MNN Comparison

Intel Core i9-10900K testing with a Gigabyte Z490 AORUS MASTER (F3 BIOS) and Gigabyte AMD Radeon RX 5500/5500M / Pro 5500M 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 2101072-SYST-210106709
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

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
Disable Color Branding
Prefer Vertical Bar Graphs

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results 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
Ryzen 9 5950X
January 06 2021
  39 Minutes
Core i7 1165G7
January 06 2021
  1 Hour, 13 Minutes
EPYC 7742 2P
January 06 2021
  2 Hours, 8 Minutes
Ryzen 5 4500U
January 06 2021
  55 Minutes
Xeon Platinum 8280 2P
January 06 2021
  3 Hours, 17 Minutes
Core i9 10900K
January 07 2021
  39 Minutes
Invert Hiding All Results Option
  1 Hour, 29 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):


MNN ComparisonProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionRyzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900KAMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads)ASUS ROG CROSSHAIR VIII HERO (2702 BIOS)AMD Starship/Matisse16GB1000GB Sabrent Rocket 4.0 1TB + 1000GB Samsung SSD 980 PRO 1TBSapphire AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 6GB (1780/875MHz)AMD Navi 10 HDMI AudioASUS VP28URealtek RTL8125 2.5GbE + Intel I211Ubuntu 20.105.10.0-phx (x86_64)GNOME Shell 3.38.1X Server 1.20.9modesetting 1.20.94.6 Mesa 20.2.1 (LLVM 11.0.0)1.2.131GCC 10.2.0ext43840x2160Intel Core i7-1165G7 @ 4.70GHz (4 Cores / 8 Threads)Dell 0GG9PT (1.0.3 BIOS)Intel Tiger Lake-LPKioxia KBG40ZNS256G NVMe 256GBIntel UHD 3GB (1300MHz)Realtek ALC289Intel Wi-Fi 6 AX2015.11.0-rc1-phx (x86_64) 202012284.6 Mesa 21.0.0-devel (git-7d8d99e 2020-12-25 groovy-oibaf-ppa)1.2.1451920x12002 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads)AMD DAYTONA_X (RDY1006G BIOS)AMD Starship/Matisse504GB2 x 3841GB Micron_9300_MTFDHAL3T8TDPllvmpipeVE2282 x Mellanox MT27710Ubuntu 20.045.4.0-48-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.83.3 Mesa 20.0.8 (LLVM 10.0.0 128 bits)GCC 9.3.01920x1080AMD Ryzen 5 4500U @ 2.38GHz (6 Cores)LENOVO LNVNB161216 (EECN20WW BIOS)AMD Renoir Root Complex16GB256GB SK hynix HFM256GDHTNI-87A0BAMD Renoir 512MB (1500/400MHz)AMD Device 1637Realtek RTL8822CE 802.11ac PCIeUbuntu 20.105.10.0-pts (x86_64)GNOME Shell 3.38.1X Server 1.20.9amdgpu 19.1.04.6 Mesa 21.0.0-devel (git-448e603 2020-12-21 groovy-oibaf-ppa) (LLVM 11.0.0)1.2.145GCC 10.2.02 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads)GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS)Intel Sky Lake-E DMI3 Registers378GB280GB INTEL SSDPED1D280GAllvmpipeVE2282 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbEUbuntu 20.045.4.0-18-generic (x86_64)GNOME Shell 3.36.0X Server 1.20.7modesetting 1.20.73.3 Mesa 20.0.2 (LLVM 9.0.1 256 bits)GCC 9.3.0Intel Core i9-10900K @ 5.30GHz (10 Cores / 20 Threads)Gigabyte Z490 AORUS MASTER (F3 BIOS)Intel Comet Lake PCH16GBSamsung SSD 970 EVO 250GBGigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB (1900/875MHz)Realtek ALC1220ASUS MG28UIntel + Intel Wi-Fi 6 AX201Ubuntu 20.105.11.0-rc1-phx (x86_64) 20201228GNOME Shell 3.38.1X Server 1.20.9modesetting 1.20.94.6 Mesa 20.2.1 (LLVM 11.0.0)1.2.131GCC 10.2.03840x2160OpenBenchmarking.orgCompiler Details- Ryzen 9 5950X: --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 - Core i7 1165G7: --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 - EPYC 7742 2P: --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 - Ryzen 5 4500U: --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 - Xeon Platinum 8280 2P: --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 - Core i9 10900K: --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- Ryzen 9 5950X: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201009- Core i7 1165G7: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 2.3- EPYC 7742 2P: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8301034- Ryzen 5 4500U: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8600102- Xeon Platinum 8280 2P: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- Core i9 10900K: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xe0 - Thermald 2.3Security Details- Ryzen 9 5950X: 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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected- Core i7 1165G7: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7742 2P: 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 IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected- Ryzen 5 4500U: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled + srbds: Not affected + tsx_async_abort: Not affected- Xeon Platinum 8280 2P: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled- Core i9 10900K: itlb_multihit: KVM: Mitigation of VMX disabled + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900KResult OverviewPhoronix Test Suite100%143%186%230%273%Mobile Neural NetworkMobile Neural NetworkMobile Neural NetworkMobile Neural NetworkMobile Neural NetworkMobile Neural NetworkMobile Neural NetworkMobile Neural NetworkMobile Neural NetworkMobile Neural Networkmobilenet-v1-1.0SqueezeNetV1.0inception-v3SqueezeNetV1.0inception-v3mobilenet-v1-1.0resnet-v2-50MobileNetV2_224resnet-v2-50MobileNetV2_224

MNN Comparisonmnn: mobilenet-v1-1.0mnn: SqueezeNetV1.0mnn: inception-v3mnn: SqueezeNetV1.0mnn: inception-v3mnn: mobilenet-v1-1.0mnn: resnet-v2-50mnn: MobileNetV2_224mnn: resnet-v2-50mnn: MobileNetV2_224Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K5.8136.49428.1785.12528.6253.53527.8303.18826.6033.3578.11110.84065.9957.88360.7845.38351.8925.91743.3764.3945.59811.95235.45911.49939.8053.51234.1465.74730.1305.0215.0388.92246.1708.13739.8854.82434.3635.49639.1904.8085.1359.18930.4957.21432.4512.58932.8395.09226.8024.0252.9734.47529.6775.01232.0733.76325.5833.00628.4753.323OpenBenchmarking.org

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 2020-09-17Model: mobilenet-v1-1.0Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K246810SE +/- 0.007, N = 3SE +/- 0.006, N = 3SE +/- 0.029, N = 12SE +/- 0.016, N = 3SE +/- 0.016, N = 15SE +/- 0.017, N = 35.8138.1115.5985.0385.1352.973MIN: 5.6 / MAX: 15.97MIN: 7.94 / MAX: 23.02MIN: 5.23 / MAX: 28.01MIN: 4.36 / MAX: 22.26MIN: 4.87 / MAX: 13.62MIN: 2.81 / MAX: 11.991. (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 2020-09-17Model: mobilenet-v1-1.0Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K3691215Min: 5.8 / Avg: 5.81 / Max: 5.82Min: 8.1 / Avg: 8.11 / Max: 8.12Min: 5.5 / Avg: 5.6 / Max: 5.84Min: 5.02 / Avg: 5.04 / Max: 5.07Min: 5.01 / Avg: 5.13 / Max: 5.25Min: 2.94 / Avg: 2.97 / Max: 31. (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 2020-09-17Model: SqueezeNetV1.0Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K3691215SE +/- 0.010, N = 3SE +/- 0.028, N = 3SE +/- 0.369, N = 12SE +/- 0.135, N = 3SE +/- 0.230, N = 15SE +/- 0.054, N = 36.49410.84011.9528.9229.1894.475MIN: 6.05 / MAX: 16.53MIN: 10.3 / MAX: 25.66MIN: 9.51 / MAX: 28.35MIN: 7.72 / MAX: 27.24MIN: 7.02 / MAX: 16.88MIN: 4.08 / MAX: 14.031. (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 2020-09-17Model: SqueezeNetV1.0Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K3691215Min: 6.47 / Avg: 6.49 / Max: 6.51Min: 10.79 / Avg: 10.84 / Max: 10.88Min: 10.26 / Avg: 11.95 / Max: 14.65Min: 8.76 / Avg: 8.92 / Max: 9.19Min: 7.35 / Avg: 9.19 / Max: 10.16Min: 4.37 / Avg: 4.47 / Max: 4.561. (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 2020-09-17Model: inception-v3Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K1530456075SE +/- 0.32, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 12SE +/- 1.05, N = 3SE +/- 0.20, N = 15SE +/- 0.16, N = 328.1866.0035.4646.1730.5029.68MIN: 26.69 / MAX: 79.62MIN: 65.27 / MAX: 103.19MIN: 33 / MAX: 142.28MIN: 42.15 / MAX: 128.35MIN: 24.64 / MAX: 154.56MIN: 28.66 / MAX: 39.591. (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 2020-09-17Model: inception-v3Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K1326395265Min: 27.62 / Avg: 28.18 / Max: 28.74Min: 65.9 / Avg: 66 / Max: 66.14Min: 35 / Avg: 35.46 / Max: 36.69Min: 44.63 / Avg: 46.17 / Max: 48.19Min: 28.26 / Avg: 30.49 / Max: 31.23Min: 29.43 / Avg: 29.68 / Max: 29.971. (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 1.1.1Model: SqueezeNetV1.0Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K3691215SE +/- 0.054, N = 3SE +/- 0.008, N = 3SE +/- 0.121, N = 3SE +/- 0.135, N = 3SE +/- 0.231, N = 12SE +/- 0.055, N = 35.1257.88311.4998.1377.2145.012MIN: 4.84 / MAX: 14.46MIN: 7.79 / MAX: 22.3MIN: 9.91 / MAX: 15.08MIN: 7.06 / MAX: 25.42MIN: 5.38 / MAX: 19.43MIN: 4.39 / MAX: 45.461. (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 1.1.1Model: SqueezeNetV1.0Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K3691215Min: 5.05 / Avg: 5.12 / Max: 5.23Min: 7.87 / Avg: 7.88 / Max: 7.9Min: 11.36 / Avg: 11.5 / Max: 11.74Min: 7.96 / Avg: 8.14 / Max: 8.4Min: 5.56 / Avg: 7.21 / Max: 8.18Min: 4.91 / Avg: 5.01 / Max: 5.091. (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 1.1.1Model: inception-v3Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K1428425670SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 1.02, N = 3SE +/- 0.55, N = 3SE +/- 0.12, N = 12SE +/- 0.21, N = 328.6360.7839.8139.8932.4532.07MIN: 27.55 / MAX: 40.86MIN: 59.66 / MAX: 120.25MIN: 35.7 / MAX: 352.78MIN: 36.85 / MAX: 68.38MIN: 28.79 / MAX: 149.23MIN: 30.7 / MAX: 50.81. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.1Model: inception-v3Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K1224364860Min: 28.59 / Avg: 28.62 / Max: 28.67Min: 60.7 / Avg: 60.78 / Max: 60.84Min: 38.34 / Avg: 39.8 / Max: 41.77Min: 38.81 / Avg: 39.89 / Max: 40.63Min: 31.92 / Avg: 32.45 / Max: 33.2Min: 31.72 / Avg: 32.07 / Max: 32.431. (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 1.1.1Model: mobilenet-v1-1.0Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K1.21122.42243.63364.84486.056SE +/- 0.024, N = 3SE +/- 0.005, N = 3SE +/- 0.277, N = 3SE +/- 0.033, N = 3SE +/- 0.013, N = 12SE +/- 0.006, N = 33.5355.3833.5124.8242.5893.763MIN: 3.34 / MAX: 14.12MIN: 5.3 / MAX: 19.58MIN: 2.91 / MAX: 6.99MIN: 4.16 / MAX: 22.5MIN: 2.42 / MAX: 3.5MIN: 3.49 / MAX: 12.41. (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 1.1.1Model: mobilenet-v1-1.0Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K246810Min: 3.49 / Avg: 3.54 / Max: 3.58Min: 5.38 / Avg: 5.38 / Max: 5.39Min: 2.96 / Avg: 3.51 / Max: 3.81Min: 4.76 / Avg: 4.82 / Max: 4.87Min: 2.54 / Avg: 2.59 / Max: 2.69Min: 3.75 / Avg: 3.76 / Max: 3.771. (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 2020-09-17Model: resnet-v2-50Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K1224364860SE +/- 0.03, N = 3SE +/- 1.08, N = 3SE +/- 0.42, N = 12SE +/- 0.45, N = 3SE +/- 0.25, N = 15SE +/- 0.17, N = 327.8351.8934.1534.3632.8425.58MIN: 26.53 / MAX: 38.71MIN: 31.81 / MAX: 69.41MIN: 29.94 / MAX: 262.37MIN: 31.71 / MAX: 94.36MIN: 30.04 / MAX: 156.69MIN: 24.65 / MAX: 35.81. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: resnet-v2-50Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K1020304050Min: 27.79 / Avg: 27.83 / Max: 27.88Min: 49.76 / Avg: 51.89 / Max: 53.27Min: 32.33 / Avg: 34.15 / Max: 37.25Min: 33.8 / Avg: 34.36 / Max: 35.26Min: 30.55 / Avg: 32.84 / Max: 34.55Min: 25.25 / Avg: 25.58 / Max: 25.81. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: MobileNetV2_224Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K1.33132.66263.99395.32526.6565SE +/- 0.008, N = 3SE +/- 0.025, N = 3SE +/- 0.102, N = 12SE +/- 0.033, N = 3SE +/- 0.154, N = 15SE +/- 0.050, N = 33.1885.9175.7475.4965.0923.006MIN: 2.97 / MAX: 13.1MIN: 5.77 / MAX: 20.66MIN: 4.74 / MAX: 14.71MIN: 4.74 / MAX: 23.14MIN: 4.25 / MAX: 6.15MIN: 2.62 / MAX: 12.151. (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 2020-09-17Model: MobileNetV2_224Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K246810Min: 3.18 / Avg: 3.19 / Max: 3.2Min: 5.88 / Avg: 5.92 / Max: 5.96Min: 5.28 / Avg: 5.75 / Max: 6.72Min: 5.44 / Avg: 5.5 / Max: 5.56Min: 4.4 / Avg: 5.09 / Max: 5.88Min: 2.91 / Avg: 3.01 / Max: 3.061. (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 1.1.1Model: resnet-v2-50Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K1020304050SE +/- 0.10, N = 3SE +/- 1.10, N = 3SE +/- 0.28, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 12SE +/- 0.28, N = 326.6043.3830.1339.1926.8028.48MIN: 25.42 / MAX: 37.11MIN: 27.03 / MAX: 64.42MIN: 25.61 / MAX: 107.35MIN: 36.97 / MAX: 61.79MIN: 25.76 / MAX: 95.87MIN: 27.36 / MAX: 37.061. (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 1.1.1Model: resnet-v2-50Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K918273645Min: 26.41 / Avg: 26.6 / Max: 26.71Min: 41.17 / Avg: 43.38 / Max: 44.55Min: 29.64 / Avg: 30.13 / Max: 30.6Min: 39.07 / Avg: 39.19 / Max: 39.34Min: 26.25 / Avg: 26.8 / Max: 27.46Min: 28.11 / Avg: 28.48 / Max: 29.031. (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 1.1.1Model: MobileNetV2_224Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K1.12972.25943.38914.51885.6485SE +/- 0.003, N = 3SE +/- 0.010, N = 3SE +/- 0.207, N = 3SE +/- 0.024, N = 3SE +/- 0.088, N = 12SE +/- 0.122, N = 33.3574.3945.0214.8084.0253.323MIN: 3.09 / MAX: 4.49MIN: 4.23 / MAX: 18.64MIN: 4.52 / MAX: 13.36MIN: 3.97 / MAX: 22.02MIN: 3.49 / MAX: 5.28MIN: 2.98 / MAX: 13.711. (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 1.1.1Model: MobileNetV2_224Ryzen 9 5950XCore i7 1165G7EPYC 7742 2PRyzen 5 4500UXeon Platinum 8280 2PCore i9 10900K246810Min: 3.35 / Avg: 3.36 / Max: 3.36Min: 4.38 / Avg: 4.39 / Max: 4.41Min: 4.61 / Avg: 5.02 / Max: 5.24Min: 4.76 / Avg: 4.81 / Max: 4.84Min: 3.63 / Avg: 4.02 / Max: 4.52Min: 3.19 / Avg: 3.32 / Max: 3.571. (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

10 Results Shown

Mobile Neural Network:
  mobilenet-v1-1.0
  SqueezeNetV1.0
  inception-v3
Mobile Neural Network:
  SqueezeNetV1.0
  inception-v3
  mobilenet-v1-1.0
Mobile Neural Network:
  resnet-v2-50
  MobileNetV2_224
Mobile Neural Network:
  resnet-v2-50
  MobileNetV2_224