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.

HTML result view exported from: https://openbenchmarking.org/result/2008243-FI-ICELAKETE47&sro.

IceLake TensorFlow LiteProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen Resolutioni7-1065G7 Base RunRun 2Run 3Run 4Intel 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 9.3.0ext41920x1200OpenBenchmarking.orgProcessor Details- Scaling Governor: intel_pstate powersave - CPU Microcode: 0x78Security Details- 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

IceLake TensorFlow Litetensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2i7-1065G7 Base RunRun 2Run 3Run 462440990599274512624191324181038205123626580921516345620442387542367783010276259679152753455889423160422567828782062644891803774552954237714229468304020OpenBenchmarking.org

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetRun 2Run 3Run 4i7-1065G7 Base Run130K260K390K520K650KSE +/- 6624.90, N = 8SE +/- 6115.93, N = 9SE +/- 6155.90, N = 9SE +/- 6173.06, N = 9626580625967626448624409

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Run 2Run 3Run 4i7-1065G7 Base Run2M4M6M8M10MSE +/- 33881.36, N = 3SE +/- 7167.26, N = 3SE +/- 1006.75, N = 3SE +/- 1678.14, N = 39215163915275391803779059927

TensorFlow Lite

Model: NASNet Mobile

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

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatRun 2Run 3Run 4i7-1065G7 Base Run90K180K270K360K450KSE +/- 3379.39, N = 3SE +/- 3567.59, N = 3SE +/- 3564.86, N = 3SE +/- 2847.74, N = 3423875423160423771419132

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantRun 2Run 3Run 4i7-1065G7 Base Run90K180K270K360K450KSE +/- 3033.64, N = 3SE +/- 3385.38, N = 3SE +/- 3381.27, N = 3SE +/- 3745.57, N = 3423677422567422946418103

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Run 2Run 3Run 4i7-1065G7 Base Run2M4M6M8M10MSE +/- 4154.54, N = 3SE +/- 4935.89, N = 3SE +/- 7204.57, N = 3SE +/- 2058.80, N = 38301027828782083040208205123

Phoronix Test Suite v10.8.4