tensorflowlite1800xbench

AMD Ryzen 7 1800X Eight-Core testing with a ASUS ROG STRIX X470-F GAMING (5603 BIOS) and NVIDIA GeForce RTX 2060 6GB 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 2101158-HA-TENSORFLO88
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
Only show results matching title/arguments (delimit multiple options with a comma):


tensorflowlite1800xbenchOpenBenchmarking.orgPhoronix Test Suite 10.2.2AMD Ryzen 7 1800X Eight-Core @ 3.60GHz (8 Cores / 16 Threads)ASUS ROG STRIX X470-F GAMING (5603 BIOS)AMD 17h32GB2 x HP SSD EX950 512GB + 1000GB Western Digital WD10EFRX-68F + 1000GB Western Digital WD10JPCX-24U + 4001GB Seagate ST4000DM004-2CV1 + 16GB Cruzer BladeNVIDIA GeForce RTX 2060 6GB (1365/7000MHz)NVIDIA TU106 HD AudioFG276Intel I211Ubuntu 20.045.8.0-38-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.9NVIDIA 455.32.004.6.01.2.142GCC 9.3.0 + CUDA 11.1ext42560x1440ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionTensorflowlite1800xbench BenchmarksSystem Logs- Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8001138- 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

tensorflowlite1800xbenchtensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V21800x21855131582671998341464581521582866507OpenBenchmarking.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: SqueezeNet1800x50K100K150K200K250KSE +/- 118.56, N = 3218551

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V41800x700K1400K2100K2800K3500KSE +/- 2041.93, N = 33158267

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet Mobile1800x40K80K120K160K200KSE +/- 962.60, N = 3199834

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Float1800x30K60K90K120K150KSE +/- 233.68, N = 3146458

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quant1800x30K60K90K120K150KSE +/- 70.63, N = 3152158

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V21800x600K1200K1800K2400K3000KSE +/- 6847.46, N = 32866507


OpenBenchmarking.org Community User Comments

Post A Comment