tr 3970x eo june

AMD Ryzen Threadripper 3970X 32-Core testing with a ASUS ROG ZENITH II EXTREME (1201 BIOS) and AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB on Ubuntu 20.10 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 2106285-PTS-TR3970XE29
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
Performance Per
Dollar
Date
Run
  Test
  Duration
1
June 28 2021
  4 Hours, 15 Minutes
2
June 28 2021
  55 Minutes
3
June 28 2021
  56 Minutes
Invert Hiding All Results Option
  2 Hours, 2 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):

1

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/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 Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301039
Graphics Notes: GLAMOR
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

2

3

Processor: AMD Ryzen Threadripper 3970X 32-Core @ 4.55GHz (32 Cores / 64 Threads), Motherboard: ASUS ROG ZENITH II EXTREME (1201 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: Samsung SSD 980 PRO 500GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 20.10, Kernel: 5.11.0-rc6-phx (x86_64) 20210203, Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, OpenGL: 4.6 Mesa 20.2.1 (LLVM 11.0.0), Vulkan: 1.2.131, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 3840x2160

tr 3970x eo juneProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen Resolution123AMD Ryzen Threadripper 3970X 32-Core @ 4.55GHz (32 Cores / 64 Threads)ASUS ROG ZENITH II EXTREME (1201 BIOS)AMD Starship/Matisse64GBSamsung SSD 980 PRO 500GBAMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz)AMD Navi 10 HDMI AudioASUS VP28UAquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 20.105.11.0-rc6-phx (x86_64) 20210203GNOME Shell 3.38.1X Server 1.20.94.6 Mesa 20.2.1 (LLVM 11.0.0)1.2.131GCC 10.2.0ext43840x2160OpenBenchmarking.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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/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: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301039Graphics Details- GLAMORSecurity 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 Suite100%101%103%104%106%UnvanquishedMobile Neural NetworkC-BloscNCNNTNNGravityMark

tr 3970x eo junegravitymark: 1920 x 1080 - OpenGLgravitymark: 1920 x 1080 - Vulkangravitymark: 2560 x 1440 - OpenGLgravitymark: 2560 x 1440 - Vulkangravitymark: 3840 x 2160 - OpenGLgravitymark: 3840 x 2160 - Vulkanunvanquished: 1920 x 1080 - Highunvanquished: 1920 x 1200 - Highunvanquished: 2560 x 1440 - Highunvanquished: 3840 x 2160 - Highunvanquished: 1920 x 1080 - Ultraunvanquished: 1920 x 1200 - Ultraunvanquished: 2560 x 1440 - Ultraunvanquished: 3840 x 2160 - Ultraunvanquished: 1920 x 1080 - Mediumunvanquished: 1920 x 1200 - Mediumunvanquished: 2560 x 1440 - Mediumunvanquished: 3840 x 2160 - Mediumblosc: blosclzmnn: 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 v1.112380.087.969.177.050.456.2205.7191.1199.5206.1209.4199.3204.2196.5194.2216.8205.7206.624266.02.5184.44920.3996.0114.1242.84323.87617.557.637.307.877.0210.123.5817.7633.7314.479.6523.2326.0319.9921.132657.479268.49863.136233.87982.887.867.777.35156.6174.8198.6199.5234226.4206.2200.5229.5186.8184.7192.9170.324488.52.4444.27220.3285.8114.1192.81723.71217.327.67.067.87.149.753.6216.6833.913.969.2823.0925.9219.6320.792657.589269.21362.605229.4748287.969.676.950.356.5210.4174184.9174.2182.7213.3220168.8186224.9175.7201.923982.12.594.57120.9176.1064.1262.84323.97117.227.687.17.776.759.913.5516.7534.8114.49.4123.0625.9120.1120.42651.012267.68161.911234.328OpenBenchmarking.org

GravityMark

OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.1bResolution: 1920 x 1080 - Renderer: OpenGL12320406080100SE +/- 1.32, N = 380.082.882.0
OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.1bResolution: 1920 x 1080 - Renderer: OpenGL1231632486480Min: 78 / Avg: 80 / Max: 82.5

OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.1bResolution: 1920 x 1080 - Renderer: Vulkan12320406080100SE +/- 0.20, N = 387.987.887.9
OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.1bResolution: 1920 x 1080 - Renderer: Vulkan12320406080100Min: 87.6 / Avg: 87.93 / Max: 88.3

OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.1bResolution: 2560 x 1440 - Renderer: OpenGL1231530456075SE +/- 0.69, N = 369.167.769.6
OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.1bResolution: 2560 x 1440 - Renderer: OpenGL1231326395265Min: 67.9 / Avg: 69.13 / Max: 70.3

OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.1bResolution: 2560 x 1440 - Renderer: Vulkan12320406080100SE +/- 0.10, N = 377.077.376.9
OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.1bResolution: 2560 x 1440 - Renderer: Vulkan1231530456075Min: 76.8 / Avg: 77 / Max: 77.1

OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.1bResolution: 3840 x 2160 - Renderer: OpenGL1231224364860SE +/- 0.31, N = 350.451.050.3
OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.1bResolution: 3840 x 2160 - Renderer: OpenGL1231020304050Min: 50 / Avg: 50.4 / Max: 51

OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.1bResolution: 3840 x 2160 - Renderer: Vulkan1231326395265SE +/- 0.18, N = 356.256.656.5
OpenBenchmarking.orgFrames Per Second, More Is BetterGravityMark 1.1bResolution: 3840 x 2160 - Renderer: Vulkan1231122334455Min: 55.9 / Avg: 56.17 / Max: 56.5

Unvanquished

Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1080 - Effects Quality: High12350100150200250SE +/- 5.21, N = 12205.7174.8210.4
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1080 - Effects Quality: High1234080120160200Min: 179.3 / Avg: 205.73 / Max: 238.4

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1200 - Effects Quality: High1234080120160200SE +/- 5.65, N = 15191.1198.6174.0
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1200 - Effects Quality: High1234080120160200Min: 171.3 / Avg: 191.09 / Max: 239.3

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 2560 x 1440 - Effects Quality: High1234080120160200SE +/- 4.72, N = 15199.5199.5184.9
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 2560 x 1440 - Effects Quality: High1234080120160200Min: 174.7 / Avg: 199.55 / Max: 237.2

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 3840 x 2160 - Effects Quality: High12350100150200250SE +/- 6.53, N = 15206.1234.0174.2
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 3840 x 2160 - Effects Quality: High1234080120160200Min: 167.2 / Avg: 206.14 / Max: 263.2

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1080 - Effects Quality: Ultra12350100150200250SE +/- 8.75, N = 15209.4226.4182.7
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1080 - Effects Quality: Ultra1234080120160200Min: 170.5 / Avg: 209.37 / Max: 283

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1200 - Effects Quality: Ultra12350100150200250SE +/- 4.65, N = 14199.3206.2213.3
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1200 - Effects Quality: Ultra1234080120160200Min: 172.4 / Avg: 199.27 / Max: 223.5

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 2560 x 1440 - Effects Quality: Ultra12350100150200250SE +/- 5.83, N = 15204.2200.5220.0
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 2560 x 1440 - Effects Quality: Ultra1234080120160200Min: 169.1 / Avg: 204.15 / Max: 239.3

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 3840 x 2160 - Effects Quality: Ultra12350100150200250SE +/- 6.89, N = 15196.5229.5168.8
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 3840 x 2160 - Effects Quality: Ultra1234080120160200Min: 168.3 / Avg: 196.52 / Max: 244.3

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1080 - Effects Quality: Medium1234080120160200SE +/- 5.32, N = 15194.2186.8186.0
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1080 - Effects Quality: Medium1234080120160200Min: 168.4 / Avg: 194.22 / Max: 238.1

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1200 - Effects Quality: Medium12350100150200250SE +/- 8.25, N = 15216.8184.7224.9
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1200 - Effects Quality: Medium1234080120160200Min: 167.5 / Avg: 216.77 / Max: 287.7

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 2560 x 1440 - Effects Quality: Medium12350100150200250SE +/- 7.79, N = 15205.7192.9175.7
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 2560 x 1440 - Effects Quality: Medium1234080120160200Min: 170.1 / Avg: 205.75 / Max: 275.3

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 3840 x 2160 - Effects Quality: Medium12350100150200250SE +/- 8.63, N = 15206.6170.3201.9
OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 3840 x 2160 - Effects Quality: Medium1234080120160200Min: 170 / Avg: 206.62 / Max: 295.5

C-Blosc

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

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.0Compressor: blosclz1235K10K15K20K25KSE +/- 252.81, N = 324266.024488.523982.11. (CC) gcc options: -std=gnu99 -O3 -pthread -lrt -lm
OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.0Compressor: blosclz1234K8K12K16K20KMin: 23816.7 / Avg: 24265.97 / Max: 24691.51. (CC) gcc options: -std=gnu99 -O3 -pthread -lrt -lm

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: mobilenetV31230.58281.16561.74842.33122.914SE +/- 0.013, N = 32.5182.4442.590MIN: 2.44 / MAX: 2.71MIN: 2.41 / MAX: 2.61MIN: 2.52 / MAX: 3.241. (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: 2.49 / Avg: 2.52 / Max: 2.531. (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: squeezenetv1.11231.02852.0573.08554.1145.1425SE +/- 0.116, N = 34.4494.2724.571MIN: 4.18 / MAX: 4.73MIN: 4.22 / MAX: 4.44MIN: 4.51 / MAX: 4.841. (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: 4.22 / Avg: 4.45 / Max: 4.581. (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-v2-50123510152025SE +/- 0.19, N = 320.4020.3320.92MIN: 19.85 / MAX: 21.42MIN: 20.04 / MAX: 20.94MIN: 20.68 / MAX: 22.51. (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-v2-50123510152025Min: 20.05 / Avg: 20.4 / Max: 20.681. (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 +/- 0.083, N = 36.0115.8116.106MIN: 5.8 / MAX: 6.42MIN: 5.74 / MAX: 6.33MIN: 6.04 / MAX: 6.651. (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: SqueezeNetV1.0123246810Min: 5.85 / Avg: 6.01 / Max: 6.131. (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_2241230.92841.85682.78523.71364.642SE +/- 0.012, N = 34.1244.1194.126MIN: 4.07 / MAX: 4.3MIN: 4.08 / MAX: 4.26MIN: 4.09 / MAX: 4.231. (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: 4.11 / Avg: 4.12 / Max: 4.151. (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-v1-1.01230.63971.27941.91912.55883.1985SE +/- 0.003, N = 32.8432.8172.843MIN: 2.8 / MAX: 3MIN: 2.78 / MAX: 2.91MIN: 2.81 / MAX: 3.031. (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: 2.84 / Avg: 2.84 / Max: 2.851. (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: inception-v3123612182430SE +/- 0.08, N = 323.8823.7123.97MIN: 23.51 / MAX: 24.82MIN: 23.46 / MAX: 25.21MIN: 23.66 / MAX: 24.581. (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-v3123612182430Min: 23.78 / Avg: 23.88 / Max: 24.041. (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

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 +/- 0.03, N = 317.5517.3217.22MIN: 16.78 / MAX: 54.56MIN: 16.64 / MAX: 19.26MIN: 16.57 / MAX: 18.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mobilenet12348121620Min: 17.5 / Avg: 17.55 / Max: 17.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v2123246810SE +/- 0.03, N = 37.637.607.68MIN: 7.24 / MAX: 9.1MIN: 7.19 / MAX: 18.28MIN: 7.29 / MAX: 9.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v21233691215Min: 7.56 / Avg: 7.63 / Max: 7.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v3123246810SE +/- 0.22, N = 37.307.067.10MIN: 6.81 / MAX: 110.43MIN: 6.8 / MAX: 8.54MIN: 6.84 / MAX: 8.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v31233691215Min: 7.05 / Avg: 7.3 / Max: 7.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v2123246810SE +/- 0.07, N = 37.877.807.77MIN: 7.44 / MAX: 9.36MIN: 7.42 / MAX: 8.91MIN: 7.42 / MAX: 10.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v21233691215Min: 7.8 / Avg: 7.87 / Max: 81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet123246810SE +/- 0.04, N = 37.027.146.75MIN: 6.7 / MAX: 9.47MIN: 6.62 / MAX: 8.3MIN: 6.51 / MAX: 7.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnet1233691215Min: 6.94 / Avg: 7.02 / Max: 7.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b01233691215SE +/- 0.11, N = 310.129.759.91MIN: 9.6 / MAX: 19.22MIN: 9.44 / MAX: 10.88MIN: 9.59 / MAX: 11.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b01233691215Min: 9.95 / Avg: 10.12 / Max: 10.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface1230.81451.6292.44353.2584.0725SE +/- 0.04, N = 33.583.623.55MIN: 3.38 / MAX: 12.86MIN: 3.45 / MAX: 4.81MIN: 3.39 / MAX: 4.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazeface123246810Min: 3.54 / Avg: 3.58 / Max: 3.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet12348121620SE +/- 0.08, N = 317.7616.6816.75MIN: 16.75 / MAX: 26.73MIN: 16.35 / MAX: 18MIN: 16.36 / MAX: 18.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenet12348121620Min: 17.63 / Avg: 17.76 / Max: 17.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg16123816243240SE +/- 0.19, N = 333.7333.9034.81MIN: 33.02 / MAX: 44.88MIN: 33.16 / MAX: 57.25MIN: 33.66 / MAX: 43.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg16123714212835Min: 33.44 / Avg: 33.73 / Max: 34.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet1812348121620SE +/- 0.08, N = 314.4713.9614.40MIN: 13.7 / MAX: 22.69MIN: 13.25 / MAX: 15.98MIN: 13.52 / MAX: 73.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet1812348121620Min: 14.36 / Avg: 14.47 / Max: 14.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet1233691215SE +/- 0.24, N = 39.659.289.41MIN: 8.85 / MAX: 12.41MIN: 8.86 / MAX: 11.09MIN: 8.93 / MAX: 11.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnet1233691215Min: 9.24 / Avg: 9.65 / Max: 10.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet50123612182430SE +/- 0.12, N = 323.2323.0923.06MIN: 22.06 / MAX: 33.11MIN: 22.07 / MAX: 32.05MIN: 22.05 / MAX: 26.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet50123510152025Min: 23.05 / Avg: 23.23 / Max: 23.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny123612182430SE +/- 0.07, N = 326.0325.9225.91MIN: 24.91 / MAX: 49.23MIN: 25.03 / MAX: 28.88MIN: 24.73 / MAX: 45.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tiny123612182430Min: 25.89 / Avg: 26.03 / Max: 26.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd123510152025SE +/- 0.03, N = 319.9919.6320.11MIN: 19.11 / MAX: 28.91MIN: 18.9 / MAX: 21.5MIN: 18.97 / MAX: 109.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssd123510152025Min: 19.95 / Avg: 19.99 / Max: 20.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m123510152025SE +/- 0.17, N = 321.1320.7920.40MIN: 20.22 / MAX: 23.98MIN: 20.13 / MAX: 23.47MIN: 19.75 / MAX: 23.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400m123510152025Min: 20.94 / Avg: 21.13 / Max: 21.481. (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 +/- 2.01, N = 32657.482657.592651.01MIN: 2552.48 / MAX: 2772.13MIN: 2555.66 / MAX: 2793.47MIN: 2514.73 / MAX: 2780.711. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNet1235001000150020002500Min: 2653.46 / Avg: 2657.48 / Max: 2659.581. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v212360120180240300SE +/- 0.87, N = 3268.50269.21267.68MIN: 248.69 / MAX: 327.41MIN: 249.65 / MAX: 314.41MIN: 248.78 / MAX: 312.081. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v212350100150200250Min: 267.62 / Avg: 268.5 / Max: 270.241. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v21231428425670SE +/- 0.39, N = 363.1462.6161.91MIN: 62.24 / MAX: 65.89MIN: 62.02 / MAX: 63.15MIN: 61.06 / MAX: 70.591. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v21231224364860Min: 62.6 / Avg: 63.14 / Max: 63.91. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.112350100150200250SE +/- 0.14, N = 3233.88229.47234.33MIN: 233.28 / MAX: 234.44MIN: 228.76 / MAX: 243.35MIN: 233.77 / MAX: 235.341. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.11234080120160200Min: 233.62 / Avg: 233.88 / Max: 234.071. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

1

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/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 Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301039
Graphics Notes: GLAMOR
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 28 June 2021 10:44 by user pts.

2

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/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 Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301039
Graphics Notes: GLAMOR
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 28 June 2021 14:15 by user pts.

3

Processor: AMD Ryzen Threadripper 3970X 32-Core @ 4.55GHz (32 Cores / 64 Threads), Motherboard: ASUS ROG ZENITH II EXTREME (1201 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: Samsung SSD 980 PRO 500GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 20.10, Kernel: 5.11.0-rc6-phx (x86_64) 20210203, Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, OpenGL: 4.6 Mesa 20.2.1 (LLVM 11.0.0), Vulkan: 1.2.131, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/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 Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301039
Graphics Notes: GLAMOR
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 28 June 2021 14:59 by user pts.