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
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.
,,"MBP M1 Max Machine Learning","ML Tests"
Processor,,Apple M1 Max (10 Cores),AMD Ryzen 9 5900HX @ 3.30GHz (8 Cores / 16 Threads)
Motherboard,,Apple MacBook Pro,System76 Kudu (1.07.09RSA1 BIOS)
Memory,,64GB,16GB
Disk,,1859GB,Samsung SSD 970 EVO Plus 500GB
Graphics,,Apple M1 Max,AMD Cezanne (2100/400MHz)
Monitor,,Color LCD,
Chipset,,,AMD Renoir/Cezanne
Audio,,,AMD Renoir Radeon HD Audio
Network,,,Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX200
OS,,macOS 12.1,Pop 21.10
Kernel,,21.2.0 (arm64),5.15.15-76051515-generic (x86_64)
OpenCL,,OpenCL 1.2 (Nov 13 2021 00:45:09),
Compiler,,GCC 13.0.0 + Clang 13.0.0,GCC 11.2.0
File-System,,APFS,ext4
Screen Resolution,,3456x2234,1920x1080
Desktop,,,GNOME Shell 40.5
Display Server,,,X Server 1.20.13
OpenGL,,,4.6 Mesa 21.2.2 (LLVM 12.0.1)
Vulkan,,,1.2.182
,,"MBP M1 Max Machine Learning","ML Tests"
"Caffe - Model: GoogleNet - Acceleration: CPU - Iterations: 1000 (ms)",LIB,,868758
"LeelaChessZero - Backend: BLAS (Nodes/s)",HIB,,563
"ECP-CANDLE - Benchmark: P3B1 (sec)",LIB,,1463.722
"Mobile Neural Network - Model: inception-v3 (ms)",LIB,58.253,31.576
"Mobile Neural Network - Model: mobilenet-v1-1.0 (ms)",LIB,8.205,2.440
"Mobile Neural Network - Model: MobileNetV2_224 (ms)",LIB,10.677,2.387
"Mobile Neural Network - Model: SqueezeNetV1.0 (ms)",LIB,9.967,4.546
"Mobile Neural Network - Model: resnet-v2-50 (ms)",LIB,42.428,22.441
"Mobile Neural Network - Model: squeezenetv1.1 (ms)",LIB,7.274,2.803
"Mobile Neural Network - Model: mobilenetV3 (ms)",LIB,9.152,1.202
"Caffe - Model: AlexNet - Acceleration: CPU - Iterations: 1000 (ms)",LIB,,325884
"PlaidML - FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU (FPS)",HIB,,6.88
"ECP-CANDLE - Benchmark: P3B2 (sec)",LIB,,730.736
"PlaidML - FP16: No - Mode: Inference - Network: VGG16 - Device: CPU (FPS)",HIB,,12.47
"TNN - Target: CPU - Model: DenseNet (ms)",LIB,,2736.173
"oneDNN - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,2237.65
"Caffe - Model: GoogleNet - Acceleration: CPU - Iterations: 200 (ms)",LIB,,173671
"TensorFlow Lite - Model: Inception V4 (us)",LIB,,2749623
"TensorFlow Lite - Model: Inception ResNet V2 (us)",LIB,,2479080
"Mlpack Benchmark - Benchmark: scikit_qda (sec)",LIB,,65.69
"Numpy Benchmark - (Score)",HIB,,422.45
"NCNN - Target: CPU - Model: regnety_400m (ms)",LIB,7.18,6.90
"NCNN - Target: CPU - Model: squeezenet_ssd (ms)",LIB,20.53,18.56
"NCNN - Target: CPU - Model: yolov4-tiny (ms)",LIB,30.24,24.97
"NCNN - Target: CPU - Model: resnet50 (ms)",LIB,43.16,25.17
"NCNN - Target: CPU - Model: alexnet (ms)",LIB,29.93,14.55
"NCNN - Target: CPU - Model: resnet18 (ms)",LIB,16.82,15.78
"NCNN - Target: CPU - Model: vgg16 (ms)",LIB,71.01,71.97
"NCNN - Target: CPU - Model: googlenet (ms)",LIB,24.96,13.74
"NCNN - Target: CPU - Model: blazeface (ms)",LIB,1.65,1.20
"NCNN - Target: CPU - Model: efficientnet-b0 (ms)",LIB,8.69,5.22
"NCNN - Target: CPU - Model: mnasnet (ms)",LIB,5.40,3.25
"NCNN - Target: CPU - Model: shufflenet-v2 (ms)",LIB,3.47,2.75
"NCNN - Target: CPU-v3-v3 - Model: mobilenet-v3 (ms)",LIB,4.36,3.41
"NCNN - Target: CPU-v2-v2 - Model: mobilenet-v2 (ms)",LIB,5.33,3.99
"NCNN - Target: CPU - Model: mobilenet (ms)",LIB,20.32,15.95
"NCNN - Target: Vulkan GPU - Model: regnety_400m (ms)",LIB,7.19,5.28
"NCNN - Target: Vulkan GPU - Model: squeezenet_ssd (ms)",LIB,20.55,15.36
"NCNN - Target: Vulkan GPU - Model: yolov4-tiny (ms)",LIB,30.33,18.82
"NCNN - Target: Vulkan GPU - Model: resnet50 (ms)",LIB,43.08,13.12
"NCNN - Target: Vulkan GPU - Model: alexnet (ms)",LIB,29.89,6.32
"NCNN - Target: Vulkan GPU - Model: resnet18 (ms)",LIB,16.80,6.09
"NCNN - Target: Vulkan GPU - Model: vgg16 (ms)",LIB,70.89,43.99
"NCNN - Target: Vulkan GPU - Model: googlenet (ms)",LIB,24.9,8.73
"NCNN - Target: Vulkan GPU - Model: blazeface (ms)",LIB,1.64,1.35
"NCNN - Target: Vulkan GPU - Model: efficientnet-b0 (ms)",LIB,8.71,10.07
"NCNN - Target: Vulkan GPU - Model: mnasnet (ms)",LIB,5.37,3.89
"NCNN - Target: Vulkan GPU - Model: shufflenet-v2 (ms)",LIB,3.46,3.02
"NCNN - Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 (ms)",LIB,4.35,4.69
"NCNN - Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 (ms)",LIB,5.30,3.88
"NCNN - Target: Vulkan GPU - Model: mobilenet (ms)",LIB,20.30,10.27
"Caffe - Model: GoogleNet - Acceleration: CPU - Iterations: 100 (ms)",LIB,,86567
"OpenCV - Test: DNN - Deep Neural Network (ms)",LIB,,13787
"Caffe - Model: AlexNet - Acceleration: CPU - Iterations: 200 (ms)",LIB,,65986
"TensorFlow Lite - Model: SqueezeNet (us)",LIB,,189764
"TensorFlow Lite - Model: NASNet Mobile (us)",LIB,,152186
"TensorFlow Lite - Model: Mobilenet Quant (us)",LIB,,141174
"TensorFlow Lite - Model: Mobilenet Float (us)",LIB,,127818
"Mlpack Benchmark - Benchmark: scikit_ica (sec)",LIB,,48.40
"oneDNN - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,3577.00
"oneDNN - Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,,3587.17
"oneDNN - Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU (ms)",LIB,,3579.00
"Mlpack Benchmark - Benchmark: scikit_linearridgeregression (sec)",LIB,,2.10
"oneDNN - Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,,2228.17
"oneDNN - Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU (ms)",LIB,,2219.13
"Caffe - Model: AlexNet - Acceleration: CPU - Iterations: 100 (ms)",LIB,,33496
"DeepSpeech - Acceleration: CPU (sec)",LIB,,74.44043
"Mlpack Benchmark - Benchmark: scikit_svm (sec)",LIB,,17.60
"R Benchmark - (sec)",LIB,,0.1293
"oneDNN - Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU (ms)",LIB,,4.25855
"TNN - Target: CPU - Model: MobileNet v2 (ms)",LIB,,249.477
"RNNoise - (sec)",LIB,,16.137
"TNN - Target: CPU - Model: SqueezeNet v1.1 (ms)",LIB,,222.326
"ECP-CANDLE - Benchmark: P1B2 (sec)",LIB,,37.51
"oneDNN - Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU (ms)",LIB,,8.34789
"oneDNN - Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,,2.11771
"oneDNN - Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,,1.62985
"oneDNN - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU (ms)",LIB,,4.59343
"oneDNN - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,,2.98659
"oneDNN - Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU (ms)",LIB,,12.0926
"oneDNN - Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,,2.69210
"TNN - Target: CPU - Model: SqueezeNet v2 (ms)",LIB,,55.434
"oneDNN - Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,,23.7674
"oneDNN - Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU (ms)",LIB,,22.7926
"Tensorflow - Build: Cifar10 (sec)",LIB,,
"oneDNN - Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU (ms)",LIB,,6.74559
"oneDNN - Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,,3.24784
"Numenta Anomaly Benchmark - Detector: EXPoSE (sec)",LIB,,
"Numenta Anomaly Benchmark - Detector: Bayesian Changepoint (sec)",LIB,,
"Numenta Anomaly Benchmark - Detector: Relative Entropy (sec)",LIB,,
"Numenta Anomaly Benchmark - Detector: Earthgecko Skyline (sec)",LIB,,
"Numenta Anomaly Benchmark - Detector: Windowed Gaussian (sec)",LIB,,
"AI Benchmark Alpha - (Score)",HIB,,
"ONNX Runtime - Model: yolov4 - Device: CPU (Inferences/min)",HIB,,
"ONNX Runtime - Model: super-resolution-10 - Device: CPU (Inferences/min)",HIB,,
"ONNX Runtime - Model: shufflenet-v2-10 - Device: CPU (Inferences/min)",HIB,,
"ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU (Inferences/min)",HIB,,
"oneDNN - Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,
"oneDNN - Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,
"OpenVINO - Model: Age Gender Recognition Retail 0013 FP32 - Device: Intel GPU (FPS)",HIB,,
"OpenVINO - Model: Age Gender Recognition Retail 0013 FP16 - Device: Intel GPU (FPS)",HIB,,
"OpenVINO - Model: Person Detection 0106 FP16 - Device: Intel GPU (FPS)",HIB,,
"OpenVINO - Model: Face Detection 0106 FP32 - Device: CPU (FPS)",HIB,,
"OpenVINO - Model: Face Detection 0106 FP16 - Device: CPU (FPS)",HIB,,
"oneDNN - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,
"oneDNN - Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,
"oneDNN - Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,
"oneDNN - Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,
"OpenVINO - Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU (FPS)",HIB,,
"OpenVINO - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU (FPS)",HIB,,
"OpenVINO - Model: Person Detection 0106 FP32 - Device: Intel GPU (FPS)",HIB,,
"OpenVINO - Model: Person Detection 0106 FP32 - Device: CPU (FPS)",HIB,,
"OpenVINO - Model: Person Detection 0106 FP16 - Device: CPU (FPS)",HIB,,
"OpenVINO - Model: Face Detection 0106 FP32 - Device: Intel GPU (FPS)",HIB,,
"OpenVINO - Model: Face Detection 0106 FP16 - Device: Intel GPU (FPS)",HIB,,