Tensorflow-Lite_FLOAT

Intel Core i7-9750H testing with a Dell 0F7T8V (1.14.0 BIOS) and NVIDIA GeForce RTX 2070 with Max-Q Design 8GB on EndeavourOS rolling via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2304136-EIRI-230412085.

Tensorflow-Lite_FLOATProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen ResolutionRTX-2070MQ_UHD-630_i7-9750HRTX-2070MQ_UHD-630_i7-9750H-XanmodIntel Core i7-9750H @ 4.50GHz (6 Cores / 12 Threads)Dell 0F7T8V (1.14.0 BIOS)Intel Cannon Lake PCH32GB2000GB Samsung SSD 970 EVO Plus 2TB + 1000GB CT1000MX500SSD1NVIDIA GeForce RTX 2070 with Max-Q Design 8GBRealtek ALC3204Realtek Device 2502 + Intel-AC 9260EndeavourOS rolling6.2.10-arch1-1 (x86_64)KDE Plasma 5.27.4X Server 1.21.1.8NVIDIA 530.41.034.6.0OpenCL 3.0 + OpenCL 3.0 CUDA 12.1.98GCC 12.2.1 20230201 + Clang 15.0.7 + LLVM 15.0.7 + CUDA 12.1ext41920x10806.2.10-x64v1-xanmod1-1 (x86_64)OpenBenchmarking.orgKernel Details- RTX-2070MQ_UHD-630_i7-9750H: Transparent Huge Pages: always- RTX-2070MQ_UHD-630_i7-9750H-Xanmod: Transparent Huge Pages: madviseProcessor Details- RTX-2070MQ_UHD-630_i7-9750H: Scaling Governor: intel_pstate powersave (EPP: performance) - CPU Microcode: 0xf0 - RTX-2070MQ_UHD-630_i7-9750H-Xanmod: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xf0 Security Details- itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: vulnerable + mds: Vulnerable; SMT vulnerable + meltdown: Vulnerable + mmio_stale_data: Vulnerable + retbleed: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled PBRSB-eIBRS: Not affected + srbds: Vulnerable + tsx_async_abort: Not affected

Tensorflow-Lite_FLOATtensorflow-lite: Mobilenet FloatDifferenceStandard ErrorStandard DeviationRTX-2070MQ_UHD-630_i7-9750HRTX-2070MQ_UHD-630_i7-9750H-Xanmod4422.461.08x56.202.20%4812.701.00x12.440.45%OpenBenchmarking.org

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet FloatRTX-2070MQ_UHD-630_i7-9750HRTX-2070MQ_UHD-630_i7-9750H-Xanmod10002000300040005000SE +/- 56.20, N = 3SE +/- 12.44, N = 34422.464812.70

Phoronix Test Suite v10.8.4