dnn Benchmarks for a future article. AMD Ryzen AI 9 HX 370 testing with a ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS) and llvmpipe on Ubuntu 24.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2410169-NE-DNN04230192&sor&grw .
dnn Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution a b 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 llvmpipe 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 4.5 Mesa 24.2.3-1ubuntu1 (LLVM 19.1.0 256 bits) GCC 14.2.0 ext4 2880x1800 OpenBenchmarking.org Kernel Details - 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
dnn xnnpack: FP32MobileNetV1 litert: Inception ResNet V2 litert: Quantized COCO SSD MobileNet v1 litert: Mobilenet Float litert: Inception V4 litert: NASNet Mobile litert: DeepLab V3 litert: SqueezeNet xnnpack: FP32MobileNetV2 xnnpack: FP32MobileNetV3Large xnnpack: FP32MobileNetV3Small xnnpack: FP16MobileNetV1 xnnpack: FP16MobileNetV2 xnnpack: FP16MobileNetV3Large xnnpack: FP16MobileNetV3Small litert: Mobilenet Quant xnnpack: QS8MobileNetV2 onednn: IP Shapes 1D - CPU onednn: IP Shapes 3D - CPU onednn: Convolution Batch Shapes Auto - CPU onednn: Deconvolution Batch shapes_1d - CPU onednn: Deconvolution Batch shapes_3d - CPU onednn: Recurrent Neural Network Training - CPU onednn: Recurrent Neural Network Inference - CPU a b 2387 39825.1 2844.21 2260.57 49706.2 12624.7 4268.97 3784.36 1932 2267 1103 3214 2368 2583 1267 1976.79 1160 2.76848 3.56923 8.4918 5.20977 6.37788 3085.55 2194.27 2353 37957.1 2983.71 2266.86 50678.3 12537.6 3750.1 3787.29 1908 2215 1084 3203 2358 2536 1248 1801.7 1129 2.68462 3.57302 8.43828 5.17517 6.37874 3030.55 1616.68 OpenBenchmarking.org
XNNPACK Model: FP32MobileNetV1 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV1 b a 500 1000 1500 2000 2500 2353 2387 1. (CXX) g++ options: -O3 -lrt -lm
LiteRT Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Inception ResNet V2 b a 9K 18K 27K 36K 45K 37957.1 39825.1
LiteRT Model: Quantized COCO SSD MobileNet v1 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Quantized COCO SSD MobileNet v1 a b 600 1200 1800 2400 3000 2844.21 2983.71
LiteRT Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Mobilenet Float a b 500 1000 1500 2000 2500 2260.57 2266.86
LiteRT Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Inception V4 a b 11K 22K 33K 44K 55K 49706.2 50678.3
LiteRT Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: NASNet Mobile b a 3K 6K 9K 12K 15K 12537.6 12624.7
LiteRT Model: DeepLab V3 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: DeepLab V3 b a 900 1800 2700 3600 4500 3750.10 4268.97
LiteRT Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: SqueezeNet a b 800 1600 2400 3200 4000 3784.36 3787.29
XNNPACK Model: FP32MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV2 b a 400 800 1200 1600 2000 1908 1932 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP32MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV3Large b a 500 1000 1500 2000 2500 2215 2267 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP32MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV3Small b a 200 400 600 800 1000 1084 1103 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP16MobileNetV1 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV1 b a 700 1400 2100 2800 3500 3203 3214 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP16MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV2 b a 500 1000 1500 2000 2500 2358 2368 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP16MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV3Large b a 600 1200 1800 2400 3000 2536 2583 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP16MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV3Small b a 300 600 900 1200 1500 1248 1267 1. (CXX) g++ options: -O3 -lrt -lm
LiteRT Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Mobilenet Quant b a 400 800 1200 1600 2000 1801.70 1976.79
XNNPACK Model: QS8MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: QS8MobileNetV2 b a 200 400 600 800 1000 1129 1160 1. (CXX) g++ options: -O3 -lrt -lm
oneDNN Harness: IP Shapes 1D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: IP Shapes 1D - Engine: CPU b a 0.6229 1.2458 1.8687 2.4916 3.1145 2.68462 2.76848 MIN: 2.35 MIN: 2.35 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
oneDNN Harness: IP Shapes 3D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: IP Shapes 3D - Engine: CPU a b 0.8039 1.6078 2.4117 3.2156 4.0195 3.56923 3.57302 MIN: 3.5 MIN: 3.49 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Convolution Batch Shapes Auto - Engine: CPU b a 2 4 6 8 10 8.43828 8.49180 MIN: 8.21 MIN: 8.23 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Deconvolution Batch shapes_1d - Engine: CPU b a 1.1722 2.3444 3.5166 4.6888 5.861 5.17517 5.20977 MIN: 4.43 MIN: 4.16 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Deconvolution Batch shapes_3d - Engine: CPU a b 2 4 6 8 10 6.37788 6.37874 MIN: 5.6 MIN: 5.57 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
oneDNN Harness: Recurrent Neural Network Training - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Recurrent Neural Network Training - Engine: CPU b a 700 1400 2100 2800 3500 3030.55 3085.55 MIN: 3004.46 MIN: 3048.43 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
oneDNN Harness: Recurrent Neural Network Inference - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Recurrent Neural Network Inference - Engine: CPU b a 500 1000 1500 2000 2500 1616.68 2194.27 MIN: 1589 MIN: 2132.82 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
Phoronix Test Suite v10.8.5