tflite Core i9 10980XE

Intel Core i9-10980XE testing with a ASRock X299 Steel Legend (P1.30 BIOS) and NVIDIA NV132 11GB on Ubuntu 20.10 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-FI-TFLITECOR37
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
Num 1
August 23 2020
  24 Minutes
Num 2
August 23 2020
  22 Minutes
Num 3
August 23 2020
  22 Minutes
Invert Hiding All Results Option
  22 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):


tflite Core i9 10980XEOpenBenchmarking.orgPhoronix Test SuiteIntel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads)ASRock X299 Steel Legend (P1.30 BIOS)Intel Sky Lake-E DMI3 Registers32GBSamsung SSD 970 PRO 512GBNVIDIA NV132 11GBRealtek ALC1220ASUS MG28UIntel I219-V + Intel I211Ubuntu 20.105.4.0-42-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.3 Mesa 20.1.2GCC 10.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionTflite Core I9 10980XE BenchmarksSystem Logs- Scaling Governor: intel_pstate performance - CPU Microcode: 0x5002f01- 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: Not affected + tsx_async_abort: Mitigation of TSX disabled

Num 1Num 2Num 3Result OverviewPhoronix Test Suite100%100%101%101%101%TensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteMobilenet QuantSqueezeNetNASNet MobileInception V4I.R.VMobilenet Float

tflite Core i9 10980XEtensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2Num 1Num 2Num 3127959185124311616887370.791222.81638423126963184899311613187387.390039.21638780126974184958011599887380.190060.31638593OpenBenchmarking.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: SqueezeNetNum 1Num 2Num 330K60K90K120K150KSE +/- 918.07, N = 3SE +/- 41.70, N = 3SE +/- 23.60, N = 3127959126963126974
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetNum 1Num 2Num 320K40K60K80K100KMin: 126994 / Avg: 127958.67 / Max: 129794Min: 126881 / Avg: 126963.33 / Max: 127016Min: 126930 / Avg: 126973.67 / Max: 127011

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Num 1Num 2Num 3400K800K1200K1600K2000KSE +/- 1718.93, N = 3SE +/- 71.26, N = 3SE +/- 179.26, N = 3185124318489931849580
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Num 1Num 2Num 3300K600K900K1200K1500KMin: 1849290 / Avg: 1851243.33 / Max: 1854670Min: 1848890 / Avg: 1848993.33 / Max: 1849130Min: 1849280 / Avg: 1849580 / Max: 1849900

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileNum 1Num 2Num 320K40K60K80K100KSE +/- 142.50, N = 3SE +/- 36.98, N = 3SE +/- 123.55, N = 3116168116131115998
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileNum 1Num 2Num 320K40K60K80K100KMin: 116025 / Avg: 116168 / Max: 116453Min: 116072 / Avg: 116130.67 / Max: 116199Min: 115754 / Avg: 115997.67 / Max: 116155

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatNum 1Num 2Num 320K40K60K80K100KSE +/- 37.71, N = 3SE +/- 39.50, N = 3SE +/- 26.48, N = 387370.787387.387380.1
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatNum 1Num 2Num 315K30K45K60K75KMin: 87295.3 / Avg: 87370.67 / Max: 87410.9Min: 87308.3 / Avg: 87387.3 / Max: 87427Min: 87328.2 / Avg: 87380.1 / Max: 87415.2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantNum 1Num 2Num 320K40K60K80K100KSE +/- 1175.66, N = 5SE +/- 35.59, N = 3SE +/- 34.95, N = 391222.890039.290060.3
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantNum 1Num 2Num 316K32K48K64K80KMin: 89965.5 / Avg: 91222.84 / Max: 95924.1Min: 89973.7 / Avg: 90039.2 / Max: 90096.1Min: 89993.1 / Avg: 90060.33 / Max: 90110.5

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Num 1Num 2Num 3400K800K1200K1600K2000KSE +/- 273.03, N = 3SE +/- 202.32, N = 3SE +/- 282.98, N = 3163842316387801638593
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Num 1Num 2Num 3300K600K900K1200K1500KMin: 1637900 / Avg: 1638423.33 / Max: 1638820Min: 1638420 / Avg: 1638780 / Max: 1639120Min: 1638110 / Avg: 1638593.33 / Max: 1639090