Apple M2 Pro testing with a Apple Mac mini and Apple M2 Pro on macOS 13.5 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 2312093-REIN-PTSHPC077 pts-hpc - Phoronix Test Suite pts-hpc Apple M2 Pro testing with a Apple Mac mini and Apple M2 Pro on macOS 13.5 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2312093-REIN-PTSHPC077&gru .
pts-hpc Processor Motherboard Memory Disk Graphics Monitor OS Kernel Compiler File-System Screen Resolution pts-hpc Apple M2 Pro (10 Cores) Apple Mac mini 16GB 461GB Apple M2 Pro Apple M2 Pro macOS 13.5 22.6.0 (arm64) GCC 14.0.3 + Clang 17.0.6 + LLVM 17.0.6 + Xcode 14.3.1 APFS x OpenBenchmarking.org - LDFLAGS=-L/opt/homebrew/opt/llvm/lib CPPFLAGS=-I/opt/homebrew/opt/llvm/include - Python 3.11.5
pts-hpc namd: ATPase Simulation - 327,506 Atoms onednn: IP Shapes 1D - f32 - CPU onednn: IP Shapes 3D - f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU onednn: Recurrent Neural Network Training - f32 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU mnn: nasnet mnn: mobilenetV3 mnn: squeezenetv1.1 mnn: resnet-v2-50 mnn: SqueezeNetV1.0 mnn: MobileNetV2_224 mnn: mobilenet-v1-1.0 mnn: inception-v3 ncnn: CPU - mobilenet ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU - shufflenet-v2 ncnn: CPU - mnasnet ncnn: CPU - efficientnet-b0 ncnn: CPU - blazeface ncnn: CPU - googlenet ncnn: CPU - vgg16 ncnn: CPU - resnet18 ncnn: CPU - alexnet ncnn: CPU - resnet50 ncnn: CPU - yolov4-tiny ncnn: CPU - squeezenet_ssd ncnn: CPU - regnety_400m ncnn: CPU - vision_transformer ncnn: CPU - FastestDet ncnn: Vulkan GPU - mobilenet ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - vision_transformer ncnn: Vulkan GPU - FastestDet mafft: Multiple Sequence Alignment - LSU RNA pyhpc: CPU - TensorFlow - 4194304 - Isoneutral Mixing pts-hpc 2.36706 198.544 127.933 266.297 341.080 349.577 888.776 348.905 771.373 612.431 375.870 216031 132806 215461 132819 215425 132815 11.523 1.825 3.199 25.079 5.527 3.629 4.664 35.277 18.07 4.64 3.77 2.69 4.73 7.59 0.88 22.11 66.25 14.85 16.75 40.62 26.77 13.80 6.44 1187.73 2.11 18.01 4.59 3.73 2.66 4.69 7.51 0.87 21.91 65.60 14.72 16.59 40.27 26.71 13.69 6.38 1187.42 2.11 8.166 OpenBenchmarking.org
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms pts-hpc 0.5335 1.067 1.6005 2.134 2.6675 SE +/- 0.00197, N = 3 2.37121
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU pts-hpc 40 80 120 160 200 SE +/- 0.02, N = 3 198.54 MIN: 196.75 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU pts-hpc 30 60 90 120 150 SE +/- 0.15, N = 3 127.93 MIN: 127.07 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU pts-hpc 60 120 180 240 300 SE +/- 0.07, N = 3 266.30 MIN: 263.27 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU pts-hpc 70 140 210 280 350 SE +/- 0.55, N = 3 341.08 MIN: 338.54 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU pts-hpc 80 160 240 320 400 SE +/- 0.66, N = 3 349.58 MIN: 344.76 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU pts-hpc 200 400 600 800 1000 SE +/- 0.33, N = 3 888.78 MIN: 885.43 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU pts-hpc 80 160 240 320 400 SE +/- 0.07, N = 3 348.91 MIN: 347.12 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU pts-hpc 170 340 510 680 850 SE +/- 0.26, N = 3 771.37 MIN: 767 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU pts-hpc 130 260 390 520 650 SE +/- 0.99, N = 3 612.43 MIN: 601.38 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU pts-hpc 80 160 240 320 400 SE +/- 0.24, N = 3 375.87 MIN: 374.29 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU pts-hpc 50K 100K 150K 200K 250K SE +/- 134.13, N = 3 216031 MIN: 215664 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU pts-hpc 30K 60K 90K 120K 150K SE +/- 36.42, N = 3 132806 MIN: 132690 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU pts-hpc 50K 100K 150K 200K 250K SE +/- 20.22, N = 3 215461 MIN: 215323 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU pts-hpc 30K 60K 90K 120K 150K SE +/- 17.95, N = 3 132819 MIN: 132710 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU pts-hpc 50K 100K 150K 200K 250K SE +/- 24.27, N = 3 215425 MIN: 215254 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU pts-hpc 30K 60K 90K 120K 150K SE +/- 13.69, N = 3 132815 MIN: 132719 1. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot
Mobile Neural Network Model: nasnet OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: nasnet pts-hpc 3 6 9 12 15 SE +/- 0.13, N = 4 11.52 MIN: 9.02 / MAX: 16.91 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 -arch -isysroot
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenetV3 pts-hpc 0.4106 0.8212 1.2318 1.6424 2.053 SE +/- 0.013, N = 4 1.825 MIN: 1.48 / MAX: 4.15 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 -arch -isysroot
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: squeezenetv1.1 pts-hpc 0.7198 1.4396 2.1594 2.8792 3.599 SE +/- 0.048, N = 4 3.199 MIN: 2.25 / MAX: 4.68 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 -arch -isysroot
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: resnet-v2-50 pts-hpc 6 12 18 24 30 SE +/- 0.14, N = 4 25.08 MIN: 20.97 / MAX: 29.29 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 -arch -isysroot
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: SqueezeNetV1.0 pts-hpc 1.2436 2.4872 3.7308 4.9744 6.218 SE +/- 0.049, N = 4 5.527 MIN: 4.29 / MAX: 7.17 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 -arch -isysroot
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: MobileNetV2_224 pts-hpc 0.8165 1.633 2.4495 3.266 4.0825 SE +/- 0.021, N = 4 3.629 MIN: 2.95 / MAX: 5.88 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 -arch -isysroot
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 pts-hpc 1.0494 2.0988 3.1482 4.1976 5.247 SE +/- 0.066, N = 4 4.664 MIN: 3.82 / MAX: 6.8 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 -arch -isysroot
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: inception-v3 pts-hpc 8 16 24 32 40 SE +/- 0.77, N = 4 35.28 MIN: 29.23 / MAX: 39.49 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 -arch -isysroot
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mobilenet pts-hpc 4 8 12 16 20 SE +/- 0.04, N = 3 18.07 MIN: 17.9 / MAX: 18.9 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 pts-hpc 1.044 2.088 3.132 4.176 5.22 SE +/- 0.04, N = 3 4.64 MIN: 4.57 / MAX: 5.17 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 pts-hpc 0.8483 1.6966 2.5449 3.3932 4.2415 SE +/- 0.04, N = 3 3.77 MIN: 3.72 / MAX: 4.12 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: shufflenet-v2 pts-hpc 0.6053 1.2106 1.8159 2.4212 3.0265 SE +/- 0.02, N = 3 2.69 MIN: 2.65 / MAX: 3.21 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mnasnet pts-hpc 1.0643 2.1286 3.1929 4.2572 5.3215 SE +/- 0.04, N = 3 4.73 MIN: 4.67 / MAX: 5.2 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: efficientnet-b0 pts-hpc 2 4 6 8 10 SE +/- 0.07, N = 3 7.59 MIN: 7.48 / MAX: 8.33 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: blazeface pts-hpc 0.198 0.396 0.594 0.792 0.99 SE +/- 0.01, N = 3 0.88 MIN: 0.86 / MAX: 1.01 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: googlenet pts-hpc 5 10 15 20 25 SE +/- 0.18, N = 3 22.11 MIN: 21.7 / MAX: 23.38 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vgg16 pts-hpc 15 30 45 60 75 SE +/- 0.56, N = 3 66.25 MIN: 64.89 / MAX: 68.2 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet18 pts-hpc 4 8 12 16 20 SE +/- 0.14, N = 3 14.85 MIN: 14.54 / MAX: 15.6 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: alexnet pts-hpc 4 8 12 16 20 SE +/- 0.13, N = 3 16.75 MIN: 16.47 / MAX: 17.64 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet50 pts-hpc 9 18 27 36 45 SE +/- 0.32, N = 3 40.62 MIN: 39.97 / MAX: 41.55 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: yolov4-tiny pts-hpc 6 12 18 24 30 SE +/- 0.04, N = 3 26.77 MIN: 26.45 / MAX: 27.89 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: squeezenet_ssd pts-hpc 4 8 12 16 20 SE +/- 0.12, N = 3 13.80 MIN: 13.33 / MAX: 14.61 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: regnety_400m pts-hpc 2 4 6 8 10 SE +/- 0.06, N = 3 6.44 MIN: 6.35 / MAX: 7.03 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vision_transformer pts-hpc 300 600 900 1200 1500 SE +/- 0.19, N = 3 1187.73 MIN: 1186.86 / MAX: 1190.11 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: CPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: FastestDet pts-hpc 0.4748 0.9496 1.4244 1.8992 2.374 SE +/- 0.00, N = 3 2.11 MIN: 2.1 / MAX: 2.34 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mobilenet pts-hpc 4 8 12 16 20 SE +/- 0.01, N = 3 18.01 MIN: 17.89 / MAX: 19.77 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 pts-hpc 1.0328 2.0656 3.0984 4.1312 5.164 SE +/- 0.00, N = 3 4.59 MIN: 4.57 / MAX: 5.11 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 pts-hpc 0.8393 1.6786 2.5179 3.3572 4.1965 SE +/- 0.00, N = 3 3.73 MIN: 3.71 / MAX: 4.09 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 pts-hpc 0.5985 1.197 1.7955 2.394 2.9925 SE +/- 0.00, N = 3 2.66 MIN: 2.65 / MAX: 2.96 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mnasnet pts-hpc 1.0553 2.1106 3.1659 4.2212 5.2765 SE +/- 0.00, N = 3 4.69 MIN: 4.67 / MAX: 5.07 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 pts-hpc 2 4 6 8 10 SE +/- 0.00, N = 3 7.51 MIN: 7.48 / MAX: 8.21 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: blazeface pts-hpc 0.1958 0.3916 0.5874 0.7832 0.979 SE +/- 0.00, N = 3 0.87 MIN: 0.86 / MAX: 0.92 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: googlenet pts-hpc 5 10 15 20 25 SE +/- 0.03, N = 3 21.91 MIN: 21.46 / MAX: 22.99 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vgg16 pts-hpc 15 30 45 60 75 SE +/- 0.04, N = 3 65.60 MIN: 64.87 / MAX: 66.51 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet18 pts-hpc 4 8 12 16 20 SE +/- 0.01, N = 3 14.72 MIN: 14.36 / MAX: 15.98 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: alexnet pts-hpc 4 8 12 16 20 SE +/- 0.02, N = 3 16.59 MIN: 16.45 / MAX: 17.39 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet50 pts-hpc 9 18 27 36 45 SE +/- 0.02, N = 3 40.27 MIN: 39.89 / MAX: 41.05 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny pts-hpc 6 12 18 24 30 SE +/- 0.02, N = 3 26.71 MIN: 26.45 / MAX: 28.29 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd pts-hpc 4 8 12 16 20 SE +/- 0.01, N = 3 13.69 MIN: 13.56 / MAX: 14.55 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m pts-hpc 2 4 6 8 10 SE +/- 0.00, N = 3 6.38 MIN: 6.35 / MAX: 6.97 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer pts-hpc 300 600 900 1200 1500 SE +/- 0.23, N = 3 1187.42 MIN: 1186.29 / MAX: 1189.54 1. (CXX) g++ options: -O3 -arch -isysroot
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: FastestDet pts-hpc 0.4748 0.9496 1.4244 1.8992 2.374 SE +/- 0.00, N = 3 2.11 MIN: 2.1 / MAX: 2.21 1. (CXX) g++ options: -O3 -arch -isysroot
Timed MAFFT Alignment Multiple Sequence Alignment - LSU RNA OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 7.471 Multiple Sequence Alignment - LSU RNA pts-hpc 2 4 6 8 10 SE +/- 0.091, N = 3 8.315 1. (CC) gcc options: -std=c99 -O3 -lm -lpthread
Phoronix Test Suite v10.8.4