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

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

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.

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.

Mlpack Benchmark

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

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.

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

Result

Inference Time Cost (ms)

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.

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.

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.

TNN

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

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.

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.

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.

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.

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.

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.

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.

R Benchmark

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

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.

Numpy Benchmark

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

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.

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: 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:

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.

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

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.

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

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.

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.

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.

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: 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'

Mlpack Benchmark

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

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.

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.

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'

ONNX Runtime

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

Model: yolov4 - Device: CPU - Executor: Parallel

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: P3B2

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: P1B2

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

OpenVINO

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.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

TensorFlow

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.

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.

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.

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.

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: 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: 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.

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.

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

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

oneDNN

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

227 Results Shown

Whisper.cpp:
ggml-medium.en - 2016 State of the Union
ggml-small.en - 2016 State of the Union
ggml-base.en - 2016 State of the Union
Scikit-Learn:
Sparse Rand Projections / 100 Iterations
Kernel PCA Solvers / Time vs. N Components
Kernel PCA Solvers / Time vs. N Samples
Hist Gradient Boosting Categorical Only
Plot Polynomial Kernel Approximation
20 Newsgroups / Logistic Regression
Hist Gradient Boosting Higgs Boson
Plot Singular Value Decomposition
Hist Gradient Boosting Threading
Hist Gradient Boosting Adult
Covertype Dataset Benchmark
Sample Without Replacement
Hist Gradient Boosting
Plot Incremental PCA
TSNE MNIST Dataset
LocalOutlierFactor
Feature Expansions
Plot OMP vs. LARS
Plot Hierarchical
Text Vectorizers
Plot Lasso Path
SGD Regression
Plot Neighbors
MNIST Dataset
Plot Ward
Sparsify
Lasso
Tree
SAGA
GLM
Mlpack Benchmark:
scikit_svm
scikit_ica
ONNX Runtime:
Faster R-CNN R-50-FPN-int8 - CPU - Standard
Faster R-CNN R-50-FPN-int8 - CPU - Parallel
super-resolution-10 - CPU - Standard
super-resolution-10 - CPU - Parallel
ResNet50 v1-12-int8 - CPU - Standard
ResNet50 v1-12-int8 - CPU - Parallel
ArcFace ResNet-100 - CPU - Standard
ArcFace ResNet-100 - CPU - Parallel
fcn-resnet101-11 - CPU - Standard
fcn-resnet101-11 - CPU - Parallel
CaffeNet 12-int8 - CPU - Standard
CaffeNet 12-int8 - CPU - Parallel
bertsquad-12 - CPU - Standard
bertsquad-12 - CPU - Parallel
GPT-2 - CPU - Standard
GPT-2 - CPU - Parallel
Numenta Anomaly Benchmark:
Contextual Anomaly Detector OSE
Bayesian Changepoint
Earthgecko Skyline
Windowed Gaussian
Relative Entropy
KNN CAD
OpenVINO:
Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
ms
FPS
Handwritten English Recognition FP16-INT8 - CPU:
ms
FPS
Age Gender Recognition Retail 0013 FP16 - CPU:
ms
FPS
Handwritten English Recognition FP16 - CPU:
ms
FPS
Weld Porosity Detection FP16-INT8 - CPU:
ms
FPS
Machine Translation EN To DE FP16 - CPU:
ms
FPS
Road Segmentation ADAS FP16-INT8 - CPU:
ms
FPS
Face Detection Retail FP16-INT8 - CPU:
ms
FPS
Weld Porosity Detection FP16 - CPU:
ms
FPS
Vehicle Detection FP16-INT8 - CPU:
ms
FPS
Road Segmentation ADAS FP16 - CPU:
ms
FPS
Face Detection Retail FP16 - CPU:
ms
FPS
Face Detection FP16-INT8 - CPU:
ms
FPS
Vehicle Detection FP16 - CPU:
ms
FPS
Person Detection FP32 - CPU:
ms
FPS
Person Detection FP16 - CPU:
ms
FPS
Face Detection FP16 - CPU:
ms
FPS
PlaidML:
No - Inference - ResNet 50 - CPU
No - Inference - VGG16 - CPU
TNN:
CPU - SqueezeNet v1.1
CPU - SqueezeNet v2
CPU - MobileNet v2
CPU - DenseNet
NCNN:
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
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
Mobile Neural Network:
inception-v3
mobilenet-v1-1.0
MobileNetV2_224
SqueezeNetV1.0
resnet-v2-50
squeezenetv1.1
mobilenetV3
nasnet
Caffe:
GoogleNet - CPU - 1000
GoogleNet - CPU - 200
GoogleNet - CPU - 100
AlexNet - CPU - 1000
AlexNet - CPU - 200
AlexNet - CPU - 100
TensorFlow:
GPU - 256 - GoogLeNet
CPU - 256 - GoogLeNet
GPU - 64 - GoogLeNet
GPU - 32 - ResNet-50
GPU - 32 - GoogLeNet
GPU - 16 - ResNet-50
GPU - 16 - GoogLeNet
CPU - 64 - ResNet-50
CPU - 64 - GoogLeNet
CPU - 32 - ResNet-50
CPU - 32 - GoogLeNet
CPU - 16 - ResNet-50
CPU - 16 - GoogLeNet
GPU - 512 - AlexNet
GPU - 256 - AlexNet
GPU - 1 - ResNet-50
GPU - 1 - GoogLeNet
CPU - 512 - AlexNet
CPU - 256 - AlexNet
CPU - 1 - ResNet-50
CPU - 1 - GoogLeNet
GPU - 64 - AlexNet
GPU - 32 - AlexNet
GPU - 16 - AlexNet
CPU - 64 - AlexNet
CPU - 32 - AlexNet
CPU - 16 - AlexNet
GPU - 64 - VGG-16
GPU - 32 - VGG-16
GPU - 16 - VGG-16
GPU - 1 - AlexNet
CPU - 64 - VGG-16
CPU - 32 - VGG-16
CPU - 16 - VGG-16
CPU - 1 - AlexNet
GPU - 1 - VGG-16
CPU - 1 - VGG-16
PyTorch:
CPU - 512 - Efficientnet_v2_l
CPU - 256 - Efficientnet_v2_l
CPU - 64 - Efficientnet_v2_l
CPU - 32 - Efficientnet_v2_l
CPU - 16 - Efficientnet_v2_l
CPU - 1 - Efficientnet_v2_l
CPU - 512 - ResNet-152
CPU - 256 - ResNet-152
CPU - 64 - ResNet-152
CPU - 512 - ResNet-50
CPU - 32 - ResNet-152
CPU - 256 - ResNet-50
CPU - 16 - ResNet-152
CPU - 64 - ResNet-50
CPU - 32 - ResNet-50
CPU - 16 - ResNet-50
CPU - 1 - ResNet-152
CPU - 1 - ResNet-50
TensorFlow Lite:
Inception ResNet V2
Mobilenet Quant
Mobilenet Float
NASNet Mobile
Inception V4
SqueezeNet
RNNoise
R Benchmark
DeepSpeech
Numpy Benchmark
oneDNN:
Recurrent Neural Network Inference - bf16bf16bf16 - CPU
Recurrent Neural Network Training - bf16bf16bf16 - CPU
Recurrent Neural Network Inference - u8s8f32 - CPU
Recurrent Neural Network Training - u8s8f32 - CPU
Recurrent Neural Network Inference - f32 - CPU
Recurrent Neural Network Training - f32 - CPU
Deconvolution Batch shapes_3d - u8s8f32 - CPU
Deconvolution Batch shapes_1d - u8s8f32 - CPU
Convolution Batch Shapes Auto - u8s8f32 - CPU
Deconvolution Batch shapes_3d - f32 - CPU
Deconvolution Batch shapes_1d - f32 - CPU
Convolution Batch Shapes Auto - f32 - CPU
IP Shapes 3D - u8s8f32 - CPU
IP Shapes 1D - u8s8f32 - CPU
IP Shapes 3D - f32 - CPU
IP Shapes 1D - f32 - CPU
TensorFlow

AMD Radeon HD 7480D - AMD A4-5300 APU

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

HDR3-A44000-1

Statistics

Graph Settings

Multi-Way Comparison

Table

Run Management

AMD Radeon HD 7480D - AMD A4-5300 APU

Whisper.cpp

Scikit-Learn

Mlpack Benchmark

ONNX Runtime

Numenta Anomaly Benchmark

OpenVINO

PlaidML

TNN

NCNN

Mobile Neural Network

Caffe

TensorFlow

PyTorch

TensorFlow Lite

RNNoise

R Benchmark

DeepSpeech

Numpy Benchmark

oneDNN

OpenCV

Scikit-Learn

Mlpack Benchmark

AI Benchmark Alpha

ONNX Runtime

ECP-CANDLE

OpenVINO

spaCy

Neural Magic DeepSparse

TensorFlow

oneDNN

LeelaChessZero

227 Results Shown

AMD Radeon HD 7480D - AMD A4-5300 APU