Intel Core i5-1135G7 testing with a Dell 08642J (3.3.0 BIOS) and Intel Xe TGL GT2 3GB on Ubuntu 20.04 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 2203305-NE-ONEDNNTGL55 onednn tgl - Phoronix Test Suite onednn tgl Intel Core i5-1135G7 testing with a Dell 08642J (3.3.0 BIOS) and Intel Xe TGL GT2 3GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2203305-NE-ONEDNNTGL55&gru&sor&rro .
onednn tgl Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution A V C Intel Core i5-1135G7 @ 4.20GHz (4 Cores / 8 Threads) Dell 08642J (3.3.0 BIOS) Intel Device a0ef 8GB PC SN530 NVMe WDC 256GB Intel Xe TGL GT2 3GB (1300MHz) Realtek ALC289 Intel Device a0f0 Ubuntu 20.04 5.14.0-1029-oem (x86_64) GNOME Shell 3.36.9 X Server 1.20.9 4.6 Mesa 21.2.6 1.2.182 GCC 9.4.0 ext4 3456x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-Av3uEd/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --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 Details - Scaling Governor: intel_pstate powersave (EPP: balance_power) - CPU Microcode: 0x88 - Thermald 1.9.1 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + 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
onednn tgl onednn: IP Shapes 1D - f32 - CPU onednn: IP Shapes 3D - f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU onednn: IP Shapes 1D - bf16bf16bf16 - CPU onednn: IP Shapes 3D - bf16bf16bf16 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU onednn: Recurrent Neural Network Training - f32 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU onednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU onednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPU A V C 10.2134 6.61640 2.10994 2.70766 25.6483 6.44962 10.3470 16.5694 13.5318 8.51257 2.63798 3.14203 7561.25 4465.24 8685.42 52.5447 60.1397 52.9428 3840.02 3.15249 8798.47 4543.09 1.50550 10.8998 10.2234 6.72230 2.11645 2.71662 25.6377 6.52050 10.3449 17.1800 13.5573 8.49301 2.63758 3.15049 8754.58 4565.49 8986.95 52.5377 60.1925 52.9356 4396.18 3.15675 8805.12 4563.71 1.52166 10.8912 10.2147 6.54558 2.10776 2.69766 25.6419 6.51208 10.3111 17.1237 13.5892 8.50841 2.64240 3.14523 7565.21 4553.79 9364.40 52.5455 60.2420 52.7790 4467.07 3.15390 8811.18 4558.69 1.50861 10.8797 OpenBenchmarking.org
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU V C A 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 10.22 10.21 10.21 MIN: 9.17 MIN: 8.88 MIN: 9.58 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU V A C 2 4 6 8 10 SE +/- 0.04745, N = 15 SE +/- 0.07031, N = 3 SE +/- 0.07707, N = 4 6.72230 6.61640 6.54558 MIN: 6.21 MIN: 6.22 MIN: 6.22 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU V A C 0.4762 0.9524 1.4286 1.9048 2.381 SE +/- 0.00628, N = 3 SE +/- 0.00492, N = 3 SE +/- 0.00482, N = 3 2.11645 2.10994 2.10776 MIN: 1.84 MIN: 1.89 MIN: 1.86 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU V A C 0.6112 1.2224 1.8336 2.4448 3.056 SE +/- 0.00630, N = 3 SE +/- 0.01070, N = 3 SE +/- 0.00412, N = 3 2.71662 2.70766 2.69766 MIN: 2.61 MIN: 2.64 MIN: 2.61 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU A C V 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 25.65 25.64 25.64 MIN: 25.15 MIN: 25.14 MIN: 25.14 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU V C A 2 4 6 8 10 SE +/- 0.04034, N = 3 SE +/- 0.02219, N = 3 SE +/- 0.01617, N = 3 6.52050 6.51208 6.44962 MIN: 5.93 MIN: 5.91 MIN: 5.95 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU A V C 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 10.35 10.34 10.31 MIN: 10.25 MIN: 10.24 MIN: 10.25 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU V C A 4 8 12 16 20 SE +/- 0.18, N = 5 SE +/- 0.31, N = 15 SE +/- 0.23, N = 3 17.18 17.12 16.57 MIN: 15.23 MIN: 15.19 MIN: 15.22 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU C V A 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 13.59 13.56 13.53 MIN: 13.42 MIN: 13.37 MIN: 13.4 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU A C V 2 4 6 8 10 SE +/- 0.01210, N = 3 SE +/- 0.00998, N = 3 SE +/- 0.00155, N = 3 8.51257 8.50841 8.49301 MIN: 8.4 MIN: 8.39 MIN: 8.4 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU C A V 0.5945 1.189 1.7835 2.378 2.9725 SE +/- 0.00064, N = 3 SE +/- 0.00335, N = 3 SE +/- 0.00141, N = 3 2.64240 2.63798 2.63758 MIN: 2.61 MIN: 2.6 MIN: 2.6 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU V C A 0.7089 1.4178 2.1267 2.8356 3.5445 SE +/- 0.00828, N = 3 SE +/- 0.00779, N = 3 SE +/- 0.00616, N = 3 3.15049 3.14523 3.14203 MIN: 3.12 MIN: 3.12 MIN: 3.11 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU V C A 2K 4K 6K 8K 10K SE +/- 135.26, N = 15 SE +/- 6.65, N = 3 SE +/- 6.49, N = 3 8754.58 7565.21 7561.25 MIN: 7528.22 MIN: 7517.11 MIN: 7509.86 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU V C A 1000 2000 3000 4000 5000 SE +/- 2.96, N = 3 SE +/- 6.34, N = 3 SE +/- 65.02, N = 15 4565.49 4553.79 4465.24 MIN: 4519.64 MIN: 4499.14 MIN: 3809.91 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU C V A 2K 4K 6K 8K 10K SE +/- 338.92, N = 15 SE +/- 11.00, N = 3 SE +/- 167.45, N = 12 9364.40 8986.95 8685.42 MIN: 7528.44 MIN: 8916.06 MIN: 7519.48 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU C A V 12 24 36 48 60 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 52.55 52.54 52.54 MIN: 52.3 MIN: 52.31 MIN: 52.3 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU C V A 13 26 39 52 65 SE +/- 0.10, N = 3 SE +/- 0.14, N = 3 SE +/- 0.08, N = 3 60.24 60.19 60.14 MIN: 59.37 MIN: 59.35 MIN: 59.39 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU A V C 12 24 36 48 60 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 52.94 52.94 52.78 MIN: 52.65 MIN: 52.59 MIN: 52.55 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU C V A 1000 2000 3000 4000 5000 SE +/- 65.79, N = 15 SE +/- 87.30, N = 12 SE +/- 2.59, N = 3 4467.07 4396.18 3840.02 MIN: 3801.94 MIN: 3804.91 MIN: 3795.34 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU V C A 0.7103 1.4206 2.1309 2.8412 3.5515 SE +/- 0.00453, N = 3 SE +/- 0.00193, N = 3 SE +/- 0.00130, N = 3 3.15675 3.15390 3.15249 MIN: 3.07 MIN: 3.07 MIN: 3.07 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU C V A 2K 4K 6K 8K 10K SE +/- 126.15, N = 15 SE +/- 129.34, N = 15 SE +/- 129.93, N = 15 8811.18 8805.12 8798.47 MIN: 7525.68 MIN: 7514.46 MIN: 7521.74 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU V C A 1000 2000 3000 4000 5000 SE +/- 1.30, N = 3 SE +/- 5.97, N = 3 SE +/- 7.37, N = 3 4563.71 4558.69 4543.09 MIN: 4521.55 MIN: 4497.76 MIN: 4472.94 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU V C A 0.3424 0.6848 1.0272 1.3696 1.712 SE +/- 0.01522, N = 6 SE +/- 0.00199, N = 3 SE +/- 0.00306, N = 3 1.52166 1.50861 1.50550 MIN: 1.45 MIN: 1.45 MIN: 1.45 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU A V C 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 10.90 10.89 10.88 MIN: 10.65 MIN: 10.67 MIN: 10.66 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
Phoronix Test Suite v10.8.4