Core i9 10900K TensorFlow Lite

Intel Core i9-10900K testing with a Gigabyte Z490 AORUS MASTER (F3 BIOS) and Gigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB on Ubuntu 20.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2008231-SYST-COREI9100&rdt.

Core i9 10900K TensorFlow LiteProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionGo 1Go 2Go 3Intel Core i9-10900K @ 5.30GHz (10 Cores / 20 Threads)Gigabyte Z490 AORUS MASTER (F3 BIOS)Intel Comet Lake PCH16GBSamsung SSD 970 EVO 250GBGigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB (1890/875MHz)Realtek ALC1220DELL P2415QIntel Device 15f3 + Intel Wi-Fi 6 AX201Ubuntu 20.045.8.1-050801-generic (x86_64)GNOME Shell 3.36.3X Server 1.20.8modesetting 1.20.84.6 Mesa 20.2.0-devel (git-ef67218 2020-07-07 focal-oibaf-ppa) (LLVM 10.0.1)OpenCL 1.1 Mesa 20.2.0-devel (git-c977567db6)1.2.131GCC 9.3.0ext43840x2160OpenBenchmarking.orgProcessor Details- Scaling Governor: intel_pstate powersave - CPU Microcode: 0xc8Security Details- 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: Not affected

Core i9 10900K TensorFlow Litetensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2Go 1Go 2Go 3167615237927314741411429411865121418071675432375430147181114256117317214166316756023749601472131140781174102141327OpenBenchmarking.org

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetGo 1Go 2Go 340K80K120K160K200KSE +/- 25.12, N = 3SE +/- 34.11, N = 3SE +/- 15.56, N = 3167615167543167560

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Go 1Go 2Go 3500K1000K1500K2000K2500KSE +/- 3903.95, N = 3SE +/- 11.55, N = 3SE +/- 260.83, N = 3237927323754302374960

TensorFlow Lite

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileGo 1Go 2Go 330K60K90K120K150KSE +/- 66.02, N = 3SE +/- 89.66, N = 3SE +/- 144.80, N = 3147414147181147213

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatGo 1Go 2Go 320K40K60K80K100KSE +/- 141.41, N = 3SE +/- 86.19, N = 3SE +/- 50.71, N = 3114294114256114078

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantGo 1Go 2Go 330K60K90K120K150KSE +/- 1241.85, N = 3SE +/- 141.34, N = 3SE +/- 210.41, N = 3118651117317117410

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Go 1Go 2Go 3500K1000K1500K2000K2500KSE +/- 140.99, N = 3SE +/- 37.12, N = 3SE +/- 61.19, N = 3214180721416632141327


Phoronix Test Suite v10.8.4