NN TR 3960X + Radeon RX 5500 XT

AMD Ryzen Threadripper 3960X 24-Core testing with a MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) and Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB 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 2009245-PTS-NNTR396012
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
1
September 24 2020
  4 Hours, 57 Minutes
2
September 24 2020
  3 Hours, 1 Minute
3
September 24 2020
  3 Hours, 3 Minutes
Invert Behavior (Only Show Selected Data)
  3 Hours, 40 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):


NN TR 3960X + Radeon RX 5500 XTProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen Resolution123AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads)MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS)AMD Starship/Matisse32GB1000GB Sabrent Rocket 4.0 1TBSapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB (1900/875MHz)AMD Navi 10 HDMI AudioASUS MG28UAquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 20.045.9.0-rc5-14sep-patch (x86_64) 20200914GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.6 Mesa 20.0.8 (LLVM 10.0.0)1.2.128GCC 9.3.0ext43840x2160OpenBenchmarking.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,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 ondemand - CPU Microcode: 0x8301025Security 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%100%100%101%101%NCNNTNNRealSR-NCNN

NN TR 3960X + Radeon RX 5500 XTncnn: CPU - resnet18ncnn: CPU - googlenetncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - vgg16ncnn: CPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - squeezenetncnn: CPU - squeezenetncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - efficientnet-b0ncnn: Vulkan GPU - googlenetncnn: CPU - blazefacencnn: Vulkan GPU - shufflenet-v2ncnn: CPU - mnasnetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenetncnn: Vulkan GPU - yolov4-tinyncnn: CPU - shufflenet-v2tnn: CPU - SqueezeNet v1.1ncnn: Vulkan GPU - mnasnetrealsr-ncnn: 4x - Notnn: CPU - MobileNet v2realsr-ncnn: 4x - Yesncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - mobilenet12320.2539.5311.4356.9727.3869.586.7436.3034.1628.1620.8258.790.8912.067.228.5741.212.903.206.524.3716.9921.287.13237.8164.4425.178257.861183.30786.058.439.5919.8039.2711.7156.3528.0069.736.7137.2333.5128.6020.9258.780.9011.987.198.5741.372.883.206.494.3516.9321.307.15237.2364.4525.135257.621183.34470.438.229.3021.0141.2211.8858.1628.2171.616.9036.7834.1728.4520.6058.060.9012.117.258.6441.082.893.226.504.3616.9321.357.15237.8264.4425.184257.427183.38069.458.219.54OpenBenchmarking.org

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet18123510152025SE +/- 0.52, N = 3SE +/- 0.03, N = 3SE +/- 0.17, N = 320.2519.8021.01MIN: 19.51 / MAX: 24.44MIN: 19.56 / MAX: 24.32MIN: 20.51 / MAX: 33.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenet123918273645SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.14, N = 339.5339.2741.22MIN: 38.19 / MAX: 97.58MIN: 38.25 / MAX: 49.66MIN: 40.07 / MAX: 42.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnet1233691215SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 311.4311.7111.88MIN: 11.22 / MAX: 12.3MIN: 11.51 / MAX: 12.77MIN: 11.76 / MAX: 12.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet501231326395265SE +/- 0.80, N = 3SE +/- 0.18, N = 3SE +/- 0.67, N = 356.9756.3558.16MIN: 55.76 / MAX: 116.12MIN: 55.8 / MAX: 101.34MIN: 56.46 / MAX: 72.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tiny123714212835SE +/- 0.21, N = 3SE +/- 0.30, N = 3SE +/- 0.13, N = 327.3828.0028.21MIN: 26.82 / MAX: 28.17MIN: 27.26 / MAX: 46.57MIN: 27.77 / MAX: 32.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg161231632486480SE +/- 0.37, N = 3SE +/- 0.18, N = 3SE +/- 0.33, N = 369.5869.7371.61MIN: 67.57 / MAX: 82.43MIN: 68.49 / MAX: 77.46MIN: 69.64 / MAX: 129.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v3123246810SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.16, N = 36.746.716.90MIN: 6.57 / MAX: 7.22MIN: 6.56 / MAX: 7.43MIN: 6.54 / MAX: 105.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenet123918273645SE +/- 0.40, N = 7SE +/- 0.30, N = 3SE +/- 0.18, N = 336.3037.2336.78MIN: 34.06 / MAX: 93.7MIN: 36.09 / MAX: 42.49MIN: 34.68 / MAX: 102.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenet123816243240SE +/- 0.51, N = 3SE +/- 0.24, N = 3SE +/- 0.26, N = 334.1633.5134.17MIN: 32.67 / MAX: 117.09MIN: 32.21 / MAX: 92.06MIN: 33.09 / MAX: 77.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnet123714212835SE +/- 0.22, N = 7SE +/- 0.18, N = 3SE +/- 0.17, N = 328.1628.6028.45MIN: 24.94 / MAX: 57.14MIN: 24.84 / MAX: 71.78MIN: 25.05 / MAX: 67.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18123510152025SE +/- 0.13, N = 7SE +/- 0.21, N = 3SE +/- 0.01, N = 320.8220.9220.60MIN: 20.25 / MAX: 23.91MIN: 20.37 / MAX: 21.98MIN: 19.97 / MAX: 80.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet501231326395265SE +/- 0.07, N = 7SE +/- 0.18, N = 3SE +/- 0.85, N = 358.7958.7858.06MIN: 57.94 / MAX: 143.22MIN: 58.17 / MAX: 141.3MIN: 56.02 / MAX: 60.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazeface1230.20250.4050.60750.811.0125SE +/- 0.00, N = 7SE +/- 0.00, N = 3SE +/- 0.00, N = 30.890.900.90MIN: 0.87 / MAX: 1.19MIN: 0.88 / MAX: 1.25MIN: 0.88 / MAX: 1.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b01233691215SE +/- 0.11, N = 7SE +/- 0.03, N = 3SE +/- 0.15, N = 312.0611.9812.11MIN: 10.04 / MAX: 43.67MIN: 10.04 / MAX: 38.23MIN: 10.06 / MAX: 39.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v2123246810SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 37.227.197.25MIN: 6.94 / MAX: 7.7MIN: 6.97 / MAX: 7.73MIN: 6.86 / MAX: 7.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b0123246810SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 38.578.578.64MIN: 8.35 / MAX: 9.02MIN: 8.44 / MAX: 9.1MIN: 8.43 / MAX: 9.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenet123918273645SE +/- 0.13, N = 7SE +/- 0.15, N = 3SE +/- 0.20, N = 341.2141.3741.08MIN: 39.9 / MAX: 107.26MIN: 40.38 / MAX: 43.2MIN: 39.95 / MAX: 42.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazeface1230.65251.3051.95752.613.2625SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 32.902.882.89MIN: 2.76 / MAX: 3.07MIN: 2.74 / MAX: 3.29MIN: 2.77 / MAX: 3.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v21230.72451.4492.17352.8983.6225SE +/- 0.00, N = 7SE +/- 0.00, N = 3SE +/- 0.01, N = 33.203.203.22MIN: 3.14 / MAX: 3.47MIN: 3.14 / MAX: 3.4MIN: 3.14 / MAX: 5.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnet123246810SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 36.526.496.50MIN: 6.35 / MAX: 8.85MIN: 6.34 / MAX: 8.66MIN: 6.23 / MAX: 6.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v21230.98331.96662.94993.93324.9165SE +/- 0.01, N = 7SE +/- 0.00, N = 3SE +/- 0.00, N = 34.374.354.36MIN: 4.08 / MAX: 8.18MIN: 4.18 / MAX: 5.04MIN: 4.18 / MAX: 4.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenet12348121620SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 316.9916.9316.93MIN: 16.74 / MAX: 18.01MIN: 16.66 / MAX: 17.45MIN: 16.64 / MAX: 17.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tiny123510152025SE +/- 0.22, N = 7SE +/- 0.06, N = 3SE +/- 0.29, N = 321.2821.3021.35MIN: 11.57 / MAX: 43.2MIN: 10.97 / MAX: 44.03MIN: 11.91 / MAX: 44.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v2123246810SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 37.137.157.15MIN: 6.84 / MAX: 7.57MIN: 6.93 / MAX: 8.31MIN: 6.91 / MAX: 8.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

TNN

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

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.112350100150200250SE +/- 0.56, N = 3SE +/- 0.79, N = 3SE +/- 2.15, N = 3237.82237.24237.83MIN: 234.12 / MAX: 239.65MIN: 234.05 / MAX: 239.25MIN: 230.78 / MAX: 240.861. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnet1231.00132.00263.00394.00525.0065SE +/- 0.00, N = 7SE +/- 0.01, N = 3SE +/- 0.01, N = 34.444.454.44MIN: 4.28 / MAX: 4.89MIN: 4.3 / MAX: 4.78MIN: 4.29 / MAX: 4.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

RealSR-NCNN

RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: No123612182430SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 325.1825.1425.18

TNN

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

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v212360120180240300SE +/- 0.71, N = 3SE +/- 0.04, N = 3SE +/- 0.56, N = 3257.86257.62257.43MIN: 244.35 / MAX: 289.49MIN: 248.05 / MAX: 298.14MIN: 248.96 / MAX: 288.021. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

RealSR-NCNN

RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: Yes1234080120160200SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3183.31183.34183.38

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg1612320406080100SE +/- 16.43, N = 7SE +/- 0.28, N = 3SE +/- 0.18, N = 386.0570.4369.45MIN: 67.47 / MAX: 1163.59MIN: 68.71 / MAX: 81.81MIN: 68.18 / MAX: 83.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3123246810SE +/- 0.13, N = 7SE +/- 0.15, N = 3SE +/- 0.38, N = 38.438.228.21MIN: 6.97 / MAX: 52MIN: 6.98 / MAX: 50.24MIN: 7 / MAX: 35.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenet1233691215SE +/- 0.24, N = 7SE +/- 0.39, N = 3SE +/- 0.47, N = 39.599.309.54MIN: 6.09 / MAX: 36.77MIN: 6.71 / MAX: 31.05MIN: 6.58 / MAX: 28.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread