN: 10.1 / MAX: 10.46MIN: 10.1 / MAX: 10.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m1233691215Min: 10.16 / Avg: 10.54 / Max: 11.28Min: 10.18 / Avg: 10.19 / Max: 10.19Min: 10.17 / Avg: 10.18 / Max: 10.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

TNN

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

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNet1236001200180024003000SE +/- 8.10, N = 3SE +/- 8.27, N = 3SE +/- 3.19, N = 32877.782881.722888.97MIN: 2766.93 / MAX: 2988.44MIN: 2773.43 / MAX: 2985.5MIN: 2783.25 / MAX: 2990.511. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNet1235001000150020002500Min: 2865.94 / Avg: 2877.78 / Max: 2893.27Min: 2865.41 / Avg: 2881.72 / Max: 2892.25Min: 2885.22 / Avg: 2888.97 / Max: 2895.311. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v212350100150200250SE +/- 0.73, N = 3SE +/- 1.15, N = 3SE +/- 1.57, N = 3247.99248.41249.55MIN: 240.12 / MAX: 277.2MIN: 241.17 / MAX: 260.2MIN: 241.36 / MAX: 2751. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v212350100150200250Min: 246.62 / Avg: 247.99 / Max: 249.12Min: 246.15 / Avg: 248.41 / Max: 249.96Min: 246.74 / Avg: 249.55 / Max: 252.171. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v21231428425670SE +/- 0.09, N = 3SE +/- 0.23, N = 3SE +/- 0.42, N = 361.0561.6060.90MIN: 60.42 / MAX: 61.71MIN: 60.92 / MAX: 62.71MIN: 59.77 / MAX: 61.851. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v21231224364860Min: 60.88 / Avg: 61.05 / Max: 61.17Min: 61.29 / Avg: 61.6 / Max: 62.06Min: 60.07 / Avg: 60.9 / Max: 61.321. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.112350100150200250SE +/- 0.31, N = 3SE +/- 0.14, N = 3SE +/- 0.10, N = 3219.77217.47225.88MIN: 218.71 / MAX: 229.87MIN: 216.8 / MAX: 226.51MIN: 224.92 / MAX: 233.11. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.11234080120160200Min: 219.15 / Avg: 219.77 / Max: 220.16Min: 217.3 / Avg: 217.47 / Max: 217.74Min: 225.73 / Avg: 225.88 / Max: 226.051. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl