2107171-PTS-ML

AMD Ryzen 5 3600 6-Core testing with a Gigabyte X570 AORUS PRO (F34 BIOS) and AMD Radeon VII 16GB on ManjaroLinux 21.1.0 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2107171-IB-2107171PT13.

2107171-PTS-MLProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDisplay ServerOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionRyzen 5 3600 Radeon VII x2AMD Ryzen 5 3600 6-Core @ 3.60GHz (6 Cores / 12 Threads)Gigabyte X570 AORUS PRO (F34 BIOS)AMD Starship/Matisse32GB1000GB Sabrent Rocket 4.0 1TB + 240GB SanDisk SDSSDA24 + 256GB SanDisk SD8SN8U2 + 0GB Multiple ReaderAMD Radeon VII 16GB (1801/1000MHz)AMD Vega 20 HDMI AudioIntel I211 + Intel Wi-Fi 6 AX200ManjaroLinux 21.1.05.13.1-3-MANJARO (x86_64)X Server 1.20.114.6 Mesa 21.1.4 (LLVM 12.0.0)OpenCL 2.0 AMD-APP.dbg (3275.0)1.2.179GCC 11.1.0 + Clang 12.0.1f2fs2560x1440OpenBenchmarking.org- amdgpu.ppfeaturemask=0xffffffff - Transparent Huge Pages: madvise- --disable-libssp --disable-libstdcxx-pch --disable-libunwind-exceptions --disable-werror --enable-__cxa_atexit --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-install-libiberty --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++,d --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-isl --with-linker-hash-style=gnu - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8701021- GLAMOR- Python 3.9.6- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

2107171-PTS-MLshoc: OpenCL - S3Dshoc: OpenCL - Triadshoc: OpenCL - FFT SPshoc: OpenCL - MD5 Hashshoc: OpenCL - Reductionshoc: OpenCL - GEMM SGEMM_Nshoc: OpenCL - Max SP Flopsshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Texture Read Bandwidthonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUnumpy: deepspeech: CPUrbenchmark: rnnoise: tensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2mnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3ncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mtnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.1plaidml: No - Inference - VGG16 - CPUplaidml: No - Inference - ResNet 50 - CPUonnx: yolov4 - OpenMP CPUonnx: fcn-resnet101-11 - OpenMP CPUonnx: shufflenet-v2-10 - OpenMP CPUonnx: super-resolution-10 - OpenMP CPUmlpack: scikit_svmmlpack: scikit_linearridgeregressionscikit-learn: Ryzen 5 3600 Radeon VII x2272.5926.83302402.3617.0273304.830799.06171448277.16367.1501459.0205.162927.503263.651202.1946714.29606.845308.9302215.14065.033646.946364347.262566.614324.852577.673.627144326.472565.154.28037407.6462.021590.556819.104266900395331722786518279718731035764072.2934.20828.9285.5753.3244.01031.89716.174.954.324.454.156.831.8514.6555.4215.7512.3227.1925.8121.709.5716.304.944.314.444.156.931.8514.7555.1515.8512.6727.3626.0421.749.553430.453285.99768.656253.87811.876.602975614032425624.06192.73109.479OpenBenchmarking.org

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: S3D

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DRyzen 5 3600 Radeon VII x260120180240300SE +/- 0.92, N = 3272.591. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Triad

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: TriadRyzen 5 3600 Radeon VII x2246810SE +/- 0.0019, N = 36.83301. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: FFT SP

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPRyzen 5 3600 Radeon VII x25001000150020002500SE +/- 2.43, N = 32402.361. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: MD5 Hash

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashRyzen 5 3600 Radeon VII x248121620SE +/- 0.00, N = 317.031. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Reduction

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: ReductionRyzen 5 3600 Radeon VII x270140210280350SE +/- 0.02, N = 3304.831. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: GEMM SGEMM_N

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NRyzen 5 3600 Radeon VII x22004006008001000SE +/- 0.93, N = 3799.061. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Max SP Flops

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP FlopsRyzen 5 3600 Radeon VII x21.5M3M4.5M6M7.5MSE +/- 51044.83, N = 371448271. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Download

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed DownloadRyzen 5 3600 Radeon VII x2246810SE +/- 0.0023, N = 37.16361. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Readback

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed ReadbackRyzen 5 3600 Radeon VII x2246810SE +/- 0.0009, N = 37.15011. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Texture Read Bandwidth

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthRyzen 5 3600 Radeon VII x2100200300400500SE +/- 0.85, N = 3459.021. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPURyzen 5 3600 Radeon VII x21.16172.32343.48514.64685.8085SE +/- 0.00906, N = 35.16292MIN: 4.951. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPURyzen 5 3600 Radeon VII x2246810SE +/- 0.00793, N = 37.50326MIN: 7.41. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPURyzen 5 3600 Radeon VII x20.82151.6432.46453.2864.1075SE +/- 0.01077, N = 33.65120MIN: 3.561. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPURyzen 5 3600 Radeon VII x20.49380.98761.48141.97522.469SE +/- 0.00060, N = 32.19467MIN: 2.141. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPURyzen 5 3600 Radeon VII x248121620SE +/- 0.01, N = 314.30MIN: 14.031. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPURyzen 5 3600 Radeon VII x2246810SE +/- 0.03858, N = 36.84530MIN: 6.431. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPURyzen 5 3600 Radeon VII x2246810SE +/- 0.00465, N = 38.93022MIN: 8.761. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPURyzen 5 3600 Radeon VII x248121620SE +/- 0.01, N = 315.14MIN: 14.921. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPURyzen 5 3600 Radeon VII x21.13262.26523.39784.53045.663SE +/- 0.00240, N = 35.03364MIN: 4.911. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPURyzen 5 3600 Radeon VII x2246810SE +/- 0.01792, N = 36.94636MIN: 6.721. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPURyzen 5 3600 Radeon VII x29001800270036004500SE +/- 23.45, N = 34347.26MIN: 4301.241. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPURyzen 5 3600 Radeon VII x26001200180024003000SE +/- 1.73, N = 32566.61MIN: 2543.381. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPURyzen 5 3600 Radeon VII x29001800270036004500SE +/- 3.00, N = 34324.85MIN: 4295.911. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPURyzen 5 3600 Radeon VII x26001200180024003000SE +/- 13.64, N = 32577.67MIN: 2547.491. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPURyzen 5 3600 Radeon VII x20.81611.63222.44833.26444.0805SE +/- 0.00457, N = 33.62714MIN: 3.341. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPURyzen 5 3600 Radeon VII x29001800270036004500SE +/- 1.40, N = 34326.47MIN: 4303.741. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPURyzen 5 3600 Radeon VII x26001200180024003000SE +/- 1.90, N = 32565.15MIN: 2547.831. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPURyzen 5 3600 Radeon VII x20.96311.92622.88933.85244.8155SE +/- 0.00055, N = 34.28037MIN: 4.171. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Numpy Benchmark

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkRyzen 5 3600 Radeon VII x290180270360450SE +/- 1.19, N = 3407.64

DeepSpeech

Acceleration: CPU

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPURyzen 5 3600 Radeon VII x21428425670SE +/- 0.19, N = 362.02

R Benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterR BenchmarkRyzen 5 3600 Radeon VII x20.12530.25060.37590.50120.6265SE +/- 0.0015, N = 30.55681. R scripting front-end version 4.1.0 (2021-05-18)

RNNoise

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28Ryzen 5 3600 Radeon VII x2510152025SE +/- 0.07, N = 319.101. (CC) gcc options: -O2 -pedantic -fvisibility=hidden -lm

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetRyzen 5 3600 Radeon VII x260K120K180K240K300KSE +/- 246.38, N = 3266900

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Ryzen 5 3600 Radeon VII x2800K1600K2400K3200K4000KSE +/- 2104.09, N = 33953317

TensorFlow Lite

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileRyzen 5 3600 Radeon VII x250K100K150K200K250KSE +/- 83.13, N = 3227865

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatRyzen 5 3600 Radeon VII x240K80K120K160K200KSE +/- 144.30, N = 3182797

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantRyzen 5 3600 Radeon VII x240K80K120K160K200KSE +/- 48.18, N = 3187310

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Ryzen 5 3600 Radeon VII x2800K1600K2400K3200K4000KSE +/- 2344.47, N = 33576407

Mobile Neural Network

Model: mobilenetV3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV3Ryzen 5 3600 Radeon VII x20.51591.03181.54772.06362.5795SE +/- 0.032, N = 32.293MIN: 2.19 / MAX: 7.481. (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

Mobile Neural Network

Model: squeezenetv1.1

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: squeezenetv1.1Ryzen 5 3600 Radeon VII x20.94681.89362.84043.78724.734SE +/- 0.098, N = 34.208MIN: 3.98 / MAX: 96.761. (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

Mobile Neural Network

Model: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: resnet-v2-50Ryzen 5 3600 Radeon VII x2714212835SE +/- 0.11, N = 328.93MIN: 28.21 / MAX: 62.041. (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

Mobile Neural Network

Model: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: SqueezeNetV1.0Ryzen 5 3600 Radeon VII x21.25442.50883.76325.01766.272SE +/- 0.029, N = 35.575MIN: 5.42 / MAX: 10.791. (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

Mobile Neural Network

Model: MobileNetV2_224

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: MobileNetV2_224Ryzen 5 3600 Radeon VII x20.74791.49582.24372.99163.7395SE +/- 0.007, N = 33.324MIN: 3.26 / MAX: 8.651. (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

Mobile Neural Network

Model: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenet-v1-1.0Ryzen 5 3600 Radeon VII x20.90231.80462.70693.60924.5115SE +/- 0.005, N = 34.010MIN: 3.93 / MAX: 9.241. (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

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: inception-v3Ryzen 5 3600 Radeon VII x2714212835SE +/- 0.25, N = 331.90MIN: 30.94 / MAX: 37.941. (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

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mobilenetRyzen 5 3600 Radeon VII x248121620SE +/- 0.08, N = 316.17MIN: 15.76 / MAX: 20.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v2Ryzen 5 3600 Radeon VII x21.11382.22763.34144.45525.569SE +/- 0.01, N = 34.95MIN: 4.84 / MAX: 9.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v3Ryzen 5 3600 Radeon VII x20.9721.9442.9163.8884.86SE +/- 0.01, N = 34.32MIN: 4.22 / MAX: 9.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v2Ryzen 5 3600 Radeon VII x21.00132.00263.00394.00525.0065SE +/- 0.01, N = 34.45MIN: 4.36 / MAX: 8.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnetRyzen 5 3600 Radeon VII x20.93381.86762.80143.73524.669SE +/- 0.01, N = 34.15MIN: 4.07 / MAX: 8.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b0Ryzen 5 3600 Radeon VII x2246810SE +/- 0.01, N = 36.83MIN: 6.72 / MAX: 11.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazefaceRyzen 5 3600 Radeon VII x20.41630.83261.24891.66522.0815SE +/- 0.01, N = 31.85MIN: 1.8 / MAX: 6.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenetRyzen 5 3600 Radeon VII x248121620SE +/- 0.01, N = 314.65MIN: 14.45 / MAX: 19.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg16Ryzen 5 3600 Radeon VII x21224364860SE +/- 0.81, N = 355.42MIN: 53.87 / MAX: 357.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet18Ryzen 5 3600 Radeon VII x248121620SE +/- 0.03, N = 315.75MIN: 15.52 / MAX: 20.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnetRyzen 5 3600 Radeon VII x23691215SE +/- 0.01, N = 312.32MIN: 12.16 / MAX: 16.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet50Ryzen 5 3600 Radeon VII x2612182430SE +/- 0.09, N = 327.19MIN: 26.68 / MAX: 38.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tinyRyzen 5 3600 Radeon VII x2612182430SE +/- 0.08, N = 325.81MIN: 25.45 / MAX: 30.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssdRyzen 5 3600 Radeon VII x2510152025SE +/- 0.08, N = 321.70MIN: 21.15 / MAX: 59.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400mRyzen 5 3600 Radeon VII x23691215SE +/- 0.02, N = 39.57MIN: 9.4 / MAX: 16.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: mobilenetRyzen 5 3600 Radeon VII x248121620SE +/- 0.08, N = 316.30MIN: 15.85 / MAX: 21.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2Ryzen 5 3600 Radeon VII x21.11152.2233.33454.4465.5575SE +/- 0.01, N = 34.94MIN: 4.84 / MAX: 9.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3Ryzen 5 3600 Radeon VII x20.96981.93962.90943.87924.849SE +/- 0.01, N = 34.31MIN: 4.22 / MAX: 8.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: shufflenet-v2Ryzen 5 3600 Radeon VII x20.9991.9982.9973.9964.995SE +/- 0.01, N = 34.44MIN: 4.28 / MAX: 8.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: mnasnetRyzen 5 3600 Radeon VII x20.93381.86762.80143.73524.669SE +/- 0.01, N = 34.15MIN: 4.05 / MAX: 8.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: efficientnet-b0Ryzen 5 3600 Radeon VII x2246810SE +/- 0.12, N = 36.93MIN: 6.71 / MAX: 46.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: blazefaceRyzen 5 3600 Radeon VII x20.41630.83261.24891.66522.0815SE +/- 0.02, N = 31.85MIN: 1.81 / MAX: 1.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: googlenetRyzen 5 3600 Radeon VII x248121620SE +/- 0.12, N = 314.75MIN: 14.45 / MAX: 19.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: vgg16Ryzen 5 3600 Radeon VII x21224364860SE +/- 0.24, N = 355.15MIN: 54.19 / MAX: 78.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: resnet18Ryzen 5 3600 Radeon VII x248121620SE +/- 0.06, N = 315.85MIN: 15.58 / MAX: 41.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: alexnetRyzen 5 3600 Radeon VII x23691215SE +/- 0.17, N = 312.67MIN: 12.2 / MAX: 17.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: resnet50Ryzen 5 3600 Radeon VII x2612182430SE +/- 0.05, N = 327.36MIN: 27.02 / MAX: 31.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: yolov4-tinyRyzen 5 3600 Radeon VII x2612182430SE +/- 0.06, N = 326.04MIN: 25.59 / MAX: 30.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: squeezenet_ssdRyzen 5 3600 Radeon VII x2510152025SE +/- 0.03, N = 321.74MIN: 21.39 / MAX: 28.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: Vulkan GPU - Model: regnety_400mRyzen 5 3600 Radeon VII x23691215SE +/- 0.02, N = 39.55MIN: 9.37 / MAX: 14.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

TNN

Target: CPU - Model: DenseNet

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetRyzen 5 3600 Radeon VII x27001400210028003500SE +/- 10.05, N = 33430.45MIN: 3365.76 / MAX: 3558.71. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: MobileNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2Ryzen 5 3600 Radeon VII x260120180240300SE +/- 1.38, N = 3286.00MIN: 278.3 / MAX: 334.931. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: SqueezeNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2Ryzen 5 3600 Radeon VII x21530456075SE +/- 0.32, N = 368.66MIN: 67.75 / MAX: 73.931. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

TNN

Target: CPU - Model: SqueezeNet v1.1

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1Ryzen 5 3600 Radeon VII x260120180240300SE +/- 1.07, N = 3253.88MIN: 251.34 / MAX: 255.871. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

PlaidML

FP16: No - Mode: Inference - Network: VGG16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPURyzen 5 3600 Radeon VII x23691215SE +/- 0.08, N = 311.87

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPURyzen 5 3600 Radeon VII x2246810SE +/- 0.01, N = 36.60

ONNX Runtime

Model: yolov4 - Device: OpenMP CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: yolov4 - Device: OpenMP CPURyzen 5 3600 Radeon VII x260120180240300SE +/- 0.88, N = 3297

ONNX Runtime

Model: fcn-resnet101-11 - Device: OpenMP CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: fcn-resnet101-11 - Device: OpenMP CPURyzen 5 3600 Radeon VII x21326395265SE +/- 1.01, N = 356

ONNX Runtime

Model: shufflenet-v2-10 - Device: OpenMP CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: shufflenet-v2-10 - Device: OpenMP CPURyzen 5 3600 Radeon VII x23K6K9K12K15KSE +/- 231.67, N = 314032

ONNX Runtime

Model: super-resolution-10 - Device: OpenMP CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: super-resolution-10 - Device: OpenMP CPURyzen 5 3600 Radeon VII x29001800270036004500SE +/- 18.46, N = 34256

Mlpack Benchmark

Benchmark: scikit_svm

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmRyzen 5 3600 Radeon VII x2612182430SE +/- 0.03, N = 324.06

Mlpack Benchmark

Benchmark: scikit_linearridgeregression

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionRyzen 5 3600 Radeon VII x24080120160200SE +/- 0.13, N = 3192.73

Scikit-Learn

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.22.1Ryzen 5 3600 Radeon VII x220406080100SE +/- 0.10, N = 3109.48

Phoronix Test Suite v10.8.4