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.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2410169-NE-DNN04230192
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
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

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
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
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
October 16
  38 Minutes
b
October 16
  38 Minutes
Invert Behavior (Only Show Selected Data)
  38 Minutes
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):


dnnOpenBenchmarking.orgPhoronix Test SuiteAMD 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 15074 x 8GB LPDDR5-7500MT/s Samsung K3KL9L90CM-MGCT1024GB MTFDKBA1T0QFM-1BD1AABGBllvmpipeAMD Rembrandt Radeon HD AudioMEDIATEK Device 7925Ubuntu 24.106.11.0-rc6-phx (x86_64)GNOME Shell 47.0X Server + Wayland4.5 Mesa 24.2.3-1ubuntu1 (LLVM 19.1.0 256 bits)GCC 14.2.0ext42880x1800ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionDnn 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,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 - Scaling Governor: amd-pstate-epp powersave (Boost: Enabled EPP: balance_performance) - Platform Profile: balanced - CPU Microcode: 0xb204011 - ACPI Profile: balanced - 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

a vs. b ComparisonPhoronix Test SuiteBaseline+8.9%+8.9%+17.8%+17.8%+26.7%+26.7%+35.6%+35.6%35.7%13.8%9.7%4.9%3.1%2.7%2.3%R.N.N.I - CPUDeepLab V3Mobilenet QuantI.R.VQ.C.S.M.v4.9%IP Shapes 1D - CPUQS8MobileNetV2FP32MobileNetV3LargeInception V42%oneDNNLiteRTLiteRTLiteRTLiteRToneDNNXNNPACKXNNPACKLiteRTab

dnnlitert: DeepLab V3litert: SqueezeNetlitert: Inception V4litert: NASNet Mobilelitert: Mobilenet Floatlitert: Mobilenet Quantlitert: Inception ResNet V2litert: Quantized COCO SSD MobileNet v1onednn: IP Shapes 1D - CPUonednn: IP Shapes 3D - CPUonednn: Convolution Batch Shapes Auto - CPUonednn: Deconvolution Batch shapes_1d - CPUonednn: Deconvolution Batch shapes_3d - CPUonednn: Recurrent Neural Network Training - CPUonednn: Recurrent Neural Network Inference - CPUxnnpack: FP32MobileNetV1xnnpack: FP32MobileNetV2xnnpack: FP32MobileNetV3Largexnnpack: FP32MobileNetV3Smallxnnpack: FP16MobileNetV1xnnpack: FP16MobileNetV2xnnpack: FP16MobileNetV3Largexnnpack: FP16MobileNetV3Smallxnnpack: QS8MobileNetV2ab4268.973784.3649706.212624.72260.571976.7939825.12844.212.768483.569238.49185.209776.377883085.552194.272387193222671103321423682583126711603750.13787.2950678.312537.62266.861801.737957.12983.712.684623.573028.438285.175176.378743030.551616.68235319082215108432032358253612481129OpenBenchmarking.org

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: DeepLab V3ab90018002700360045004268.973750.10

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: SqueezeNetab80016002400320040003784.363787.29

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception V4ab11K22K33K44K55K49706.250678.3

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: NASNet Mobileab3K6K9K12K15K12624.712537.6

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Floatab50010001500200025002260.572266.86

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Quantab4008001200160020001976.791801.70

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception ResNet V2ab9K18K27K36K45K39825.137957.1

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Quantized COCO SSD MobileNet v1ab60012001800240030002844.212983.71

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: IP Shapes 1D - Engine: CPUab0.62291.24581.86872.49163.11452.768482.68462MIN: 2.35MIN: 2.351. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: IP Shapes 3D - Engine: CPUab0.80391.60782.41173.21564.01953.569233.57302MIN: 3.5MIN: 3.491. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Convolution Batch Shapes Auto - Engine: CPUab2468108.491808.43828MIN: 8.23MIN: 8.211. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Deconvolution Batch shapes_1d - Engine: CPUab1.17222.34443.51664.68885.8615.209775.17517MIN: 4.16MIN: 4.431. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Deconvolution Batch shapes_3d - Engine: CPUab2468106.377886.37874MIN: 5.6MIN: 5.571. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Recurrent Neural Network Training - Engine: CPUab70014002100280035003085.553030.55MIN: 3048.43MIN: 3004.461. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Recurrent Neural Network Inference - Engine: CPUab50010001500200025002194.271616.68MIN: 2132.82MIN: 15891. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV1ab5001000150020002500238723531. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV2ab400800120016002000193219081. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Largeab5001000150020002500226722151. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Smallab2004006008001000110310841. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV1ab7001400210028003500321432031. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV2ab5001000150020002500236823581. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Largeab6001200180024003000258325361. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Smallab30060090012001500126712481. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: QS8MobileNetV2ab2004006008001000116011291. (CXX) g++ options: -O3 -lrt -lm