pytorch.txt

ARMv8 Cortex-A78E testing with a NVIDIA Jetson Orin NX Engineering Developer Kit (36.3.0-gcid-36191598 BIOS) and Orin on Ubuntu 22.04 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 2408262-NE-PYTORCHTX65
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
all of them
August 26
  19 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):


pytorch.txtOpenBenchmarking.orgPhoronix Test SuiteARMv8 Cortex-A78E @ 1.98GHz (8 Cores)NVIDIA Jetson Orin NX Engineering Developer Kit (36.3.0-gcid-36191598 BIOS)16GB128GB FORESEE XP1000F128GOrinRealtek RTL8111/8168/8411Ubuntu 22.045.15.136-tegra (aarch64)GNOME Shell 42.9X Server 1.21.1.4NVIDIA1.3.251GCC 11.4.0 + CUDA 12.2ext46582x1234ProcessorMotherboardMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerDisplay DriverVulkanCompilerFile-SystemScreen ResolutionPytorch.txt BenchmarksSystem Logs- Transparent Huge Pages: always- Scaling Governor: tegra194 performance- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of CSV2 but not BHB + srbds: Not affected + tsx_async_abort: Not affected

pytorch.txttensorflow-lite: Inception V4tensorflow-lite: Inception ResNet V2tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: SqueezeNettensorflow-lite: Mobilenet Quantall of them12846611751122370.46848.708886.223307.88OpenBenchmarking.org

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.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4all of them30K60K90K120K150KSE +/- 310.94, N = 3128466

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2all of them30K60K90K120K150KSE +/- 57.20, N = 3117511

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet Mobileall of them5K10K15K20K25KSE +/- 161.30, N = 322370.4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Floatall of them15003000450060007500SE +/- 50.47, N = 36848.70

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetall of them2K4K6K8K10KSE +/- 30.83, N = 38886.22

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Quantall of them7001400210028003500SE +/- 4.64, N = 33307.88