RTX 3080 NN Vulkan

AMD Ryzen 9 3950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS) and NVIDIA GeForce RTX 3080 10GB 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 2010075-PTS-RTX3080N35
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:

NVIDIA GPU Compute 2 Tests
Vulkan Compute 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
Performance Per
Dollar
Date
Run
  Test
  Duration
1
October 07 2020
  21 Minutes
2
October 07 2020
  12 Minutes
3
October 07 2020
  12 Minutes
4
October 07 2020
  12 Minutes
Invert Hiding All Results Option
  14 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

Processor: AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 2000GB Corsair Force MP600 + 2000GB, Graphics: NVIDIA GeForce RTX 3080 10GB (1710/9501MHz), Audio: NVIDIA Device 1aef, Monitor: DELL P2415Q, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 20.04, Kernel: 5.4.0-48-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: NVIDIA 455.23.05, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 11.1.70, Vulkan: 1.2.142, Compiler: GCC 9.3.0 + CUDA 11.1, File-System: ext4, Screen Resolution: 3840x2160

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++,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 Notes: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8701013
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

Changed Graphics to NVIDIA GeForce RTX 3080 10GB (360/5001MHz).

3

Changed Graphics to NVIDIA GeForce RTX 3080 10GB (1710/9501MHz).

4

Changed Graphics to NVIDIA GeForce RTX 3080 10GB (375/810MHz).

RTX 3080 NN VulkanProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen Resolution1234AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS)AMD Starship/Matisse16GB2000GB Corsair Force MP600 + 2000GBNVIDIA GeForce RTX 3080 10GB (1710/9501MHz)NVIDIA Device 1aefDELL P2415QRealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 20.045.4.0-48-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8NVIDIA 455.23.054.6.0OpenCL 1.2 CUDA 11.1.701.2.142GCC 9.3.0 + CUDA 11.1ext43840x2160NVIDIA GeForce RTX 3080 10GB (360/5001MHz)NVIDIA GeForce RTX 3080 10GB (1710/9501MHz)NVIDIA GeForce RTX 3080 10GB (375/810MHz)OpenBenchmarking.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 performance - CPU Microcode: 0x8701013Security 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

1234Result OverviewPhoronix Test Suite100%107%114%121%128%RealSR-NCNNRealSR-NCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNN4x - No4x - YesVulkan GPU - blazefaceVulkan GPU - resnet18Vulkan GPU - shufflenet-v2Vulkan GPU - efficientnet-b0Vulkan GPU - alexnetVulkan GPU-v2-v2 - mobilenet-v2Vulkan GPU - resnet50Vulkan GPU - mnasnetVulkan GPU - googlenetVulkan GPU - squeezenetVulkan GPU - yolov4-tinyVulkan GPU-v3-v3 - mobilenet-v3Vulkan GPU - vgg16Vulkan GPU - mobilenet

RTX 3080 NN Vulkanrealsr-ncnn: 4x - Norealsr-ncnn: 4x - Yesncnn: Vulkan GPU - squeezenetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tiny12348.79236.3413.494.261.481.741.331.572.740.583.284.111.251.463.106.996.89634.7423.484.271.481.751.341.582.730.593.284.101.261.473.096.996.86234.6883.474.261.471.741.331.572.720.573.264.101.251.463.106.956.92034.7353.484.271.471.741.331.572.720.573.274.091.251.473.116.96OpenBenchmarking.org

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: No1234246810SE +/- 0.311, N = 12SE +/- 0.039, N = 3SE +/- 0.044, N = 3SE +/- 0.045, N = 38.7926.8966.8626.920
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: No12343691215Min: 7.04 / Avg: 8.79 / Max: 10.26Min: 6.83 / Avg: 6.9 / Max: 6.96Min: 6.78 / Avg: 6.86 / Max: 6.93Min: 6.84 / Avg: 6.92 / Max: 6.99

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: Yes1234816243240SE +/- 0.41, N = 15SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 336.3434.7434.6934.74
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: Yes1234816243240Min: 34.88 / Avg: 36.34 / Max: 39.06Min: 34.59 / Avg: 34.74 / Max: 34.89Min: 34.62 / Avg: 34.69 / Max: 34.74Min: 34.56 / Avg: 34.73 / Max: 34.9

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 20200916Target: Vulkan GPU - Model: squeezenet12340.78531.57062.35593.14123.9265SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 33.493.483.473.48MIN: 3.36 / MAX: 4.27MIN: 3.34 / MAX: 3.7MIN: 3.29 / MAX: 4.32MIN: 3.34 / MAX: 3.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenet1234246810Min: 3.47 / Avg: 3.49 / Max: 3.53Min: 3.45 / Avg: 3.48 / Max: 3.53Min: 3.42 / Avg: 3.47 / Max: 3.5Min: 3.46 / Avg: 3.48 / Max: 3.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenet12340.96081.92162.88243.84324.804SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 34.264.274.264.27MIN: 4.17 / MAX: 4.66MIN: 4.16 / MAX: 4.62MIN: 4.19 / MAX: 4.53MIN: 4.2 / MAX: 4.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenet1234246810Min: 4.22 / Avg: 4.26 / Max: 4.3Min: 4.22 / Avg: 4.27 / Max: 4.32Min: 4.22 / Avg: 4.26 / Max: 4.29Min: 4.25 / Avg: 4.27 / Max: 4.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v212340.3330.6660.9991.3321.665SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.481.481.471.47MIN: 1.46 / MAX: 2.64MIN: 1.46 / MAX: 2.51MIN: 1.46 / MAX: 2.61MIN: 1.46 / MAX: 2.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v21234246810Min: 1.47 / Avg: 1.48 / Max: 1.48Min: 1.47 / Avg: 1.48 / Max: 1.49Min: 1.47 / Avg: 1.47 / Max: 1.48Min: 1.47 / Avg: 1.47 / Max: 1.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v312340.39380.78761.18141.57521.969SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 31.741.751.741.74MIN: 1.72 / MAX: 2.53MIN: 1.72 / MAX: 5.64MIN: 1.72 / MAX: 2.24MIN: 1.71 / MAX: 2.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v31234246810Min: 1.73 / Avg: 1.74 / Max: 1.74Min: 1.74 / Avg: 1.75 / Max: 1.77Min: 1.73 / Avg: 1.74 / Max: 1.74Min: 1.73 / Avg: 1.74 / Max: 1.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v212340.30150.6030.90451.2061.5075SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.331.341.331.33MIN: 1.31 / MAX: 1.92MIN: 1.31 / MAX: 2.49MIN: 1.31 / MAX: 2.35MIN: 1.31 / MAX: 2.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v21234246810Min: 1.33 / Avg: 1.33 / Max: 1.34Min: 1.33 / Avg: 1.34 / Max: 1.35Min: 1.33 / Avg: 1.33 / Max: 1.34Min: 1.33 / Avg: 1.33 / Max: 1.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnet12340.35550.7111.06651.4221.7775SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.571.581.571.57MIN: 1.56 / MAX: 1.74MIN: 1.55 / MAX: 2.59MIN: 1.55 / MAX: 1.77MIN: 1.56 / MAX: 1.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnet1234246810Min: 1.57 / Avg: 1.57 / Max: 1.58Min: 1.57 / Avg: 1.58 / Max: 1.58Min: 1.57 / Avg: 1.57 / Max: 1.57Min: 1.56 / Avg: 1.57 / Max: 1.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b012340.61651.2331.84952.4663.0825SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.742.732.722.72MIN: 2.7 / MAX: 7.8MIN: 2.7 / MAX: 4.03MIN: 2.69 / MAX: 3.24MIN: 2.68 / MAX: 4.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b01234246810Min: 2.72 / Avg: 2.74 / Max: 2.75Min: 2.72 / Avg: 2.73 / Max: 2.73Min: 2.72 / Avg: 2.72 / Max: 2.73Min: 2.71 / Avg: 2.72 / Max: 2.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazeface12340.13280.26560.39840.53120.664SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.580.590.570.57MIN: 0.56 / MAX: 0.76MIN: 0.55 / MAX: 1.31MIN: 0.55 / MAX: 0.74MIN: 0.55 / MAX: 0.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazeface1234246810Min: 0.58 / Avg: 0.58 / Max: 0.58Min: 0.57 / Avg: 0.59 / Max: 0.6Min: 0.57 / Avg: 0.57 / Max: 0.58Min: 0.57 / Avg: 0.57 / Max: 0.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenet12340.7381.4762.2142.9523.69SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.283.283.263.27MIN: 3.24 / MAX: 4.17MIN: 3.24 / MAX: 3.95MIN: 3.24 / MAX: 3.66MIN: 3.24 / MAX: 4.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenet1234246810Min: 3.27 / Avg: 3.28 / Max: 3.28Min: 3.27 / Avg: 3.28 / Max: 3.28Min: 3.26 / Avg: 3.26 / Max: 3.27Min: 3.26 / Avg: 3.27 / Max: 3.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg1612340.92481.84962.77443.69924.624SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 34.114.104.104.09MIN: 4.06 / MAX: 7.85MIN: 4.06 / MAX: 5.4MIN: 4.04 / MAX: 10.03MIN: 4.06 / MAX: 6.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg161234246810Min: 4.09 / Avg: 4.11 / Max: 4.12Min: 4.09 / Avg: 4.1 / Max: 4.11Min: 4.09 / Avg: 4.1 / Max: 4.11Min: 4.09 / Avg: 4.09 / Max: 4.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet1812340.28350.5670.85051.1341.4175SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.251.261.251.25MIN: 1.23 / MAX: 1.82MIN: 1.23 / MAX: 2.21MIN: 1.23 / MAX: 1.54MIN: 1.23 / MAX: 1.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet181234246810Min: 1.25 / Avg: 1.25 / Max: 1.25Min: 1.25 / Avg: 1.26 / Max: 1.26Min: 1.24 / Avg: 1.25 / Max: 1.25Min: 1.24 / Avg: 1.25 / Max: 1.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnet12340.33080.66160.99241.32321.654SE +/- 0.01, N = 3SE +/- 0.01, N = 2SE +/- 0.00, N = 2SE +/- 0.01, N = 21.461.471.461.47MIN: 1.44 / MAX: 1.62MIN: 1.45 / MAX: 1.87MIN: 1.45 / MAX: 1.62MIN: 1.44 / MAX: 1.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnet1234246810Min: 1.45 / Avg: 1.46 / Max: 1.47Min: 1.46 / Avg: 1.47 / Max: 1.47Min: 1.46 / Avg: 1.46 / Max: 1.46Min: 1.46 / Avg: 1.47 / Max: 1.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet5012340.69981.39962.09942.79923.499SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 33.103.093.103.11MIN: 3.07 / MAX: 3.63MIN: 3.07 / MAX: 3.51MIN: 3.06 / MAX: 4.18MIN: 3.07 / MAX: 10.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet501234246810Min: 3.1 / Avg: 3.1 / Max: 3.11Min: 3.09 / Avg: 3.09 / Max: 3.09Min: 3.09 / Avg: 3.1 / Max: 3.1Min: 3.09 / Avg: 3.11 / Max: 3.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tiny1234246810SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 36.996.996.956.96MIN: 6.7 / MAX: 11.21MIN: 6.63 / MAX: 10.85MIN: 6.65 / MAX: 10.85MIN: 6.66 / MAX: 19.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tiny12343691215Min: 6.92 / Avg: 6.99 / Max: 7.06Min: 6.89 / Avg: 6.99 / Max: 7.08Min: 6.88 / Avg: 6.95 / Max: 6.99Min: 6.92 / Avg: 6.96 / Max: 7.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

1

Processor: AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 2000GB Corsair Force MP600 + 2000GB, Graphics: NVIDIA GeForce RTX 3080 10GB (1710/9501MHz), Audio: NVIDIA Device 1aef, Monitor: DELL P2415Q, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 20.04, Kernel: 5.4.0-48-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: NVIDIA 455.23.05, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 11.1.70, Vulkan: 1.2.142, Compiler: GCC 9.3.0 + CUDA 11.1, File-System: ext4, Screen Resolution: 3840x2160

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++,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 Notes: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8701013
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 7 October 2020 07:06 by user pts.

2

Processor: AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 2000GB Corsair Force MP600 + 2000GB, Graphics: NVIDIA GeForce RTX 3080 10GB (360/5001MHz), Audio: NVIDIA Device 1aef, Monitor: DELL P2415Q, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 20.04, Kernel: 5.4.0-48-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: NVIDIA 455.23.05, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 11.1.70, Vulkan: 1.2.142, Compiler: GCC 9.3.0 + CUDA 11.1, File-System: ext4, Screen Resolution: 3840x2160

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++,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 Notes: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8701013
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 7 October 2020 07:22 by user pts.

3

Processor: AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 2000GB Corsair Force MP600 + 2000GB, Graphics: NVIDIA GeForce RTX 3080 10GB (1710/9501MHz), Audio: NVIDIA Device 1aef, Monitor: DELL P2415Q, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 20.04, Kernel: 5.4.0-48-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: NVIDIA 455.23.05, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 11.1.70, Vulkan: 1.2.142, Compiler: GCC 9.3.0 + CUDA 11.1, File-System: ext4, Screen Resolution: 3840x2160

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++,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 Notes: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8701013
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 7 October 2020 08:20 by user pts.

4

Processor: AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 2000GB Corsair Force MP600 + 2000GB, Graphics: NVIDIA GeForce RTX 3080 10GB (375/810MHz), Audio: NVIDIA Device 1aef, Monitor: DELL P2415Q, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 20.04, Kernel: 5.4.0-48-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: NVIDIA 455.23.05, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 11.1.70, Vulkan: 1.2.142, Compiler: GCC 9.3.0 + CUDA 11.1, File-System: ext4, Screen Resolution: 3840x2160

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++,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 Notes: Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8701013
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 7 October 2020 08:25 by user pts.