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.

pts-hpcProcessorMotherboardMemoryDiskGraphicsMonitorOSKernelCompilerFile-SystemScreen Resolutionpts-hpcApple M2 Pro (10 Cores)Apple Mac mini16GB461GBApple M2 ProApple M2 PromacOS 13.522.6.0 (arm64)GCC 14.0.3 + Clang 17.0.6 + LLVM 17.0.6 + Xcode 14.3.1APFSxOpenBenchmarking.org- LDFLAGS=-L/opt/homebrew/opt/llvm/lib CPPFLAGS=-I/opt/homebrew/opt/llvm/include - Python 3.11.5

pts-hpcnamd: ATPase Simulation - 327,506 Atomsmafft: Multiple Sequence Alignment - LSU RNAonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUmnn: nasnetmnn: 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: CPU - vision_transformerncnn: CPU - FastestDetncnn: 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_400mncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - FastestDetpyhpc: CPU - TensorFlow - 4194304 - Isoneutral Mixingpts-hpc2.367068.166198.544127.933266.297341.080349.577888.776348.905771.373612.431375.87021603113280621546113281921542513281511.5231.8253.19925.0795.5273.6294.66435.27718.074.643.772.694.737.590.8822.1166.2514.8516.7540.6226.7713.806.441187.732.1118.014.593.732.664.697.510.8721.9165.6014.7216.5940.2726.7113.696.381187.422.11OpenBenchmarking.org

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atomspts-hpc0.53351.0671.60052.1342.6675SE +/- 0.00197, N = 32.37121

Timed MAFFT Alignment

Multiple Sequence Alignment - LSU RNA

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNApts-hpc246810SE +/- 0.091, N = 38.3151. (CC) gcc options: -std=c99 -O3 -lm -lpthread

oneDNN

Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUpts-hpc4080120160200SE +/- 0.02, N = 3198.54MIN: 196.751. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUpts-hpc306090120150SE +/- 0.15, N = 3127.93MIN: 127.071. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUpts-hpc60120180240300SE +/- 0.07, N = 3266.30MIN: 263.271. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUpts-hpc70140210280350SE +/- 0.55, N = 3341.08MIN: 338.541. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUpts-hpc80160240320400SE +/- 0.66, N = 3349.58MIN: 344.761. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUpts-hpc2004006008001000SE +/- 0.33, N = 3888.78MIN: 885.431. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUpts-hpc80160240320400SE +/- 0.07, N = 3348.91MIN: 347.121. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUpts-hpc170340510680850SE +/- 0.26, N = 3771.37MIN: 7671. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUpts-hpc130260390520650SE +/- 0.99, N = 3612.43MIN: 601.381. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUpts-hpc80160240320400SE +/- 0.24, N = 3375.87MIN: 374.291. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUpts-hpc50K100K150K200K250KSE +/- 134.13, N = 3216031MIN: 2156641. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUpts-hpc30K60K90K120K150KSE +/- 36.42, N = 3132806MIN: 1326901. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUpts-hpc50K100K150K200K250KSE +/- 20.22, N = 3215461MIN: 2153231. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUpts-hpc30K60K90K120K150KSE +/- 17.95, N = 3132819MIN: 1327101. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUpts-hpc50K100K150K200K250KSE +/- 24.27, N = 3215425MIN: 2152541. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUpts-hpc30K60K90K120K150KSE +/- 13.69, N = 3132815MIN: 1327191. (CXX) g++ options: -O3 -march=native -mcpu=native -fPIC -arch -isysroot

Mobile Neural Network

Model: nasnet

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: nasnetpts-hpc3691215SE +/- 0.13, N = 411.52MIN: 9.02 / MAX: 16.911. (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.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenetV3pts-hpc0.41060.82121.23181.64242.053SE +/- 0.013, N = 41.825MIN: 1.48 / MAX: 4.151. (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.orgms, Fewer Is BetterMobile Neural Network 2.1Model: squeezenetv1.1pts-hpc0.71981.43962.15942.87923.599SE +/- 0.048, N = 43.199MIN: 2.25 / MAX: 4.681. (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.orgms, Fewer Is BetterMobile Neural Network 2.1Model: resnet-v2-50pts-hpc612182430SE +/- 0.14, N = 425.08MIN: 20.97 / MAX: 29.291. (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.orgms, Fewer Is BetterMobile Neural Network 2.1Model: SqueezeNetV1.0pts-hpc1.24362.48723.73084.97446.218SE +/- 0.049, N = 45.527MIN: 4.29 / MAX: 7.171. (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.orgms, Fewer Is BetterMobile Neural Network 2.1Model: MobileNetV2_224pts-hpc0.81651.6332.44953.2664.0825SE +/- 0.021, N = 43.629MIN: 2.95 / MAX: 5.881. (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.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenet-v1-1.0pts-hpc1.04942.09883.14824.19765.247SE +/- 0.066, N = 44.664MIN: 3.82 / MAX: 6.81. (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.orgms, Fewer Is BetterMobile Neural Network 2.1Model: inception-v3pts-hpc816243240SE +/- 0.77, N = 435.28MIN: 29.23 / MAX: 39.491. (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.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mobilenetpts-hpc48121620SE +/- 0.04, N = 318.07MIN: 17.9 / MAX: 18.91. (CXX) g++ options: -O3 -arch -isysroot

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v2pts-hpc1.0442.0883.1324.1765.22SE +/- 0.04, N = 34.64MIN: 4.57 / MAX: 5.171. (CXX) g++ options: -O3 -arch -isysroot

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v3pts-hpc0.84831.69662.54493.39324.2415SE +/- 0.04, N = 33.77MIN: 3.72 / MAX: 4.121. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v2pts-hpc0.60531.21061.81592.42123.0265SE +/- 0.02, N = 32.69MIN: 2.65 / MAX: 3.211. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnetpts-hpc1.06432.12863.19294.25725.3215SE +/- 0.04, N = 34.73MIN: 4.67 / MAX: 5.21. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b0pts-hpc246810SE +/- 0.07, N = 37.59MIN: 7.48 / MAX: 8.331. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazefacepts-hpc0.1980.3960.5940.7920.99SE +/- 0.01, N = 30.88MIN: 0.86 / MAX: 1.011. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenetpts-hpc510152025SE +/- 0.18, N = 322.11MIN: 21.7 / MAX: 23.381. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg16pts-hpc1530456075SE +/- 0.56, N = 366.25MIN: 64.89 / MAX: 68.21. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet18pts-hpc48121620SE +/- 0.14, N = 314.85MIN: 14.54 / MAX: 15.61. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnetpts-hpc48121620SE +/- 0.13, N = 316.75MIN: 16.47 / MAX: 17.641. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet50pts-hpc918273645SE +/- 0.32, N = 340.62MIN: 39.97 / MAX: 41.551. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tinypts-hpc612182430SE +/- 0.04, N = 326.77MIN: 26.45 / MAX: 27.891. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssdpts-hpc48121620SE +/- 0.12, N = 313.80MIN: 13.33 / MAX: 14.611. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400mpts-hpc246810SE +/- 0.06, N = 36.44MIN: 6.35 / MAX: 7.031. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformerpts-hpc30060090012001500SE +/- 0.19, N = 31187.73MIN: 1186.86 / MAX: 1190.111. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDetpts-hpc0.47480.94961.42441.89922.374SE +/- 0.00, N = 32.11MIN: 2.1 / MAX: 2.341. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenetpts-hpc48121620SE +/- 0.01, N = 318.01MIN: 17.89 / MAX: 19.771. (CXX) g++ options: -O3 -arch -isysroot

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2pts-hpc1.03282.06563.09844.13125.164SE +/- 0.00, N = 34.59MIN: 4.57 / MAX: 5.111. (CXX) g++ options: -O3 -arch -isysroot

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3pts-hpc0.83931.67862.51793.35724.1965SE +/- 0.00, N = 33.73MIN: 3.71 / MAX: 4.091. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2pts-hpc0.59851.1971.79552.3942.9925SE +/- 0.00, N = 32.66MIN: 2.65 / MAX: 2.961. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnetpts-hpc1.05532.11063.16594.22125.2765SE +/- 0.00, N = 34.69MIN: 4.67 / MAX: 5.071. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0pts-hpc246810SE +/- 0.00, N = 37.51MIN: 7.48 / MAX: 8.211. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefacepts-hpc0.19580.39160.58740.78320.979SE +/- 0.00, N = 30.87MIN: 0.86 / MAX: 0.921. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenetpts-hpc510152025SE +/- 0.03, N = 321.91MIN: 21.46 / MAX: 22.991. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16pts-hpc1530456075SE +/- 0.04, N = 365.60MIN: 64.87 / MAX: 66.511. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18pts-hpc48121620SE +/- 0.01, N = 314.72MIN: 14.36 / MAX: 15.981. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnetpts-hpc48121620SE +/- 0.02, N = 316.59MIN: 16.45 / MAX: 17.391. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50pts-hpc918273645SE +/- 0.02, N = 340.27MIN: 39.89 / MAX: 41.051. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinypts-hpc612182430SE +/- 0.02, N = 326.71MIN: 26.45 / MAX: 28.291. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdpts-hpc48121620SE +/- 0.01, N = 313.69MIN: 13.56 / MAX: 14.551. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mpts-hpc246810SE +/- 0.00, N = 36.38MIN: 6.35 / MAX: 6.971. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformerpts-hpc30060090012001500SE +/- 0.23, N = 31187.42MIN: 1186.29 / MAX: 1189.541. (CXX) g++ options: -O3 -arch -isysroot

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDetpts-hpc0.47480.94961.42441.89922.374SE +/- 0.00, N = 32.11MIN: 2.1 / MAX: 2.211. (CXX) g++ options: -O3 -arch -isysroot

Phoronix Test Suite v10.8.4