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.

HTML result view exported from: https://openbenchmarking.org/result/2008234-NI-3400GTENS74.

3400G TensorFlow Lite + NAMDProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionTry 1Try 2Try 3AMD 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 20191008ext41280x800OpenBenchmarking.orgProcessor Details- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8108109Security Details- 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

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

ATPase Simulation - 327,506 Atoms

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

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetTry 1Try 2Try 380K160K240K320K400KSE +/- 2990.14, N = 3SE +/- 4476.61, N = 3SE +/- 3198.10, N = 3391789391858391661

TensorFlow Lite

Model: Inception V4

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

TensorFlow Lite

Model: NASNet Mobile

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

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatTry 1Try 2Try 360K120K180K240K300KSE +/- 586.86, N = 3SE +/- 709.89, N = 3SE +/- 711.88, N = 3261110261142260997

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantTry 1Try 2Try 360K120K180K240K300KSE +/- 304.66, N = 3SE +/- 1417.12, N = 3SE +/- 1253.31, N = 3278243277533277236

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Try 1Try 2Try 31.1M2.2M3.3M4.4M5.5MSE +/- 19214.00, N = 3SE +/- 14146.26, N = 3SE +/- 19365.14, N = 3520177752014135181893

Phoronix Test Suite v10.8.4