IceLake TensorFlow Lite

Intel Core i7-1065G7 testing with a Dell 06CDVY (1.0.9 BIOS) and Intel Iris Plus G7 3GB 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 2008243-FI-ICELAKETE47
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
i7-1065G7 Base Run
August 23 2020
  35 Minutes
Run 2
August 24 2020
  34 Minutes
Run 3
August 24 2020
  35 Minutes
Run 4
August 24 2020
  35 Minutes
Invert Hiding All Results Option
  35 Minutes

Only show results where is faster than
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):


IceLake TensorFlow LiteOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads)Dell 06CDVY (1.0.9 BIOS)Intel Device 34ef16GBKBG40ZPZ512G NVMe TOSHIBA 512GBIntel Iris Plus G7 3GB (1100MHz)Realtek ALC289Intel Killer Wi-Fi 6 AX1650i 160MHzUbuntu 20.045.9.0-050900rc1daily20200819-generic (x86_64) 20200818GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.6 Mesa 20.0.41.2.131GCC 9.3.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionIceLake TensorFlow Lite BenchmarksSystem Logs- Scaling Governor: intel_pstate powersave - CPU Microcode: 0x78- itlb_multihit: KVM: Mitigation of VMX disabled + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

i7-1065G7 Base RunRun 2Run 3Run 4Result OverviewPhoronix Test Suite100%100%101%101%102%TensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteInception V4Mobilenet QuantI.R.VMobilenet FloatNASNet MobileSqueezeNet

IceLake TensorFlow Litetensorflow-lite: SqueezeNettensorflow-lite: Inception ResNet V2tensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanti7-1065G7 Base RunRun 2Run 3Run 462440982051239059927451262419132418103626580830102792151634562044238754236776259678287820915275345588942316042256762644883040209180377455295423771422946OpenBenchmarking.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: SqueezeNetRun 2Run 4Run 3i7-1065G7 Base Run130K260K390K520K650KSE +/- 6624.90, N = 8SE +/- 6155.90, N = 9SE +/- 6115.93, N = 9SE +/- 6173.06, N = 9626580626448625967624409
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetRun 2Run 4Run 3i7-1065G7 Base Run110K220K330K440K550KMin: 580225 / Avg: 626580.38 / Max: 633689Min: 577241 / Avg: 626448.44 / Max: 633365Min: 577116 / Avg: 625967 / Max: 633420Min: 582443 / Avg: 624408.78 / Max: 655444

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Run 4Run 2Run 3i7-1065G7 Base Run2M4M6M8M10MSE +/- 7204.57, N = 3SE +/- 4154.54, N = 3SE +/- 4935.89, N = 3SE +/- 2058.80, N = 38304020830102782878208205123
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Run 4Run 2Run 3i7-1065G7 Base Run1.4M2.8M4.2M5.6M7MMin: 8291720 / Avg: 8304020 / Max: 8316670Min: 8292750 / Avg: 8301026.67 / Max: 8305800Min: 8281960 / Avg: 8287820 / Max: 8297630Min: 8202210 / Avg: 8205123.33 / Max: 8209100

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Run 2Run 4Run 3i7-1065G7 Base Run2M4M6M8M10MSE +/- 33881.36, N = 3SE +/- 1006.75, N = 3SE +/- 7167.26, N = 3SE +/- 1678.14, N = 39215163918037791527539059927
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Run 2Run 4Run 3i7-1065G7 Base Run1.6M3.2M4.8M6.4M8MMin: 9174120 / Avg: 9215163.33 / Max: 9282380Min: 9179200 / Avg: 9180376.67 / Max: 9182380Min: 9139780 / Avg: 9152753.33 / Max: 9164520Min: 9058000 / Avg: 9059926.67 / Max: 9063270

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileRun 2Run 3Run 4i7-1065G7 Base Run100K200K300K400K500KSE +/- 3205.03, N = 3SE +/- 3240.40, N = 3SE +/- 3348.20, N = 3SE +/- 3425.92, N = 3456204455889455295451262
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileRun 2Run 3Run 4i7-1065G7 Base Run80K160K240K320K400KMin: 449794 / Avg: 456204 / Max: 459431Min: 449409 / Avg: 455889 / Max: 459217Min: 448621 / Avg: 455295.33 / Max: 459103Min: 444415 / Avg: 451262.33 / Max: 454901

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatRun 2Run 4Run 3i7-1065G7 Base Run90K180K270K360K450KSE +/- 3379.39, N = 3SE +/- 3564.86, N = 3SE +/- 3567.59, N = 3SE +/- 2847.74, N = 3423875423771423160419132
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatRun 2Run 4Run 3i7-1065G7 Base Run70K140K210K280K350KMin: 417148 / Avg: 423875.33 / Max: 427803Min: 416696 / Avg: 423771 / Max: 428072Min: 416075 / Avg: 423159.67 / Max: 427436Min: 413439 / Avg: 419131.67 / Max: 422133

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantRun 2Run 4Run 3i7-1065G7 Base Run90K180K270K360K450KSE +/- 3033.64, N = 3SE +/- 3381.27, N = 3SE +/- 3385.38, N = 3SE +/- 3745.57, N = 3423677422946422567418103
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantRun 2Run 4Run 3i7-1065G7 Base Run70K140K210K280K350KMin: 417613 / Avg: 423677.33 / Max: 426873Min: 416228 / Avg: 422946.33 / Max: 426974Min: 415796 / Avg: 422566.67 / Max: 425982Min: 410612 / Avg: 418103 / Max: 421888