tensorflow_linux_5_8

AMD Ryzen 5 3500U testing with a LENOVO LNVNB161216 (ARCN33WW BIOS) and AMD Picasso 2GB 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 2010180-NI-TENSORFLO06
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
Tensorflow Lite Ryzen 3500U Linux Kernel 5.8
October 18 2020
  40 Minutes
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):


tensorflow_linux_5_8OpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 5 3500U @ 2.10GHz (4 Cores / 8 Threads)LENOVO LNVNB161216 (ARCN33WW BIOS)AMD Raven/Raven26GB256GB Western Digital PC SN520 SDAPMUW-256G-1101AMD Picasso 2GB (1200/1200MHz)AMD Raven/Raven2/FenghuangRealtek RTL8111/8168/8411 + Realtek RTL8821CE 802.11ac PCIeUbuntu 20.045.8.0-23-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.6 Mesa 20.1.5 (LLVM 10.0.1)OpenCL 2.1 AMD-APP (3180.7)GCC 9.3.0 + Clang 10.0.0-4ubuntu1ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen ResolutionTensorflow_linux_5_8 BenchmarksSystem Logs- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8108102- 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 STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

tensorflow_linux_5_8tensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2Tensorflow Lite Ryzen 3500U Linux Kernel 5.853631879763583700063475563558397158020OpenBenchmarking.org

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. 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 2020-08-23Model: SqueezeNetTensorflow Lite Ryzen 3500U Linux Kernel 5.8110K220K330K440K550KSE +/- 3085.96, N = 3536318

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Tensorflow Lite Ryzen 3500U Linux Kernel 5.82M4M6M8M10MSE +/- 107773.02, N = 47976358

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileTensorflow Lite Ryzen 3500U Linux Kernel 5.880K160K240K320K400KSE +/- 4012.61, N = 3370006

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatTensorflow Lite Ryzen 3500U Linux Kernel 5.870K140K210K280K350KSE +/- 3263.45, N = 12347556

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantTensorflow Lite Ryzen 3500U Linux Kernel 5.880K160K240K320K400KSE +/- 4388.61, N = 3355839

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Tensorflow Lite Ryzen 3500U Linux Kernel 5.81.5M3M4.5M6M7.5MSE +/- 2863.67, N = 37158020