3400G TensorFlow Lite + NAMD

AMD Ryzen 5 3400G testing with a ASUS PRIME B450M-A (2006 BIOS) and ASUS AMD Picasso 2GB 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 2008234-NI-3400GTENS74
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
Try 1
August 23 2020
  40 Minutes
Try 2
August 23 2020
  39 Minutes
Try 3
August 23 2020
  39 Minutes
Invert Hiding All Results Option
  39 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):


3400G TensorFlow Lite + NAMDOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 5 3400G @ 3.70GHz (4 Cores / 8 Threads)ASUS PRIME B450M-A (2006 BIOS)AMD Raven/Raven22 x 8192 MB DDR4-3000MT/s CRUCIAL29GB INTEL MEMPEK1W032GA + 4 x 6001GB Seagate ST6000VN0033-2EEASUS AMD Picasso 2GB (1400/1500MHz)AMD Raven/Raven2/FenghuangSyncMasterRealtek RTL8111/8168/8411Ubuntu 19.105.3.0-46-generic (x86_64)GNOME Shell 3.34.1X ServerGCC 9.2.1 20191008ext41280x800ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen Resolution3400G TensorFlow Lite + NAMD BenchmarksSystem Logs- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8108109- itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + tsx_async_abort: Not affected

Try 1Try 2Try 3Result OverviewPhoronix Test Suite100%100%100%100%101%TensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteNAMDTensorFlow LiteTensorFlow LiteInception V4NASNet MobileI.R.VMobilenet QuantATPase Simulation - 327,506 AtomsMobilenet FloatSqueezeNet

3400G TensorFlow Lite + NAMDnamd: ATPase Simulation - 327,506 Atomstensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2Try 1Try 2Try 34.74777391789576978028022226111027824352017774.74984391858578788328136126114227753352014134.7533739166157997402814782609972772365181893OpenBenchmarking.org

NAMD

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsTry 1Try 2Try 31.06952.1393.20854.2785.3475SE +/- 0.00239, N = 3SE +/- 0.00117, N = 3SE +/- 0.00373, N = 34.747774.749844.75337
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsTry 1Try 2Try 3246810Min: 4.74 / Avg: 4.75 / Max: 4.75Min: 4.75 / Avg: 4.75 / Max: 4.75Min: 4.75 / Avg: 4.75 / Max: 4.76

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: SqueezeNetTry 3Try 1Try 280K160K240K320K400KSE +/- 3198.10, N = 3SE +/- 2990.14, N = 3SE +/- 4476.61, N = 3391661391789391858
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetTry 3Try 1Try 270K140K210K280K350KMin: 386379 / Avg: 391661.33 / Max: 397426Min: 386103 / Avg: 391788.67 / Max: 396237Min: 382914 / Avg: 391858.33 / Max: 396676

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Try 1Try 2Try 31.2M2.4M3.6M4.8M6MSE +/- 19815.32, N = 3SE +/- 9902.41, N = 3SE +/- 29287.33, N = 3576978057878835799740
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Try 1Try 2Try 31000K2000K3000K4000K5000KMin: 5731330 / Avg: 5769780 / Max: 5797320Min: 5771940 / Avg: 5787883.33 / Max: 5806030Min: 5765600 / Avg: 5799740 / Max: 5858030

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileTry 1Try 2Try 360K120K180K240K300KSE +/- 834.47, N = 3SE +/- 731.60, N = 3SE +/- 816.40, N = 3280222281361281478
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileTry 1Try 2Try 350K100K150K200K250KMin: 279084 / Avg: 280221.67 / Max: 281848Min: 279926 / Avg: 281360.67 / Max: 282327Min: 279865 / Avg: 281478 / Max: 282504

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatTry 3Try 1Try 260K120K180K240K300KSE +/- 711.88, N = 3SE +/- 586.86, N = 3SE +/- 709.89, N = 3260997261110261142
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatTry 3Try 1Try 250K100K150K200K250KMin: 259574 / Avg: 260997.33 / Max: 261739Min: 259938 / Avg: 261110.33 / Max: 261746Min: 259724 / Avg: 261142.33 / Max: 261907

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantTry 3Try 2Try 160K120K180K240K300KSE +/- 1253.31, N = 3SE +/- 1417.12, N = 3SE +/- 304.66, N = 3277236277533278243
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantTry 3Try 2Try 150K100K150K200K250KMin: 274839 / Avg: 277236.33 / Max: 279069Min: 274699 / Avg: 277532.67 / Max: 278999Min: 277707 / Avg: 278242.67 / Max: 278762

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Try 3Try 2Try 11.1M2.2M3.3M4.4M5.5MSE +/- 19365.14, N = 3SE +/- 14146.26, N = 3SE +/- 19214.00, N = 3518189352014135201777
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Try 3Try 2Try 1900K1800K2700K3600K4500KMin: 5143170 / Avg: 5181893.33 / Max: 5201890Min: 5174960 / Avg: 5201413.33 / Max: 5223330Min: 5163880 / Avg: 5201776.67 / Max: 5226240