/tmp/test.log

Docker testing on Ubuntu 20.04 LTS 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 2011178-NE-TMPTESTLO98
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
tflite0
November 17 2020
  21 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):


/tmp/test.logOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads)MSI MAG X570 TOMAHAWK WIFI (MS-7C84) v1.0 (1.40 BIOS)32GB1000GB Sabrent Rocket 4.0 1TB + 2 x 500GB CT500MX500SSD1 + 128GB KINGSTON RBU-SNS + 1000GB HGST HTS721010A9amdgpudrmfb (1366/1750MHz)XV273KUbuntu 20.04 LTS5.9.0-1-amd64 (x86_64)overlayfs3840x2160DockerProcessorMotherboardMemoryDiskGraphicsMonitorOSKernelFile-SystemScreen ResolutionSystem Layer/tmp/test.log BenchmarksSystem Logs- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0xa201009- 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

/tmp/test.logtensorflow-lite: Inception V4tensorflow-lite: Inception ResNet V2tensorflow-lite: Mobilenet Quanttensorflow-lite: NASNet Mobiletensorflow-lite: SqueezeNettensorflow-lite: Mobilenet Floattflite01788060161436392519.812498412459084363.1OpenBenchmarking.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: Inception V4tflite0400K800K1200K1600K2000KSE +/- 310.05, N = 31788060

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2tflite0300K600K900K1200K1500KSE +/- 7607.02, N = 31614363

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quanttflite020K40K60K80K100KSE +/- 17.54, N = 392519.8

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet Mobiletflite030K60K90K120K150KSE +/- 389.36, N = 3124984

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNettflite030K60K90K120K150KSE +/- 735.99, N = 3124590

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Floattflite020K40K60K80K100KSE +/- 123.62, N = 384363.1