onednn 3.0 raptor lake

Intel Core i9-13900K testing with a ASUS PRIME Z790-P WIFI (0602 BIOS) and eVGA NVIDIA GeForce RTX 3060 12GB on Ubuntu 22.10 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 2212209-PTS-ONEDNN3016
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

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
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
December 20 2022
  1 Hour, 4 Minutes
b
December 20 2022
  1 Hour, 19 Minutes
c
December 20 2022
  1 Hour, 5 Minutes
Invert Hiding All Results Option
  1 Hour, 10 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-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-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-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/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
Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x10e - Thermald 2.5.1
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

b

c

Processor: Intel Core i9-13900K @ 4.00GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0602 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: eVGA NVIDIA GeForce RTX 3060 12GB, Audio: Realtek ALC897, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7a70

OS: Ubuntu 22.10, Kernel: 5.19.0-26-generic (x86_64), Desktop: GNOME Shell 43.1, Display Server: X Server 1.21.1.4, Display Driver: NVIDIA 525.60.11, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.0.89, Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 2560x1600

onednn 3.0 raptor lakeOpenBenchmarking.orgPhoronix Test SuiteIntel Core i9-13900K @ 4.00GHz (24 Cores / 32 Threads)ASUS PRIME Z790-P WIFI (0602 BIOS)Intel Device 7a2732GB1000GB Western Digital WDS100T1X0E-00AFY0eVGA NVIDIA GeForce RTX 3060 12GBRealtek ALC897ASUS VP28URealtek RTL8125 2.5GbE + Intel Device 7a70Ubuntu 22.105.19.0-26-generic (x86_64)GNOME Shell 43.1X Server 1.21.1.4NVIDIA 525.60.114.6.0OpenCL 3.0 CUDA 12.0.891.3.224GCC 12.2.0ext42560x1600ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionOnednn 3.0 Raptor Lake 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-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-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/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 - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x10e - Thermald 2.5.1 - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

abcResult OverviewPhoronix Test Suite100%104%109%113%117%oneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNoneDNNM.M.B.S.T - f32 - CPUIP Shapes 1D - u8s8f32 - CPUIP Shapes 1D - f32 - CPUIP Shapes 3D - f32 - CPUD.B.s - f32 - CPUIP Shapes 3D - u8s8f32 - CPUD.B.s - u8s8f32 - CPUM.M.B.S.T - u8s8f32 - CPUR.N.N.I - f32 - CPUR.N.N.T - u8s8f32 - CPUR.N.N.T - bf16bf16bf16 - CPUR.N.N.T - f32 - CPUR.N.N.I - bf16bf16bf16 - CPUC.B.S.A - u8s8f32 - CPUR.N.N.I - u8s8f32 - CPUC.B.S.A - f32 - CPUD.B.s - f32 - CPUD.B.s - u8s8f32 - CPU

onednn 3.0 raptor lakeonednn: 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 - CPUabc1.715884.150080.7867090.6293035.763847.477303.427365.910060.9554041.449112119.681087.512126.291098.421.2693262117.941084.750.7830811.884913.935730.8630890.6219665.758167.366743.423915.898290.9727271.449382122.241073.622143.271099.641.1798552148.961095.580.7861771.860773.848790.8917270.5993915.751277.867923.425195.868060.9374701.448852089.671104.462097.671095.201.3829352113.691083.230.759611OpenBenchmarking.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 the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUabc0.42410.84821.27231.69642.1205SE +/- 0.01122, N = 3SE +/- 0.01809, N = 15SE +/- 0.02132, N = 151.715881.884911.86077MIN: 1.57MIN: 1.57MIN: 1.571. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUabc246810Min: 1.7 / Avg: 1.72 / Max: 1.74Min: 1.69 / Avg: 1.88 / Max: 2Min: 1.68 / Avg: 1.86 / Max: 1.931. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUabc0.93381.86762.80143.73524.669SE +/- 0.02209, N = 3SE +/- 0.00290, N = 3SE +/- 0.00182, N = 34.150083.935733.84879MIN: 4.08MIN: 3.88MIN: 3.81. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUabc246810Min: 4.13 / Avg: 4.15 / Max: 4.19Min: 3.93 / Avg: 3.94 / Max: 3.94Min: 3.85 / Avg: 3.85 / Max: 3.851. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUabc0.20060.40120.60180.80241.003SE +/- 0.034022, N = 15SE +/- 0.039890, N = 15SE +/- 0.052959, N = 150.7867090.8630890.891727MIN: 0.65MIN: 0.65MIN: 0.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUabc246810Min: 0.7 / Avg: 0.79 / Max: 1.1Min: 0.69 / Avg: 0.86 / Max: 1.13Min: 0.71 / Avg: 0.89 / Max: 1.241. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUabc0.14160.28320.42480.56640.708SE +/- 0.001158, N = 3SE +/- 0.008037, N = 14SE +/- 0.000382, N = 30.6293030.6219660.599391MIN: 0.61MIN: 0.57MIN: 0.581. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUabc246810Min: 0.63 / Avg: 0.63 / Max: 0.63Min: 0.6 / Avg: 0.62 / Max: 0.72Min: 0.6 / Avg: 0.6 / Max: 0.61. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUabc1.29692.59383.89075.18766.4845SE +/- 0.00332, N = 3SE +/- 0.00221, N = 3SE +/- 0.00220, N = 35.763845.758165.75127MIN: 5.54MIN: 5.53MIN: 5.531. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUabc246810Min: 5.76 / Avg: 5.76 / Max: 5.77Min: 5.76 / Avg: 5.76 / Max: 5.76Min: 5.75 / Avg: 5.75 / Max: 5.761. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUabc246810SE +/- 0.11831, N = 15SE +/- 0.09423, N = 15SE +/- 0.15590, N = 157.477307.366747.86792MIN: 2.84MIN: 2.98MIN: 2.721. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUabc3691215Min: 6.77 / Avg: 7.48 / Max: 8.72Min: 6.74 / Avg: 7.37 / Max: 7.89Min: 6.83 / Avg: 7.87 / Max: 9.191. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUabc0.77121.54242.31363.08483.856SE +/- 0.00441, N = 3SE +/- 0.00149, N = 3SE +/- 0.00291, N = 33.427363.423913.42519MIN: 3.38MIN: 3.39MIN: 3.381. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUabc246810Min: 3.42 / Avg: 3.43 / Max: 3.44Min: 3.42 / Avg: 3.42 / Max: 3.43Min: 3.42 / Avg: 3.43 / Max: 3.431. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUabc1.32982.65963.98945.31926.649SE +/- 0.00461, N = 3SE +/- 0.00611, N = 3SE +/- 0.00679, N = 35.910065.898295.86806MIN: 5.6MIN: 5.63MIN: 5.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUabc246810Min: 5.9 / Avg: 5.91 / Max: 5.92Min: 5.89 / Avg: 5.9 / Max: 5.9Min: 5.86 / Avg: 5.87 / Max: 5.881. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUabc0.21890.43780.65670.87561.0945SE +/- 0.007682, N = 15SE +/- 0.011174, N = 3SE +/- 0.006580, N = 30.9554040.9727270.937470MIN: 0.86MIN: 0.86MIN: 0.861. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUabc246810Min: 0.89 / Avg: 0.96 / Max: 1Min: 0.95 / Avg: 0.97 / Max: 0.99Min: 0.93 / Avg: 0.94 / Max: 0.951. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUabc0.32610.65220.97831.30441.6305SE +/- 0.00031, N = 3SE +/- 0.00127, N = 3SE +/- 0.00014, N = 31.449111.449381.44885MIN: 1.44MIN: 1.43MIN: 1.441. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUabc246810Min: 1.45 / Avg: 1.45 / Max: 1.45Min: 1.45 / Avg: 1.45 / Max: 1.45Min: 1.45 / Avg: 1.45 / Max: 1.451. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUabc5001000150020002500SE +/- 24.68, N = 3SE +/- 24.57, N = 3SE +/- 1.48, N = 32119.682122.242089.67MIN: 1981.97MIN: 1978.3MIN: 1979.871. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUabc400800120016002000Min: 2071.21 / Avg: 2119.68 / Max: 2152.04Min: 2092.38 / Avg: 2122.24 / Max: 2170.96Min: 2087.57 / Avg: 2089.67 / Max: 2092.521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUabc2004006008001000SE +/- 8.11, N = 11SE +/- 4.14, N = 3SE +/- 15.65, N = 31087.511073.621104.46MIN: 1012.76MIN: 1013.98MIN: 1015.481. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUabc2004006008001000Min: 1056.13 / Avg: 1087.51 / Max: 1130.27Min: 1066.45 / Avg: 1073.62 / Max: 1080.8Min: 1074.13 / Avg: 1104.46 / Max: 1126.331. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUabc5001000150020002500SE +/- 21.82, N = 5SE +/- 15.78, N = 11SE +/- 21.19, N = 62126.292143.272097.67MIN: 1980.46MIN: 1977.9MIN: 1978.891. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUabc400800120016002000Min: 2058.26 / Avg: 2126.29 / Max: 2190.4Min: 2074.5 / Avg: 2143.27 / Max: 2209.44Min: 2051.92 / Avg: 2097.67 / Max: 2186.841. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUabc2004006008001000SE +/- 11.90, N = 5SE +/- 10.37, N = 7SE +/- 9.64, N = 151098.421099.641095.20MIN: 1013.68MIN: 1013.55MIN: 1014.021. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUabc2004006008001000Min: 1070.56 / Avg: 1098.42 / Max: 1131.09Min: 1067.85 / Avg: 1099.64 / Max: 1125.91Min: 1051.75 / Avg: 1095.2 / Max: 1182.11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUabc0.31120.62240.93361.24481.556SE +/- 0.079866, N = 15SE +/- 0.089715, N = 12SE +/- 0.081255, N = 151.2693261.1798551.382935MIN: 0.74MIN: 0.73MIN: 0.731. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUabc246810Min: 0.89 / Avg: 1.27 / Max: 1.87Min: 0.87 / Avg: 1.18 / Max: 1.78Min: 0.9 / Avg: 1.38 / Max: 1.831. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUabc5001000150020002500SE +/- 26.18, N = 3SE +/- 25.31, N = 4SE +/- 21.10, N = 32117.942148.962113.69MIN: 1979.58MIN: 1978.19MIN: 1980.311. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUabc400800120016002000Min: 2083.66 / Avg: 2117.94 / Max: 2169.36Min: 2095.21 / Avg: 2148.96 / Max: 2208.35Min: 2073.43 / Avg: 2113.69 / Max: 2144.771. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUabc2004006008001000SE +/- 12.11, N = 4SE +/- 8.18, N = 15SE +/- 13.87, N = 31084.751095.581083.23MIN: 1014.51MIN: 1014.02MIN: 1015.171. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUabc2004006008001000Min: 1067.9 / Avg: 1084.75 / Max: 1120.52Min: 1041.86 / Avg: 1095.58 / Max: 1150.31Min: 1064.9 / Avg: 1083.23 / Max: 1110.441. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUabc0.17690.35380.53070.70760.8845SE +/- 0.020828, N = 15SE +/- 0.058336, N = 12SE +/- 0.017020, N = 150.7830810.7861770.759611MIN: 0.53MIN: 0.53MIN: 0.551. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUabc246810Min: 0.69 / Avg: 0.78 / Max: 0.93Min: 0.66 / Avg: 0.79 / Max: 1.42Min: 0.69 / Avg: 0.76 / Max: 0.951. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

a

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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-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-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/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
Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x10e - Thermald 2.5.1
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 20 December 2022 04:52 by user pts.

b

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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-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-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/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
Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x10e - Thermald 2.5.1
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 20 December 2022 06:13 by user pts.

c

Processor: Intel Core i9-13900K @ 4.00GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0602 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: eVGA NVIDIA GeForce RTX 3060 12GB, Audio: Realtek ALC897, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7a70

OS: Ubuntu 22.10, Kernel: 5.19.0-26-generic (x86_64), Desktop: GNOME Shell 43.1, Display Server: X Server 1.21.1.4, Display Driver: NVIDIA 525.60.11, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.0.89, Vulkan: 1.3.224, Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 2560x1600

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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-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-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/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
Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x10e - Thermald 2.5.1
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 20 December 2022 08:07 by user pts.