mnn ryzen AMD Ryzen AI 9 HX 370 testing with a ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS) and AMD Radeon 512MB on Ubuntu 24.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2411181-NE-MNNRYZEN513&grt&rdt .
mnn ryzen Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution a b c d AMD Ryzen AI 9 HX 370 @ 4.37GHz (12 Cores / 24 Threads) ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS) AMD Device 1507 4 x 8GB LPDDR5-7500MT/s Samsung K3KL9L90CM-MGCT 1024GB MTFDKBA1T0QFM-1BD1AABGB AMD Radeon 512MB AMD Rembrandt Radeon HD Audio MEDIATEK Device 7925 Ubuntu 24.10 6.11.0-rc6-phx (x86_64) GNOME Shell 47.0 X Server + Wayland 4.6 Mesa 24.2.3-1ubuntu1 (LLVM 19.1.0 DRM 3.58) GCC 14.2.0 ext4 2880x1800 OpenBenchmarking.org Kernel Details - amdgpu.dcdebugmask=0x600 - Transparent Huge Pages: madvise Compiler Details - --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,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/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 Details - Scaling Governor: amd-pstate-epp powersave (Boost: Enabled EPP: balance_performance) - Platform Profile: balanced - CPU Microcode: 0xb204011 - ACPI Profile: balanced Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
mnn ryzen mnn: nasnet mnn: mobilenetV3 mnn: squeezenetv1.1 mnn: resnet-v2-50 mnn: SqueezeNetV1.0 mnn: MobileNetV2_224 mnn: mobilenet-v1-1.0 mnn: inception-v3 a b c d 20.072 2.439 3.873 19.285 6.341 4.987 4.798 40.930 21.193 2.482 4.003 20.253 6.520 5.175 5.154 42.506 21.873 2.456 3.893 20.330 6.694 4.913 5.138 41.923 21.741 2.456 3.994 20.787 6.765 4.917 5.267 43.390 OpenBenchmarking.org
Mobile Neural Network Model: nasnet OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 3.0 Model: nasnet a b c d 5 10 15 20 25 SE +/- 0.60, N = 9 SE +/- 0.28, N = 9 SE +/- 0.04, N = 3 SE +/- 0.29, N = 3 20.07 21.19 21.87 21.74 MIN: 15.57 / MAX: 74.52 MIN: 18.55 / MAX: 110.28 MIN: 20.05 / MAX: 58.34 MIN: 19.7 / MAX: 84.5 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 -pthread -ldl
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 3.0 Model: mobilenetV3 a b c d 0.5585 1.117 1.6755 2.234 2.7925 SE +/- 0.070, N = 9 SE +/- 0.062, N = 9 SE +/- 0.219, N = 3 SE +/- 0.148, N = 3 2.439 2.482 2.456 2.456 MIN: 1.8 / MAX: 31.65 MIN: 1.79 / MAX: 30.83 MIN: 1.85 / MAX: 27.62 MIN: 1.78 / MAX: 23.93 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 -pthread -ldl
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 3.0 Model: squeezenetv1.1 a b c d 0.9007 1.8014 2.7021 3.6028 4.5035 SE +/- 0.129, N = 9 SE +/- 0.125, N = 9 SE +/- 0.404, N = 3 SE +/- 0.226, N = 3 3.873 4.003 3.893 3.994 MIN: 2.94 / MAX: 28.6 MIN: 2.57 / MAX: 33.92 MIN: 2.89 / MAX: 21.31 MIN: 2.86 / MAX: 26.13 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 -pthread -ldl
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 3.0 Model: resnet-v2-50 a b c d 5 10 15 20 25 SE +/- 0.45, N = 9 SE +/- 0.18, N = 9 SE +/- 0.45, N = 3 SE +/- 0.22, N = 3 19.29 20.25 20.33 20.79 MIN: 14.1 / MAX: 66.48 MIN: 17.55 / MAX: 62.76 MIN: 16.7 / MAX: 55.6 MIN: 18.61 / MAX: 58.17 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 -pthread -ldl
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 3.0 Model: SqueezeNetV1.0 a b c d 2 4 6 8 10 SE +/- 0.146, N = 9 SE +/- 0.063, N = 9 SE +/- 0.043, N = 3 SE +/- 0.088, N = 3 6.341 6.520 6.694 6.765 MIN: 5.07 / MAX: 55.12 MIN: 5.64 / MAX: 59.14 MIN: 6.18 / MAX: 39.54 MIN: 6.19 / MAX: 40.96 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 -pthread -ldl
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 3.0 Model: MobileNetV2_224 a b c d 1.1644 2.3288 3.4932 4.6576 5.822 SE +/- 0.197, N = 9 SE +/- 0.134, N = 9 SE +/- 0.447, N = 3 SE +/- 0.380, N = 3 4.987 5.175 4.913 4.917 MIN: 3.65 / MAX: 37.11 MIN: 3.9 / MAX: 43 MIN: 3.74 / MAX: 34.88 MIN: 3.93 / MAX: 36.06 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 -pthread -ldl
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 3.0 Model: mobilenet-v1-1.0 a b c d 1.1851 2.3702 3.5553 4.7404 5.9255 SE +/- 0.158, N = 9 SE +/- 0.045, N = 9 SE +/- 0.109, N = 3 SE +/- 0.060, N = 3 4.798 5.154 5.138 5.267 MIN: 3.2 / MAX: 34.94 MIN: 4.06 / MAX: 32.37 MIN: 4.7 / MAX: 29.16 MIN: 4.77 / MAX: 34.6 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 -pthread -ldl
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 3.0 Model: inception-v3 a b c d 10 20 30 40 50 SE +/- 1.11, N = 9 SE +/- 0.84, N = 9 SE +/- 3.16, N = 3 SE +/- 2.06, N = 3 40.93 42.51 41.92 43.39 MIN: 31.18 / MAX: 126.9 MIN: 31.04 / MAX: 112.57 MIN: 31.48 / MAX: 80.5 MIN: 33.57 / MAX: 125.62 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 -pthread -ldl
Phoronix Test Suite v10.8.5