HDR3-A44000-1

AMD A4-5300 APU testing with a ASRock FM2A88M-HD+ R3.0 (P1.50 BIOS) and AMD Radeon HD 7480D 256MB on Ubuntu 20.04 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 2402144-HERT-HDR3A4427
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
AMD Radeon HD 7480D - AMD A4-5300 APU
January 16
 
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

AMD Radeon HD 7480D - AMD A4-5300 APU

Processor: AMD A4-5300 APU @ 3.40GHz (1 Core / 2 Threads), Motherboard: ASRock FM2A88M-HD+ R3.0 (P1.50 BIOS), Chipset: AMD 15h, Memory: 4096MB, Disk: 1000GB Western Digital WDS100T2B0A, Graphics: AMD Radeon HD 7480D 256MB, Audio: AMD Trinity HDMI Audio, Monitor: G185BGEL01, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 20.04, Kernel: 5.15.0-89-generic (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.13, OpenGL: 4.3 Mesa 21.2.6 (LLVM 12.0.0), Vulkan: 1.1.182, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1368x768

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-9QDOt0/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x6001119
Python Notes: Python 3.8.10
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT vulnerable + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

HDR3-A44000-1OpenBenchmarking.orgPhoronix Test SuiteAMD A4-5300 APU @ 3.40GHz (1 Core / 2 Threads)ASRock FM2A88M-HD+ R3.0 (P1.50 BIOS)AMD 15h4096MB1000GB Western Digital WDS100T2B0AAMD Radeon HD 7480D 256MBAMD Trinity HDMI AudioG185BGEL01Realtek RTL8111/8168/8411Ubuntu 20.045.15.0-89-generic (x86_64)GNOME Shell 3.36.9X Server 1.20.134.3 Mesa 21.2.6 (LLVM 12.0.0)1.1.182GCC 9.4.0ext41368x768ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionHDR3-A44000-1 BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-9QDOt0/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x6001119 - Python 3.8.10- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT vulnerable + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

HDR3-A44000-1tensorflow: GPU - 64 - VGG-16tensorflow: CPU - 64 - VGG-16whisper-cpp: ggml-medium.en - 2016 State of the Uniontensorflow: GPU - 256 - GoogLeNettensorflow: GPU - 32 - VGG-16tensorflow: GPU - 512 - AlexNettensorflow: CPU - 256 - GoogLeNettensorflow: CPU - 32 - VGG-16tensorflow: GPU - 64 - ResNet-50tensorflow: CPU - 512 - AlexNettensorflow: CPU - 64 - ResNet-50tensorflow: GPU - 16 - VGG-16scikit-learn: Sparse Rand Projections / 100 Iterationswhisper-cpp: ggml-small.en - 2016 State of the Uniontensorflow: GPU - 256 - AlexNettensorflow: CPU - 16 - VGG-16tensorflow: CPU - 256 - AlexNettensorflow: GPU - 32 - ResNet-50tensorflow: CPU - 32 - ResNet-50pytorch: CPU - 64 - Efficientnet_v2_lpytorch: CPU - 32 - Efficientnet_v2_lpytorch: CPU - 256 - Efficientnet_v2_lpytorch: CPU - 512 - Efficientnet_v2_lpytorch: CPU - 16 - Efficientnet_v2_ltensorflow: GPU - 64 - GoogLeNettensorflow: CPU - 64 - GoogLeNetscikit-learn: Lassotensorflow: GPU - 16 - ResNet-50pytorch: CPU - 256 - ResNet-152pytorch: CPU - 64 - ResNet-152pytorch: CPU - 32 - ResNet-152pytorch: CPU - 16 - ResNet-152pytorch: CPU - 512 - ResNet-152whisper-cpp: ggml-base.en - 2016 State of the Unionscikit-learn: TSNE MNIST Datasetplaidml: No - Inference - VGG16 - CPUcaffe: GoogleNet - CPU - 1000tensorflow: GPU - 64 - AlexNettensorflow: CPU - 16 - ResNet-50mnn: inception-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224mnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: squeezenetv1.1mnn: mobilenetV3mnn: nasnettensorflow: GPU - 32 - GoogLeNetscikit-learn: SAGAnumenta-nab: KNN CADtensorflow: CPU - 64 - AlexNettensorflow: CPU - 32 - GoogLeNetscikit-learn: GLMpytorch: CPU - 1 - Efficientnet_v2_lplaidml: No - Inference - ResNet 50 - CPUtensorflow: GPU - 32 - AlexNetpytorch: CPU - 512 - ResNet-50pytorch: CPU - 256 - ResNet-50pytorch: CPU - 32 - ResNet-50pytorch: CPU - 64 - ResNet-50pytorch: CPU - 16 - ResNet-50caffe: AlexNet - CPU - 1000numenta-nab: Earthgecko Skylinetensorflow: GPU - 16 - GoogLeNetpytorch: CPU - 1 - ResNet-152scikit-learn: Covertype Dataset Benchmarktensorflow: CPU - 32 - AlexNetscikit-learn: Plot Lasso Pathonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUscikit-learn: LocalOutlierFactorscikit-learn: Hist Gradient Boosting Threadingscikit-learn: Plot Hierarchicaltensorflow: CPU - 16 - GoogLeNetncnn: CPU - FastestDetncnn: CPU - vision_transformerncnn: CPU - regnety_400mncnn: CPU - squeezenet_ssdncnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - alexnetncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenetncnn: Vulkan GPU - FastestDetncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetscikit-learn: Plot OMP vs. LARStensorflow: GPU - 16 - AlexNettensorflow: GPU - 1 - VGG-16tnn: CPU - DenseNetscikit-learn: Plot Singular Value Decompositionscikit-learn: Plot Polynomial Kernel Approximationscikit-learn: Kernel PCA Solvers / Time vs. N Samplestensorflow: CPU - 1 - VGG-16scikit-learn: Plot Neighborstensorflow: CPU - 16 - AlexNetcaffe: GoogleNet - CPU - 200scikit-learn: Hist Gradient Boostingscikit-learn: Hist Gradient Boosting Higgs Bosonscikit-learn: Feature Expansionsonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUnumpy: scikit-learn: SGD Regressionpytorch: CPU - 1 - ResNet-50scikit-learn: Sample Without Replacementnumenta-nab: Contextual Anomaly Detector OSEnumenta-nab: Bayesian Changepointscikit-learn: Kernel PCA Solvers / Time vs. N Componentsscikit-learn: Hist Gradient Boosting Adultcaffe: GoogleNet - CPU - 100scikit-learn: Sparsifytensorflow: GPU - 1 - ResNet-50caffe: AlexNet - CPU - 200deepspeech: CPUscikit-learn: Plot Wardscikit-learn: Treemlpack: scikit_icascikit-learn: MNIST Datasetnumenta-nab: Relative Entropytensorflow: CPU - 1 - ResNet-50scikit-learn: Text Vectorizersscikit-learn: Plot Incremental PCAcaffe: AlexNet - CPU - 100onnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelscikit-learn: 20 Newsgroups / Logistic Regressionopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUonnx: fcn-resnet101-11 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardtensorflow: GPU - 1 - AlexNetnumenta-nab: Windowed Gaussianscikit-learn: Hist Gradient Boosting Categorical Onlytensorflow: GPU - 1 - GoogLeNetonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUonnx: bertsquad-12 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Paralleltensorflow: CPU - 1 - AlexNetonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: GPT-2 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Standardonnx: super-resolution-10 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardtensorflow: CPU - 1 - GoogLeNetopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUrbenchmark: openvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUtensorflow-lite: Inception V4openvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUtensorflow-lite: Inception ResNet V2openvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16 - CPUtensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Quantopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUtensorflow-lite: Mobilenet Floattensorflow-lite: SqueezeNetopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUrnnoise: tnn: CPU - SqueezeNet v2tnn: CPU - MobileNet v2mlpack: scikit_svmtnn: CPU - SqueezeNet v1.1onednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUlczero: BLASAMD Radeon HD 7480D - AMD A4-5300 APU0.130.1544526.2960.950.132.441.260.160.323.050.460.139994.94413170.7862.200.163.030.410.540.280.280.280.280.281.231.531380.7770.420.410.410.410.410.413774.417332770.5380.5834370232.070.54595.92985.66850.31985.036405.11348.43112.278106.4871.242018.6572414.1532.951.541577.3100.541.061.921.001.001.001.001.0015300471471.1071.240.78967.6422.79934.039195189194900194775890.461880.981868.4441.5424.542052.6655.3875.22169.61211.7957.5483.34468.1696.466.8753.9434.2919.2129.6037.53125.1224.572051.9255.4075.02167.50212.5257.3083.48468.6396.636.8254.0534.1719.2629.6237.77125.24323.7641.720.1113327.611692.649675.766653.2630.14598.2172.42684725515.342425.392478.31599767.399770.999760.5115.29432.0621.93403.656503.698487.743359.541266.319342036253.9810.36304966345.29742226.357108.592276.28184.346237.6640.5170.970139.263154278448790.0222826107.64637092.160.0530168.30.03314740.96120.47775.9421.23861.050.25901614164.020.142418.630.4134582694.980.3710701.232509.260.3985251780.390.5616731456.610.686524173.2695.7712685.260211.7274458.4722.18125254.8853.92330481.2132.07812322.5963.09982141.7867.0534278.733512.70251.412838.520.710.72592731.010.7310520272733.080.73887469376.195.32797.132.51617.821.62543.241.84201.399.93440.484.54201.664.9631.8931.34125.6615.9111237411248167.4814.8248750.771429.72.74363.336.57151.7758.252156.806773.24444.21665.245337.93567.9815144.57245.657917.576275.3591172.562107.587553.90989.9328OpenBenchmarking.org

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 64 - Model: VGG-16AMD Radeon HD 7480D - AMD A4-5300 APU0.02930.05860.08790.11720.1465SE +/- 0.00, N = 30.13

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: VGG-16AMD Radeon HD 7480D - AMD A4-5300 APU0.03380.06760.10140.13520.169SE +/- 0.00, N = 30.15

Whisper.cpp

Whisper.cpp is a port of OpenAI's Whisper model in C/C++. Whisper.cpp is developed by Georgi Gerganov for transcribing WAV audio files to text / speech recognition. Whisper.cpp supports ARM NEON, x86 AVX, and other advanced CPU features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.4Model: ggml-medium.en - Input: 2016 State of the UnionAMD Radeon HD 7480D - AMD A4-5300 APU10K20K30K40K50KSE +/- 19.06, N = 344526.301. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 256 - Model: GoogLeNetAMD Radeon HD 7480D - AMD A4-5300 APU0.21380.42760.64140.85521.069SE +/- 0.01, N = 30.95

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 32 - Model: VGG-16AMD Radeon HD 7480D - AMD A4-5300 APU0.02930.05860.08790.11720.1465SE +/- 0.00, N = 30.13

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 512 - Model: AlexNetAMD Radeon HD 7480D - AMD A4-5300 APU0.5491.0981.6472.1962.745SE +/- 0.00, N = 32.44

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: GoogLeNetAMD Radeon HD 7480D - AMD A4-5300 APU0.28350.5670.85051.1341.4175SE +/- 0.01, N = 31.26

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: VGG-16AMD Radeon HD 7480D - AMD A4-5300 APU0.0360.0720.1080.1440.18SE +/- 0.00, N = 30.16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 64 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.0720.1440.2160.2880.36SE +/- 0.01, N = 30.32

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: AlexNetAMD Radeon HD 7480D - AMD A4-5300 APU0.68631.37262.05892.74523.4315SE +/- 0.01, N = 33.05

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.10350.2070.31050.4140.5175SE +/- 0.00, N = 30.46

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 16 - Model: VGG-16AMD Radeon HD 7480D - AMD A4-5300 APU0.02930.05860.08790.11720.1465SE +/- 0.00, N = 30.13

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Sparse Random Projections / 100 IterationsAMD Radeon HD 7480D - AMD A4-5300 APU2K4K6K8K10KSE +/- 13.81, N = 39994.941. (F9X) gfortran options: -O0

Whisper.cpp

Whisper.cpp is a port of OpenAI's Whisper model in C/C++. Whisper.cpp is developed by Georgi Gerganov for transcribing WAV audio files to text / speech recognition. Whisper.cpp supports ARM NEON, x86 AVX, and other advanced CPU features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.4Model: ggml-small.en - Input: 2016 State of the UnionAMD Radeon HD 7480D - AMD A4-5300 APU3K6K9K12K15KSE +/- 2.89, N = 313170.791. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 256 - Model: AlexNetAMD Radeon HD 7480D - AMD A4-5300 APU0.4950.991.4851.982.475SE +/- 0.02, N = 32.20

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: VGG-16AMD Radeon HD 7480D - AMD A4-5300 APU0.0360.0720.1080.1440.18SE +/- 0.00, N = 30.16

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: AlexNetAMD Radeon HD 7480D - AMD A4-5300 APU0.68181.36362.04542.72723.409SE +/- 0.00, N = 33.03

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 32 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.09230.18460.27690.36920.4615SE +/- 0.00, N = 30.41

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.12150.2430.36450.4860.6075SE +/- 0.00, N = 30.54

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Currently this test profile is catered to CPU-based testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_lAMD Radeon HD 7480D - AMD A4-5300 APU0.0630.1260.1890.2520.315SE +/- 0.00, N = 30.28MIN: 0.17

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_lAMD Radeon HD 7480D - AMD A4-5300 APU0.0630.1260.1890.2520.315SE +/- 0.00, N = 30.28MIN: 0.27

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_lAMD Radeon HD 7480D - AMD A4-5300 APU0.0630.1260.1890.2520.315SE +/- 0.00, N = 30.28MIN: 0.27

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_lAMD Radeon HD 7480D - AMD A4-5300 APU0.0630.1260.1890.2520.315SE +/- 0.00, N = 30.28MIN: 0.24

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_lAMD Radeon HD 7480D - AMD A4-5300 APU0.0630.1260.1890.2520.315SE +/- 0.00, N = 30.28MIN: 0.27

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 64 - Model: GoogLeNetAMD Radeon HD 7480D - AMD A4-5300 APU0.27680.55360.83041.10721.384SE +/- 0.00, N = 31.23

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

Benchmark: SGDOneClassSVM

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

Benchmark: Isolation Forest

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: GoogLeNetAMD Radeon HD 7480D - AMD A4-5300 APU0.34430.68861.03291.37721.7215SE +/- 0.00, N = 31.53

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: LassoAMD Radeon HD 7480D - AMD A4-5300 APU30060090012001500SE +/- 26.21, N = 91380.781. (F9X) gfortran options: -O0

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 16 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.09450.1890.28350.3780.4725SE +/- 0.01, N = 30.42

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Currently this test profile is catered to CPU-based testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-152AMD Radeon HD 7480D - AMD A4-5300 APU0.09230.18460.27690.36920.4615SE +/- 0.00, N = 30.41MIN: 0.39

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-152AMD Radeon HD 7480D - AMD A4-5300 APU0.09230.18460.27690.36920.4615SE +/- 0.00, N = 30.41MIN: 0.4

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-152AMD Radeon HD 7480D - AMD A4-5300 APU0.09230.18460.27690.36920.4615SE +/- 0.00, N = 30.41MIN: 0.35

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-152AMD Radeon HD 7480D - AMD A4-5300 APU0.09230.18460.27690.36920.4615SE +/- 0.00, N = 30.41MIN: 0.39

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-152AMD Radeon HD 7480D - AMD A4-5300 APU0.09230.18460.27690.36920.4615SE +/- 0.00, N = 30.41MIN: 0.37

Whisper.cpp

Whisper.cpp is a port of OpenAI's Whisper model in C/C++. Whisper.cpp is developed by Georgi Gerganov for transcribing WAV audio files to text / speech recognition. Whisper.cpp supports ARM NEON, x86 AVX, and other advanced CPU features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWhisper.cpp 1.4Model: ggml-base.en - Input: 2016 State of the UnionAMD Radeon HD 7480D - AMD A4-5300 APU8001600240032004000SE +/- 0.69, N = 33774.421. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: TSNE MNIST DatasetAMD Radeon HD 7480D - AMD A4-5300 APU6001200180024003000SE +/- 10.33, N = 32770.541. (F9X) gfortran options: -O0

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.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU0.13050.2610.39150.5220.6525SE +/- 0.01, N = 30.58

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 1000AMD Radeon HD 7480D - AMD A4-5300 APU700K1400K2100K2800K3500KSE +/- 10164.98, N = 334370231. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 64 - Model: AlexNetAMD Radeon HD 7480D - AMD A4-5300 APU0.46580.93161.39741.86322.329SE +/- 0.01, N = 32.07

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.12150.2430.36450.4860.6075SE +/- 0.00, N = 30.54

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.orgms, Fewer Is BetterMobile Neural Network 2.1Model: inception-v3AMD Radeon HD 7480D - AMD A4-5300 APU130260390520650SE +/- 0.11, N = 3595.93MIN: 593.63 / MAX: 678.311. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenet-v1-1.0AMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.08, N = 385.67MIN: 85.16 / MAX: 141.991. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: MobileNetV2_224AMD Radeon HD 7480D - AMD A4-5300 APU1122334455SE +/- 0.07, N = 350.32MIN: 49.96 / MAX: 70.931. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: SqueezeNetV1.0AMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.04, N = 385.04MIN: 84.34 / MAX: 199.751. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: resnet-v2-50AMD Radeon HD 7480D - AMD A4-5300 APU90180270360450SE +/- 0.22, N = 3405.11MIN: 402.84 / MAX: 630.911. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: squeezenetv1.1AMD Radeon HD 7480D - AMD A4-5300 APU1122334455SE +/- 0.01, N = 348.43MIN: 47.97 / MAX: 71.731. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenetV3AMD Radeon HD 7480D - AMD A4-5300 APU3691215SE +/- 0.01, N = 312.28MIN: 12.2 / MAX: 33.21. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: nasnetAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.03, N = 3106.49MIN: 106.03 / MAX: 179.41. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 32 - Model: GoogLeNetAMD Radeon HD 7480D - AMD A4-5300 APU0.2790.5580.8371.1161.395SE +/- 0.00, N = 31.24

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: SAGAAMD Radeon HD 7480D - AMD A4-5300 APU400800120016002000SE +/- 2.44, N = 32018.661. (F9X) gfortran options: -O0

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 time-series 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.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: KNN CADAMD Radeon HD 7480D - AMD A4-5300 APU5001000150020002500SE +/- 18.90, N = 32414.15

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: AlexNetAMD Radeon HD 7480D - AMD A4-5300 APU0.66381.32761.99142.65523.319SE +/- 0.00, N = 32.95

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

Benchmark: Plot Fast KMeans

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: GoogLeNetAMD Radeon HD 7480D - AMD A4-5300 APU0.34650.6931.03951.3861.7325SE +/- 0.00, N = 31.54

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: GLMAMD Radeon HD 7480D - AMD A4-5300 APU30060090012001500SE +/- 6.96, N = 31577.311. (F9X) gfortran options: -O0

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Currently this test profile is catered to CPU-based testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_lAMD Radeon HD 7480D - AMD A4-5300 APU0.12150.2430.36450.4860.6075SE +/- 0.00, N = 30.54MIN: 0.41

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.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU0.23850.4770.71550.9541.1925SE +/- 0.00, N = 31.06

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 32 - Model: AlexNetAMD Radeon HD 7480D - AMD A4-5300 APU0.4320.8641.2961.7282.16SE +/- 0.00, N = 31.92

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Currently this test profile is catered to CPU-based testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.2250.450.6750.91.125SE +/- 0.00, N = 31.00MIN: 0.95

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.2250.450.6750.91.125SE +/- 0.00, N = 31.00MIN: 0.95 / MAX: 1.01

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.2250.450.6750.91.125SE +/- 0.00, N = 31.00MIN: 0.94 / MAX: 1.01

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.2250.450.6750.91.125SE +/- 0.00, N = 31.00MIN: 0.94 / MAX: 1.01

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.2250.450.6750.91.125SE +/- 0.00, N = 31.00MIN: 0.96 / MAX: 1.01

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 1000AMD Radeon HD 7480D - AMD A4-5300 APU300K600K900K1200K1500KSE +/- 4458.54, N = 315300471. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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 time-series 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.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko SkylineAMD Radeon HD 7480D - AMD A4-5300 APU30060090012001500SE +/- 0.62, N = 31471.11

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 16 - Model: GoogLeNetAMD Radeon HD 7480D - AMD A4-5300 APU0.2790.5580.8371.1161.395SE +/- 0.00, N = 31.24

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Currently this test profile is catered to CPU-based testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-152AMD Radeon HD 7480D - AMD A4-5300 APU0.17550.3510.52650.7020.8775SE +/- 0.00, N = 30.78MIN: 0.75 / MAX: 0.79

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Covertype Dataset BenchmarkAMD Radeon HD 7480D - AMD A4-5300 APU2004006008001000SE +/- 2.14, N = 3967.641. (F9X) gfortran options: -O0

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: AlexNetAMD Radeon HD 7480D - AMD A4-5300 APU0.62781.25561.88342.51123.139SE +/- 0.00, N = 32.79

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Lasso PathAMD Radeon HD 7480D - AMD A4-5300 APU2004006008001000SE +/- 2.52, N = 3934.041. (F9X) gfortran options: -O0

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU40K80K120K160K200KSE +/- 399.73, N = 3195189MIN: 1946471. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU40K80K120K160K200KSE +/- 82.44, N = 3194900MIN: 1946591. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU40K80K120K160K200KSE +/- 25.17, N = 3194775MIN: 1946471. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: LocalOutlierFactorAMD Radeon HD 7480D - AMD A4-5300 APU2004006008001000SE +/- 0.76, N = 3890.461. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boosting ThreadingAMD Radeon HD 7480D - AMD A4-5300 APU2004006008001000SE +/- 2.64, N = 3880.981. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot HierarchicalAMD Radeon HD 7480D - AMD A4-5300 APU2004006008001000SE +/- 0.94, N = 3868.441. (F9X) gfortran options: -O0

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: GoogLeNetAMD Radeon HD 7480D - AMD A4-5300 APU0.34650.6931.03951.3861.7325SE +/- 0.00, N = 31.54

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDetAMD Radeon HD 7480D - AMD A4-5300 APU612182430SE +/- 0.04, N = 324.54MIN: 24.3 / MAX: 28.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformerAMD Radeon HD 7480D - AMD A4-5300 APU400800120016002000SE +/- 0.96, N = 32052.66MIN: 2035.51 / MAX: 2225.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400mAMD Radeon HD 7480D - AMD A4-5300 APU1224364860SE +/- 0.06, N = 355.38MIN: 55.12 / MAX: 75.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssdAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.01, N = 375.22MIN: 74.02 / MAX: 92.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tinyAMD Radeon HD 7480D - AMD A4-5300 APU4080120160200SE +/- 2.29, N = 3169.61MIN: 164.59 / MAX: 328.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet50AMD Radeon HD 7480D - AMD A4-5300 APU50100150200250SE +/- 0.03, N = 3211.79MIN: 210.17 / MAX: 231.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnetAMD Radeon HD 7480D - AMD A4-5300 APU1326395265SE +/- 0.17, N = 357.54MIN: 56.63 / MAX: 124.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet18AMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.06, N = 383.34MIN: 82.25 / MAX: 102.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg16AMD Radeon HD 7480D - AMD A4-5300 APU100200300400500SE +/- 0.38, N = 3468.16MIN: 460.53 / MAX: 519.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenetAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.06, N = 396.46MIN: 95.49 / MAX: 101.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazefaceAMD Radeon HD 7480D - AMD A4-5300 APU246810SE +/- 0.05, N = 36.87MIN: 6.71 / MAX: 11.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b0AMD Radeon HD 7480D - AMD A4-5300 APU1224364860SE +/- 0.03, N = 353.94MIN: 53.62 / MAX: 56.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnetAMD Radeon HD 7480D - AMD A4-5300 APU816243240SE +/- 0.06, N = 334.29MIN: 33.97 / MAX: 54.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v2AMD Radeon HD 7480D - AMD A4-5300 APU510152025SE +/- 0.08, N = 319.21MIN: 18.95 / MAX: 22.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v3AMD Radeon HD 7480D - AMD A4-5300 APU714212835SE +/- 0.02, N = 329.60MIN: 29.42 / MAX: 32.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v2AMD Radeon HD 7480D - AMD A4-5300 APU918273645SE +/- 0.16, N = 337.53MIN: 37.07 / MAX: 154.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mobilenetAMD Radeon HD 7480D - AMD A4-5300 APU306090120150SE +/- 0.02, N = 3125.12MIN: 124.4 / MAX: 145.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDetAMD Radeon HD 7480D - AMD A4-5300 APU612182430SE +/- 0.04, N = 324.57MIN: 24.27 / MAX: 48.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformerAMD Radeon HD 7480D - AMD A4-5300 APU400800120016002000SE +/- 1.81, N = 32051.92MIN: 2035.28 / MAX: 2279.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mAMD Radeon HD 7480D - AMD A4-5300 APU1224364860SE +/- 0.05, N = 355.40MIN: 55.12 / MAX: 75.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.05, N = 375.02MIN: 74.15 / MAX: 93.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinyAMD Radeon HD 7480D - AMD A4-5300 APU4080120160200SE +/- 0.12, N = 3167.50MIN: 164.33 / MAX: 258.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50AMD Radeon HD 7480D - AMD A4-5300 APU50100150200250SE +/- 0.61, N = 3212.52MIN: 209.71 / MAX: 320.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnetAMD Radeon HD 7480D - AMD A4-5300 APU1326395265SE +/- 0.13, N = 357.30MIN: 56.5 / MAX: 76.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18AMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.09, N = 383.48MIN: 82.54 / MAX: 87.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16AMD Radeon HD 7480D - AMD A4-5300 APU100200300400500SE +/- 0.11, N = 3468.63MIN: 461.07 / MAX: 486.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenetAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.05, N = 396.63MIN: 95.66 / MAX: 117.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefaceAMD Radeon HD 7480D - AMD A4-5300 APU246810SE +/- 0.01, N = 36.82MIN: 6.73 / MAX: 7.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0AMD Radeon HD 7480D - AMD A4-5300 APU1224364860SE +/- 0.08, N = 354.05MIN: 53.64 / MAX: 73.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnetAMD Radeon HD 7480D - AMD A4-5300 APU816243240SE +/- 0.07, N = 334.17MIN: 33.92 / MAX: 54.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2AMD Radeon HD 7480D - AMD A4-5300 APU510152025SE +/- 0.03, N = 319.26MIN: 19.06 / MAX: 22.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3AMD Radeon HD 7480D - AMD A4-5300 APU714212835SE +/- 0.05, N = 329.62MIN: 29.43 / MAX: 32.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2AMD Radeon HD 7480D - AMD A4-5300 APU918273645SE +/- 0.34, N = 337.77MIN: 37.2 / MAX: 126.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenetAMD Radeon HD 7480D - AMD A4-5300 APU306090120150SE +/- 0.09, N = 3125.24MIN: 124.32 / MAX: 145.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot OMP vs. LARSAMD Radeon HD 7480D - AMD A4-5300 APU70140210280350SE +/- 4.73, N = 9323.761. (F9X) gfortran options: -O0

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 16 - Model: AlexNetAMD Radeon HD 7480D - AMD A4-5300 APU0.3870.7741.1611.5481.935SE +/- 0.00, N = 31.72

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 1 - Model: VGG-16AMD Radeon HD 7480D - AMD A4-5300 APU0.02480.04960.07440.09920.124SE +/- 0.00, N = 30.11

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetAMD Radeon HD 7480D - AMD A4-5300 APU3K6K9K12K15KSE +/- 4.76, N = 313327.61MIN: 13283.5 / MAX: 13593.981. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Singular Value DecompositionAMD Radeon HD 7480D - AMD A4-5300 APU150300450600750SE +/- 0.98, N = 3692.651. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Polynomial Kernel ApproximationAMD Radeon HD 7480D - AMD A4-5300 APU150300450600750SE +/- 4.14, N = 3675.771. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Kernel PCA Solvers / Time vs. N SamplesAMD Radeon HD 7480D - AMD A4-5300 APU140280420560700SE +/- 4.91, N = 3653.261. (F9X) gfortran options: -O0

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 1 - Model: VGG-16AMD Radeon HD 7480D - AMD A4-5300 APU0.03150.0630.09450.1260.1575SE +/- 0.00, N = 30.14

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot NeighborsAMD Radeon HD 7480D - AMD A4-5300 APU130260390520650SE +/- 3.54, N = 3598.221. (F9X) gfortran options: -O0

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: AlexNetAMD Radeon HD 7480D - AMD A4-5300 APU0.54451.0891.63352.1782.7225SE +/- 0.01, N = 32.42

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 200AMD Radeon HD 7480D - AMD A4-5300 APU150K300K450K600K750KSE +/- 731.89, N = 36847251. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient BoostingAMD Radeon HD 7480D - AMD A4-5300 APU110220330440550SE +/- 0.99, N = 3515.341. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boosting Higgs BosonAMD Radeon HD 7480D - AMD A4-5300 APU90180270360450SE +/- 0.82, N = 3425.391. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Feature ExpansionsAMD Radeon HD 7480D - AMD A4-5300 APU100200300400500SE +/- 0.39, N = 3478.321. (F9X) gfortran options: -O0

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU20K40K60K80K100KSE +/- 36.42, N = 399767.3MIN: 996521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU20K40K60K80K100KSE +/- 12.62, N = 399770.9MIN: 99677.51. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU20K40K60K80K100KSE +/- 13.13, N = 399760.5MIN: 99635.11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkAMD Radeon HD 7480D - AMD A4-5300 APU306090120150SE +/- 0.80, N = 3115.29

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: SGD RegressionAMD Radeon HD 7480D - AMD A4-5300 APU90180270360450SE +/- 5.56, N = 3432.061. (F9X) gfortran options: -O0

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Currently this test profile is catered to CPU-based testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.43430.86861.30291.73722.1715SE +/- 0.00, N = 31.93MIN: 1.8 / MAX: 1.95

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

Benchmark: Isotonic / Logistic

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Sample Without ReplacementAMD Radeon HD 7480D - AMD A4-5300 APU90180270360450SE +/- 2.19, N = 3403.661. (F9X) gfortran options: -O0

Benchmark: Isotonic / Perturbed Logarithm

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

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 time-series 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.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Contextual Anomaly Detector OSEAMD Radeon HD 7480D - AMD A4-5300 APU110220330440550SE +/- 0.63, N = 3503.70

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian ChangepointAMD Radeon HD 7480D - AMD A4-5300 APU110220330440550SE +/- 0.36, N = 3487.74

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

Device: GPU - Batch Size: 256 - Model: VGG-16

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Kernel PCA Solvers / Time vs. N ComponentsAMD Radeon HD 7480D - AMD A4-5300 APU80160240320400SE +/- 4.01, N = 3359.541. (F9X) gfortran options: -O0

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

Benchmark: scikit_qda

AMD Radeon HD 7480D - AMD A4-5300 APU: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

Benchmark: scikit_linearridgeregression

AMD Radeon HD 7480D - AMD A4-5300 APU: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

Benchmark: Isotonic / Pathological

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boosting AdultAMD Radeon HD 7480D - AMD A4-5300 APU60120180240300SE +/- 1.72, N = 3266.321. (F9X) gfortran options: -O0

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100AMD Radeon HD 7480D - AMD A4-5300 APU70K140K210K280K350KSE +/- 501.40, N = 33420361. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: SparsifyAMD Radeon HD 7480D - AMD A4-5300 APU60120180240300SE +/- 0.08, N = 3253.981. (F9X) gfortran options: -O0

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 1 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.0810.1620.2430.3240.405SE +/- 0.00, N = 30.36

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 200AMD Radeon HD 7480D - AMD A4-5300 APU70K140K210K280K350KSE +/- 1163.57, N = 33049661. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUAMD Radeon HD 7480D - AMD A4-5300 APU80160240320400SE +/- 0.51, N = 3345.30

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot WardAMD Radeon HD 7480D - AMD A4-5300 APU50100150200250SE +/- 0.90, N = 3226.361. (F9X) gfortran options: -O0

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: TreeAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 1.00, N = 7108.591. (F9X) gfortran options: -O0

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaAMD Radeon HD 7480D - AMD A4-5300 APU60120180240300SE +/- 1.66, N = 3276.28

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: MNIST DatasetAMD Radeon HD 7480D - AMD A4-5300 APU4080120160200SE +/- 0.09, N = 3184.351. (F9X) gfortran options: -O0

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 time-series 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.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative EntropyAMD Radeon HD 7480D - AMD A4-5300 APU50100150200250SE +/- 1.03, N = 3237.66

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 1 - Model: ResNet-50AMD Radeon HD 7480D - AMD A4-5300 APU0.11250.2250.33750.450.5625SE +/- 0.00, N = 30.5

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Text VectorizersAMD Radeon HD 7480D - AMD A4-5300 APU4080120160200SE +/- 0.31, N = 3170.971. (F9X) gfortran options: -O0

Benchmark: Plot Non-Negative Matrix Factorization

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: KeyError:

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

Device: GPU - Batch Size: 512 - Model: VGG-16

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Plot Incremental PCAAMD Radeon HD 7480D - AMD A4-5300 APU306090120150SE +/- 0.05, N = 3139.261. (F9X) gfortran options: -O0

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100AMD Radeon HD 7480D - AMD A4-5300 APU30K60K90K120K150KSE +/- 2160.02, N = 31542781. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU10K20K30K40K50KSE +/- 164.20, N = 3448791. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU0.0050.010.0150.020.025SE +/- 0.0000818, N = 30.02228261. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU10K20K30K40K50KSE +/- 164.20, N = 3448791. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: 20 Newsgroups / Logistic RegressionAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.16, N = 3107.651. (F9X) gfortran options: -O0

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU8K16K24K32K40KSE +/- 19.71, N = 337092.16MIN: 37021.83 / MAX: 37160.981. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU0.01130.02260.03390.04520.0565SE +/- 0.00, N = 30.051. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

Device: GPU - Batch Size: 512 - Model: GoogLeNet

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU6K12K18K24K30KSE +/- 17.19, N = 330168.31. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU0.00750.0150.02250.030.0375SE +/- 0.0000189, N = 30.03314741. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU6K12K18K24K30KSE +/- 17.19, N = 330168.31. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

Device: CPU - Batch Size: 512 - Model: VGG-16

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: Fatal Python error: Aborted

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 1 - Model: AlexNetAMD Radeon HD 7480D - AMD A4-5300 APU0.2160.4320.6480.8641.08SE +/- 0.00, N = 30.96

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 time-series 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.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed GaussianAMD Radeon HD 7480D - AMD A4-5300 APU306090120150SE +/- 0.04, N = 3120.48

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

Device: CPU - Batch Size: 512 - Model: GoogLeNet

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

Device: GPU - Batch Size: 512 - Model: ResNet-50

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.2.2Benchmark: Hist Gradient Boosting Categorical OnlyAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.49, N = 375.941. (F9X) gfortran options: -O0

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: GPU - Batch Size: 1 - Model: GoogLeNetAMD Radeon HD 7480D - AMD A4-5300 APU0.270.540.811.081.35SE +/- 0.00, N = 31.2

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU8001600240032004000SE +/- 23.57, N = 33861.051. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU0.05830.11660.17490.23320.2915SE +/- 0.001579, N = 30.2590161. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU8001600240032004000SE +/- 23.57, N = 33861.051. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU3K6K9K12K15KSE +/- 11.78, N = 314164.02MIN: 14070.93 / MAX: 14376.21. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU0.03150.0630.09450.1260.1575SE +/- 0.00, N = 30.141. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU5001000150020002500SE +/- 3.12, N = 32418.631. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU0.0930.1860.2790.3720.465SE +/- 0.000533, N = 30.4134581. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: bertsquad-12 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU5001000150020002500SE +/- 3.12, N = 32418.631. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU6001200180024003000SE +/- 10.14, N = 32694.981. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU0.08350.1670.25050.3340.4175SE +/- 0.001392, N = 30.3710701. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU6001200180024003000SE +/- 10.14, N = 32694.981. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 1 - Model: AlexNetAMD Radeon HD 7480D - AMD A4-5300 APU0.27680.55360.83041.10721.384SE +/- 0.01, N = 31.23

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU5001000150020002500SE +/- 2.94, N = 32509.261. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU0.08970.17940.26910.35880.4485SE +/- 0.000467, N = 30.3985251. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU5001000150020002500SE +/- 2.94, N = 32509.261. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU400800120016002000SE +/- 0.75, N = 31780.391. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU0.12640.25280.37920.50560.632SE +/- 0.000238, N = 30.5616731. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU400800120016002000SE +/- 0.75, N = 31780.391. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU30060090012001500SE +/- 0.26, N = 31456.611. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU0.15450.3090.46350.6180.7725SE +/- 0.000122, N = 30.6865241. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU30060090012001500SE +/- 0.26, N = 31456.611. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU4080120160200SE +/- 0.82, N = 3173.271. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU1.29852.5973.89555.1946.4925SE +/- 0.02732, N = 35.771261. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU4080120160200SE +/- 0.82, N = 3173.271. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

Device: GPU - Batch Size: 256 - Model: ResNet-50

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.19, N = 385.261. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU3691215SE +/- 0.03, N = 311.731. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.19, N = 385.261. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU100200300400500SE +/- 2.34, N = 3458.471. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU0.49080.98161.47241.96322.454SE +/- 0.01117, N = 32.181251. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU100200300400500SE +/- 2.34, N = 3458.471. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU60120180240300SE +/- 0.08, N = 3254.891. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU0.88271.76542.64813.53084.4135SE +/- 0.00128, N = 33.923301. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU60120180240300SE +/- 0.08, N = 3254.891. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU100200300400500SE +/- 1.88, N = 3481.211. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU0.46760.93521.40281.87042.338SE +/- 0.00808, N = 32.078121. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU100200300400500SE +/- 1.88, N = 3481.211. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU70140210280350SE +/- 0.45, N = 3322.601. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU0.69751.3952.09252.793.4875SE +/- 0.00435, N = 33.099821. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: super-resolution-10 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU70140210280350SE +/- 0.45, N = 3322.601. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU306090120150SE +/- 1.00, N = 3141.791. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU246810SE +/- 0.04967, N = 37.053421. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelAMD Radeon HD 7480D - AMD A4-5300 APU306090120150SE +/- 1.00, N = 3141.791. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.68, N = 378.731. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU3691215SE +/- 0.11, N = 312.701. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.68, N = 378.731. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 1 - Model: GoogLeNetAMD Radeon HD 7480D - AMD A4-5300 APU0.31730.63460.95191.26921.5865SE +/- 0.00, N = 31.41

Device: CPU - Batch Size: 256 - Model: ResNet-50

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

Device: CPU - Batch Size: 512 - Model: ResNet-50

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU6001200180024003000SE +/- 6.10, N = 32838.52MIN: 2792.37 / MAX: 2889.041. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU0.15980.31960.47940.63920.799SE +/- 0.00, N = 30.711. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

R Benchmark

This test is a quick-running survey of general R performance Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterR BenchmarkAMD Radeon HD 7480D - AMD A4-5300 APU0.16330.32660.48990.65320.8165SE +/- 0.0024, N = 30.72591. R scripting front-end version 3.6.3 (2020-02-29)

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU6001200180024003000SE +/- 4.21, N = 32731.01MIN: 2664.5 / MAX: 2816.891. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU0.16430.32860.49290.65720.8215SE +/- 0.00, N = 30.731. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4AMD Radeon HD 7480D - AMD A4-5300 APU200K400K600K800K1000KSE +/- 496.53, N = 31052027

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU6001200180024003000SE +/- 0.78, N = 32733.08MIN: 2534.79 / MAX: 2876.111. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU0.16430.32860.49290.65720.8215SE +/- 0.00, N = 30.731. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2AMD Radeon HD 7480D - AMD A4-5300 APU200K400K600K800K1000KSE +/- 1407.00, N = 3887469

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU80160240320400SE +/- 0.70, N = 3376.19MIN: 361.34 / MAX: 438.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU1.1972.3943.5914.7885.985SE +/- 0.01, N = 35.321. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU2004006008001000SE +/- 1.03, N = 3797.13MIN: 783.45 / MAX: 824.81. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU0.56481.12961.69442.25922.824SE +/- 0.00, N = 32.511. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU130260390520650SE +/- 3.13, N = 3617.82MIN: 609.44 / MAX: 701.51. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU0.36450.7291.09351.4581.8225SE +/- 0.01, N = 31.621. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU120240360480600SE +/- 4.24, N = 3543.24MIN: 531.59 / MAX: 560.621. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU0.4140.8281.2421.6562.07SE +/- 0.02, N = 31.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU4080120160200SE +/- 0.19, N = 3201.39MIN: 170.9 / MAX: 239.11. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU3691215SE +/- 0.01, N = 39.931. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU100200300400500SE +/- 1.06, N = 3440.48MIN: 309.01 / MAX: 462.461. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU1.02152.0433.06454.0865.1075SE +/- 0.01, N = 34.541. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU4080120160200SE +/- 0.04, N = 3201.66MIN: 199.95 / MAX: 218.321. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU1.1162.2323.3484.4645.58SE +/- 0.00, N = 34.961. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU714212835SE +/- 0.08, N = 331.89MIN: 31.61 / MAX: 48.041. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU714212835SE +/- 0.08, N = 331.341. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU306090120150SE +/- 0.03, N = 3125.66MIN: 87.26 / MAX: 149.971. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU48121620SE +/- 0.00, N = 315.911. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet MobileAMD Radeon HD 7480D - AMD A4-5300 APU20K40K60K80K100KSE +/- 99.04, N = 3112374

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet QuantAMD Radeon HD 7480D - AMD A4-5300 APU20K40K60K80K100KSE +/- 22.07, N = 3112481

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU1530456075SE +/- 0.06, N = 367.48MIN: 67.13 / MAX: 101.951. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU48121620SE +/- 0.01, N = 314.821. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet FloatAMD Radeon HD 7480D - AMD A4-5300 APU10K20K30K40K50KSE +/- 133.56, N = 348750.7

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetAMD Radeon HD 7480D - AMD A4-5300 APU15K30K45K60K75KSE +/- 219.63, N = 371429.7

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU0.61651.2331.84952.4663.0825SE +/- 0.01, N = 32.74MIN: 2.69 / MAX: 18.761. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU80160240320400SE +/- 1.05, N = 3363.331. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU246810SE +/- 0.02, N = 36.57MIN: 6.46 / MAX: 50.051. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUAMD Radeon HD 7480D - AMD A4-5300 APU306090120150SE +/- 0.46, N = 3151.771. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

RNNoise

RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28AMD Radeon HD 7480D - AMD A4-5300 APU1326395265SE +/- 0.12, N = 358.251. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2AMD Radeon HD 7480D - AMD A4-5300 APU306090120150SE +/- 1.02, N = 15156.81MIN: 153.19 / MAX: 171.691. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

Device: CPU - Batch Size: 256 - Model: VGG-16

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: Fatal Python error: Aborted

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2AMD Radeon HD 7480D - AMD A4-5300 APU170340510680850SE +/- 0.74, N = 3773.24MIN: 764.76 / MAX: 783.51. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmAMD Radeon HD 7480D - AMD A4-5300 APU1020304050SE +/- 0.10, N = 344.21

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1AMD Radeon HD 7480D - AMD A4-5300 APU140280420560700SE +/- 1.32, N = 3665.25MIN: 661.66 / MAX: 675.361. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

Test: DNN - Deep Neural Network

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: [ERROR:0@0.003] global persistence.cpp:505 open Can't open file: '/opencv_extra-4.7.0/testdata/perf/dnn.xml' in read mode

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

Benchmark: RCV1 Logreg Convergencet

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: IndexError: list index out of range

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU70140210280350SE +/- 0.63, N = 3337.94MIN: 335.231. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU1530456075SE +/- 0.06, N = 367.98MIN: 67.541. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU306090120150SE +/- 0.76, N = 3144.57MIN: 141.661. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU1020304050SE +/- 0.08, N = 345.66MIN: 45.21. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU48121620SE +/- 0.05, N = 317.58MIN: 17.011. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.21, N = 375.36MIN: 74.721. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU4080120160200SE +/- 0.22, N = 3172.56MIN: 171.821. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.13, N = 3107.59MIN: 107.091. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU120240360480600SE +/- 0.04, N = 3553.91MIN: 553.311. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUAMD Radeon HD 7480D - AMD A4-5300 APU20406080100SE +/- 0.08, N = 389.93MIN: 89.441. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

Benchmark: Plot Parallel Pairwise

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: numpy.core._exceptions.MemoryError: Unable to allocate 74.5 GiB for an array with shape (100000, 100000) and data type float64

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

Model: Person Vehicle Bike Detection FP16 - Device: CPU

AMD Radeon HD 7480D - AMD A4-5300 APU: 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.

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

AI Benchmark Alpha

AI Benchmark Alpha is a Python library for evaluating artificial intelligence (AI) performance on diverse hardware platforms and relies upon the TensorFlow machine learning library. Learn more via the OpenBenchmarking.org test page.

AMD Radeon HD 7480D - AMD A4-5300 APU: The test quit with a non-zero exit status. E: AttributeError: module 'numpy' has no attribute 'typeDict'

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Scikit-Learn

Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.

Benchmark: Glmnet

AMD Radeon HD 7480D - AMD A4-5300 APU: 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 'glmnet.elastic_net'

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: OSError: Neural Magic: Encountered exception while trying to read arch.bin: Either the SIMD instruction set is unsupported or it could not be determined. On x86_64 systems, support for at least AVX2 is required.

spaCy

The spaCy library is an open-source solution for advanced neural language processing (NLP). The spaCy library leverages Python and is a leading neural language processing solution. This test profile times the spaCy CPU performance with various models. Learn more via the OpenBenchmarking.org test page.

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: TypeError: issubclass() arg 1 must be a class

ECP-CANDLE

The CANDLE benchmark codes implement deep learning architectures relevant to problems in cancer. These architectures address problems at different biological scales, specifically problems at the molecular, cellular and population scales. Learn more via the OpenBenchmarking.org test page.

Benchmark: P1B2

AMD Radeon HD 7480D - AMD A4-5300 APU: The test quit with a non-zero exit status. E: ImportError: initialization failed

Benchmark: P3B1

AMD Radeon HD 7480D - AMD A4-5300 APU: The test quit with a non-zero exit status. E: ImportError: initialization failed

Benchmark: P3B2

AMD Radeon HD 7480D - AMD A4-5300 APU: The test quit with a non-zero exit status. E: ImportError: initialization failed

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

Model: yolov4 - Device: CPU - Executor: Parallel

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: onnxruntime/onnxruntime/test/onnx/onnx_model_info.cc:45 void OnnxModelInfo::InitOnnxModelInfo(const PATH_CHAR_TYPE*) open file "yolov4/yolov4.onnx" failed: No such file or directory

Model: yolov4 - Device: CPU - Executor: Standard

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: onnxruntime/onnxruntime/test/onnx/onnx_model_info.cc:45 void OnnxModelInfo::InitOnnxModelInfo(const PATH_CHAR_TYPE*) open file "yolov4/yolov4.onnx" failed: No such file or directory

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU

AMD Radeon HD 7480D - AMD A4-5300 APU: 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

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU

AMD Radeon HD 7480D - AMD A4-5300 APU: 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

AMD Radeon HD 7480D - AMD A4-5300 APU: 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 1D - Data Type: bf16bf16bf16 - Engine: CPU

AMD Radeon HD 7480D - AMD A4-5300 APU: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

Backend: BLAS

AMD Radeon HD 7480D - AMD A4-5300 APU: 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: ./lczero: line 4: ./lc0: No such file or directory

243 Results Shown

TensorFlow:
  GPU - 64 - VGG-16
  CPU - 64 - VGG-16
Whisper.cpp
TensorFlow:
  GPU - 256 - GoogLeNet
  GPU - 32 - VGG-16
  GPU - 512 - AlexNet
  CPU - 256 - GoogLeNet
  CPU - 32 - VGG-16
  GPU - 64 - ResNet-50
  CPU - 512 - AlexNet
  CPU - 64 - ResNet-50
  GPU - 16 - VGG-16
Scikit-Learn
Whisper.cpp
TensorFlow:
  GPU - 256 - AlexNet
  CPU - 16 - VGG-16
  CPU - 256 - AlexNet
  GPU - 32 - ResNet-50
  CPU - 32 - ResNet-50
PyTorch:
  CPU - 64 - Efficientnet_v2_l
  CPU - 32 - Efficientnet_v2_l
  CPU - 256 - Efficientnet_v2_l
  CPU - 512 - Efficientnet_v2_l
  CPU - 16 - Efficientnet_v2_l
TensorFlow:
  GPU - 64 - GoogLeNet
  CPU - 64 - GoogLeNet
Scikit-Learn
TensorFlow
PyTorch:
  CPU - 256 - ResNet-152
  CPU - 64 - ResNet-152
  CPU - 32 - ResNet-152
  CPU - 16 - ResNet-152
  CPU - 512 - ResNet-152
Whisper.cpp
Scikit-Learn
PlaidML
Caffe
TensorFlow:
  GPU - 64 - AlexNet
  CPU - 16 - ResNet-50
Mobile Neural Network:
  inception-v3
  mobilenet-v1-1.0
  MobileNetV2_224
  SqueezeNetV1.0
  resnet-v2-50
  squeezenetv1.1
  mobilenetV3
  nasnet
TensorFlow
Scikit-Learn
Numenta Anomaly Benchmark
TensorFlow:
  CPU - 64 - AlexNet
  CPU - 32 - GoogLeNet
Scikit-Learn
PyTorch
PlaidML
TensorFlow
PyTorch:
  CPU - 512 - ResNet-50
  CPU - 256 - ResNet-50
  CPU - 32 - ResNet-50
  CPU - 64 - ResNet-50
  CPU - 16 - ResNet-50
Caffe
Numenta Anomaly Benchmark
TensorFlow
PyTorch
Scikit-Learn
TensorFlow
Scikit-Learn
oneDNN:
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
Scikit-Learn:
  LocalOutlierFactor
  Hist Gradient Boosting Threading
  Plot Hierarchical
TensorFlow
NCNN:
  CPU - FastestDet
  CPU - vision_transformer
  CPU - regnety_400m
  CPU - squeezenet_ssd
  CPU - yolov4-tiny
  CPU - resnet50
  CPU - alexnet
  CPU - resnet18
  CPU - vgg16
  CPU - googlenet
  CPU - blazeface
  CPU - efficientnet-b0
  CPU - mnasnet
  CPU - shufflenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU-v2-v2 - mobilenet-v2
  CPU - mobilenet
  Vulkan GPU - FastestDet
  Vulkan GPU - vision_transformer
  Vulkan GPU - regnety_400m
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - resnet50
  Vulkan GPU - alexnet
  Vulkan GPU - resnet18
  Vulkan GPU - vgg16
  Vulkan GPU - googlenet
  Vulkan GPU - blazeface
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - mnasnet
  Vulkan GPU - shufflenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU - mobilenet
Scikit-Learn
TensorFlow:
  GPU - 16 - AlexNet
  GPU - 1 - VGG-16
TNN
Scikit-Learn:
  Plot Singular Value Decomposition
  Plot Polynomial Kernel Approximation
  Kernel PCA Solvers / Time vs. N Samples
TensorFlow
Scikit-Learn
TensorFlow
Caffe
Scikit-Learn:
  Hist Gradient Boosting
  Hist Gradient Boosting Higgs Boson
  Feature Expansions
oneDNN:
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - f32 - CPU
Numpy Benchmark
Scikit-Learn
PyTorch
Scikit-Learn
Numenta Anomaly Benchmark:
  Contextual Anomaly Detector OSE
  Bayesian Changepoint
Scikit-Learn:
  Kernel PCA Solvers / Time vs. N Components
  Hist Gradient Boosting Adult
Caffe
Scikit-Learn
TensorFlow
Caffe
DeepSpeech
Scikit-Learn:
  Plot Ward
  Tree
Mlpack Benchmark
Scikit-Learn
Numenta Anomaly Benchmark
TensorFlow
Scikit-Learn:
  Text Vectorizers
  Plot Incremental PCA
Caffe
ONNX Runtime:
  fcn-resnet101-11 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
Scikit-Learn
OpenVINO:
  Face Detection FP16 - CPU:
    ms
    FPS
ONNX Runtime:
  fcn-resnet101-11 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
TensorFlow
Numenta Anomaly Benchmark
Scikit-Learn
TensorFlow
ONNX Runtime:
  bertsquad-12 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
OpenVINO:
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
ONNX Runtime:
  bertsquad-12 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  Faster R-CNN R-50-FPN-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
TensorFlow
ONNX Runtime:
  ArcFace ResNet-100 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  Faster R-CNN R-50-FPN-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  ArcFace ResNet-100 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  GPT-2 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  GPT-2 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  ResNet50 v1-12-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  ResNet50 v1-12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  super-resolution-10 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  super-resolution-10 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  CaffeNet 12-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  CaffeNet 12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
TensorFlow
OpenVINO:
  Machine Translation EN To DE FP16 - CPU:
    ms
    FPS
R Benchmark
OpenVINO:
  Person Detection FP16 - CPU:
    ms
    FPS
TensorFlow Lite
OpenVINO:
  Person Detection FP32 - CPU:
    ms
    FPS
TensorFlow Lite
OpenVINO:
  Road Segmentation ADAS FP16-INT8 - CPU:
    ms
    FPS
  Road Segmentation ADAS FP16 - CPU:
    ms
    FPS
  Handwritten English Recognition FP16 - CPU:
    ms
    FPS
  Handwritten English Recognition FP16-INT8 - CPU:
    ms
    FPS
  Vehicle Detection FP16-INT8 - CPU:
    ms
    FPS
  Vehicle Detection FP16 - CPU:
    ms
    FPS
  Weld Porosity Detection FP16 - CPU:
    ms
    FPS
  Face Detection Retail FP16-INT8 - CPU:
    ms
    FPS
  Face Detection Retail FP16 - CPU:
    ms
    FPS
TensorFlow Lite:
  NASNet Mobile
  Mobilenet Quant
OpenVINO:
  Weld Porosity Detection FP16-INT8 - CPU:
    ms
    FPS
TensorFlow Lite:
  Mobilenet Float
  SqueezeNet
OpenVINO:
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    ms
    FPS
  Age Gender Recognition Retail 0013 FP16 - CPU:
    ms
    FPS
RNNoise
TNN:
  CPU - SqueezeNet v2
  CPU - MobileNet v2
Mlpack Benchmark
TNN
oneDNN:
  Deconvolution Batch shapes_1d - f32 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  IP Shapes 1D - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
  IP Shapes 3D - f32 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
  Deconvolution Batch shapes_3d - u8s8f32 - CPU

AMD Radeon HD 7480D - AMD A4-5300 APU

Processor: AMD A4-5300 APU @ 3.40GHz (1 Core / 2 Threads), Motherboard: ASRock FM2A88M-HD+ R3.0 (P1.50 BIOS), Chipset: AMD 15h, Memory: 4096MB, Disk: 1000GB Western Digital WDS100T2B0A, Graphics: AMD Radeon HD 7480D 256MB, Audio: AMD Trinity HDMI Audio, Monitor: G185BGEL01, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 20.04, Kernel: 5.15.0-89-generic (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.13, OpenGL: 4.3 Mesa 21.2.6 (LLVM 12.0.0), Vulkan: 1.1.182, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1368x768

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-9QDOt0/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x6001119
Python Notes: Python 3.8.10
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT vulnerable + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 16 January 2024 08:28 by user hertz.