litert-onednn-xnnpack

2 x AMD EPYC 9575F 64-Core testing with a AMD VOLCANO (RVOT1000D BIOS) and ASPEED on Ubuntu 24.04 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-LITERTONE51
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
  1 Hour, 9 Minutes
aa
October 16
  1 Hour, 1 Minute
b
October 16
  2 Hours, 13 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 28 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):


litert-onednn-xnnpack OpenBenchmarking.orgPhoronix Test Suite2 x AMD EPYC 9575F 64-Core @ 5.01GHz (128 Cores / 256 Threads)AMD VOLCANO (RVOT1000D BIOS)AMD Device 153a1520GB2 x 3841GB SAMSUNG MZWLO3T8HCLS-00A07ASPEEDBroadcom NetXtreme BCM5720 PCIeUbuntu 24.046.8.12-powercap-1ah-patched (x86_64)GCC 13.2.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen ResolutionLitert-onednn-xnnpack BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/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-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 - a: Scaling Governor: amd-pstate-epp powersave (EPP: power) - CPU Microcode: 0xb002110 - aa: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb002110 - b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb002110 - 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

aaabLogarithmic Result OverviewPhoronix Test SuiteLiteRTLiteRToneDNNLiteRTLiteRTLiteRToneDNNoneDNNoneDNNoneDNNoneDNNoneDNNNASNet MobileDeepLab V3D.B.s - CPUMobilenet FloatInception V4SqueezeNetR.N.N.I - CPUIP Shapes 3D - CPUD.B.s - CPUC.B.S.A - CPUR.N.N.T - CPUIP Shapes 1D - CPU

litert-onednn-xnnpack litert: DeepLab V3litert: SqueezeNetlitert: Inception V4litert: NASNet Mobilelitert: Mobilenet Floatlitert: Mobilenet Quantlitert: Inception ResNet V2litert: Quantized COCO SSD MobileNet v1xnnpack: FP32MobileNetV1xnnpack: FP32MobileNetV2xnnpack: FP32MobileNetV3Largexnnpack: FP32MobileNetV3Smallxnnpack: FP16MobileNetV1xnnpack: FP16MobileNetV2xnnpack: FP16MobileNetV3Largexnnpack: FP16MobileNetV3Smallxnnpack: QS8MobileNetV2onednn: 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 - CPUaaab28110.19607.4065970.91800025922.590.6319540.4517910.25839617.81790.429801417.017387.45923838.89561.256801413385605619.3582918.413210210521.171301679622775212247483185252731925785172570.6320950.4585060.25977715.39180.425348418.838395.48822624.79771.8266603.91909876222.5536194.890362.010308.1769914325223241718810504147032707917479250890.6348810.4538330.25773515.74650.430174415.615389.988OpenBenchmarking.org

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: DeepLab V3baaa6K12K18K24K30KSE +/- 1635.57, N = 15SE +/- 3193.55, N = 1222624.723838.828110.1

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: SqueezeNetaaab2K4K6K8K10KSE +/- 109.45, N = 15SE +/- 126.71, N = 39561.259607.409771.82

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception V4abaa15K30K45K60K75KSE +/- 5520.67, N = 15SE +/- 746.34, N = 1565970.966603.968014.0

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: NASNet Mobileabaa300K600K900K1200K1500KSE +/- 16545.28, N = 12SE +/- 16019.04, N = 121800021909871338560

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Floataaab13002600390052006500SE +/- 119.72, N = 13SE +/- 104.76, N = 155619.355922.596222.55

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Quantbaa20K40K60K80K100KSE +/- 5253.23, N = 1536194.882918.4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception ResNet V2baa30K60K90K120K150KSE +/- 2643.69, N = 1290362.0132102.0

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Quantized COCO SSD MobileNet v1baa2K4K6K8K10KSE +/- 144.17, N = 310308.110521.1

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV1aab16003200480064008000713076991. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV2baa4K8K12K16K20K14325167961. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Largebaa5K10K15K20K25K22324227751. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Smallbaa5K10K15K20K25K17188212241. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV1aab2K4K6K8K10K7483105041. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV2baa4K8K12K16K20K14703185251. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Largebaa6K12K18K24K30K27079273191. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Smallbaa6K12K18K24K30K17479257851. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: QS8MobileNetV2aab5K10K15K20K25K17257250891. (CXX) g++ options: -O3 -lrt -lm

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: IP Shapes 1D - Engine: CPUaaab0.14280.28560.42840.57120.714SE +/- 0.001909, N = 3SE +/- 0.002596, N = 30.6319540.6320950.634881MIN: 0.57MIN: 0.57MIN: 0.571. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: IP Shapes 3D - Engine: CPUabaa0.10320.20640.30960.41280.516SE +/- 0.002024, N = 3SE +/- 0.000988, N = 30.4517910.4538330.458506MIN: 0.39MIN: 0.4MIN: 0.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Convolution Batch Shapes Auto - Engine: CPUbaaa0.05840.11680.17520.23360.292SE +/- 0.000249, N = 3SE +/- 0.000187, N = 30.2577350.2583960.259777MIN: 0.25MIN: 0.24MIN: 0.251. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Deconvolution Batch shapes_1d - Engine: CPUaaba48121620SE +/- 0.07, N = 3SE +/- 0.01, N = 315.3915.7517.82MIN: 13.31MIN: 13.64MIN: 14.971. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Deconvolution Batch shapes_3d - Engine: CPUaaab0.09680.19360.29040.38720.484SE +/- 0.004175, N = 3SE +/- 0.005431, N = 30.4253480.4298010.430174MIN: 0.41MIN: 0.41MIN: 0.411. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Recurrent Neural Network Training - Engine: CPUbaaa90180270360450SE +/- 1.16, N = 3SE +/- 1.82, N = 3415.62417.02418.84MIN: 408.78MIN: 406.83MIN: 408.291. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Recurrent Neural Network Inference - Engine: CPUabaa90180270360450SE +/- 2.03, N = 3SE +/- 3.25, N = 3387.46389.99395.49MIN: 376.31MIN: 376.48MIN: 382.731. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread