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.
HTML result view exported from: https://openbenchmarking.org/result/2101072-SYST-210106709&gru .
MNN Comparison Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution Ryzen 9 5950X Core i7 1165G7 EPYC 7742 2P Ryzen 5 4500U Xeon Platinum 8280 2P Core i9 10900K AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads) ASUS ROG CROSSHAIR VIII HERO (2702 BIOS) AMD Starship/Matisse 16GB 1000GB Sabrent Rocket 4.0 1TB + 1000GB Samsung SSD 980 PRO 1TB Sapphire AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 6GB (1780/875MHz) AMD Navi 10 HDMI Audio ASUS VP28U Realtek RTL8125 2.5GbE + Intel I211 Ubuntu 20.10 5.10.0-phx (x86_64) GNOME Shell 3.38.1 X Server 1.20.9 modesetting 1.20.9 4.6 Mesa 20.2.1 (LLVM 11.0.0) 1.2.131 GCC 10.2.0 ext4 3840x2160 Intel Core i7-1165G7 @ 4.70GHz (4 Cores / 8 Threads) Dell 0GG9PT (1.0.3 BIOS) Intel Tiger Lake-LP Kioxia KBG40ZNS256G NVMe 256GB Intel UHD 3GB (1300MHz) Realtek ALC289 Intel Wi-Fi 6 AX201 5.11.0-rc1-phx (x86_64) 20201228 4.6 Mesa 21.0.0-devel (git-7d8d99e 2020-12-25 groovy-oibaf-ppa) 1.2.145 1920x1200 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads) AMD DAYTONA_X (RDY1006G BIOS) AMD Starship/Matisse 504GB 2 x 3841GB Micron_9300_MTFDHAL3T8TDP llvmpipe VE228 2 x Mellanox MT27710 Ubuntu 20.04 5.4.0-48-generic (x86_64) GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 3.3 Mesa 20.0.8 (LLVM 10.0.0 128 bits) GCC 9.3.0 1920x1080 AMD Ryzen 5 4500U @ 2.38GHz (6 Cores) LENOVO LNVNB161216 (EECN20WW BIOS) AMD Renoir Root Complex 16GB 256GB SK hynix HFM256GDHTNI-87A0B AMD Renoir 512MB (1500/400MHz) AMD Device 1637 Realtek RTL8822CE 802.11ac PCIe Ubuntu 20.10 5.10.0-pts (x86_64) GNOME Shell 3.38.1 X Server 1.20.9 amdgpu 19.1.0 4.6 Mesa 21.0.0-devel (git-448e603 2020-12-21 groovy-oibaf-ppa) (LLVM 11.0.0) 1.2.145 GCC 10.2.0 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads) GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS) Intel Sky Lake-E DMI3 Registers 378GB 280GB INTEL SSDPED1D280GA llvmpipe VE228 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE Ubuntu 20.04 5.4.0-18-generic (x86_64) GNOME Shell 3.36.0 X Server 1.20.7 modesetting 1.20.7 3.3 Mesa 20.0.2 (LLVM 9.0.1 256 bits) GCC 9.3.0 Intel Core i9-10900K @ 5.30GHz (10 Cores / 20 Threads) Gigabyte Z490 AORUS MASTER (F3 BIOS) Intel Comet Lake PCH 16GB Samsung SSD 970 EVO 250GB Gigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB (1900/875MHz) Realtek ALC1220 ASUS MG28U Intel + Intel Wi-Fi 6 AX201 Ubuntu 20.10 5.11.0-rc1-phx (x86_64) 20201228 GNOME Shell 3.38.1 X Server 1.20.9 modesetting 1.20.9 4.6 Mesa 20.2.1 (LLVM 11.0.0) 1.2.131 GCC 10.2.0 3840x2160 OpenBenchmarking.org Compiler 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 2.3 Security 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
MNN Comparison mnn: SqueezeNetV1.0 mnn: resnet-v2-50 mnn: MobileNetV2_224 mnn: mobilenet-v1-1.0 mnn: inception-v3 mnn: SqueezeNetV1.0 mnn: resnet-v2-50 mnn: MobileNetV2_224 mnn: mobilenet-v1-1.0 mnn: inception-v3 Ryzen 9 5950X Core i7 1165G7 EPYC 7742 2P Ryzen 5 4500U Xeon Platinum 8280 2P Core i9 10900K 6.494 27.830 3.188 5.813 28.178 5.125 26.603 3.357 3.535 28.625 10.840 51.892 5.917 8.111 65.995 7.883 43.376 4.394 5.383 60.784 11.952 34.146 5.747 5.598 35.459 11.499 30.130 5.021 3.512 39.805 8.922 34.363 5.496 5.038 46.170 8.137 39.190 4.808 4.824 39.885 9.189 32.839 5.092 5.135 30.495 7.214 26.802 4.025 2.589 32.451 4.475 25.583 3.006 2.973 29.677 5.012 28.475 3.323 3.763 32.073 OpenBenchmarking.org
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: SqueezeNetV1.0 Ryzen 9 5950X Core i7 1165G7 EPYC 7742 2P Ryzen 5 4500U Xeon Platinum 8280 2P Core i9 10900K 3 6 9 12 15 SE +/- 0.010, N = 3 SE +/- 0.028, N = 3 SE +/- 0.369, N = 12 SE +/- 0.135, N = 3 SE +/- 0.230, N = 15 SE +/- 0.054, N = 3 6.494 10.840 11.952 8.922 9.189 4.475 MIN: 6.05 / MAX: 16.53 MIN: 10.3 / MAX: 25.66 MIN: 9.51 / MAX: 28.35 MIN: 7.72 / MAX: 27.24 MIN: 7.02 / MAX: 16.88 MIN: 4.08 / MAX: 14.03 1. (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
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: resnet-v2-50 Ryzen 9 5950X Core i7 1165G7 EPYC 7742 2P Ryzen 5 4500U Xeon Platinum 8280 2P Core i9 10900K 12 24 36 48 60 SE +/- 0.03, N = 3 SE +/- 1.08, N = 3 SE +/- 0.42, N = 12 SE +/- 0.45, N = 3 SE +/- 0.25, N = 15 SE +/- 0.17, N = 3 27.83 51.89 34.15 34.36 32.84 25.58 MIN: 26.53 / MAX: 38.71 MIN: 31.81 / MAX: 69.41 MIN: 29.94 / MAX: 262.37 MIN: 31.71 / MAX: 94.36 MIN: 30.04 / MAX: 156.69 MIN: 24.65 / MAX: 35.8 1. (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
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: MobileNetV2_224 Ryzen 9 5950X Core i7 1165G7 EPYC 7742 2P Ryzen 5 4500U Xeon Platinum 8280 2P Core i9 10900K 1.3313 2.6626 3.9939 5.3252 6.6565 SE +/- 0.008, N = 3 SE +/- 0.025, N = 3 SE +/- 0.102, N = 12 SE +/- 0.033, N = 3 SE +/- 0.154, N = 15 SE +/- 0.050, N = 3 3.188 5.917 5.747 5.496 5.092 3.006 MIN: 2.97 / MAX: 13.1 MIN: 5.77 / MAX: 20.66 MIN: 4.74 / MAX: 14.71 MIN: 4.74 / MAX: 23.14 MIN: 4.25 / MAX: 6.15 MIN: 2.62 / MAX: 12.15 1. (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
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: mobilenet-v1-1.0 Ryzen 9 5950X Core i7 1165G7 EPYC 7742 2P Ryzen 5 4500U Xeon Platinum 8280 2P Core i9 10900K 2 4 6 8 10 SE +/- 0.007, N = 3 SE +/- 0.006, N = 3 SE +/- 0.029, N = 12 SE +/- 0.016, N = 3 SE +/- 0.016, N = 15 SE +/- 0.017, N = 3 5.813 8.111 5.598 5.038 5.135 2.973 MIN: 5.6 / MAX: 15.97 MIN: 7.94 / MAX: 23.02 MIN: 5.23 / MAX: 28.01 MIN: 4.36 / MAX: 22.26 MIN: 4.87 / MAX: 13.62 MIN: 2.81 / MAX: 11.99 1. (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
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: inception-v3 Ryzen 9 5950X Core i7 1165G7 EPYC 7742 2P Ryzen 5 4500U Xeon Platinum 8280 2P Core i9 10900K 15 30 45 60 75 SE +/- 0.32, N = 3 SE +/- 0.07, N = 3 SE +/- 0.15, N = 12 SE +/- 1.05, N = 3 SE +/- 0.20, N = 15 SE +/- 0.16, N = 3 28.18 66.00 35.46 46.17 30.50 29.68 MIN: 26.69 / MAX: 79.62 MIN: 65.27 / MAX: 103.19 MIN: 33 / MAX: 142.28 MIN: 42.15 / MAX: 128.35 MIN: 24.64 / MAX: 154.56 MIN: 28.66 / MAX: 39.59 1. (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
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.1 Model: SqueezeNetV1.0 Ryzen 9 5950X Core i7 1165G7 EPYC 7742 2P Ryzen 5 4500U Xeon Platinum 8280 2P Core i9 10900K 3 6 9 12 15 SE +/- 0.054, N = 3 SE +/- 0.008, N = 3 SE +/- 0.121, N = 3 SE +/- 0.135, N = 3 SE +/- 0.231, N = 12 SE +/- 0.055, N = 3 5.125 7.883 11.499 8.137 7.214 5.012 MIN: 4.84 / MAX: 14.46 MIN: 7.79 / MAX: 22.3 MIN: 9.91 / MAX: 15.08 MIN: 7.06 / MAX: 25.42 MIN: 5.38 / MAX: 19.43 MIN: 4.39 / MAX: 45.46 1. (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
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.1 Model: resnet-v2-50 Ryzen 9 5950X Core i7 1165G7 EPYC 7742 2P Ryzen 5 4500U Xeon Platinum 8280 2P Core i9 10900K 10 20 30 40 50 SE +/- 0.10, N = 3 SE +/- 1.10, N = 3 SE +/- 0.28, N = 3 SE +/- 0.08, N = 3 SE +/- 0.11, N = 12 SE +/- 0.28, N = 3 26.60 43.38 30.13 39.19 26.80 28.48 MIN: 25.42 / MAX: 37.11 MIN: 27.03 / MAX: 64.42 MIN: 25.61 / MAX: 107.35 MIN: 36.97 / MAX: 61.79 MIN: 25.76 / MAX: 95.87 MIN: 27.36 / MAX: 37.06 1. (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
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.1 Model: MobileNetV2_224 Ryzen 9 5950X Core i7 1165G7 EPYC 7742 2P Ryzen 5 4500U Xeon Platinum 8280 2P Core i9 10900K 1.1297 2.2594 3.3891 4.5188 5.6485 SE +/- 0.003, N = 3 SE +/- 0.010, N = 3 SE +/- 0.207, N = 3 SE +/- 0.024, N = 3 SE +/- 0.088, N = 12 SE +/- 0.122, N = 3 3.357 4.394 5.021 4.808 4.025 3.323 MIN: 3.09 / MAX: 4.49 MIN: 4.23 / MAX: 18.64 MIN: 4.52 / MAX: 13.36 MIN: 3.97 / MAX: 22.02 MIN: 3.49 / MAX: 5.28 MIN: 2.98 / MAX: 13.71 1. (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
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.1 Model: mobilenet-v1-1.0 Ryzen 9 5950X Core i7 1165G7 EPYC 7742 2P Ryzen 5 4500U Xeon Platinum 8280 2P Core i9 10900K 1.2112 2.4224 3.6336 4.8448 6.056 SE +/- 0.024, N = 3 SE +/- 0.005, N = 3 SE +/- 0.277, N = 3 SE +/- 0.033, N = 3 SE +/- 0.013, N = 12 SE +/- 0.006, N = 3 3.535 5.383 3.512 4.824 2.589 3.763 MIN: 3.34 / MAX: 14.12 MIN: 5.3 / MAX: 19.58 MIN: 2.91 / MAX: 6.99 MIN: 4.16 / MAX: 22.5 MIN: 2.42 / MAX: 3.5 MIN: 3.49 / MAX: 12.4 1. (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
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.1 Model: inception-v3 Ryzen 9 5950X Core i7 1165G7 EPYC 7742 2P Ryzen 5 4500U Xeon Platinum 8280 2P Core i9 10900K 14 28 42 56 70 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 1.02, N = 3 SE +/- 0.55, N = 3 SE +/- 0.12, N = 12 SE +/- 0.21, N = 3 28.63 60.78 39.81 39.89 32.45 32.07 MIN: 27.55 / MAX: 40.86 MIN: 59.66 / MAX: 120.25 MIN: 35.7 / MAX: 352.78 MIN: 36.85 / MAX: 68.38 MIN: 28.79 / MAX: 149.23 MIN: 30.7 / MAX: 50.8 1. (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
Phoronix Test Suite v10.8.4