ncnn mnn 2022

AMD Ryzen 9 5950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS) and AMD Radeon RX 6700/6700 XT / 6800M on Ubuntu 22.04 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 2208131-PTS-NCNNMNN216
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 2 Tests
Machine Learning 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
A
August 13 2022
  3 Hours, 26 Minutes
B
August 13 2022
  9 Hours, 13 Minutes
C
August 13 2022
  8 Hours, 56 Minutes
D
August 13 2022
  11 Hours, 18 Minutes
E
August 13 2022
  11 Hours, 19 Minutes
Invert Hiding All Results Option
  8 Hours, 51 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):

A

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --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: 0xa201016
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

B

C

D

E

Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: AMD Radeon RX 6700/6700 XT / 6800M (2880/1124MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 22.04, Kernel: 5.15.0-46-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160

ncnn mnn 2022OpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS)AMD Starship/Matisse32GB1000GB Sabrent Rocket 4.0 PlusAMD Radeon RX 6700/6700 XT / 6800M (2880/1124MHz)AMD Navi 21 HDMI AudioASUS MG28URealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 22.045.15.0-46-generic (x86_64)GNOME Shell 42.2X Server 1.21.1.3 + Wayland4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42)1.3.204GCC 11.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionNcnn Mnn 2022 BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --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 - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201016 - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.0Model: mobilenetV3DAECB0.43040.86081.29121.72162.152SE +/- 0.015, N = 15SE +/- 0.020, N = 3SE +/- 0.015, N = 15SE +/- 0.014, N = 3SE +/- 0.010, N = 31.9131.9031.9021.8651.860MIN: 1.69 / MAX: 11.76MIN: 1.71 / MAX: 13.23MIN: 1.69 / MAX: 11.39MIN: 1.74 / MAX: 10.98MIN: 1.74 / MAX: 11.331. (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 2.0Model: squeezenetv1.1DECBA0.74211.48422.22632.96843.7105SE +/- 0.036, N = 15SE +/- 0.028, N = 15SE +/- 0.046, N = 3SE +/- 0.058, N = 3SE +/- 0.079, N = 33.2983.2963.2783.2273.209MIN: 2.83 / MAX: 11.8MIN: 2.88 / MAX: 12.56MIN: 3.03 / MAX: 11.65MIN: 2.95 / MAX: 11.74MIN: 2.96 / MAX: 11.861. (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 2.0Model: resnet-v2-50ADBEC510152025SE +/- 0.06, N = 3SE +/- 0.10, N = 15SE +/- 0.49, N = 3SE +/- 0.08, N = 15SE +/- 0.14, N = 321.9621.7021.5621.5421.10MIN: 19.8 / MAX: 82.59MIN: 19.47 / MAX: 39.03MIN: 19.55 / MAX: 34.8MIN: 19.51 / MAX: 34.69MIN: 19.73 / MAX: 46.881. (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 2.0Model: SqueezeNetV1.0ECDAB1.2112.4223.6334.8446.055SE +/- 0.042, N = 15SE +/- 0.070, N = 3SE +/- 0.047, N = 15SE +/- 0.029, N = 3SE +/- 0.059, N = 35.3825.3505.3025.2345.144MIN: 4.9 / MAX: 40.68MIN: 5.01 / MAX: 13.89MIN: 4.58 / MAX: 14.4MIN: 4.93 / MAX: 13.77MIN: 4.8 / MAX: 17.581. (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 2.0Model: MobileNetV2_224ECDAB0.78121.56242.34363.12483.906SE +/- 0.024, N = 15SE +/- 0.008, N = 3SE +/- 0.026, N = 15SE +/- 0.011, N = 3SE +/- 0.019, N = 33.4723.4683.4563.4493.422MIN: 3.04 / MAX: 13.37MIN: 3.25 / MAX: 13.17MIN: 3.05 / MAX: 17.71MIN: 3.24 / MAX: 13.32MIN: 3.2 / MAX: 12.931. (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 2.0Model: mobilenet-v1-1.0ADECB0.59061.18121.77182.36242.953SE +/- 0.021, N = 3SE +/- 0.025, N = 15SE +/- 0.018, N = 15SE +/- 0.031, N = 3SE +/- 0.018, N = 32.6252.5922.5812.5562.542MIN: 2.41 / MAX: 11.15MIN: 2.32 / MAX: 11.27MIN: 2.32 / MAX: 11.34MIN: 2.32 / MAX: 11.13MIN: 2.36 / MAX: 11.091. (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 2.0Model: inception-v3AEDCB612182430SE +/- 0.18, N = 3SE +/- 0.06, N = 15SE +/- 0.08, N = 15SE +/- 0.05, N = 3SE +/- 0.07, N = 326.0725.9925.9225.9125.81MIN: 24.37 / MAX: 39.27MIN: 23.91 / MAX: 39.7MIN: 23.04 / MAX: 39.16MIN: 24.43 / MAX: 37.78MIN: 24.39 / MAX: 40.841. (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

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 20220729Target: CPU - Model: mobilenetBDCEA3691215SE +/- 0.35, N = 15SE +/- 0.14, N = 3SE +/- 0.14, N = 3SE +/- 0.05, N = 3SE +/- 0.16, N = 311.9211.8411.7111.6411.46MIN: 10.28 / MAX: 716.44MIN: 10.94 / MAX: 29.92MIN: 10.59 / MAX: 60.99MIN: 10.9 / MAX: 20.48MIN: 10.61 / MAX: 19.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2BDEAC0.97431.94862.92293.89724.8715SE +/- 0.04, N = 15SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 34.334.314.304.294.28MIN: 3.93 / MAX: 33.03MIN: 3.94 / MAX: 16.66MIN: 3.94 / MAX: 12.37MIN: 3.94 / MAX: 12.29MIN: 3.95 / MAX: 12.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3BADCE0.85951.7192.57853.4384.2975SE +/- 0.04, N = 15SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.823.783.773.773.76MIN: 3.55 / MAX: 35.21MIN: 3.56 / MAX: 11.69MIN: 3.55 / MAX: 11.83MIN: 3.56 / MAX: 11.78MIN: 3.56 / MAX: 12.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2CBAED0.96751.9352.90253.874.8375SE +/- 0.01, N = 3SE +/- 0.01, N = 14SE +/- 0.03, N = 2SE +/- 0.01, N = 3SE +/- 0.01, N = 34.304.304.304.284.26MIN: 4.07 / MAX: 12.2MIN: 3.97 / MAX: 35.81MIN: 4.03 / MAX: 12.41MIN: 4.01 / MAX: 12.08MIN: 4.01 / MAX: 12.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetBEDCA0.89331.78662.67993.57324.4665SE +/- 0.05, N = 15SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.973.903.903.893.89MIN: 3.69 / MAX: 14.19MIN: 3.65 / MAX: 24.96MIN: 3.68 / MAX: 11.86MIN: 3.69 / MAX: 11.45MIN: 3.68 / MAX: 11.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0DBAEC246810SE +/- 0.08, N = 3SE +/- 0.03, N = 15SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 36.025.975.915.905.90MIN: 5.56 / MAX: 47.25MIN: 5.56 / MAX: 78.45MIN: 5.57 / MAX: 17MIN: 5.53 / MAX: 32.65MIN: 5.59 / MAX: 14.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceDECAB0.4230.8461.2691.6922.115SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 151.881.831.821.821.80MIN: 1.68 / MAX: 49.69MIN: 1.69 / MAX: 10.06MIN: 1.71 / MAX: 4.41MIN: 1.7 / MAX: 9.71MIN: 1.63 / MAX: 9.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetABDEC3691215SE +/- 0.31, N = 3SE +/- 0.10, N = 15SE +/- 0.14, N = 3SE +/- 0.11, N = 3SE +/- 0.01, N = 312.1911.6911.5611.5311.38MIN: 10.69 / MAX: 42.59MIN: 10.57 / MAX: 54.38MIN: 10.58 / MAX: 20.15MIN: 10.64 / MAX: 33.91MIN: 10.66 / MAX: 20.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16ECABD1122334455SE +/- 0.40, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 15SE +/- 0.08, N = 347.9447.5847.5847.5247.34MIN: 44.37 / MAX: 85.57MIN: 44.41 / MAX: 87.25MIN: 44.3 / MAX: 69.79MIN: 43.88 / MAX: 109.37MIN: 43.83 / MAX: 71.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18BADEC3691215SE +/- 0.05, N = 15SE +/- 0.02, N = 3SE +/- 0.17, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 312.2112.1712.1612.1412.08MIN: 10.82 / MAX: 25.49MIN: 11.06 / MAX: 20.42MIN: 10.93 / MAX: 21.19MIN: 10.93 / MAX: 29.46MIN: 10.9 / MAX: 20.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetEABDC3691215SE +/- 1.56, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 15SE +/- 0.03, N = 3SE +/- 0.09, N = 39.307.797.737.727.67MIN: 7.13 / MAX: 633.17MIN: 7.1 / MAX: 16.44MIN: 7.11 / MAX: 21.38MIN: 7.14 / MAX: 16.18MIN: 7.09 / MAX: 16.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50CDAEB510152025SE +/- 0.15, N = 3SE +/- 0.10, N = 3SE +/- 0.28, N = 3SE +/- 0.19, N = 3SE +/- 0.11, N = 1521.7021.4821.4721.3920.98MIN: 19.94 / MAX: 30.5MIN: 19.75 / MAX: 39.98MIN: 19.56 / MAX: 30.76MIN: 19.66 / MAX: 37.46MIN: 18.95 / MAX: 79.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyCAEBD510152025SE +/- 0.14, N = 3SE +/- 0.14, N = 3SE +/- 0.14, N = 3SE +/- 0.09, N = 15SE +/- 0.04, N = 321.5721.5121.4321.3321.30MIN: 19.56 / MAX: 36.88MIN: 19.61 / MAX: 83.91MIN: 19.88 / MAX: 29.43MIN: 19.29 / MAX: 47.85MIN: 19.44 / MAX: 33.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdCBDAE510152025SE +/- 0.14, N = 3SE +/- 0.13, N = 15SE +/- 0.17, N = 3SE +/- 0.19, N = 3SE +/- 0.19, N = 318.5918.5318.3918.3218.17MIN: 16.26 / MAX: 43.69MIN: 15.19 / MAX: 66.5MIN: 15.88 / MAX: 27.52MIN: 15.5 / MAX: 34.97MIN: 16.13 / MAX: 27.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mCDABE3691215SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 15SE +/- 0.10, N = 312.9012.8512.8312.8112.79MIN: 12.14 / MAX: 20.46MIN: 12.05 / MAX: 26.05MIN: 12.11 / MAX: 26.51MIN: 11.76 / MAX: 25.73MIN: 11.97 / MAX: 21.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerDAEBC306090120150SE +/- 0.36, N = 3SE +/- 0.06, N = 3SE +/- 0.61, N = 3SE +/- 0.11, N = 15SE +/- 0.17, N = 3123.87123.55123.44122.89122.63MIN: 119.07 / MAX: 187.38MIN: 119.55 / MAX: 191.98MIN: 119.37 / MAX: 173.88MIN: 119.06 / MAX: 171.55MIN: 119.12 / MAX: 162.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetACBDE1.12052.2413.36154.4825.6025SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 15SE +/- 0.02, N = 3SE +/- 0.19, N = 34.984.934.904.864.84MIN: 4.56 / MAX: 12.11MIN: 4.52 / MAX: 11.93MIN: 4.19 / MAX: 12.29MIN: 4.61 / MAX: 12MIN: 4.19 / MAX: 12.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetEDCAB3691215SE +/- 0.23, N = 15SE +/- 0.17, N = 15SE +/- 0.22, N = 15SE +/- 0.13, N = 3SE +/- 0.10, N = 310.059.909.849.459.34MIN: 4.72 / MAX: 26.35MIN: 4.66 / MAX: 29.74MIN: 5.61 / MAX: 25.64MIN: 5.91 / MAX: 20.24MIN: 5.97 / MAX: 18.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2ECDBA0.450.91.351.82.25SE +/- 0.02, N = 15SE +/- 0.04, N = 15SE +/- 0.01, N = 15SE +/- 0.05, N = 3SE +/- 0.04, N = 32.001.991.981.951.92MIN: 1.7 / MAX: 12.73MIN: 1.69 / MAX: 14.04MIN: 1.69 / MAX: 9.54MIN: 1.71 / MAX: 6.43MIN: 1.7 / MAX: 6.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3EDBAC0.54231.08461.62692.16922.7115SE +/- 0.03, N = 15SE +/- 0.01, N = 15SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 152.412.362.362.352.34MIN: 2.07 / MAX: 19.36MIN: 2.08 / MAX: 15.13MIN: 2.09 / MAX: 9.49MIN: 2.07 / MAX: 8.2MIN: 2.07 / MAX: 14.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2BEDCA0.4770.9541.4311.9082.385SE +/- 0.02, N = 3SE +/- 0.01, N = 15SE +/- 0.02, N = 15SE +/- 0.02, N = 15SE +/- 0.07, N = 32.122.092.092.092.04MIN: 1.67 / MAX: 7.91MIN: 1.65 / MAX: 9.44MIN: 1.65 / MAX: 13.26MIN: 1.65 / MAX: 9.6MIN: 1.65 / MAX: 11.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetEDBCA0.4590.9181.3771.8362.295SE +/- 0.02, N = 14SE +/- 0.02, N = 13SE +/- 0.03, N = 3SE +/- 0.01, N = 15SE +/- 0.02, N = 32.042.042.042.011.97MIN: 1.73 / MAX: 11.29MIN: 1.73 / MAX: 14.09MIN: 1.74 / MAX: 9.58MIN: 1.73 / MAX: 9.57MIN: 1.73 / MAX: 6.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0ACBED1.10932.21863.32794.43725.5465SE +/- 0.04, N = 3SE +/- 0.02, N = 15SE +/- 0.05, N = 3SE +/- 0.01, N = 15SE +/- 0.01, N = 154.934.904.894.864.86MIN: 4.52 / MAX: 29.24MIN: 4.48 / MAX: 29.81MIN: 4.53 / MAX: 27.46MIN: 4.52 / MAX: 18.87MIN: 4.49 / MAX: 18.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceECDAB0.37350.7471.12051.4941.8675SE +/- 0.02, N = 15SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.04, N = 3SE +/- 0.02, N = 31.661.651.641.641.60MIN: 1.15 / MAX: 22.72MIN: 1.15 / MAX: 12.54MIN: 1.16 / MAX: 14.86MIN: 1.18 / MAX: 11.1MIN: 1.25 / MAX: 10.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetEDBAC0.8371.6742.5113.3484.185SE +/- 0.03, N = 15SE +/- 0.04, N = 15SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 153.723.713.713.673.66MIN: 3.24 / MAX: 18.21MIN: 3.24 / MAX: 25.35MIN: 3.26 / MAX: 16.59MIN: 3.25 / MAX: 17.16MIN: 3.24 / MAX: 16.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16BEADC246810SE +/- 0.06, N = 3SE +/- 0.02, N = 15SE +/- 0.05, N = 3SE +/- 0.02, N = 15SE +/- 0.03, N = 156.936.806.776.756.75MIN: 6.25 / MAX: 28.94MIN: 6.24 / MAX: 30.4MIN: 6.25 / MAX: 25.32MIN: 6.25 / MAX: 28.85MIN: 6.25 / MAX: 36.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18AEDCB0.59181.18361.77542.36722.959SE +/- 0.03, N = 3SE +/- 0.03, N = 13SE +/- 0.03, N = 15SE +/- 0.02, N = 15SE +/- 0.02, N = 32.632.622.612.602.54MIN: 2.15 / MAX: 16.21MIN: 2.15 / MAX: 20.98MIN: 2.15 / MAX: 21.7MIN: 2.15 / MAX: 15.22MIN: 2.16 / MAX: 11.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetBECDA0.5041.0081.5122.0162.52SE +/- 0.08, N = 3SE +/- 0.03, N = 12SE +/- 0.03, N = 15SE +/- 0.02, N = 13SE +/- 0.06, N = 32.242.122.092.082.08MIN: 1.68 / MAX: 18.33MIN: 1.68 / MAX: 19.9MIN: 1.67 / MAX: 18.2MIN: 1.67 / MAX: 18.09MIN: 1.68 / MAX: 11.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50DCAEB1.1252.253.3754.55.625SE +/- 0.04, N = 15SE +/- 0.03, N = 15SE +/- 0.02, N = 3SE +/- 0.03, N = 15SE +/- 0.03, N = 35.005.004.994.974.94MIN: 4.5 / MAX: 30.89MIN: 4.49 / MAX: 33.3MIN: 4.5 / MAX: 26.58MIN: 4.49 / MAX: 30.82MIN: 4.5 / MAX: 26.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyEDACB48121620SE +/- 0.25, N = 15SE +/- 0.03, N = 15SE +/- 0.04, N = 3SE +/- 0.04, N = 15SE +/- 0.09, N = 314.7714.5914.5814.5614.48MIN: 12.94 / MAX: 50.63MIN: 12.89 / MAX: 35.38MIN: 13.18 / MAX: 22.42MIN: 12.76 / MAX: 28.55MIN: 13.05 / MAX: 21.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdEDCAB1.24882.49763.74644.99526.244SE +/- 0.14, N = 15SE +/- 0.12, N = 15SE +/- 0.13, N = 15SE +/- 0.07, N = 3SE +/- 0.10, N = 35.555.505.475.235.14MIN: 3.7 / MAX: 22.31MIN: 3.7 / MAX: 21.81MIN: 3.7 / MAX: 27.5MIN: 3.64 / MAX: 17.71MIN: 3.67 / MAX: 16.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mACDEB0.69981.39962.09942.79923.499SE +/- 0.13, N = 3SE +/- 0.03, N = 15SE +/- 0.03, N = 15SE +/- 0.03, N = 15SE +/- 0.12, N = 33.113.093.083.063.03MIN: 2.71 / MAX: 12.9MIN: 2.7 / MAX: 23.46MIN: 2.69 / MAX: 25.76MIN: 2.69 / MAX: 14.14MIN: 2.67 / MAX: 13.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerEADBC50100150200250SE +/- 0.36, N = 15SE +/- 0.44, N = 3SE +/- 0.34, N = 15SE +/- 1.44, N = 3SE +/- 0.33, N = 15220.85220.75220.31219.90219.57MIN: 204.72 / MAX: 1074.16MIN: 205.2 / MAX: 332.92MIN: 204.86 / MAX: 914.53MIN: 204.44 / MAX: 295.75MIN: 204.22 / MAX: 967.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetADECB0.56251.1251.68752.252.8125SE +/- 0.17, N = 3SE +/- 0.04, N = 15SE +/- 0.03, N = 15SE +/- 0.01, N = 14SE +/- 0.03, N = 32.502.382.372.332.28MIN: 1.86 / MAX: 8.64MIN: 1.84 / MAX: 9.1MIN: 1.85 / MAX: 17.06MIN: 1.84 / MAX: 7.89MIN: 1.85 / MAX: 8.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

A

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --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: 0xa201016
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 13 August 2022 10:00 by user pts.

B

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --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: 0xa201016
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 13 August 2022 10:28 by user pts.

C

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --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: 0xa201016
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 13 August 2022 12:05 by user pts.

D

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --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: 0xa201016
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 13 August 2022 12:41 by user pts.

E

Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: AMD Radeon RX 6700/6700 XT / 6800M (2880/1124MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 22.04, Kernel: 5.15.0-46-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, 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-bootstrap --enable-cet --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --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: 0xa201016
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 13 August 2022 13:39 by user pts.