tflite Xeon

Intel Xeon E-2288G testing with a Compulab SBC-ATCFL v1.2 (ATOP3.PRD.0.29.2 BIOS) and NVIDIA Quadro RTX 4000 on Ubuntu 19.10 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 2008238-NE-TFLITEXEO30
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
Run 1
August 23 2020
  28 Minutes
Run 2
August 23 2020
  28 Minutes
Run 3
August 23 2020
  28 Minutes
Invert Hiding All Results Option
  28 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):

Run 1

Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled

Run 2

Run 3

Processor: Intel Xeon E-2288G @ 5.00GHz (8 Cores / 16 Threads), Motherboard: Compulab SBC-ATCFL v1.2 (ATOP3.PRD.0.29.2 BIOS), Chipset: Intel Cannon Lake PCH, Memory: 2 x 32 GB DDR4-2667MT/s Samsung M378A4G43MB1-CTD, Disk: Samsung SSD 970 EVO Plus 250GB, Graphics: NVIDIA Quadro RTX 4000, Audio: Intel Cannon Lake PCH cAVS, Monitor: VE228, Network: Intel I219-LM + Intel I210

OS: Ubuntu 19.10, Kernel: 5.3.0-64-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, Compiler: GCC 11.0.0 20200822, File-System: ext4, Screen Resolution: 1920x1080

tflite XeonOpenBenchmarking.orgPhoronix Test SuiteIntel Xeon E-2288G @ 5.00GHz (8 Cores / 16 Threads)Compulab SBC-ATCFL v1.2 (ATOP3.PRD.0.29.2 BIOS)Intel Cannon Lake PCH2 x 32 GB DDR4-2667MT/s Samsung M378A4G43MB1-CTDSamsung SSD 970 EVO Plus 250GBNVIDIA Quadro RTX 4000Intel Cannon Lake PCH cAVSVE228Intel I219-LM + Intel I210Ubuntu 19.105.3.0-64-generic (x86_64)GNOME Shell 3.34.1X Server 1.20.5modesetting 1.20.5GCC 11.0.0 20200822ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionTflite Xeon BenchmarksSystem Logs- Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6- itlb_multihit: KVM: Mitigation of Split huge pages + 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: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled

Run 1Run 2Run 3Result OverviewPhoronix Test Suite100%102%104%106%109%TensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteSqueezeNetInception V4NASNet MobileMobilenet FloatMobilenet QuantI.R.V

tflite Xeontensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2Run 1Run 2Run 3220839327280320229815562616065430803702300383402483210579161973165496315279723970035135002145111639441678523187853OpenBenchmarking.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 1Run 2Run 350K100K150K200K250KSE +/- 3542.52, N = 3SE +/- 750.00, N = 3SE +/- 419.07, N = 3220839230038239700
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetRun 1Run 2Run 340K80K120K160K200KMin: 213760 / Avg: 220838.67 / Max: 224638Min: 228612 / Avg: 230038 / Max: 231154Min: 238863 / Avg: 239699.67 / Max: 240161

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Run 1Run 2Run 3800K1600K2400K3200K4000KSE +/- 4331.38, N = 3SE +/- 20471.89, N = 3SE +/- 30390.34, N = 3327280334024833513500
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Run 1Run 2Run 3600K1200K1800K2400K3000KMin: 3264730 / Avg: 3272803.33 / Max: 3279560Min: 3363030 / Avg: 3402483.33 / Max: 3431690Min: 3454690 / Avg: 3513500 / Max: 3556200

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileRun 1Run 2Run 350K100K150K200K250KSE +/- 563.19, N = 3SE +/- 964.83, N = 3SE +/- 1440.18, N = 3202298210579214511
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileRun 1Run 2Run 340K80K120K160K200KMin: 201305 / Avg: 202297.67 / Max: 203255Min: 208814 / Avg: 210579 / Max: 212137Min: 212770 / Avg: 214511.33 / Max: 217369

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatRun 1Run 2Run 340K80K120K160K200KSE +/- 351.72, N = 3SE +/- 252.50, N = 3SE +/- 1460.83, N = 3155626161973163944
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatRun 1Run 2Run 330K60K90K120K150KMin: 154992 / Avg: 155625.67 / Max: 156207Min: 161468 / Avg: 161972.67 / Max: 162241Min: 162180 / Avg: 163944 / Max: 166843

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantRun 1Run 2Run 340K80K120K160K200KSE +/- 1094.72, N = 3SE +/- 258.70, N = 3SE +/- 1338.59, N = 3160654165496167852
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantRun 1Run 2Run 330K60K90K120K150KMin: 158972 / Avg: 160654.33 / Max: 162709Min: 164979 / Avg: 165496.33 / Max: 165762Min: 166199 / Avg: 167851.67 / Max: 170502

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Run 1Run 2Run 3700K1400K2100K2800K3500KSE +/- 12577.29, N = 3SE +/- 23196.90, N = 3SE +/- 23332.12, N = 3308037031527973187853
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Run 1Run 2Run 3600K1200K1800K2400K3000KMin: 3055490 / Avg: 3080370 / Max: 3096020Min: 3116570 / Avg: 3152796.67 / Max: 3196010Min: 3142630 / Avg: 3187853.33 / Max: 3220430

Run 1

Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled

Testing initiated at 23 August 2020 14:18 by user root.

Run 2

Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled

Testing initiated at 23 August 2020 14:49 by user root.

Run 3

Processor: Intel Xeon E-2288G @ 5.00GHz (8 Cores / 16 Threads), Motherboard: Compulab SBC-ATCFL v1.2 (ATOP3.PRD.0.29.2 BIOS), Chipset: Intel Cannon Lake PCH, Memory: 2 x 32 GB DDR4-2667MT/s Samsung M378A4G43MB1-CTD, Disk: Samsung SSD 970 EVO Plus 250GB, Graphics: NVIDIA Quadro RTX 4000, Audio: Intel Cannon Lake PCH cAVS, Monitor: VE228, Network: Intel I219-LM + Intel I210

OS: Ubuntu 19.10, Kernel: 5.3.0-64-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, Compiler: GCC 11.0.0 20200822, File-System: ext4, Screen Resolution: 1920x1080

Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled

Testing initiated at 23 August 2020 15:19 by user root.