tensorflowlite-sq

Intel Pentium N3700 testing with a AMI Aptio CRB (5.11 BIOS) and Intel Atom/Celeron/Pentium x5-E8000/J3xxx/N3xxx IGP on Debian 12 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 2403139-NE-TENSORFLO76
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
tflsq
March 13
  4 Minutes


tensorflowlite-sqOpenBenchmarking.orgPhoronix Test SuiteIntel Pentium N3700 @ 2.40GHz (4 Cores)AMI Aptio CRB (5.11 BIOS)Intel Atom/Celeron/Pentium8GBSHAREVDI 128GB SIntel Atom/Celeron/Pentium x5-E8000/J3xxx/N3xxx IGP (700MHz)Intel Atom/Celeron/PentiumSB220Q4 x Intel I225-VDebian 126.1.0-18-amd64 (x86_64)GCC 12.2.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelCompilerFile-SystemScreen ResolutionTensorflowlite-sq BenchmarksSystem Logs- Transparent Huge Pages: always- Scaling Governor: intel_cpufreq schedutil - CPU Microcode: 0x368- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Mitigation of Clear buffers; SMT disabled + meltdown: Mitigation of PTI + mmio_stale_data: Unknown: No mitigations + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Not affected + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

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: SqueezeNettflsq20K40K60K80K100KSE +/- 54.22, N = 389903.1