onednn onnx alderlake

Intel Core i9-12900K testing with a ASUS ROG STRIX Z690-E GAMING WIFI (1003 BIOS) and Gigabyte AMD Radeon RX 6800 XT 16GB on Ubuntu 21.10 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 2203319-NE-ONEDNNONN20
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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
A
March 31 2022
  1 Hour, 52 Minutes
B
March 31 2022
  1 Hour, 51 Minutes
C
March 31 2022
  1 Hour, 47 Minutes
D
March 31 2022
  1 Hour, 47 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 49 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):

A

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/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 Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.6
Python Notes: Python 3.9.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

B

C

D

Processor: Intel Core i9-12900K @ 5.20GHz (16 Cores / 24 Threads), Motherboard: ASUS ROG STRIX Z690-E GAMING WIFI (1003 BIOS), Chipset: Intel Device 7aa7, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Gigabyte AMD Radeon RX 6800 XT 16GB (2575/1000MHz), Audio: Intel Device 7ad0, Monitor: ASUS VP28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Ubuntu 21.10, Kernel: 5.17.0-phx (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13 + Wayland, OpenGL: 4.6 Mesa 22.1.0-devel (git-ae710f3 2022-03-26 impish-oibaf-ppa) (LLVM 13.0.1 DRM 3.46), Vulkan: 1.3.207, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160

onednn onnx alderlakeOpenBenchmarking.orgPhoronix Test SuiteIntel Core i9-12900K @ 5.20GHz (16 Cores / 24 Threads)ASUS ROG STRIX Z690-E GAMING WIFI (1003 BIOS)Intel Device 7aa732GB1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GBGigabyte AMD Radeon RX 6800 XT 16GB (2575/1000MHz)Intel Device 7ad0ASUS VP28UIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 21.105.17.0-phx (x86_64)GNOME Shell 40.5X Server 1.20.13 + Wayland4.6 Mesa 22.1.0-devel (git-ae710f3 2022-03-26 impish-oibaf-ppa) (LLVM 13.0.1 DRM 3.46)1.3.207GCC 11.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionOnednn Onnx Alderlake 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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/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: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.6- Python 3.9.7- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

ABCDResult OverviewPhoronix Test Suite100%106%113%119%125%oneDNNoneDNNONNX RuntimeoneDNNoneDNNoneDNNoneDNNONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeoneDNNoneDNNONNX RuntimeONNX RuntimeONNX RuntimeoneDNNONNX RuntimeoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNONNX RuntimeM.M.B.S.T - u8s8f32 - CPUM.M.B.S.T - f32 - CPUbertsquad-12 - CPU - ParallelD.B.s - f32 - CPUIP Shapes 3D - u8s8f32 - CPUIP Shapes 1D - u8s8f32 - CPUIP Shapes 3D - f32 - CPUsuper-resolution-10 - CPU - Parallelbertsquad-12 - CPU - StandardGPT-2 - CPU - ParallelArcFace ResNet-100 - CPU - Standardfcn-resnet101-11 - CPU - Standardsuper-resolution-10 - CPU - StandardD.B.s - u8s8f32 - CPUR.N.N.I - bf16bf16bf16 - CPUyolov4 - CPU - StandardGPT-2 - CPU - Standardyolov4 - CPU - ParallelIP Shapes 1D - f32 - CPUArcFace ResNet-100 - CPU - ParallelR.N.N.I - u8s8f32 - CPUR.N.N.T - f32 - CPUR.N.N.T - u8s8f32 - CPUR.N.N.T - bf16bf16bf16 - CPUR.N.N.I - f32 - CPUC.B.S.A - u8s8f32 - CPUD.B.s - u8s8f32 - CPUC.B.S.A - f32 - CPUD.B.s - f32 - CPUfcn-resnet101-11 - CPU - Parallel

onednn onnx alderlakeonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - StandardABCD2.637243.912131.082790.8820825.908658.276805.245366.054361.353762.217372883.121614.542881.961617.551.245672884.941615.081.033654798911035628670925931111963631908451853322.651353.818871.055780.8516275.903208.384115.246016.046151.353322.220082875.931611.802885.961612.801.255102881.541630.530.826339811011077632664937916111953641913450453492.631803.884871.057540.8817995.905788.214155.246486.056621.340612.220752881.761612.972882.621611.271.284322879.531618.780.842998804611079631666933918111953621896444453282.632873.887171.059230.8850575.909308.050845.248266.047981.342962.219302879.921614.782880.351614.271.310812882.221616.111.01114180951112363366996492611195364189345065384OpenBenchmarking.org

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of Intel oneAPI. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUABCD0.59661.19321.78982.38642.983SE +/- 0.00542, N = 3SE +/- 0.01495, N = 3SE +/- 0.00440, N = 3SE +/- 0.00281, N = 32.637242.651352.631802.63287MIN: 2.5MIN: 2.51MIN: 2.49MIN: 2.511. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUABCD0.88021.76042.64063.52084.401SE +/- 0.00073, N = 3SE +/- 0.00339, N = 3SE +/- 0.00218, N = 3SE +/- 0.00582, N = 33.912133.818873.884873.88717MIN: 3.89MIN: 3.78MIN: 3.86MIN: 3.851. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUABCD0.24360.48720.73080.97441.218SE +/- 0.01605, N = 15SE +/- 0.00867, N = 3SE +/- 0.00884, N = 3SE +/- 0.00217, N = 31.082791.055781.057541.05923MIN: 1.01MIN: 1.01MIN: 1.01MIN: 1.021. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUABCD0.19910.39820.59730.79640.9955SE +/- 0.000523, N = 3SE +/- 0.003743, N = 3SE +/- 0.002403, N = 3SE +/- 0.006655, N = 30.8820820.8516270.8817990.885057MIN: 0.87MIN: 0.83MIN: 0.86MIN: 0.861. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU

A: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

B: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

C: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

D: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU

A: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

B: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

C: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

D: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUABCD1.32962.65923.98885.31846.648SE +/- 0.00465, N = 3SE +/- 0.00395, N = 3SE +/- 0.00383, N = 3SE +/- 0.00197, N = 35.908655.903205.905785.90930MIN: 5.79MIN: 5.83MIN: 5.82MIN: 5.751. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUABCD246810SE +/- 0.10247, N = 15SE +/- 0.11946, N = 14SE +/- 0.09831, N = 15SE +/- 0.05693, N = 38.276808.384118.214158.05084MIN: 4.02MIN: 3.99MIN: 4.09MIN: 4.241. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUABCD1.18092.36183.54274.72365.9045SE +/- 0.00223, N = 3SE +/- 0.00260, N = 3SE +/- 0.00169, N = 3SE +/- 0.00317, N = 35.245365.246015.246485.24826MIN: 5.18MIN: 5.17MIN: 5.19MIN: 5.171. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUABCD246810SE +/- 0.00353, N = 3SE +/- 0.00195, N = 3SE +/- 0.00242, N = 3SE +/- 0.00248, N = 36.054366.046156.056626.04798MIN: 5.99MIN: 5.97MIN: 5.9MIN: 5.951. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUABCD0.30460.60920.91381.21841.523SE +/- 0.01690, N = 3SE +/- 0.01445, N = 3SE +/- 0.00457, N = 3SE +/- 0.00783, N = 31.353761.353321.340611.34296MIN: 1.28MIN: 1.28MIN: 1.28MIN: 1.281. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUABCD0.49970.99941.49911.99882.4985SE +/- 0.00202, N = 3SE +/- 0.00095, N = 3SE +/- 0.00145, N = 3SE +/- 0.00390, N = 32.217372.220082.220752.21930MIN: 2.2MIN: 2.19MIN: 2.2MIN: 2.191. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUABCD6001200180024003000SE +/- 3.43, N = 3SE +/- 3.97, N = 3SE +/- 2.26, N = 3SE +/- 3.46, N = 32883.122875.932881.762879.92MIN: 2869.72MIN: 2865.18MIN: 2866.35MIN: 2866.641. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUABCD30060090012001500SE +/- 2.06, N = 3SE +/- 2.11, N = 3SE +/- 0.75, N = 3SE +/- 1.49, N = 31614.541611.801612.971614.78MIN: 1608.19MIN: 1603.03MIN: 1606.37MIN: 1607.961. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUABCD6001200180024003000SE +/- 6.09, N = 3SE +/- 2.20, N = 3SE +/- 1.28, N = 3SE +/- 2.59, N = 32881.962885.962882.622880.35MIN: 2865.7MIN: 2873.23MIN: 2872.99MIN: 2869.741. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU

A: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

B: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

C: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

D: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU

A: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

B: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

C: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

D: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU

A: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

B: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

C: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

D: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUABCD30060090012001500SE +/- 5.04, N = 3SE +/- 1.77, N = 3SE +/- 1.60, N = 3SE +/- 0.67, N = 31617.551612.801611.271614.27MIN: 1606.77MIN: 1604.84MIN: 1602.83MIN: 1608.321. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUABCD0.29490.58980.88471.17961.4745SE +/- 0.01358, N = 3SE +/- 0.01551, N = 3SE +/- 0.01243, N = 3SE +/- 0.02113, N = 151.245671.255101.284321.31081MIN: 1.17MIN: 1.17MIN: 1.19MIN: 1.171. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUABCD6001200180024003000SE +/- 4.56, N = 3SE +/- 4.30, N = 3SE +/- 2.50, N = 3SE +/- 0.97, N = 32884.942881.542879.532882.22MIN: 2874.53MIN: 2866.57MIN: 2866.7MIN: 2871.871. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUABCD400800120016002000SE +/- 3.13, N = 3SE +/- 22.13, N = 3SE +/- 3.52, N = 3SE +/- 2.17, N = 31615.081630.531618.781616.11MIN: 1605.12MIN: 1601.77MIN: 1609.4MIN: 1608.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUABCD0.23260.46520.69780.93041.163SE +/- 0.086658, N = 12SE +/- 0.001870, N = 3SE +/- 0.006474, N = 3SE +/- 0.091776, N = 121.0336540.8263390.8429981.011141MIN: 0.71MIN: 0.71MIN: 0.72MIN: 0.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU

A: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

B: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

C: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

D: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: ParallelABCD2K4K6K8K10KSE +/- 58.12, N = 3SE +/- 47.85, N = 3SE +/- 40.10, N = 3SE +/- 24.57, N = 379898110804680951. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: StandardABCD2K4K6K8K10KSE +/- 13.90, N = 3SE +/- 11.10, N = 3SE +/- 13.33, N = 3SE +/- 41.07, N = 3110351107711079111231. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: ParallelABCD140280420560700SE +/- 2.75, N = 3SE +/- 2.03, N = 3SE +/- 2.05, N = 3SE +/- 1.17, N = 36286326316331. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: StandardABCD140280420560700SE +/- 2.33, N = 3SE +/- 4.18, N = 3SE +/- 2.74, N = 3SE +/- 3.53, N = 36706646666691. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: ParallelABCD2004006008001000SE +/- 8.08, N = 3SE +/- 10.12, N = 5SE +/- 12.55, N = 3SE +/- 6.62, N = 39259379339641. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: StandardABCD2004006008001000SE +/- 5.01, N = 3SE +/- 3.92, N = 3SE +/- 9.18, N = 3SE +/- 2.60, N = 39319169189261. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelABCD20406080100SE +/- 0.60, N = 3SE +/- 0.29, N = 3SE +/- 0.17, N = 3SE +/- 0.17, N = 31111111111111. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: StandardABCD20406080100SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.00, N = 3969595951. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelABCD80160240320400SE +/- 0.17, N = 3SE +/- 0.50, N = 3SE +/- 0.17, N = 3SE +/- 0.29, N = 33633643623641. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardABCD400800120016002000SE +/- 5.36, N = 3SE +/- 2.93, N = 3SE +/- 11.79, N = 3SE +/- 4.07, N = 319081913189618931. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: ParallelABCD10002000300040005000SE +/- 53.96, N = 3SE +/- 63.24, N = 3SE +/- 28.86, N = 3SE +/- 57.47, N = 345184504444445061. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: StandardABCD12002400360048006000SE +/- 20.95, N = 3SE +/- 31.64, N = 3SE +/- 28.50, N = 3SE +/- 52.89, N = 353325349532853841. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

A

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/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 Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.6
Python Notes: Python 3.9.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 31 March 2022 05:14 by user phoronix.

B

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/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 Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.6
Python Notes: Python 3.9.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 31 March 2022 07:33 by user phoronix.

C

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/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 Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.6
Python Notes: Python 3.9.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 31 March 2022 12:06 by user phoronix.

D

Processor: Intel Core i9-12900K @ 5.20GHz (16 Cores / 24 Threads), Motherboard: ASUS ROG STRIX Z690-E GAMING WIFI (1003 BIOS), Chipset: Intel Device 7aa7, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 2000GB, Graphics: Gigabyte AMD Radeon RX 6800 XT 16GB (2575/1000MHz), Audio: Intel Device 7ad0, Monitor: ASUS VP28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Ubuntu 21.10, Kernel: 5.17.0-phx (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13 + Wayland, OpenGL: 4.6 Mesa 22.1.0-devel (git-ae710f3 2022-03-26 impish-oibaf-ppa) (LLVM 13.0.1 DRM 3.46), Vulkan: 1.3.207, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/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 Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.6
Python Notes: Python 3.9.7
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 31 March 2022 14:09 by user phoronix.