MBP M1 Max Machine Learning

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

HTML result view exported from: https://openbenchmarking.org/result/2202161-NE-MBPM1MAXM40&grt.

MBP M1 Max Machine LearningProcessorMotherboardMemoryDiskGraphicsMonitorOSKernelOpenCLCompilerFile-SystemScreen ResolutionMBP M1 Max Machine LearningApple 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.org- XPC_FLAGS=0x0- Python 2.7.18 + Python 3.8.9

MBP M1 Max Machine Learningmnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3ncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400monednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUMBP M1 Max Machine Learning9.1527.27442.4289.96710.6778.20558.25320.325.334.363.475.408.691.6524.9671.0116.8229.9343.1630.2420.537.1820.305.304.353.465.378.711.6424.970.8916.8029.8943.0830.3320.557.19OpenBenchmarking.org

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV3MBP M1 Max Machine Learning3691215SE +/- 0.487, N = 99.152MIN: 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 -arch -isysroot

Mobile Neural Network

Model: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: squeezenetv1.1MBP M1 Max Machine Learning246810SE +/- 0.345, N = 97.274MIN: 2.75 / MAX: 117.921. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -arch -isysroot

Mobile Neural Network

Model: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: resnet-v2-50MBP M1 Max Machine Learning1020304050SE +/- 4.17, N = 942.43MIN: 24 / MAX: 197.771. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -arch -isysroot

Mobile Neural Network

Model: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: SqueezeNetV1.0MBP M1 Max Machine Learning3691215SE +/- 0.664, N = 99.967MIN: 4.34 / MAX: 49.521. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -arch -isysroot

Mobile Neural Network

Model: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: MobileNetV2_224MBP M1 Max Machine Learning3691215SE +/- 0.19, N = 910.68MIN: 5.12 / MAX: 61.591. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -arch -isysroot

Mobile Neural Network

Model: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenet-v1-1.0MBP M1 Max Machine Learning246810SE +/- 0.384, N = 98.205MIN: 4.27 / MAX: 48.51. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -arch -isysroot

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: inception-v3MBP M1 Max Machine Learning1326395265SE +/- 6.12, N = 958.25MIN: 30.46 / MAX: 200.211. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -arch -isysroot

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenetMBP M1 Max Machine Learning510152025SE +/- 0.02, N = 320.32MIN: 20.23 / MAX: 21.331. (CXX) g++ options: -O3 -arch -isysroot

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2MBP M1 Max Machine Learning1.19932.39863.59794.79725.9965SE +/- 0.03, N = 35.33MIN: 5.27 / MAX: 5.611. (CXX) g++ options: -O3 -arch -isysroot

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3MBP M1 Max Machine Learning0.9811.9622.9433.9244.905SE +/- 0.03, N = 34.36MIN: 4.32 / MAX: 4.611. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2MBP M1 Max Machine Learning0.78081.56162.34243.12323.904SE +/- 0.02, N = 33.47MIN: 3.43 / MAX: 3.841. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetMBP M1 Max Machine Learning1.2152.433.6454.866.075SE +/- 0.03, N = 35.40MIN: 5.35 / MAX: 5.681. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0MBP M1 Max Machine Learning246810SE +/- 0.04, N = 38.69MIN: 8.59 / MAX: 9.151. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazefaceMBP M1 Max Machine Learning0.37130.74261.11391.48521.8565SE +/- 0.01, N = 31.65MIN: 1.64 / MAX: 1.721. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetMBP M1 Max Machine Learning612182430SE +/- 0.07, N = 324.96MIN: 24.82 / MAX: 25.911. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16MBP M1 Max Machine Learning1632486480SE +/- 0.15, N = 371.01MIN: 70.58 / MAX: 74.441. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18MBP M1 Max Machine Learning48121620SE +/- 0.04, N = 316.82MIN: 16.69 / MAX: 17.581. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetMBP M1 Max Machine Learning714212835SE +/- 0.05, N = 329.93MIN: 29.79 / MAX: 31.031. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50MBP M1 Max Machine Learning1020304050SE +/- 0.07, N = 343.16MIN: 42.92 / MAX: 44.811. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinyMBP M1 Max Machine Learning714212835SE +/- 0.03, N = 330.24MIN: 29.85 / MAX: 31.871. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdMBP M1 Max Machine Learning510152025SE +/- 0.05, N = 320.53MIN: 20.37 / MAX: 21.531. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: regnety_400mMBP M1 Max Machine Learning246810SE +/- 0.00, N = 37.18MIN: 7.14 / MAX: 8.131. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mobilenetMBP M1 Max Machine Learning510152025SE +/- 0.02, N = 320.30MIN: 20.23 / MAX: 21.481. (CXX) g++ options: -O3 -arch -isysroot

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2MBP M1 Max Machine Learning1.19252.3853.57754.775.9625SE +/- 0.01, N = 35.30MIN: 5.28 / MAX: 5.981. (CXX) g++ options: -O3 -arch -isysroot

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3MBP M1 Max Machine Learning0.97881.95762.93643.91524.894SE +/- 0.00, N = 34.35MIN: 4.32 / MAX: 4.631. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: shufflenet-v2MBP M1 Max Machine Learning0.77851.5572.33553.1143.8925SE +/- 0.01, N = 33.46MIN: 3.44 / MAX: 3.821. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mnasnetMBP M1 Max Machine Learning1.20832.41663.62494.83326.0415SE +/- 0.00, N = 35.37MIN: 5.35 / MAX: 5.621. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: efficientnet-b0MBP M1 Max Machine Learning246810SE +/- 0.02, N = 38.71MIN: 8.6 / MAX: 9.431. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: blazefaceMBP M1 Max Machine Learning0.3690.7381.1071.4761.845SE +/- 0.00, N = 31.64MIN: 1.63 / MAX: 1.791. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: googlenetMBP M1 Max Machine Learning612182430SE +/- 0.00, N = 324.9MIN: 24.82 / MAX: 25.791. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: vgg16MBP M1 Max Machine Learning1632486480SE +/- 0.02, N = 370.89MIN: 70.59 / MAX: 73.621. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet18MBP M1 Max Machine Learning48121620SE +/- 0.01, N = 316.80MIN: 16.69 / MAX: 18.251. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: alexnetMBP M1 Max Machine Learning714212835SE +/- 0.00, N = 329.89MIN: 29.79 / MAX: 31.071. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet50MBP M1 Max Machine Learning1020304050SE +/- 0.01, N = 343.08MIN: 42.9 / MAX: 45.661. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: yolov4-tinyMBP M1 Max Machine Learning714212835SE +/- 0.07, N = 330.33MIN: 29.85 / MAX: 32.581. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: squeezenet_ssdMBP M1 Max Machine Learning510152025SE +/- 0.05, N = 320.55MIN: 20.39 / MAX: 22.131. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: regnety_400mMBP M1 Max Machine Learning246810SE +/- 0.00, N = 37.19MIN: 7.15 / MAX: 7.721. (CXX) g++ options: -O3 -arch -isysroot

Phoronix Test Suite v10.8.5