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.
machine-learning-macbook-air-catalina Processor: Intel Core i5-4250U @ 1.30GHz (2 Cores / 4 Threads), Motherboard: Apple MacBook Air, Chipset: Apple SSD, Memory: 2 x GB DDR3-1600MHz, Disk: 121 33GB APPLE SSD TS0128F, Graphics: Intel HD 5000 2GB, Monitor: Color LCD
OS: macOS 10.15.7, Kernel: 19.6.0 (x86_64), Compiler: Clang 12.0.0 + GCC 12.0.0, File-System: APFS, Screen Resolution: 1366x768
Environment Notes: XPC_FLAGS=0x0Processor Notes: CPU Microcode: 38Python Notes: Python 2.7.16 + Python 3.10.8
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: 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
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
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: 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'
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: 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'
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
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.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: nasnet machine-learning-macbook-air-catalina 6 12 18 24 30 SE +/- 0.20, N = 3 26.38 MIN: 25.73 / MAX: 49.38 1. (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.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenetV3 machine-learning-macbook-air-catalina 0.8449 1.6898 2.5347 3.3796 4.2245 SE +/- 0.003, N = 3 3.755 MIN: 3.7 / MAX: 8.21 1. (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.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: squeezenetv1.1 machine-learning-macbook-air-catalina 3 6 9 12 15 SE +/- 0.068, N = 3 9.070 MIN: 8.66 / MAX: 17.09 1. (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.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: resnet-v2-50 machine-learning-macbook-air-catalina 20 40 60 80 100 SE +/- 0.74, N = 3 81.32 MIN: 78.54 / MAX: 117.53 1. (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.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: SqueezeNetV1.0 machine-learning-macbook-air-catalina 4 8 12 16 20 SE +/- 0.15, N = 3 16.65 MIN: 15.94 / MAX: 30.04 1. (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.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: MobileNetV2_224 machine-learning-macbook-air-catalina 3 6 9 12 15 SE +/- 0.048, N = 3 9.115 MIN: 8.93 / MAX: 20.86 1. (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.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 machine-learning-macbook-air-catalina 3 6 9 12 15 SE +/- 0.10, N = 3 12.05 MIN: 11.79 / MAX: 24.19 1. (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.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: inception-v3 machine-learning-macbook-air-catalina 20 40 60 80 100 SE +/- 0.25, N = 3 109.12 MIN: 106.8 / MAX: 163.22 1. (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.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 machine-learning-macbook-air-catalina 7 14 21 28 35 SE +/- 0.12, N = 3 30.28 MIN: 29.5 / MAX: 37 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 machine-learning-macbook-air-catalina 6 12 18 24 30 SE +/- 0.06, N = 3 24.24 MIN: 23.73 / MAX: 27.63 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: shufflenet-v2 machine-learning-macbook-air-catalina 4 8 12 16 20 SE +/- 0.06, N = 3 17.68 MIN: 17.34 / MAX: 22.39 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mnasnet machine-learning-macbook-air-catalina 7 14 21 28 35 SE +/- 0.13, N = 3 28.88 MIN: 28.18 / MAX: 32.67 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: efficientnet-b0 machine-learning-macbook-air-catalina 11 22 33 44 55 SE +/- 0.08, N = 3 47.47 MIN: 46.54 / MAX: 59.07 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: blazeface machine-learning-macbook-air-catalina 0.873 1.746 2.619 3.492 4.365 SE +/- 0.01, N = 3 3.88 MIN: 3.83 / MAX: 5.09 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: googlenet machine-learning-macbook-air-catalina 20 40 60 80 100 SE +/- 0.20, N = 3 85.54 MIN: 83.14 / MAX: 110.91 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vgg16 machine-learning-macbook-air-catalina 80 160 240 320 400 SE +/- 0.41, N = 3 350.41 MIN: 339.91 / MAX: 405.35 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet18 machine-learning-macbook-air-catalina 15 30 45 60 75 SE +/- 0.31, N = 3 67.60 MIN: 65.5 / MAX: 82.4 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: alexnet machine-learning-macbook-air-catalina 12 24 36 48 60 SE +/- 0.27, N = 3 51.56 MIN: 49.46 / MAX: 64.84 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet50 machine-learning-macbook-air-catalina 40 80 120 160 200 SE +/- 0.21, N = 3 204.77 MIN: 200.78 / MAX: 233.25 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: yolov4-tiny machine-learning-macbook-air-catalina 30 60 90 120 150 SE +/- 0.12, N = 3 132.01 MIN: 129.3 / MAX: 156.26 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: squeezenet_ssd machine-learning-macbook-air-catalina 20 40 60 80 100 SE +/- 0.41, N = 3 78.52 MIN: 76.43 / MAX: 92.52 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: regnety_400m machine-learning-macbook-air-catalina 8 16 24 32 40 SE +/- 0.17, N = 3 35.43 MIN: 34.84 / MAX: 40.49 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vision_transformer machine-learning-macbook-air-catalina 700 1400 2100 2800 3500 SE +/- 1.55, N = 3 3280.84 MIN: 3254.79 / MAX: 3527.44 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: FastestDet machine-learning-macbook-air-catalina 4 8 12 16 20 SE +/- 0.07, N = 3 14.71 MIN: 14.31 / MAX: 19.16 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mobilenet machine-learning-macbook-air-catalina 20 40 60 80 100 SE +/- 0.07, N = 3 110.19 MIN: 108.64 / MAX: 131.65 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 machine-learning-macbook-air-catalina 7 14 21 28 35 SE +/- 0.04, N = 3 30.17 MIN: 29.54 / MAX: 34.78 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 machine-learning-macbook-air-catalina 6 12 18 24 30 SE +/- 0.04, N = 3 24.25 MIN: 23.71 / MAX: 27.38 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: shufflenet-v2 machine-learning-macbook-air-catalina 4 8 12 16 20 SE +/- 0.02, N = 3 17.51 MIN: 17.32 / MAX: 19.98 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mnasnet machine-learning-macbook-air-catalina 7 14 21 28 35 SE +/- 0.33, N = 3 28.84 MIN: 28.14 / MAX: 41.32 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: efficientnet-b0 machine-learning-macbook-air-catalina 11 22 33 44 55 SE +/- 0.20, N = 3 47.84 MIN: 46.51 / MAX: 56.6 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: blazeface machine-learning-macbook-air-catalina 0.8753 1.7506 2.6259 3.5012 4.3765 SE +/- 0.01, N = 3 3.89 MIN: 3.83 / MAX: 4.32 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: googlenet machine-learning-macbook-air-catalina 20 40 60 80 100 SE +/- 0.46, N = 3 85.08 MIN: 83.08 / MAX: 100.41 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vgg16 machine-learning-macbook-air-catalina 80 160 240 320 400 SE +/- 0.97, N = 3 351.16 MIN: 340.08 / MAX: 410.51 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet18 machine-learning-macbook-air-catalina 15 30 45 60 75 SE +/- 0.30, N = 3 67.68 MIN: 65.55 / MAX: 88.02 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: alexnet machine-learning-macbook-air-catalina 12 24 36 48 60 SE +/- 0.30, N = 3 51.84 MIN: 49.64 / MAX: 63.42 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet50 machine-learning-macbook-air-catalina 50 100 150 200 250 SE +/- 0.76, N = 3 205.77 MIN: 201.02 / MAX: 231.97 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: yolov4-tiny machine-learning-macbook-air-catalina 30 60 90 120 150 SE +/- 0.34, N = 3 133.69 MIN: 129.53 / MAX: 168.53 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: squeezenet_ssd machine-learning-macbook-air-catalina 20 40 60 80 100 SE +/- 0.20, N = 3 78.15 MIN: 76.06 / MAX: 91.61 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: regnety_400m machine-learning-macbook-air-catalina 8 16 24 32 40 SE +/- 0.09, N = 3 35.42 MIN: 34.83 / MAX: 39.61 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vision_transformer machine-learning-macbook-air-catalina 700 1400 2100 2800 3500 SE +/- 0.62, N = 3 3282.30 MIN: 3256.98 / MAX: 3398.28 1. (CXX) g++ options: -O3 -isysroot
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: FastestDet machine-learning-macbook-air-catalina 4 8 12 16 20 SE +/- 0.08, N = 3 14.74 MIN: 14.32 / MAX: 18.37 1. (CXX) g++ options: -O3 -isysroot
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU machine-learning-macbook-air-catalina 10 20 30 40 50 SE +/- 0.50, N = 3 45.46 MIN: 44.49 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU machine-learning-macbook-air-catalina 11 22 33 44 55 SE +/- 0.05, N = 3 49.25 MIN: 48.48 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU machine-learning-macbook-air-catalina 7 14 21 28 35 SE +/- 0.41, N = 3 31.89 MIN: 31.14 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU machine-learning-macbook-air-catalina 5 10 15 20 25 SE +/- 0.01, N = 3 20.25 MIN: 19.86 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
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.
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.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU machine-learning-macbook-air-catalina 13 26 39 52 65 SE +/- 0.18, N = 3 56.15 MIN: 54.52 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU machine-learning-macbook-air-catalina 20 40 60 80 100 SE +/- 0.22, N = 3 94.51 MIN: 93.68 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU machine-learning-macbook-air-catalina 20 40 60 80 100 SE +/- 0.07, N = 3 85.20 MIN: 84.89 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU machine-learning-macbook-air-catalina 16 32 48 64 80 SE +/- 0.12, N = 3 72.79 MIN: 72.26 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU machine-learning-macbook-air-catalina 11 22 33 44 55 SE +/- 0.08, N = 3 48.54 MIN: 48.2 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU machine-learning-macbook-air-catalina 15 30 45 60 75 SE +/- 0.03, N = 3 68.14 MIN: 67.94 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU machine-learning-macbook-air-catalina 10K 20K 30K 40K 50K SE +/- 193.20, N = 3 48294.9 MIN: 47892.2 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU machine-learning-macbook-air-catalina 5K 10K 15K 20K 25K SE +/- 54.41, N = 3 23725.4 MIN: 23567.7 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU machine-learning-macbook-air-catalina 10K 20K 30K 40K 50K SE +/- 87.73, N = 3 48107.5 MIN: 47752 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
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: 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: 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.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU machine-learning-macbook-air-catalina 5K 10K 15K 20K 25K SE +/- 59.64, N = 3 23837.1 MIN: 23587.5 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU machine-learning-macbook-air-catalina 6 12 18 24 30 SE +/- 0.10, N = 3 23.43 MIN: 23.17 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU machine-learning-macbook-air-catalina 11K 22K 33K 44K 55K SE +/- 566.53, N = 3 49197.6 MIN: 47949.9 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU machine-learning-macbook-air-catalina 5K 10K 15K 20K 25K SE +/- 241.36, N = 3 24266.6 MIN: 23635.4 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU machine-learning-macbook-air-catalina 5 10 15 20 25 SE +/- 0.02, N = 3 20.33 MIN: 20.17 1. (CXX) g++ options: -O3 -march=native -msse4.1 -fPIC -isysroot
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.
machine-learning-macbook-air-catalina Processor: Intel Core i5-4250U @ 1.30GHz (2 Cores / 4 Threads), Motherboard: Apple MacBook Air, Chipset: Apple SSD, Memory: 2 x GB DDR3-1600MHz, Disk: 121 33GB APPLE SSD TS0128F, Graphics: Intel HD 5000 2GB, Monitor: Color LCD
OS: macOS 10.15.7, Kernel: 19.6.0 (x86_64), Compiler: Clang 12.0.0 + GCC 12.0.0, File-System: APFS, Screen Resolution: 1366x768
Environment Notes: XPC_FLAGS=0x0Processor Notes: CPU Microcode: 38Python Notes: Python 2.7.16 + Python 3.10.8
Testing initiated at 22 October 2022 21:11 by user progdan.