MBP M1 Max Machine Learning, sys76-kudu-ML

Apple M1 Max testing with a Apple MacBook Pro and Apple M1 Max on macOS 12.1 via the Phoronix Test Suite.

sys76-kudu-ML: AMD Ryzen 9 5900HX testing with a System76 Kudu (1.07.09RSA1 BIOS) and AMD Cezanne on Pop 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 2202161-NE-MBPM1MAXM40
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

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
MBP M1 Max Machine Learning
February 16 2022
  6 Hours, 21 Minutes
ML Tests
February 15 2022
  7 Hours, 15 Minutes
Invert Behavior (Only Show Selected Data)
  6 Hours, 48 Minutes
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):


MBP M1 Max Machine Learning, sys76-kudu-MLProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkMonitorOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionOpenCLML TestsMBP M1 Max Machine LearningAMD Ryzen 9 5900HX @ 3.30GHz (8 Cores / 16 Threads)System76 Kudu (1.07.09RSA1 BIOS)AMD Renoir/Cezanne16GBSamsung SSD 970 EVO Plus 500GBAMD Cezanne (2100/400MHz)AMD Renoir Radeon HD AudioRealtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX200Pop 21.105.15.15-76051515-generic (x86_64)GNOME Shell 40.5X Server 1.20.134.6 Mesa 21.2.2 (LLVM 12.0.1)1.2.182GCC 11.2.0ext41920x1080Apple M1 Max (10 Cores)Apple MacBook Pro64GB1859GBApple M1 MaxColor LCDmacOS 12.121.2.0 (arm64)OpenCL 1.2 (Nov 13 2021 00:45:09)GCC 13.0.0 + Clang 13.0.0APFS3456x2234OpenBenchmarking.orgKernel Details- ML Tests: Transparent Huge Pages: madviseCompiler Details- ML Tests: --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 Details- ML Tests: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa50000cGraphics Details- ML Tests: GLAMOR - BAR1 / Visible vRAM Size: 512 MBPython Details- ML Tests: Python 3.9.7- MBP M1 Max Machine Learning: Python 2.7.18 + Python 3.8.9Security Details- ML Tests: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected Environment Details- MBP M1 Max Machine Learning: XPC_FLAGS=0x0

ML Tests vs. MBP M1 Max Machine Learning ComparisonPhoronix Test SuiteBaseline+165.4%+165.4%+330.8%+330.8%+496.2%+496.2%15.6%7.8%mobilenetV3661.4%Vulkan GPU - alexnet372.9%MobileNetV2_224347.3%mobilenet-v1-1.0236.3%Vulkan GPU - resnet50228.4%Vulkan GPU - googlenet185.2%Vulkan GPU - resnet18175.9%squeezenetv1.1159.5%SqueezeNetV1.0119.2%CPU - alexnet105.7%Vulkan GPU - mobilenet97.7%resnet-v2-5089.1%inception-v384.5%CPU - googlenet81.7%CPU - resnet5071.5%CPU - efficientnet-b066.5%CPU - mnasnet66.2%Vulkan GPU - yolov4-tiny61.2%Vulkan GPU - vgg1661.2%Vulkan GPU - mnasnet38%CPU - blazeface37.5%Vulkan GPU-v2-v2 - mobilenet-v236.6%Vulkan GPU - regnety_400m36.2%Vulkan GPU - squeezenet_ssd33.8%CPU-v2-v2 - mobilenet-v233.6%CPU-v3-v3 - mobilenet-v327.9%CPU - mobilenet27.4%CPU - shufflenet-v226.2%Vulkan GPU - blazeface21.5%CPU - yolov4-tiny21.1%Vulkan GPU - efficientnet-b0Vulkan GPU - shufflenet-v214.6%CPU - squeezenet_ssd10.6%Vulkan GPU-v3-v3 - mobilenet-v3CPU - resnet186.6%CPU - regnety_400m4.1%Mobile Neural NetworkNCNNMobile Neural NetworkMobile Neural NetworkNCNNNCNNNCNNMobile Neural NetworkMobile Neural NetworkNCNNNCNNMobile Neural NetworkMobile Neural NetworkNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNML TestsMBP M1 Max Machine Learning

MBP M1 Max Machine Learning, sys76-kudu-MLncnn: Vulkan GPU - alexnetmnn: MobileNetV2_224ncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - resnet18ncnn: CPU - alexnetncnn: Vulkan GPU - mobilenetncnn: CPU - googlenetncnn: CPU - resnet50ncnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - mnasnetncnn: CPU - blazefacencnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - mobilenetncnn: CPU - shufflenet-v2ncnn: Vulkan GPU - blazefacencnn: CPU - yolov4-tinyncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - shufflenet-v2ncnn: CPU - squeezenet_ssdncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: CPU - resnet18ncnn: CPU - regnety_400mncnn: CPU - vgg16mlpack: scikit_linearridgeregressionmlpack: scikit_svmmlpack: scikit_qdamlpack: scikit_icaecp-candle: P3B2ecp-candle: P3B1ecp-candle: P1B2plaidml: No - Inference - ResNet 50 - CPUplaidml: No - Inference - VGG16 - CPUtnn: CPU - SqueezeNet v1.1tnn: CPU - SqueezeNet v2tnn: CPU - MobileNet v2tnn: CPU - DenseNetcaffe: GoogleNet - CPU - 1000caffe: GoogleNet - CPU - 200caffe: GoogleNet - CPU - 100caffe: AlexNet - CPU - 1000caffe: AlexNet - CPU - 200caffe: AlexNet - CPU - 100tensorflow-lite: Inception ResNet V2tensorflow-lite: Mobilenet Quanttensorflow-lite: Mobilenet Floattensorflow-lite: NASNet Mobiletensorflow-lite: Inception V4tensorflow-lite: SqueezeNetrnnoise: rbenchmark: lczero: BLASdeepspeech: CPUnumpy: onednn: 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_3d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - f32 - CPUopencv: DNN - Deep Neural Networkmnn: inception-v3mnn: mobilenet-v1-1.0mnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: squeezenetv1.1mnn: mobilenetV3onednn: IP Shapes 1D - bf16bf16bf16 - CPUML TestsMBP M1 Max Machine Learning6.322.38713.128.736.0914.5510.2713.7425.175.223.2518.8243.993.891.203.885.2815.363.993.4115.952.751.3524.9710.073.0218.564.6915.786.9071.972.1017.6065.6948.40730.7361463.72237.516.8812.47222.32655.434249.4772736.1738687581736718656732588465986334962479080141174127818152186274962318976416.1370.129356374.44043422.452.986592237.653577.004.593432228.173587.172219.133579.003.247842.1177123.76746.745598.3478922.79262.692101.6298512.09264.258551378731.5762.4404.54622.4412.8031.20229.8910.67743.0824.916.8029.9320.3024.9643.168.695.4030.3370.895.371.655.307.1920.555.334.3620.323.471.6430.248.713.4620.534.3516.827.1871.0158.2538.2059.96742.4287.2749.152OpenBenchmarking.org

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: alexnetMBP M1 Max Machine LearningML Tests714212835SE +/- 0.00, N = 3SE +/- 0.03, N = 329.896.32-arch -isysroot - MIN: 29.79 / MAX: 31.07-rdynamic -lgomp -lpthread - MIN: 5.95 / MAX: 7.491. (CXX) g++ options: -O3

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: MobileNetV2_224MBP M1 Max Machine LearningML Tests3691215SE +/- 0.187, N = 9SE +/- 0.018, N = 310.6772.387-arch -isysroot - MIN: 5.12 / MAX: 61.59-fomit-frame-pointer -rdynamic -pthread -ldl - MIN: 2.24 / MAX: 17.041. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet50MBP M1 Max Machine LearningML Tests1020304050SE +/- 0.01, N = 3SE +/- 0.06, N = 343.0813.12-arch -isysroot - MIN: 42.9 / MAX: 45.66-rdynamic -lgomp -lpthread - MIN: 12.27 / MAX: 15.041. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: googlenetMBP M1 Max Machine LearningML Tests612182430SE +/- 0.00, N = 3SE +/- 0.25, N = 324.908.73-arch -isysroot - MIN: 24.82 / MAX: 25.79-rdynamic -lgomp -lpthread - MIN: 7.89 / MAX: 10.641. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet18MBP M1 Max Machine LearningML Tests48121620SE +/- 0.01, N = 3SE +/- 0.08, N = 316.806.09-arch -isysroot - MIN: 16.69 / MAX: 18.25-rdynamic -lgomp -lpthread - MIN: 5.63 / MAX: 7.521. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetMBP M1 Max Machine LearningML Tests714212835SE +/- 0.05, N = 3SE +/- 0.06, N = 329.9314.55-arch -isysroot - MIN: 29.79 / MAX: 31.03-rdynamic -lgomp -lpthread - MIN: 13.9 / MAX: 33.491. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mobilenetMBP M1 Max Machine LearningML Tests510152025SE +/- 0.02, N = 3SE +/- 0.09, N = 320.3010.27-arch -isysroot - MIN: 20.23 / MAX: 21.48-rdynamic -lgomp -lpthread - MIN: 9.59 / MAX: 17.841. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetMBP M1 Max Machine LearningML Tests612182430SE +/- 0.07, N = 3SE +/- 0.28, N = 324.9613.74-arch -isysroot - MIN: 24.82 / MAX: 25.91-rdynamic -lgomp -lpthread - MIN: 12.47 / MAX: 28.561. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50MBP M1 Max Machine LearningML Tests1020304050SE +/- 0.07, N = 3SE +/- 0.06, N = 343.1625.17-arch -isysroot - MIN: 42.92 / MAX: 44.81-rdynamic -lgomp -lpthread - MIN: 23.91 / MAX: 41.271. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0MBP M1 Max Machine LearningML Tests246810SE +/- 0.04, N = 3SE +/- 0.01, N = 38.695.22-arch -isysroot - MIN: 8.59 / MAX: 9.15-rdynamic -lgomp -lpthread - MIN: 4.86 / MAX: 20.631. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetMBP M1 Max Machine LearningML Tests1.2152.433.6454.866.075SE +/- 0.03, N = 3SE +/- 0.03, N = 35.403.25-arch -isysroot - MIN: 5.35 / MAX: 5.68-rdynamic -lgomp -lpthread - MIN: 2.82 / MAX: 16.821. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: yolov4-tinyMBP M1 Max Machine LearningML Tests714212835SE +/- 0.07, N = 3SE +/- 0.42, N = 330.3318.82-arch -isysroot - MIN: 29.85 / MAX: 32.58-rdynamic -lgomp -lpthread - MIN: 17.12 / MAX: 24.451. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: vgg16MBP M1 Max Machine LearningML Tests1632486480SE +/- 0.02, N = 3SE +/- 0.07, N = 370.8943.99-arch -isysroot - MIN: 70.59 / MAX: 73.62-rdynamic -lgomp -lpthread - MIN: 43.17 / MAX: 45.591. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mnasnetMBP M1 Max Machine LearningML Tests1.20832.41663.62494.83326.0415SE +/- 0.00, N = 3SE +/- 0.11, N = 25.373.89-arch -isysroot - MIN: 5.35 / MAX: 5.62-rdynamic -lgomp -lpthread - MIN: 3.56 / MAX: 5.011. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazefaceMBP M1 Max Machine LearningML Tests0.37130.74261.11391.48521.8565SE +/- 0.01, N = 3SE +/- 0.01, N = 31.651.20-arch -isysroot - MIN: 1.64 / MAX: 1.72-rdynamic -lgomp -lpthread - MIN: 1.16 / MAX: 1.781. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2MBP M1 Max Machine LearningML Tests1.19252.3853.57754.775.9625SE +/- 0.01, N = 3SE +/- 0.06, N = 35.303.88-arch -isysroot - MIN: 5.28 / MAX: 5.98-rdynamic -lgomp -lpthread - MIN: 3.49 / MAX: 5.251. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: regnety_400mMBP M1 Max Machine LearningML Tests246810SE +/- 0.00, N = 3SE +/- 0.06, N = 37.195.28-arch -isysroot - MIN: 7.15 / MAX: 7.72-rdynamic -lgomp -lpthread - MIN: 4.68 / MAX: 6.441. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: squeezenet_ssdMBP M1 Max Machine LearningML Tests510152025SE +/- 0.05, N = 3SE +/- 0.36, N = 320.5515.36-arch -isysroot - MIN: 20.39 / MAX: 22.13-rdynamic -lgomp -lpthread - MIN: 14.17 / MAX: 22.531. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2MBP M1 Max Machine LearningML Tests1.19932.39863.59794.79725.9965SE +/- 0.03, N = 3SE +/- 0.02, N = 35.333.99-arch -isysroot - MIN: 5.27 / MAX: 5.61-rdynamic -lgomp -lpthread - MIN: 3.71 / MAX: 19.111. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3MBP M1 Max Machine LearningML Tests0.9811.9622.9433.9244.905SE +/- 0.03, N = 3SE +/- 0.02, N = 34.363.41-arch -isysroot - MIN: 4.32 / MAX: 4.61-rdynamic -lgomp -lpthread - MIN: 3.11 / MAX: 17.471. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenetMBP M1 Max Machine LearningML Tests510152025SE +/- 0.02, N = 3SE +/- 0.09, N = 320.3215.95-arch -isysroot - MIN: 20.23 / MAX: 21.33-rdynamic -lgomp -lpthread - MIN: 14.92 / MAX: 35.661. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2MBP M1 Max Machine LearningML Tests0.78081.56162.34243.12323.904SE +/- 0.02, N = 3SE +/- 0.04, N = 33.472.75-arch -isysroot - MIN: 3.43 / MAX: 3.84-rdynamic -lgomp -lpthread - MIN: 2.48 / MAX: 16.131. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: blazefaceMBP M1 Max Machine LearningML Tests0.3690.7381.1071.4761.845SE +/- 0.00, N = 3SE +/- 0.01, N = 31.641.35-arch -isysroot - MIN: 1.63 / MAX: 1.79-rdynamic -lgomp -lpthread - MIN: 1.17 / MAX: 2.431. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinyMBP M1 Max Machine LearningML Tests714212835SE +/- 0.03, N = 3SE +/- 0.12, N = 330.2424.97-arch -isysroot - MIN: 29.85 / MAX: 31.87-rdynamic -lgomp -lpthread - MIN: 23.9 / MAX: 38.981. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: efficientnet-b0MBP M1 Max Machine LearningML Tests3691215SE +/- 0.02, N = 3SE +/- 0.06, N = 38.7110.07-arch -isysroot - MIN: 8.6 / MAX: 9.43-rdynamic -lgomp -lpthread - MIN: 9.06 / MAX: 11.431. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: shufflenet-v2MBP M1 Max Machine LearningML Tests0.77851.5572.33553.1143.8925SE +/- 0.01, N = 3SE +/- 0.07, N = 33.463.02-arch -isysroot - MIN: 3.44 / MAX: 3.82-rdynamic -lgomp -lpthread - MIN: 2.54 / MAX: 4.381. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdMBP M1 Max Machine LearningML Tests510152025SE +/- 0.05, N = 3SE +/- 0.15, N = 320.5318.56-arch -isysroot - MIN: 20.37 / MAX: 21.53-rdynamic -lgomp -lpthread - MIN: 17.64 / MAX: 34.931. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3MBP M1 Max Machine LearningML Tests1.05532.11063.16594.22125.2765SE +/- 0.00, N = 3SE +/- 0.12, N = 34.354.69-arch -isysroot - MIN: 4.32 / MAX: 4.63-rdynamic -lgomp -lpthread - MIN: 4.29 / MAX: 5.941. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18MBP M1 Max Machine LearningML Tests48121620SE +/- 0.04, N = 3SE +/- 0.43, N = 316.8215.78-arch -isysroot - MIN: 16.69 / MAX: 17.58-rdynamic -lgomp -lpthread - MIN: 14.59 / MAX: 30.811. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: regnety_400mMBP M1 Max Machine LearningML Tests246810SE +/- 0.00, N = 3SE +/- 0.04, N = 37.186.90-arch -isysroot - MIN: 7.14 / MAX: 8.13-rdynamic -lgomp -lpthread - MIN: 6.35 / MAX: 21.531. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16MBP M1 Max Machine LearningML Tests1632486480SE +/- 0.15, N = 3SE +/- 0.16, N = 371.0171.97-arch -isysroot - MIN: 70.58 / MAX: 74.44-rdynamic -lgomp -lpthread - MIN: 69.95 / MAX: 94.761. (CXX) g++ options: -O3

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionML Tests0.47250.9451.41751.892.3625SE +/- 0.01, N = 32.10

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmML Tests48121620SE +/- 0.02, N = 317.60

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaML Tests1530456075SE +/- 0.03, N = 365.69

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaML Tests1122334455SE +/- 0.12, N = 348.40

ECP-CANDLE

The CANDLE benchmark codes implement deep learning architectures relevant to problems in cancer. These architectures address problems at different biological scales, specifically problems at the molecular, cellular and population scales. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterECP-CANDLE 0.4Benchmark: P3B2ML Tests160320480640800730.74

OpenBenchmarking.orgSeconds, Fewer Is BetterECP-CANDLE 0.4Benchmark: P3B1ML Tests300600900120015001463.72

OpenBenchmarking.orgSeconds, Fewer Is BetterECP-CANDLE 0.4Benchmark: P1B2ML Tests91827364537.51

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUML Tests246810SE +/- 0.02, N = 36.88

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUML Tests3691215SE +/- 0.07, N = 312.47

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1ML Tests50100150200250SE +/- 0.13, N = 3222.33MIN: 221.49 / MAX: 224.651. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2ML Tests1224364860SE +/- 0.62, N = 355.43MIN: 54.24 / MAX: 57.061. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2ML Tests50100150200250SE +/- 0.40, N = 3249.48MIN: 247.22 / MAX: 255.161. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetML Tests6001200180024003000SE +/- 0.83, N = 32736.17MIN: 2687.97 / MAX: 2827.521. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 1000ML Tests200K400K600K800K1000KSE +/- 470.76, N = 38687581. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 200ML Tests40K80K120K160K200KSE +/- 318.11, N = 31736711. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100ML Tests20K40K60K80K100KSE +/- 103.35, N = 3865671. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 1000ML Tests70K140K210K280K350KSE +/- 469.87, N = 33258841. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 200ML Tests14K28K42K56K70KSE +/- 167.60, N = 3659861. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100ML Tests7K14K21K28K35KSE +/- 37.32, N = 3334961. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2ML Tests500K1000K1500K2000K2500KSE +/- 1189.89, N = 32479080

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantML Tests30K60K90K120K150KSE +/- 38.25, N = 3141174

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatML Tests30K60K90K120K150KSE +/- 174.79, N = 3127818

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileML Tests30K60K90K120K150KSE +/- 344.97, N = 3152186

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4ML Tests600K1200K1800K2400K3000KSE +/- 1719.91, N = 32749623

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetML Tests40K80K120K160K200KSE +/- 108.90, N = 3189764

RNNoise

RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28ML Tests48121620SE +/- 0.02, N = 316.141. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

R Benchmark

This test is a quick-running survey of general R performance Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterR BenchmarkML Tests0.02910.05820.08730.11640.1455SE +/- 0.0003, N = 30.12931. R scripting front-end version 4.0.4 (2021-02-15)

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLASML Tests120240360480600SE +/- 5.14, N = 75631. (CXX) g++ options: -flto -pthread

DeepSpeech

Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUML Tests20406080100SE +/- 0.17, N = 374.44

Acceleration: CPU

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkML Tests90180270360450SE +/- 0.84, N = 3422.45

MBP M1 Max Machine Learning: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

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 initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUML Tests0.6721.3442.0162.6883.36SE +/- 0.01068, N = 32.98659MIN: 2.721. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUML Tests5001000150020002500SE +/- 14.65, N = 142237.65MIN: 2174.761. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUML Tests8001600240032004000SE +/- 4.93, N = 33577.00MIN: 3514.721. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUML Tests1.03352.0673.10054.1345.1675SE +/- 0.00541, N = 34.59343MIN: 4.391. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUML Tests5001000150020002500SE +/- 6.34, N = 32228.17MIN: 2189.621. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUML Tests8001600240032004000SE +/- 4.16, N = 33587.17MIN: 3527.151. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUML Tests5001000150020002500SE +/- 1.17, N = 32219.13MIN: 2182.151. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUML Tests8001600240032004000SE +/- 7.39, N = 33579.00MIN: 3519.931. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUML Tests0.73081.46162.19242.92323.654SE +/- 0.02694, N = 33.24784MIN: 2.761. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUML Tests0.47650.9531.42951.9062.3825SE +/- 0.00458, N = 32.11771MIN: 1.911. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUML Tests612182430SE +/- 0.02, N = 323.77MIN: 22.91. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUML Tests246810SE +/- 0.01002, N = 36.74559MIN: 6.521. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUML Tests246810SE +/- 0.02843, N = 38.34789MIN: 4.751. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUML Tests510152025SE +/- 0.03, N = 322.79MIN: 21.941. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUML Tests0.60571.21141.81712.42283.0285SE +/- 0.00222, N = 32.69210MIN: 2.571. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUML Tests0.36670.73341.10011.46681.8335SE +/- 0.00920, N = 31.62985MIN: 1.491. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUML Tests3691215SE +/- 0.02, N = 312.09MIN: 11.921. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUML Tests0.95821.91642.87463.83284.791SE +/- 0.03780, N = 74.25855MIN: 3.881. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.5.4Test: DNN - Deep Neural NetworkML Tests3K6K9K12K15KSE +/- 269.19, N = 15137871. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

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.

Model: super-resolution-10 - Device: CPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnxruntime/onnxruntime/test/onnx/onnx_model_info.cc:45 void OnnxModelInfo::InitOnnxModelInfo(const PATH_CHAR_TYPE*) open file "super_resolution/super_resolution.onnx" failed: No such file or directory

Model: shufflenet-v2-10 - Device: CPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnxruntime/onnxruntime/test/onnx/onnx_model_info.cc:45 void OnnxModelInfo::InitOnnxModelInfo(const PATH_CHAR_TYPE*) open file "model/test_shufflenetv2/model.onnx" failed: No such file or directory

Model: fcn-resnet101-11 - Device: CPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnxruntime/onnxruntime/test/onnx/onnx_model_info.cc:45 void OnnxModelInfo::InitOnnxModelInfo(const PATH_CHAR_TYPE*) open file "fcn-resnet101-11/model.onnx" failed: No such file or directory

Model: yolov4 - Device: CPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnxruntime/onnxruntime/test/onnx/onnx_model_info.cc:45 void OnnxModelInfo::InitOnnxModelInfo(const PATH_CHAR_TYPE*) open file "yolov4/yolov4.onnx" failed: No such file or directory

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

Model: Age Gender Recognition Retail 0013 FP32 - Device: Intel GPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./openvino: line 2: ./openvino-github-2021/bin/intel64/Release/benchmark_app: No such file or directory

Model: Age Gender Recognition Retail 0013 FP16 - Device: Intel GPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./openvino: line 2: ./openvino-github-2021/bin/intel64/Release/benchmark_app: No such file or directory

Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./openvino: line 2: ./openvino-github-2021/bin/intel64/Release/benchmark_app: No such file or directory

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./openvino: line 2: ./openvino-github-2021/bin/intel64/Release/benchmark_app: No such file or directory

Model: Person Detection 0106 FP32 - Device: Intel GPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./openvino: line 2: ./openvino-github-2021/bin/intel64/Release/benchmark_app: No such file or directory

Model: Person Detection 0106 FP16 - Device: Intel GPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./openvino: line 2: ./openvino-github-2021/bin/intel64/Release/benchmark_app: No such file or directory

Model: Face Detection 0106 FP32 - Device: Intel GPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./openvino: line 2: ./openvino-github-2021/bin/intel64/Release/benchmark_app: No such file or directory

Model: Face Detection 0106 FP16 - Device: Intel GPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./openvino: line 2: ./openvino-github-2021/bin/intel64/Release/benchmark_app: No such file or directory

Model: Person Detection 0106 FP32 - Device: CPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./openvino: line 2: ./openvino-github-2021/bin/intel64/Release/benchmark_app: No such file or directory

Model: Person Detection 0106 FP16 - Device: CPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./openvino: line 2: ./openvino-github-2021/bin/intel64/Release/benchmark_app: No such file or directory

Model: Face Detection 0106 FP32 - Device: CPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./openvino: line 2: ./openvino-github-2021/bin/intel64/Release/benchmark_app: No such file or directory

Model: Face Detection 0106 FP16 - Device: CPU

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./openvino: line 2: ./openvino-github-2021/bin/intel64/Release/benchmark_app: No such file or directory

Tensorflow

This is a benchmark of the Tensorflow deep learning framework using the CIFAR10 data set. Learn more via the OpenBenchmarking.org test page.

Build: Cifar10

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: AttributeError: module 'tensorflow' has no attribute 'app'

AI Benchmark Alpha

AI Benchmark Alpha is a Python library for evaluating artificial intelligence (AI) performance on diverse hardware platforms and relies upon the TensorFlow machine learning library. Learn more via the OpenBenchmarking.org test page.

ML Tests: The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'tensorflow'

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. E: SyntaxError: invalid syntax

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

Detector: Bayesian Changepoint

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'pandas'

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'pandas'

Detector: Earthgecko Skyline

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'pandas'

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'pandas'

Detector: Windowed Gaussian

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'pandas'

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'pandas'

Detector: Relative Entropy

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'pandas'

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'pandas'

Detector: EXPoSE

ML Tests: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'pandas'

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'pandas'

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: inception-v3MBP M1 Max Machine LearningML Tests1326395265SE +/- 6.12, N = 9SE +/- 0.42, N = 358.2531.58-arch -isysroot - MIN: 30.46 / MAX: 200.21-fomit-frame-pointer -rdynamic -pthread -ldl - MIN: 29.6 / MAX: 48.321. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenet-v1-1.0MBP M1 Max Machine LearningML Tests246810SE +/- 0.384, N = 9SE +/- 0.019, N = 38.2052.440-arch -isysroot - MIN: 4.27 / MAX: 48.5-fomit-frame-pointer -rdynamic -pthread -ldl - MIN: 2.17 / MAX: 181. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: SqueezeNetV1.0MBP M1 Max Machine LearningML Tests3691215SE +/- 0.664, N = 9SE +/- 0.040, N = 39.9674.546-arch -isysroot - MIN: 4.34 / MAX: 49.52-fomit-frame-pointer -rdynamic -pthread -ldl - MIN: 4.32 / MAX: 20.481. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: resnet-v2-50MBP M1 Max Machine LearningML Tests1020304050SE +/- 4.17, N = 9SE +/- 0.09, N = 342.4322.44-arch -isysroot - MIN: 24 / MAX: 197.77-fomit-frame-pointer -rdynamic -pthread -ldl - MIN: 21.5 / MAX: 43.071. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: squeezenetv1.1MBP M1 Max Machine LearningML Tests246810SE +/- 0.345, N = 9SE +/- 0.009, N = 37.2742.803-arch -isysroot - MIN: 2.75 / MAX: 117.92-fomit-frame-pointer -rdynamic -pthread -ldl - MIN: 2.6 / MAX: 17.211. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV3MBP M1 Max Machine LearningML Tests3691215SE +/- 0.487, N = 9SE +/- 0.005, N = 39.1521.202-arch -isysroot - MIN: 3.37 / MAX: 58.791. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions

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 initiative. Learn more via the OpenBenchmarking.org test page.

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

ML Tests: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

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

ML Tests: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

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

ML Tests: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

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

ML Tests: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

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

ML Tests: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

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

ML Tests: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

MBP M1 Max Machine Learning: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onednn: line 6: ./benchdnn: No such file or directory

86 Results Shown

NCNN
Mobile Neural Network
NCNN:
  Vulkan GPU - resnet50
  Vulkan GPU - googlenet
  Vulkan GPU - resnet18
  CPU - alexnet
  Vulkan GPU - mobilenet
  CPU - googlenet
  CPU - resnet50
  CPU - efficientnet-b0
  CPU - mnasnet
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - vgg16
  Vulkan GPU - mnasnet
  CPU - blazeface
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU - regnety_400m
  Vulkan GPU - squeezenet_ssd
  CPU-v2-v2 - mobilenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU - mobilenet
  CPU - shufflenet-v2
  Vulkan GPU - blazeface
  CPU - yolov4-tiny
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - shufflenet-v2
  CPU - squeezenet_ssd
  Vulkan GPU-v3-v3 - mobilenet-v3
  CPU - resnet18
  CPU - regnety_400m
  CPU - vgg16
Mlpack Benchmark:
  scikit_linearridgeregression
  scikit_svm
  scikit_qda
  scikit_ica
ECP-CANDLE:
  P3B2
  P3B1
  P1B2
PlaidML:
  No - Inference - ResNet 50 - CPU
  No - Inference - VGG16 - CPU
TNN:
  CPU - SqueezeNet v1.1
  CPU - SqueezeNet v2
  CPU - MobileNet v2
  CPU - DenseNet
Caffe:
  GoogleNet - CPU - 1000
  GoogleNet - CPU - 200
  GoogleNet - CPU - 100
  AlexNet - CPU - 1000
  AlexNet - CPU - 200
  AlexNet - CPU - 100
TensorFlow Lite:
  Inception ResNet V2
  Mobilenet Quant
  Mobilenet Float
  NASNet Mobile
  Inception V4
  SqueezeNet
RNNoise
R Benchmark
LeelaChessZero
DeepSpeech
Numpy Benchmark
oneDNN:
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
  Deconvolution Batch shapes_1d - f32 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
  IP Shapes 3D - f32 - CPU
  IP Shapes 1D - f32 - CPU
OpenCV
Mobile Neural Network:
  inception-v3
  mobilenet-v1-1.0
  SqueezeNetV1.0
  resnet-v2-50
  squeezenetv1.1
  mobilenetV3