machine-learning-macbook-air-catalina

Intel Core i5-4250U testing with a Apple MacBook Air and Intel HD 5000 2GB on macOS 10.15.7 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 2210307-PROG-MACHINE12
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
machine-learning-macbook-air-catalina
October 22 2022
  1 Day, 22 Hours, 43 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):


machine-learning-macbook-air-catalinaOpenBenchmarking.orgPhoronix Test SuiteIntel Core i5-4250U @ 1.30GHz (2 Cores / 4 Threads)Apple MacBook AirApple SSD2 x GB DDR3-1600MHz121 33GB APPLE SSD TS0128FIntel HD 5000 2GBColor LCDmacOS 10.15.719.6.0 (x86_64)Clang 12.0.0 + GCC 12.0.0APFS1366x768ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorOSKernelCompilerFile-SystemScreen ResolutionMachine-learning-macbook-air-catalina BenchmarksSystem Logs- XPC_FLAGS=0x0- CPU Microcode: 38- Python 2.7.16 + Python 3.10.8

machine-learning-macbook-air-catalinaai-benchmark: Device AI Scoreai-benchmark: Device Training Scoreai-benchmark: Device Inference Scorenumenta-nab: Earthgecko Skylinenumenta-nab: Windowed Gaussianncnn: Vulkan GPU - FastestDetncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: 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: Vulkan GPU - mobilenetncnn: CPU - FastestDetncnn: CPU - vision_transformerncnn: CPU - regnety_400mncnn: CPU - squeezenet_ssdncnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - alexnetncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: 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: SqueezeNetV1.0mnn: resnet-v2-50mnn: squeezenetv1.1mnn: mobilenetV3mnn: nasnetnumpy: 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 - CPUonednn: IP Shapes 1D - bf16bf16bf16 - CPUmachine-learning-macbook-air-catalina4182052131095.64597.13414.743282.3035.4278.15133.69205.7751.8467.68351.1685.083.8947.8428.8417.5124.2530.17110.1914.713280.8435.4378.52132.01204.7751.5667.60350.4185.543.8847.4728.8817.6824.2430.28110.94109.12012.0509.11516.65381.3189.0703.75526.384169.0820.331824266.649197.623.431723837.148107.523725.448294.968.139148.544872.790685.197594.509356.148120.245531.894149.249845.4618OpenBenchmarking.org

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.

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI Scoremachine-learning-macbook-air-catalina90180270360450418

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training Scoremachine-learning-macbook-air-catalina4080120160200205

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference Scoremachine-learning-macbook-air-catalina50100150200250213

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko Skylinemachine-learning-macbook-air-catalina2004006008001000SE +/- 2.80, N = 31095.65

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed Gaussianmachine-learning-macbook-air-catalina20406080100SE +/- 0.12, N = 397.13

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 20220729Target: Vulkan GPU - Model: FastestDetmachine-learning-macbook-air-catalina48121620SE +/- 0.08, N = 314.74MIN: 14.32 / MAX: 18.371. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformermachine-learning-macbook-air-catalina7001400210028003500SE +/- 0.62, N = 33282.30MIN: 3256.98 / MAX: 3398.281. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mmachine-learning-macbook-air-catalina816243240SE +/- 0.09, N = 335.42MIN: 34.83 / MAX: 39.611. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdmachine-learning-macbook-air-catalina20406080100SE +/- 0.20, N = 378.15MIN: 76.06 / MAX: 91.611. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinymachine-learning-macbook-air-catalina306090120150SE +/- 0.34, N = 3133.69MIN: 129.53 / MAX: 168.531. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50machine-learning-macbook-air-catalina50100150200250SE +/- 0.76, N = 3205.77MIN: 201.02 / MAX: 231.971. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetmachine-learning-macbook-air-catalina1224364860SE +/- 0.30, N = 351.84MIN: 49.64 / MAX: 63.421. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18machine-learning-macbook-air-catalina1530456075SE +/- 0.30, N = 367.68MIN: 65.55 / MAX: 88.021. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16machine-learning-macbook-air-catalina80160240320400SE +/- 0.97, N = 3351.16MIN: 340.08 / MAX: 410.511. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetmachine-learning-macbook-air-catalina20406080100SE +/- 0.46, N = 385.08MIN: 83.08 / MAX: 100.411. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefacemachine-learning-macbook-air-catalina0.87531.75062.62593.50124.3765SE +/- 0.01, N = 33.89MIN: 3.83 / MAX: 4.321. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0machine-learning-macbook-air-catalina1122334455SE +/- 0.20, N = 347.84MIN: 46.51 / MAX: 56.61. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetmachine-learning-macbook-air-catalina714212835SE +/- 0.33, N = 328.84MIN: 28.14 / MAX: 41.321. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2machine-learning-macbook-air-catalina48121620SE +/- 0.02, N = 317.51MIN: 17.32 / MAX: 19.981. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3machine-learning-macbook-air-catalina612182430SE +/- 0.04, N = 324.25MIN: 23.71 / MAX: 27.381. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2machine-learning-macbook-air-catalina714212835SE +/- 0.04, N = 330.17MIN: 29.54 / MAX: 34.781. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetmachine-learning-macbook-air-catalina20406080100SE +/- 0.07, N = 3110.19MIN: 108.64 / MAX: 131.651. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetmachine-learning-macbook-air-catalina48121620SE +/- 0.07, N = 314.71MIN: 14.31 / MAX: 19.161. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformermachine-learning-macbook-air-catalina7001400210028003500SE +/- 1.55, N = 33280.84MIN: 3254.79 / MAX: 3527.441. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mmachine-learning-macbook-air-catalina816243240SE +/- 0.17, N = 335.43MIN: 34.84 / MAX: 40.491. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdmachine-learning-macbook-air-catalina20406080100SE +/- 0.41, N = 378.52MIN: 76.43 / MAX: 92.521. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinymachine-learning-macbook-air-catalina306090120150SE +/- 0.12, N = 3132.01MIN: 129.3 / MAX: 156.261. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50machine-learning-macbook-air-catalina4080120160200SE +/- 0.21, N = 3204.77MIN: 200.78 / MAX: 233.251. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetmachine-learning-macbook-air-catalina1224364860SE +/- 0.27, N = 351.56MIN: 49.46 / MAX: 64.841. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18machine-learning-macbook-air-catalina1530456075SE +/- 0.31, N = 367.60MIN: 65.5 / MAX: 82.41. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16machine-learning-macbook-air-catalina80160240320400SE +/- 0.41, N = 3350.41MIN: 339.91 / MAX: 405.351. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetmachine-learning-macbook-air-catalina20406080100SE +/- 0.20, N = 385.54MIN: 83.14 / MAX: 110.911. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefacemachine-learning-macbook-air-catalina0.8731.7462.6193.4924.365SE +/- 0.01, N = 33.88MIN: 3.83 / MAX: 5.091. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0machine-learning-macbook-air-catalina1122334455SE +/- 0.08, N = 347.47MIN: 46.54 / MAX: 59.071. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetmachine-learning-macbook-air-catalina714212835SE +/- 0.13, N = 328.88MIN: 28.18 / MAX: 32.671. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2machine-learning-macbook-air-catalina48121620SE +/- 0.06, N = 317.68MIN: 17.34 / MAX: 22.391. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3machine-learning-macbook-air-catalina612182430SE +/- 0.06, N = 324.24MIN: 23.73 / MAX: 27.631. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2machine-learning-macbook-air-catalina714212835SE +/- 0.12, N = 330.28MIN: 29.5 / MAX: 371. (CXX) g++ options: -O3 -isysroot

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetmachine-learning-macbook-air-catalina20406080100SE +/- 0.16, N = 3110.94MIN: 108.53 / MAX: 123.911. (CXX) g++ options: -O3 -isysroot

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. This MNN test profile is building the OpenMP / CPU threaded version for processor benchmarking and not any GPU-accelerated test. MNN does allow making use of AVX-512 extensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: inception-v3machine-learning-macbook-air-catalina20406080100SE +/- 0.25, N = 3109.12MIN: 106.8 / MAX: 163.221. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenet-v1-1.0machine-learning-macbook-air-catalina3691215SE +/- 0.10, N = 312.05MIN: 11.79 / MAX: 24.191. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: MobileNetV2_224machine-learning-macbook-air-catalina3691215SE +/- 0.048, N = 39.115MIN: 8.93 / MAX: 20.861. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: SqueezeNetV1.0machine-learning-macbook-air-catalina48121620SE +/- 0.15, N = 316.65MIN: 15.94 / MAX: 30.041. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: resnet-v2-50machine-learning-macbook-air-catalina20406080100SE +/- 0.74, N = 381.32MIN: 78.54 / MAX: 117.531. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: squeezenetv1.1machine-learning-macbook-air-catalina3691215SE +/- 0.068, N = 39.070MIN: 8.66 / MAX: 17.091. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenetV3machine-learning-macbook-air-catalina0.84491.68982.53473.37964.2245SE +/- 0.003, N = 33.755MIN: 3.7 / MAX: 8.211. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: nasnetmachine-learning-macbook-air-catalina612182430SE +/- 0.20, N = 326.38MIN: 25.73 / MAX: 49.381. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -isysroot

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 Benchmarkmachine-learning-macbook-air-catalina4080120160200SE +/- 0.39, N = 3169.08

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUmachine-learning-macbook-air-catalina510152025SE +/- 0.02, N = 320.33MIN: 20.171. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUmachine-learning-macbook-air-catalina5K10K15K20K25KSE +/- 241.36, N = 324266.6MIN: 23635.41. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUmachine-learning-macbook-air-catalina11K22K33K44K55KSE +/- 566.53, N = 349197.6MIN: 47949.91. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUmachine-learning-macbook-air-catalina612182430SE +/- 0.10, N = 323.43MIN: 23.171. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUmachine-learning-macbook-air-catalina5K10K15K20K25KSE +/- 59.64, N = 323837.1MIN: 23587.51. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUmachine-learning-macbook-air-catalina10K20K30K40K50KSE +/- 87.73, N = 348107.5MIN: 477521. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUmachine-learning-macbook-air-catalina5K10K15K20K25KSE +/- 54.41, N = 323725.4MIN: 23567.71. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUmachine-learning-macbook-air-catalina10K20K30K40K50KSE +/- 193.20, N = 348294.9MIN: 47892.21. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUmachine-learning-macbook-air-catalina1530456075SE +/- 0.03, N = 368.14MIN: 67.941. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUmachine-learning-macbook-air-catalina1122334455SE +/- 0.08, N = 348.54MIN: 48.21. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUmachine-learning-macbook-air-catalina1632486480SE +/- 0.12, N = 372.79MIN: 72.261. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUmachine-learning-macbook-air-catalina20406080100SE +/- 0.07, N = 385.20MIN: 84.891. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUmachine-learning-macbook-air-catalina20406080100SE +/- 0.22, N = 394.51MIN: 93.681. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUmachine-learning-macbook-air-catalina1326395265SE +/- 0.18, N = 356.15MIN: 54.521. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUmachine-learning-macbook-air-catalina510152025SE +/- 0.01, N = 320.25MIN: 19.861. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUmachine-learning-macbook-air-catalina714212835SE +/- 0.41, N = 331.89MIN: 31.141. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUmachine-learning-macbook-air-catalina1122334455SE +/- 0.05, N = 349.25MIN: 48.481. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUmachine-learning-macbook-air-catalina1020304050SE +/- 0.50, N = 345.46MIN: 44.491. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot

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

machine-learning-macbook-air-catalina: 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 'scipy'

Detector: Relative Entropy

machine-learning-macbook-air-catalina: 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 'scipy'

Detector: EXPoSE

machine-learning-macbook-air-catalina: 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 'sklearn'

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.

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

machine-learning-macbook-air-catalina: 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: plaidml: line 24: /.local/bin/plaidbench: No such file or directory

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

machine-learning-macbook-air-catalina: 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: plaidml: line 24: /.local/bin/plaidbench: No such file or directory

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.

Acceleration: CPU

machine-learning-macbook-air-catalina: 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: Reason: image not found

oneDNN

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

machine-learning-macbook-air-catalina: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

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

machine-learning-macbook-air-catalina: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

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

machine-learning-macbook-air-catalina: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

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

machine-learning-macbook-air-catalina: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

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

machine-learning-macbook-air-catalina: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

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

machine-learning-macbook-air-catalina: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

66 Results Shown

AI Benchmark Alpha:
  Device AI Score
  Device Training Score
  Device Inference Score
Numenta Anomaly Benchmark:
  Earthgecko Skyline
  Windowed Gaussian
NCNN:
  Vulkan GPU - FastestDet
  Vulkan GPU - vision_transformer
  Vulkan GPU - regnety_400m
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - resnet50
  Vulkan GPU - alexnet
  Vulkan GPU - resnet18
  Vulkan GPU - vgg16
  Vulkan GPU - googlenet
  Vulkan GPU - blazeface
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - mnasnet
  Vulkan GPU - shufflenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU - mobilenet
  CPU - FastestDet
  CPU - vision_transformer
  CPU - regnety_400m
  CPU - squeezenet_ssd
  CPU - yolov4-tiny
  CPU - resnet50
  CPU - alexnet
  CPU - resnet18
  CPU - vgg16
  CPU - googlenet
  CPU - blazeface
  CPU - efficientnet-b0
  CPU - mnasnet
  CPU - shufflenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU-v2-v2 - mobilenet-v2
  CPU - mobilenet
Mobile Neural Network:
  inception-v3
  mobilenet-v1-1.0
  MobileNetV2_224
  SqueezeNetV1.0
  resnet-v2-50
  squeezenetv1.1
  mobilenetV3
  nasnet
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