Coder Radio XPS 13 ML Ubuntu Benchmark

Intel Core i7-10510U testing with a LENOVO 20U9CTO1WW (N2WET24W 1.14 BIOS) and Intel UHD 3GB on Fedora 33 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2101022-AS-2101015FI37&grs&rdt.

Coder Radio XPS 13 ML Ubuntu BenchmarkProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet LakeIntel Core i5-1135G7 @ 4.20GHz (4 Cores / 8 Threads)Dell 0THX8P (1.1.1 BIOS)Intel Device a0ef16GBMicron 2300 NVMe 512GBIntel Xe 3GB (1300MHz)Realtek ALC289Intel Device a0f0Ubuntu 20.045.6.0-1036-oem (x86_64)GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.6 Mesa 20.0.81.2.131GCC 9.3.0ext41920x1200Intel Core i7-10510U @ 4.90GHz (4 Cores / 8 Threads)LENOVO 20U9CTO1WW (N2WET24W 1.14 BIOS)Intel Comet Lake PCH-LP2 x 8 GB LPDDR3-2133MT/s Samsung256GB Western Digital PC SN730 SDBQNTY-256G-1001Intel UHD 3GB (1150MHz)Realtek ALC285Intel + Intel Comet Lake PCH-LP CNVi WiFiFedora 335.9.16-200.fc33.x86_64 (x86_64)KDE Plasma 5.20.4X Server 1.20.10modesetting 1.20.104.6 Mesa 20.2.6GCC 10.2.1 20201125 + Clang 11.0.0btrfs2560x1440OpenBenchmarking.orgCompiler Details- XPS 13 Tiger Lake Ubuntu 20.04: --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-HskZEa/gcc-9-9.3.0/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 - ThinkPad X1 Fedora Comet Lake: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver Processor Details- XPS 13 Tiger Lake Ubuntu 20.04: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 1.9.1- ThinkPad X1 Fedora Comet Lake: Scaling Governor: intel_pstate powersavePython Details- XPS 13 Tiger Lake Ubuntu 20.04: Python 3.8.5- ThinkPad X1 Fedora Comet Lake: Python 3.9.1Security Details- XPS 13 Tiger Lake Ubuntu 20.04: 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 - ThinkPad X1 Fedora Comet Lake: SELinux + itlb_multihit: KVM: Mitigation of VMX unsupported + 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: Mitigation of TSX disabled + tsx_async_abort: Not affected

Coder Radio XPS 13 ML Ubuntu Benchmarkonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUplaidml: No - Inference - VGG16 - CPUmnn: resnet-v2-50ncnn: CPU - vgg16ncnn: Vulkan GPU - vgg16onednn: IP Shapes 3D - u8s8f32 - CPUncnn: CPU - alexnetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU - yolov4-tinyplaidml: No - Inference - ResNet 50 - CPUtensorflow-lite: Inception ResNet V2tensorflow-lite: Inception V4onednn: Deconvolution Batch shapes_3d - f32 - CPUnumpy: ncnn: Vulkan GPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3scikit-learn: mlpack: scikit_linearridgeregressionmlpack: scikit_svmmlpack: scikit_qdamlpack: scikit_icaai-benchmark: Device AI Scoreai-benchmark: Device Training Scoreai-benchmark: Device Inference Scorenumenta-nab: Bayesian Changepointnumenta-nab: Earthgecko Skylinenumenta-nab: Windowed Gaussiannumenta-nab: Relative Entropynumenta-nab: EXPoSErnnoise: onednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUonednn: IP Shapes 3D - bf16bf16bf16 - CPUonednn: IP Shapes 1D - bf16bf16bf16 - CPUncnn: CPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3opencv: DNN - Deep Neural Networkncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: CPU - regnety_400mncnn: CPU - squeezenet_ssdncnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - resnet18ncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenetmnn: inception-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224mnn: SqueezeNetV1.0tensorflow-lite: Mobilenet Quanttensorflow-lite: Mobilenet Floattensorflow-lite: NASNet Mobiletensorflow-lite: SqueezeNetonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: IP Shapes 1D - f32 - CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake2.942626.593507.934503.136842.4305111.56326.4754.69168.5069.162.6298119.0635.1144.683.278329360922023013.4125293.1817.90013.5034.66138.24123.23118663055681.062333.63927.70248.6091139.24131.94711.807252.682457.054652.42846.3997925.8282535121.0139.5351.1319.2322.2524.582.8011.838.1310.306.707.7121.1139.6144.6551.0122.0725.012.8512.538.109.996.717.7835.0368.5238.3206.23811.2564195064243094555256274872.123074516.608859.053.932984528.118875.335736.438862.6514.632610.277321.8817.9521.148.185.8822.023.7488.35108.71107.703.9526.5546.4158.162.57101779331113446715.85299.9946.4145.37796820.1444.7165.5925.7528.3328.853.2413.748.7712.808.289.6422.3445.6157.1067.2030.2331.393.8015.229.7614.589.1010.6745.3797.7113.159.6218.0453589752531259756976960111.827969.0315837.416.738004.4115828.668215.0815729.9620.7115.77OpenBenchmarking.org

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake510152025SE +/- 0.02862, N = 12SE +/- 0.09223, N = 32.9426221.88000-O2 - MIN: 19.111. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake48121620SE +/- 0.01444, N = 3SE +/- 0.01158, N = 36.5935017.95000MIN: 6.09-O2 - MIN: 13.821. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake510152025SE +/- 0.02049, N = 3SE +/- 0.16335, N = 37.9345021.14000MIN: 7.85-O2 - MIN: 20.411. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake246810SE +/- 0.00316, N = 3SE +/- 0.08942, N = 33.136848.18000MIN: 3.11-O2 - MIN: 7.761. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake1.3232.6463.9695.2926.615SE +/- 0.02334, N = 14SE +/- 0.02743, N = 32.430515.88000MIN: 1.9-O2 - MIN: 5.151. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake510152025SE +/- 0.13, N = 15SE +/- 0.02, N = 311.5622.02MIN: 10.07-O2 - MIN: 21.811. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

PlaidML

FP16: No - Mode: Inference - Network: VGG16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake246810SE +/- 0.02, N = 3SE +/- 0.04, N = 76.473.74

Mobile Neural Network

Model: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: resnet-v2-50XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake20406080100SE +/- 0.17, N = 11SE +/- 1.68, N = 354.6988.35MIN: 53.32 / MAX: 132.87MIN: 67.94 / MAX: 196.351. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg16XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake20406080100SE +/- 0.25, N = 3SE +/- 1.36, N = 1268.50108.71-O3 - MIN: 67.14 / MAX: 86.96-O2 - MIN: 101.54 / MAX: 1158.671. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: vgg16XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake20406080100SE +/- 0.54, N = 3SE +/- 1.75, N = 369.16107.70-O3 - MIN: 67.22 / MAX: 89.29-O2 - MIN: 103.24 / MAX: 139.51. (CXX) g++ options: -rdynamic -lgomp -lpthread

oneDNN

Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake0.88881.77762.66643.55524.444SE +/- 0.00152, N = 3SE +/- 0.05749, N = 32.629813.95000MIN: 2.56-O2 - MIN: 3.461. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnetXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake612182430SE +/- 0.02, N = 3SE +/- 0.44, N = 1219.0626.55-O3 - MIN: 18.7 / MAX: 27.76-O2 - MIN: 22.72 / MAX: 58.371. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mobilenetXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake1122334455SE +/- 0.48, N = 3SE +/- 0.13, N = 335.1146.41-O3 - MIN: 34.07 / MAX: 62.97-O2 - MIN: 44.19 / MAX: 58.771. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: yolov4-tinyXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake1326395265SE +/- 0.57, N = 3SE +/- 1.59, N = 344.6858.16-O3 - MIN: 43.68 / MAX: 64.97-O2 - MIN: 48.75 / MAX: 86.051. (CXX) g++ options: -rdynamic -lgomp -lpthread

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake0.73581.47162.20742.94323.679SE +/- 0.01, N = 3SE +/- 0.01, N = 33.272.57

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake2M4M6M8M10MSE +/- 33855.35, N = 3SE +/- 63902.46, N = 3832936010177933

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake2M4M6M8M10MSE +/- 32590.84, N = 3SE +/- 16976.19, N = 3922023011134467

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake48121620SE +/- 0.05, N = 3SE +/- 0.27, N = 313.4115.85MIN: 13.24-O2 - MIN: 14.871. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Numpy Benchmark

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake70140210280350SE +/- 0.46, N = 3SE +/- 3.17, N = 3293.18299.99

NCNN

Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3ThinkPad X1 Fedora Comet Lake1122334455SE +/- 0.13, N = 346.41MIN: 44.19 / MAX: 58.771. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

Scikit-Learn

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.22.1XPS 13 Tiger Lake Ubuntu 20.0448121620SE +/- 0.15, N = 317.90

Mlpack Benchmark

Benchmark: scikit_linearridgeregression

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionXPS 13 Tiger Lake Ubuntu 20.043691215SE +/- 0.02, N = 313.50

Mlpack Benchmark

Benchmark: scikit_svm

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmXPS 13 Tiger Lake Ubuntu 20.04816243240SE +/- 0.04, N = 334.66

Mlpack Benchmark

Benchmark: scikit_qda

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaXPS 13 Tiger Lake Ubuntu 20.04306090120150SE +/- 0.10, N = 3138.24

Mlpack Benchmark

Benchmark: scikit_ica

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaXPS 13 Tiger Lake Ubuntu 20.04306090120150SE +/- 1.89, N = 3123.23

AI Benchmark Alpha

Device AI Score

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI ScoreXPS 13 Tiger Lake Ubuntu 20.04300600900120015001186

AI Benchmark Alpha

Device Training Score

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training ScoreXPS 13 Tiger Lake Ubuntu 20.04140280420560700630

AI Benchmark Alpha

Device Inference Score

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference ScoreXPS 13 Tiger Lake Ubuntu 20.04120240360480600556

Numenta Anomaly Benchmark

Detector: Bayesian Changepoint

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian ChangepointXPS 13 Tiger Lake Ubuntu 20.0420406080100SE +/- 1.06, N = 481.06

Numenta Anomaly Benchmark

Detector: Earthgecko Skyline

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko SkylineXPS 13 Tiger Lake Ubuntu 20.0470140210280350SE +/- 0.78, N = 3333.64

Numenta Anomaly Benchmark

Detector: Windowed Gaussian

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed GaussianXPS 13 Tiger Lake Ubuntu 20.04714212835SE +/- 0.41, N = 327.70

Numenta Anomaly Benchmark

Detector: Relative Entropy

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative EntropyXPS 13 Tiger Lake Ubuntu 20.041122334455SE +/- 0.59, N = 648.61

Numenta Anomaly Benchmark

Detector: EXPoSE

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: EXPoSEXPS 13 Tiger Lake Ubuntu 20.042004006008001000SE +/- 2.32, N = 31139.24

RNNoise

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28XPS 13 Tiger Lake Ubuntu 20.04714212835SE +/- 0.01, N = 331.951. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.043691215SE +/- 0.12, N = 1211.81MIN: 10.581. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.041224364860SE +/- 0.07, N = 352.68MIN: 52.491. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.041326395265SE +/- 0.64, N = 657.05MIN: 54.121. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.041224364860SE +/- 0.02, N = 352.43MIN: 52.311. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04246810SE +/- 0.06267, N = 36.39979MIN: 5.731. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04612182430SE +/- 0.10, N = 325.83MIN: 25.211. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

NCNN

Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3ThinkPad X1 Fedora Comet Lake1020304050SE +/- 0.96, N = 1245.37MIN: 36.97 / MAX: 552.341. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

OpenCV

Test: DNN - Deep Neural Network

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.4Test: DNN - Deep Neural NetworkXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake2K4K6K8K10KSE +/- 87.51, N = 3SE +/- 973.85, N = 1253517968-O3-O21. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -ldl -lm -lpthread -lrt

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: regnety_400mXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake510152025SE +/- 0.90, N = 3SE +/- 2.18, N = 321.0120.14-O3 - MIN: 18.85 / MAX: 41.97-O2 - MIN: 15.81 / MAX: 33.221. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: squeezenet_ssdXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake1020304050SE +/- 0.23, N = 3SE +/- 2.49, N = 339.5344.71-O3 - MIN: 39 / MAX: 49.44-O2 - MIN: 38.9 / MAX: 62.291. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet50XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake1530456075SE +/- 0.13, N = 3SE +/- 5.84, N = 351.1365.59-O3 - MIN: 50.6 / MAX: 85.33-O2 - MIN: 48.53 / MAX: 137.661. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: alexnetXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake612182430SE +/- 0.20, N = 3SE +/- 0.92, N = 319.2325.75-O3 - MIN: 18.73 / MAX: 22.46-O2 - MIN: 23.88 / MAX: 46.021. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet18XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake714212835SE +/- 0.17, N = 3SE +/- 1.78, N = 322.2528.33-O3 - MIN: 21.22 / MAX: 66.35-O2 - MIN: 24.76 / MAX: 38.341. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: googlenetXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake714212835SE +/- 0.60, N = 3SE +/- 2.51, N = 324.5828.85-O3 - MIN: 20.79 / MAX: 125.42-O2 - MIN: 22.37 / MAX: 44.421. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: blazefaceXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake0.7291.4582.1872.9163.645SE +/- 0.06, N = 3SE +/- 0.52, N = 32.803.24-O3 - MIN: 2.58 / MAX: 5.23-O2 - MIN: 2.22 / MAX: 5.151. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: efficientnet-b0XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake48121620SE +/- 0.66, N = 3SE +/- 1.57, N = 311.8313.74-O3 - MIN: 10.35 / MAX: 14.92-O2 - MIN: 10.93 / MAX: 18.121. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mnasnetXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake246810SE +/- 0.54, N = 3SE +/- 1.15, N = 38.138.77-O3 - MIN: 6.99 / MAX: 27.68-O2 - MIN: 6.73 / MAX: 11.941. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: shufflenet-v2XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake3691215SE +/- 0.67, N = 3SE +/- 2.09, N = 310.3012.80-O3 - MIN: 8.76 / MAX: 26.22-O2 - MIN: 8.9 / MAX: 18.091. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake246810SE +/- 0.01, N = 3SE +/- 0.97, N = 36.708.28-O3 - MIN: 6.52 / MAX: 9.63-O2 - MIN: 6.56 / MAX: 11.291. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake3691215SE +/- 0.03, N = 3SE +/- 1.35, N = 37.719.64-O3 - MIN: 7.52 / MAX: 10.75-O2 - MIN: 7.97 / MAX: 19.41. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400mXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake510152025SE +/- 0.17, N = 3SE +/- 0.62, N = 1221.1122.34-O3 - MIN: 18.89 / MAX: 41.4-O2 - MIN: 18.96 / MAX: 70.81. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssdXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake1020304050SE +/- 0.23, N = 3SE +/- 1.00, N = 1239.6145.61-O3 - MIN: 39.09 / MAX: 57.3-O2 - MIN: 37.69 / MAX: 158.081. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tinyXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake1326395265SE +/- 0.55, N = 3SE +/- 1.17, N = 1244.6557.10-O3 - MIN: 43.73 / MAX: 74-O2 - MIN: 48.72 / MAX: 192.161. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet50XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake1530456075SE +/- 0.12, N = 3SE +/- 2.13, N = 1251.0167.20-O3 - MIN: 50.55 / MAX: 116.37-O2 - MIN: 48.46 / MAX: 167.351. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet18XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake714212835SE +/- 0.02, N = 3SE +/- 0.80, N = 1222.0730.23-O3 - MIN: 21.29 / MAX: 25.98-O2 - MIN: 24.75 / MAX: 110.111. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenetXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake714212835SE +/- 0.11, N = 3SE +/- 0.89, N = 1225.0131.39-O3 - MIN: 23.82 / MAX: 51.99-O2 - MIN: 26.34 / MAX: 90.631. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazefaceXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake0.8551.712.5653.424.275SE +/- 0.02, N = 3SE +/- 0.11, N = 122.853.80-O3 - MIN: 2.56 / MAX: 3.12-O2 - MIN: 3.13 / MAX: 13.741. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b0XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake48121620SE +/- 0.04, N = 3SE +/- 0.51, N = 1212.5315.22-O3 - MIN: 12.32 / MAX: 31.52-O2 - MIN: 10.96 / MAX: 26.841. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnetXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake3691215SE +/- 0.50, N = 3SE +/- 0.39, N = 128.109.76-O3 - MIN: 7 / MAX: 12.21-O2 - MIN: 6.72 / MAX: 21.361. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v2XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake48121620SE +/- 0.59, N = 3SE +/- 0.67, N = 129.9914.58-O3 - MIN: 8.78 / MAX: 13.35-O2 - MIN: 8.91 / MAX: 27.371. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v3XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake3691215SE +/- 0.02, N = 3SE +/- 0.34, N = 126.719.10-O3 - MIN: 6.52 / MAX: 10.19-O2 - MIN: 6.6 / MAX: 12.731. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v2XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake3691215SE +/- 0.05, N = 3SE +/- 0.58, N = 127.7810.67-O3 - MIN: 7.55 / MAX: 25.73-O2 - MIN: 7.99 / MAX: 44.881. (CXX) g++ options: -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenetXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake1020304050SE +/- 0.56, N = 3SE +/- 0.96, N = 1235.0345.37-O3 - MIN: 34.13 / MAX: 54.59-O2 - MIN: 36.97 / MAX: 552.341. (CXX) g++ options: -rdynamic -lgomp -lpthread

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: inception-v3XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake20406080100SE +/- 0.25, N = 11SE +/- 4.98, N = 368.5297.71MIN: 66.62 / MAX: 223.45MIN: 80.89 / MAX: 306.211. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: mobilenet-v1-1.0XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake3691215SE +/- 0.171, N = 11SE +/- 1.044, N = 38.32013.150MIN: 6.48 / MAX: 30.71MIN: 10.33 / MAX: 65.741. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: MobileNetV2_224XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake3691215SE +/- 0.012, N = 11SE +/- 1.171, N = 36.2389.620MIN: 6.15 / MAX: 28.03MIN: 5.03 / MAX: 90.691. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Mobile Neural Network

Model: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: SqueezeNetV1.0XPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake48121620SE +/- 0.24, N = 11SE +/- 0.10, N = 311.2618.04MIN: 8.69 / MAX: 35.37MIN: 16.55 / MAX: 73.331. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake110K220K330K440K550KSE +/- 4741.44, N = 3SE +/- 10547.34, N = 15419506535897

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake110K220K330K440K550KSE +/- 2876.33, N = 3SE +/- 10164.17, N = 15424309525312

TensorFlow Lite

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake130K260K390K520K650KSE +/- 4542.22, N = 3SE +/- 10287.96, N = 15455525597569

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake160K320K480K640K800KSE +/- 7916.64, N = 5SE +/- 15694.37, N = 15627487769601

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake3691215SE +/- 0.00736, N = 3SE +/- 0.36808, N = 152.1230711.82000-O2 - MIN: 9.181. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake2K4K6K8K10KSE +/- 5.17, N = 3SE +/- 202.13, N = 154516.607969.03MIN: 4500.62-O2 - MIN: 6667.751. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake3K6K9K12K15KSE +/- 1.56, N = 3SE +/- 318.55, N = 128859.0515837.41MIN: 8815.8-O2 - MIN: 13562.81. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake246810SE +/- 0.01624, N = 3SE +/- 0.16653, N = 153.932986.73000MIN: 3.57-O2 - MIN: 5.421. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake2K4K6K8K10KSE +/- 10.91, N = 3SE +/- 200.39, N = 154528.118004.41MIN: 4494.22-O2 - MIN: 6681.81. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake3K6K9K12K15KSE +/- 18.79, N = 3SE +/- 292.22, N = 128875.3315828.66MIN: 8833.23-O2 - MIN: 13821.51. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake2K4K6K8K10KSE +/- 1216.13, N = 12SE +/- 175.62, N = 125736.438215.08MIN: 4504.31-O2 - MIN: 6630.851. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake3K6K9K12K15KSE +/- 5.47, N = 3SE +/- 284.25, N = 128862.6515729.96MIN: 8818.95-O2 - MIN: 13106.71. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake510152025SE +/- 0.12, N = 13SE +/- 0.74, N = 1514.6320.71MIN: 13.05-O2 - MIN: 15.711. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUXPS 13 Tiger Lake Ubuntu 20.04ThinkPad X1 Fedora Comet Lake48121620SE +/- 0.06, N = 3SE +/- 0.62, N = 1510.2815.77MIN: 9.23-O2 - MIN: 9.111. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Phoronix Test Suite v10.8.5